JP7557762B2 - Waveform signal control method and control device - Google Patents

Description

This disclosure relates to a waveform signal control method and control device that outputs a waveform signal to be applied to an inkjet head of an inkjet device.

Patent Document 1 discloses an inkjet device that aims to automatically create an input waveform to a pressurizing means that takes into account the flight characteristics of the ink. The inkjet device includes a pressure chamber to which ink is supplied, a pressurizing means that pressurizes the pressure chamber to eject the ink, and a waveform generating means that generates an input waveform to the pressurizing means, the waveform generating means creating an input waveform that optimizes an evaluation function related to the flight characteristics of the ink.

Japanese Patent Application Publication No. 9-174835

The technology disclosed in Patent Document 1 makes it possible to control the velocity, volume, and satellites that are uniquely determined when ink droplets are ejected, but it is not possible to suppress the generation of mist that is not reproducible.

Therefore, the present disclosure provides a waveform signal control method and control device that can suppress the generation of mist.

A waveform signal control method according to one aspect of the present disclosure is a method for controlling a waveform signal applied to an inkjet head provided in an inkjet device, in which a first waveform signal is set to a second voltage higher than a first voltage at a second time after a first time, a third voltage higher than the first voltage at a third time after the second time, and a fourth voltage lower than the third voltage at a fourth time after the third time, and a continuous ink jet is discharged from the inkjet head by applying the first waveform signal to the inkjet head. The method includes acquiring a shape data group including a plurality of shape data pieces that are continuous in time, outputting a probability of mist generation from the inkjet head based on the shape data group, and outputting, when the output probability is equal to or greater than a predetermined value, information indicating a second waveform signal obtained by changing at least one of the time from the second time to the third time, the differential voltage between the third voltage and the fourth voltage, and the amount of change in voltage per unit time from the third time to the fourth time, of the first waveform signal, to the inkjet device.

In addition, a control device according to one aspect of the present disclosure is a control device that controls a waveform signal applied to an inkjet head included in an inkjet device, and the first waveform signal is a signal in which a second voltage higher than a first voltage at a second time after a first time is set, a third voltage higher than the first voltage at a third time after the second time is set, and a fourth voltage lower than the third voltage is set at a fourth time after the third time, and the first waveform signal is applied to the inkjet head to cause continuous ejection from the inkjet head. The ink jet head includes an acquisition unit that acquires a shape data group including multiple shape data that are continuous in time, the shape data being shape data indicating the shape of the ink that has been generated; a control unit that outputs the probability of mist being generated from the inkjet head based on the shape data group; and an output unit that outputs, when the output probability is equal to or greater than a predetermined value, information indicating a second waveform signal obtained by changing at least one of the time from the second time to the third time, the differential voltage between the third voltage and the fourth voltage, and the amount of change in voltage per unit time from the third time to the fourth time, to the inkjet device.

These comprehensive or specific aspects may be realized as a system, a method, an integrated circuit, a computer program, or a computer-readable recording medium such as a CD-ROM, or may be realized as any combination of a system, an integrated circuit, a computer program, and a recording medium.

The waveform signal control method according to one aspect of the present disclosure can suppress the generation of mist.

FIG. 1 is a diagram showing a schematic configuration of an inkjet system according to a first embodiment. FIG. 2 is a block diagram showing a functional configuration of the inkjet system according to the first embodiment. FIG. 3 is a diagram for explaining waveform signals applied to the ink-jet head according to the first embodiment. FIG. 4 is a diagram showing time-series data of image data obtained by photographing ink ejected from the inkjet head according to the first embodiment. FIG. 5A is a diagram for explaining an example of the capture timing of image data according to the first embodiment. FIG. 5B is a diagram for explaining another example of the capture timing of image data according to the first embodiment. FIG. 6A is a diagram showing an example of a shape data group in a case where no mist is generated according to the first embodiment. FIG. 6B is a diagram showing an example of a shape data group when mist is generated according to the first embodiment. FIG. 7 is a diagram for explaining a work camera of the inkjet system according to the first embodiment. FIG. 8 is a flowchart showing a method for generating a learning model according to the first embodiment. FIG. 9 is a flowchart showing an operation of outputting a waveform signal of the inkjet system according to the first embodiment. FIG. 10 is a diagram showing an example of a condition table of a waveform signal according to the second embodiment. FIG. 11 is a flowchart showing an operation of outputting a waveform signal of the inkjet system according to the second embodiment. FIG. 12 is a diagram showing an example of an updated condition table according to the second embodiment. FIG. 13 is a block diagram showing a functional configuration of an inkjet system according to the third embodiment. FIG. 14 is a flowchart showing a method for generating a learning model according to the third embodiment. FIG. 15A is a diagram showing a workpiece when no mist is generated according to the third embodiment. FIG. 15B is a diagram showing a workpiece when mist is generated according to the third embodiment. FIG. 16 is a flowchart showing a printing operation in the inkjet system according to the third embodiment.

(Background to this disclosure)
It is known that an inkjet device that ejects ink by an inkjet method generates mist that is not reproducible. Mist is a droplet in which part of the ink ejected from the nozzle of the inkjet head becomes small droplets or mist, and the position where the mist is generated is not reproducible (see times T9 and T15 in FIG. 6B described later). In other words, mist is a droplet whose generation position is uncontrollable. Furthermore, mist is a droplet whose generation timing is also uncontrollable. Since mist adheres to a workpiece and causes the workpiece to be soiled, it is desirable to suppress the generation of mist. The workpiece is a printing object of the inkjet device, for example, a workpiece 50 shown in FIG. 7 described later.

In addition, in recent years, the applications of inkjet printing have expanded. Inkjet devices are also used to decorate the surfaces of printed objects such as electrical products. Inkjet devices are also used to form functional films using functional inks containing functional materials. Functional materials include inorganic or organic materials that can impart desired functions, such as conductors, dielectrics, semiconductors, insulators, resistors, colorants such as pigments, and chemical-resistant materials. For example, inkjet devices are also used to form wiring on a substrate by applying ink containing electronic materials such as conductors as functional materials to the substrate.

As the applications of inkjet printing expand, the variety of inks used is also increasing. Some inks are designed to prioritize functionality over printability. It is believed that such inks are more likely to generate mist. For this reason, it is desirable to suppress the generation of mist, regardless of the printability of the ink.

The inventors of the present application conducted extensive research into suppressing the generation of mist, and discovered that it is possible to suppress the generation of mist by changing certain parameters of the waveform signal applied to the inkjet head when ejecting ink. They then devised a waveform signal control method and control device, which are described below.

The following describes embodiments with reference to the drawings. The embodiments described below are all comprehensive or specific examples. The numerical values, shapes, materials, components, component placement and connection forms, steps, and order of steps shown in the following embodiments are merely examples and are not intended to limit the present disclosure. Furthermore, among the components in the following embodiments, components that are not described in an independent claim are described as optional components.

The figures are schematic diagrams and are not necessarily rigorous illustrations. In addition, in each figure, the same reference numerals are used for substantially the same configurations, and duplicate explanations may be omitted or simplified.

In addition, in this specification, terms that indicate relationships between elements, such as same, perpendicular, and parallel, as well as numerical values and numerical ranges, are not expressions that express only the strict meaning, but are expressions that include a substantially equivalent range, for example, a difference of about a few percent.

(Embodiment 1)
[1-1. Configuration of Inkjet System]
First, the configuration of an inkjet system 1 according to the present embodiment will be described with reference to Figures 1 to 7. Figure 1 is a diagram showing a schematic configuration of the inkjet system 1 according to the present embodiment. Figure 2 is a block diagram showing the functional configuration of the inkjet system 1 according to the present embodiment. Note that in Figure 1, the control unit 10a, the work camera 18, etc. are omitted from illustration.

As shown in FIG. 1, the inkjet system 1 includes an inkjet device 10, a network 20, and a server device 30. The inkjet device 10 is a liquid ejection device that ejects ink using an inkjet method under the control of the server device 30. The network 20 is a communication network that connects the inkjet device 10 and the server device 30 so that they can communicate with each other.

In this specification, ink refers to a liquid that is ejected by an inkjet method. Various known inks can be used as the ink ejected from the inkjet head 13. The ink may be an ink that has functionality. An ink that has functionality is, for example, an ink that contains functional materials such as a capacitor, resistor, or light-emitting layer material. Such inks are sometimes designed with functionality as a priority so that they have the desired function after being printed.

As shown in Figures 1 and 2, the inkjet device 10 includes a control unit 10a, a tank 11, a flow path 12, a pump 12a, an inkjet head 13, a signal generator 15, a light source 16, a droplet camera 17, a workpiece camera 18, and a communication unit 19.

The control unit 10a is a control device that controls each component of the inkjet device 10. Based on a control signal from the server device 30, the control unit 10a causes the signal generator 15 to output a waveform signal corresponding to the control signal. In addition, when ink is ejected from the nozzle 13c, the control unit 10a controls the light source 16 and the droplet camera 17 to capture an image of the ink droplet I (ink droplet I). For example, the control unit 10a may set an arbitrary delay time based on a synchronization signal from the signal generator 15 and cause the light source 16 to emit light. In this case, the emission time may be, for example, 0.1 μsec. This allows the droplet camera 17 to continuously capture an image at the moment of emission. The control unit 10a may cause the light source 16 to emit light at all times.

The control unit 10a may also control the movement of the inkjet head 13 according to the printing position of the workpiece, and may control the pump 12a to adjust the circulation and pressure of the ink in the flow path 12.

The tank 11 is a container filled with ink to be supplied to the pressure chamber 13b of the inkjet head 13. The tank 11 functions as an ink supply unit that supplies ink to the inkjet head 13. The tank 11 may be, for example, an ink cartridge. The pressure of the ink in the tank 11 is adjustable, and is adjusted to a constant pressure, for example.

The flow path 12 forms a first flow path for ink sent from the tank 11 to the pressure chamber 13b of the inkjet head 13, and a second flow path for ink collected from the pressure chamber 13b of the inkjet head 13 and returned to the tank 11. The flow path 12 is configured to include at least a portion of, for example, a flexible tube or the like that can deform when the inkjet head 13 moves.

The pump 12a is provided on the first flow path and circulates the ink through the flow path 12. This makes it possible to prevent the ink near the nozzle 13c from drying out. The pump 12a may have a function to adjust the pressure of the ink before it is supplied to the inkjet head 13, and may have a function to adjust the flow rate of the ink.

The inkjet head 13 is a print head that ejects ink using an inkjet method. The inkjet head 13 ejects ink from the nozzles 13c in response to a waveform signal (driving waveform) input from a signal generator 15. The inkjet head 13 has a main body 13a and a driving unit 14. The main body 13a is a member in which a pressure chamber 13b and a nozzle 13c are formed. The pressure chamber 13b is a space filled with ink supplied (transported) from the tank 11. When the pressure chamber 13b is filled with ink and pressure is applied to the pressure chamber 13b from the driving unit 14, ink droplets I are ejected from the nozzles 13c. The nozzles 13c are openings for ejecting ink and are connected to the pressure chambers 13b. A plurality of nozzles 13c are formed on the surface of the main body 13a that faces the workpiece.

The drive unit 14 controls the ink ejection operation of the inkjet head 13 by changing the pressure in the pressure chamber 13b using a waveform signal from the signal generator 15. The drive unit 14 expands and contracts based on the waveform signal to change the pressure in the pressure chamber 13b, thereby controlling the ejection of ink from the nozzle 13c and the vibration of the ink surface of the nozzle 13c after ejection. The drive unit 14 pressurizes the ink in the pressure chamber 13b by, for example, expanding, causing the ink to be ejected from the nozzle 13c.

The driving unit 14 is realized, for example, by a piezoelectric element that can expand and contract in response to an applied waveform signal. From the viewpoint of piezoelectric properties, the driving unit 14 may be realized, for example, by a PZT (lead zirconate titanate) element. In this way, the inkjet head 13 according to this embodiment ejects ink using a piezoelectric method. The inkjet head 13 has multiple piezoelectric elements corresponding to the multiple nozzles 13c.

The signal generator 15 generates an arbitrary waveform signal (voltage waveform signal) having a voltage waveform for driving the inkjet head 13 in response to a command from the control unit 10a, and outputs the generated waveform signal to the inkjet head 13. Specifically, the signal generator 15 applies the waveform signal generated in response to a command from the control unit 10a to the drive unit 14 of the inkjet head 13.

The signal generator 15 is not particularly limited in configuration as long as it can generate a waveform signal capable of controlling the ink ejection operation in the inkjet head 13, but may be configured with a logic circuit or a control circuit including a CPU (Central Processing Unit), ROM (Read Only Memory), RAM (Random Access Memory), etc.

The waveform signal generated by the signal generator 15 will be described with reference to FIG. 3. FIG. 3 is a diagram for explaining the waveform signal applied to the inkjet head 13 according to this embodiment. The horizontal axis of the graph shown in FIG. 3 indicates time (μsec), and the vertical axis indicates voltage (V). In addition, when the waveform signal shown in FIG. 3 is applied to the drive unit 14, ink is ejected once (for example, one drop).

As shown in FIG. 3, the waveform signal has a pre-processing portion before the first time t1 and a portion for controlling ejection after the first time t1. The pre-processing portion of the waveform signal is a signal for applying a voltage that is not enough to eject ink from the nozzle 13c, and pre-vibrating the drive unit 14. This adjusts the viscosity of the ink in the pressure chamber 13b. Note that no ink is ejected at this time. The pre-processing portion of the waveform signal shown in FIG. 3 is a signal for controlling the state of the ink before it is ejected.

The portion of the waveform signal used for ejection control is a signal for ejecting ink from the nozzle 13c and for damping the vibration of the ink near the nozzle 13c after ejection. In this embodiment, the shape of the portion of the waveform signal used for ejection control is changed to suppress mist. The portion used for ejection control is described in detail below. In addition, unless otherwise specified, the portion of the waveform signal used for ejection control is also simply referred to as the waveform signal below.

Here, position S1 indicates a position in the waveform signal where the time is a first time t1 and the voltage is a first voltage V1. Position S2 indicates a position in the waveform signal where the time is a second time t2 and the voltage is a second voltage V2. Position S3 indicates a position in the waveform signal where the time is a third time t3 and the voltage is a third voltage V3. Position S4 indicates a position in the waveform signal where the time is a fourth time t4 and the voltage is a fourth voltage V4. Position S5 indicates a position in the waveform signal where the time is a fifth time t5 and the voltage is a fifth voltage V5. The signal generator 15 can change the shape of the waveform signal by adjusting the voltage or time of positions S1 to S5 in the waveform signal.

In the example of FIG. 3, between positions S1 and S2, the voltage is increased from a first voltage V1 at a first time t1 to a second voltage V2 at a second time t2. It then transitions to a third voltage V3 at a third time t3. In the case of FIG. 3, the second voltage V2 and the third voltage V3 are the same. That is, the voltage is held at the second voltage V2 from the second time t2 to the third time t3. It then transitions to a fourth voltage V4 at a fourth time t4. It then transitions to a fifth voltage V5 at a fifth time t5. In the case of FIG. 3, the fourth voltage V4 and the fifth voltage V5 are the same. That is, the voltage is held at the fourth voltage V4 from the fourth time t4 to the fifth time t5.

When the voltage is increased from the first voltage V1 at the first time t1 to the second voltage V2 at the second time t2, the volume of the pressure chamber 13b decreases rapidly as the drive unit 14 expands with the voltage increase. This causes the pressure in the pressure chamber 13b to increase, and ink is ejected vigorously from the opened nozzle 13c. The initial velocity at this time changes depending on the boost rate from the first voltage V1 to the second voltage V2. In other words, the initial velocity changes depending on the amount of change in voltage per unit time from the first time t1 to the second time t2. The higher the boost rate (the greater the amount of change in voltage per unit time), the faster the initial velocity tends to be. Also, the greater the voltage difference from the first voltage V1 to the second voltage V2, the greater the decrease in the volume of the pressure chamber 13b, and therefore the greater the volume of ink ejected. The voltage increase rate from the first voltage V1 to the second voltage V2 and the voltage difference from the first voltage V1 to the second voltage V2, that is, the initial velocity and volume of the ink, have desired target values for each workpiece 50.

Next, in the transition from the second voltage V2 at the second time t2 to the third voltage V3 at the third time t3, the second voltage V2 is usually set to be equal to the third voltage V3, and the voltage is maintained between the second time t2 and the third time t3. This period from the second time t2 to the third time t3 is set in combination with the reduction to the fourth voltage V4 at the fourth time t4 as a period for stabilizing the vibration of the ink surface (meniscus portion) of the nozzle 13c after the ink is ejected.

In other words, between the second time t2 and the third time t3, the ink near the nozzle 13c, i.e., the meniscus, vibrates while gradually attenuating according to the pressure state inside the pressure chamber 13b. At this time, the third voltage V3 (= the second voltage V2) is in a high potential state, and the drive unit 14 is in an extended state. By lowering this to the fourth voltage V4, which is a low potential, the pressure inside the pressure chamber 13b can be reduced. If the timing for starting this voltage reduction is matched to the state when the pressure inside the pressure chamber 13b is high, i.e., the timing when the meniscus is about to go out from the nozzle 13c, the pressure of the meniscus trying to go out and the pressure of the meniscus going into the pressure chamber 13b due to the pressure reduction inside the pressure chamber 13b are offset. Therefore, it is possible to stabilize the pressure inside the pressure chamber 13b.

Furthermore, by gradually setting the step-down rate from the third voltage V3 at the third time t3 to the fourth voltage V4 at the fourth time t4 according to the magnitude of vibration of the meniscus portion, it is possible to avoid excessive pressure suppression and achieve settling in a shorter time. Furthermore, shortening the settling time leads to shortening the preparation time until the next ejection, and enables ejection at a high repetition frequency.

Here, we explain the relationship between the waveform signal and the suppression of mist generation.

The causes of mist generation are difficult to generalize, as they are interrelated between the physical properties of the ink itself and the speed and shape of the ink droplet I after it is ejected. However, it is clear from observation of the ink at the moment it is ejected that mist is generated from the elongated, stretched portion (see, for example, ink droplet I1 shown in Figure 4, described below) where the ink droplet I leaves the nozzle 13c, or in its vicinity. Therefore, shortening this elongated portion as much as possible while maintaining the speed and volume of the ejected ink droplet I will lead to the suppression of mist.

The period from the first time t1 to the third time t3 (t3-t1), or the period from the second time t2 to the third time t3 (t3-t2), is changed to adjust the vibration damping timing. The period from the first time t1 to the third time t3, or the period from the second time t2 to the third time t3, is related to the vibration damping operation for stabilizing the meniscus portion. This third time t3 determines the timing for starting vibration damping, and by appropriately setting this time, it is possible to shorten the elongated portion when the ink droplet I separates. In other words, by actively retracting the meniscus portion before the elongated portion spontaneously breaks due to the ejected ink droplet I, it is possible to shorten the length of the elongated portion at the time of breakage. This reduces the volume of the elongated portion of the ink droplet I, which is the source of mist, and as a result, it leads to suppressing the generation of mist.

The differential voltage between the third voltage V3 and the fourth voltage V4 is changed to adjust the vibration control depth. This differential voltage corresponds to the amount of displacement when the drive unit 14 retracts from the extended state, and by lowering the pressure in the pressure chamber 13b, the meniscus portion can be retracted and the extended portion of the ejected droplet can be shortened. This reduces the volume of the extended portion of the ink droplet I, which is the source of mist, and as a result, leads to suppression of mist.

The amount of change in voltage per unit time from the third time t3 to the fourth time t4 (the "slope" shown in Figure 3) is changed to adjust the slope of the voltage drop waveform.

The amount of change in this voltage per unit time corresponds to the speed at which the drive unit 14 retreats from the extended state, and it is possible to control the rate at which the pressure in the pressure chamber 13b drops. This makes it possible to suppress unnecessary vibration of the meniscus itself and unnecessary extension of the extended portion due to the sudden retreat of the meniscus, thereby allowing the ink to be stably released. This therefore minimizes the volume of the extended portion of the ink droplet I, which is the source of mist, and as a result leads to the suppression of mist.

In this embodiment, when changing the waveform signal that generates mist, the parameters from position S2 onwards are changed with priority, but this is not limited to this.

Referring again to FIG. 2, the light source 16 emits light for the droplet camera 17 to capture an image of the ink droplet I ejected from the nozzle 13c. The light source 16 may emit light of a color that makes it easier for the droplet camera 17 to capture the shape of the ink, depending on, for example, the type of ink (e.g., the color of the ink). The light source 16 is, for example, configured to have a light-emitting module having multiple light-emitting elements, but is not limited to this. The light source 16 is also disposed on the opposite side of the droplet camera 17 across the ink droplet I, but is not limited to this.

The droplet camera 17 is an image capturing device that captures the flight state of the ink droplets I ejected from the nozzle 13c. The flight state includes the flight shape of the ink droplets I. The droplet camera 17 captures images of the ink shape in a state in which the ink is continuously ejected from the inkjet head 13 in a continuous time sequence. The droplet camera 17 outputs the captured image data to the control unit 10a. In this embodiment, the droplet camera 17 is an example of a detector that acquires a group of shape data of the ink ejected from the inkjet head 13.

Here, the acquisition of image data by the droplet camera 17 will be described with reference to Figs. 4 to 6B. Fig. 4 is a diagram showing time series data of image data (droplet image data) obtained by photographing ink (ink droplets I) ejected from the inkjet head 13 according to this embodiment. Figs. 4 to 6B show image data obtained when the droplet camera 17 photographs the image plane A shown in Fig. 1. The image plane A is a plane that includes a direction perpendicular to the ejection direction of the ink droplets I and is perpendicular to the work feed direction (see Fig. 7) described below. The ink is ejected at a set period (for example, the interval T in Fig. 4). The image data is an example of shape data that shows the shape of the ink droplets I.

Figure 4 shows image data when ink is ejected at times T1, T4, and T7. Times T1, T4, and T7 are the ejection timings at which ink is ejected. Ink droplet I1 ejected at time T1 moves downward as times T2 and T3 progress. The same is true for ink droplet I2 from time T4 to time T6, and ink droplet I3 from time T7 to time T9. Note that ink droplet I2 is the ink ejected after ink droplet I1, and ink droplet I3 is the ink ejected after ink droplet I2.

Figure 5A is a diagram for explaining an example of the timing of capturing image data according to this embodiment. Figure 5B is a diagram for explaining another example of the timing of capturing image data according to this embodiment. Figures 5A and 5B are image data captured continuously in time from a direction perpendicular to the capturing plane A, showing the flight state of ink droplets I. The image data is captured by the droplet camera 17, for example, by irradiating the ink droplets I with strobe light from the light source 16.

As shown in FIG. 5A, by shifting the strobe emission rate for the strobe emission timing (times T1, T5, T9) from an integer multiple (e.g., an integer multiple of the interval T shown in FIG. 4) of the ejection rate for the ejection timing (times T1, T4, T7), it is possible to dynamically capture the state of the ink droplet I along the ink flight path from when the ink is ejected from the inkjet head 13 to when the ink lands on the workpiece 50. For example, it is possible to dynamically capture the state of the ink droplet I using a general-purpose camera without preparing a high-performance camera capable of capturing images at high speed.

Also, as shown in FIG. 5B, by setting the strobe emission rate for the strobe emission timings (times T3, T6, and T9) to an integer multiple of the ejection rate for the ejection timings (times T1, T4, and T7), it is possible to statically capture the state of the ink droplet I at a specific position in the ink flight path.

The image data shown in either FIG. 5A or FIG. 5B is used as the image data for generating the learning model and the image data for determining whether mist is occurring, which will be described below. For example, the timing of capturing the image data for generating the learning model and the timing of capturing the image data for determining whether mist is occurring may be the same or different.

Next, the occurrence of mist will be described with reference to Figures 6A and 6B. Figure 6A is a diagram showing an example of a shape data group when mist is not occurring according to this embodiment. Figure 6B is a diagram showing an example of a shape data group when mist is occurring according to this embodiment. Note that Figures 6A and 6B show a case where the state of an ink droplet I at a specific position in the flight path of the ink is statically captured.

Figure 6A shows image data captured continuously over time when no mist is generated. The continuous image data showing the state of the ink droplet I is composed of multiple image data with high reproducibility. The multiple image data with high reproducibility is an example of a shape data group.

Figure 6B shows successive image data in time when mist is occurring. Mist does not always occur in the same way; the shape and position differ for each capture timing, such as the mist occurring at time T9 and the mist occurring at time T15. In other words, the mist occurrence state differs depending on the time of capture. Furthermore, mist does not occur at times other than T9 and T15. In other words, there are cases where mist is not occurring. When mist is occurring, the successive image data showing the state of the ink droplets I is composed of multiple image data with low reproducibility. Multiple image data with low reproducibility is an example of a shape data group.

Referring again to FIG. 2, the work camera 18 is an imaging device that captures the printing state of the work on which ink has been printed. FIG. 7 is a diagram for explaining the work camera 18 of the inkjet system 1 according to this embodiment. Note that FIG. 7 shows an example in which the work 50 is a substrate used in an organic EL (Electro Luminescence) display.

As shown in FIG. 7, the workpiece camera 18 is disposed above the scanning stage 40 together with the inkjet head 13. The workpiece 50 is fixed (e.g., fixed by suction) onto the scanning stage 40. The scanning stage 40 is scanned in the workpiece feed direction (direction of the arrow). The workpiece camera 18 is disposed behind the inkjet head 13 in the scanning direction. It can also be said that the workpiece camera 18 is disposed on the workpiece feed direction side of the inkjet head 13.

Ink is ejected from each nozzle 13c of the inkjet head 13 to the coordinates of the workpiece 50 being scanned. For example, multiple patterns (cells) are formed in advance on the workpiece 50, and ink is ejected from the nozzles 13c corresponding to each cell, filling the cells with ink. The workpiece camera 18 photographs the workpiece 50, whose cells are filled with ink, from above the workpiece 50.

Such a workpiece camera 18 may be a line scanner or a microscope camera. When a microscope camera is used, the workpiece 50 may be photographed while the microscope camera is moved in the sub-scanning direction (e.g., the direction in which the inkjet head 13 extends).

The multiple nozzles 13c of the inkjet head 13 are arranged, for example, in the sub-scanning direction.

Referring again to FIG. 2, the communication unit 19 is a communication circuit (communication module) for the inkjet device 10 to communicate with the server device 30 via the network 20. The communication unit 19 transmits and receives various information under the control of the control unit 10a. For example, the communication unit 19 transmits at least a group of shape data captured by the droplet camera 17 to the server device 30 via the network 20. The communication unit 19 may also transmit image data captured by the work camera 18 to the server device 30 via the network 20. The communication unit 19 also receives a control signal for controlling the waveform signal of the signal generator 15 from the server device 30 via the network 20.

Next, the server device 30 will be described. The server device 30 controls the inkjet device 10 based on information acquired from the inkjet device 10. In this embodiment, the server device 30 acquires image data captured by the droplet camera 17 from the droplet camera 17, and generates a control signal for controlling the waveform signal that the signal generator 15 applies to the drive unit 14 based on the acquired image data. The server device 30 includes a communication unit 31, a control unit 32, and a storage unit 33. The server device 30 is an example of a control device that controls the waveform signal applied to the inkjet head 13.

The communication unit 31 is a communication circuit (communication module) that allows the server device 30 to communicate with the inkjet device 10 via the network 20. The communication unit 31 transmits and receives various information under the control of the control unit 32. The communication unit 31 functions as an acquisition unit that acquires a shape data group from the inkjet device 10. The communication unit 31 also functions as an output unit that outputs information indicating a waveform signal to the inkjet device 10.

The control unit 32 is a control device that controls various components of the server device 30. The control unit 32 also outputs the probability of mist generation from the inkjet head 13 based on the shape data group acquired via the communication unit 31, and generates a control signal for controlling the waveform signal of the signal generator 15 based on the probability. The control unit 32 transmits the generated control signal to the inkjet device 10 via the communication unit 31. The control unit 32 has a model generation unit 32a and a determination unit 32b.

The model generation unit 32a is a processing unit for generating a learning model that is trained to input a group of shape data captured by the droplet camera 17 and output the probability of mist being generated from the inkjet head 13. The model generation unit 32a generates the above learning model in advance. The learning model is, for example, composed of a neural network, but is not limited to this.

The model generation unit 32a generates a learning model by, for example, machine learning the relationship between the shape data group acquired from the droplet camera 17 and the probability of mist generation in the shape data group. For example, in the machine learning, teacher data that represents the shape data group acquired from the droplet camera 17 in association with the probability of mist generation in the shape data group is used. For example, the probability of mist generation may be determined by the result of determining whether or not mist occurs in the shape data group. In this way, the learning model is learned by supervised learning, but it may also be learned by other learning methods such as unsupervised learning. In addition, the learning model may be a learning model that is trained to input the shape data group captured by the droplet camera 17 and output the presence or absence of mist generation from the inkjet head 13.

The determination unit 32b uses the learning model generated by the model generation unit 32a and a group of shape data of ink droplets I newly acquired by the droplet camera 17 to determine whether or not mist will occur in the group of shape data. Specifically, the determination unit 32b determines whether or not mist will occur based on the probability of mist occurrence, which is the output obtained by inputting the group of shape data into the learning model. For example, the determination unit 32b determines that mist will occur if the occurrence probability is equal to or greater than a predetermined value. The predetermined value is, for example, stored in advance in the memory unit 33. The predetermined value is appropriately determined depending on the type of workpiece 50, etc.

In addition, if the learning model is trained to output whether or not mist is generated, the determination unit 32b may obtain the presence or absence of mist generation, which is an output obtained by inputting the group of shape data into the learning model. This is also included in the determination by the determination unit 32b of whether or not mist is generated.

In the above, an example has been described in which the determination unit 32b obtains the probability of mist generation using a learning model, but this is not limiting. For example, the determination unit 32b may calculate the probability of mist generation by image analysis of image data included in the shape data group, and determine whether or not mist will occur based on the calculated probability of mist generation. For example, the determination unit 32b may calculate the probability of mist generation based on the number of image data included in the shape data group and the number of image data in which mist is generated. Note that in this case, the server device 30 does not need to be equipped with the model generation unit 32a.

The memory unit 33 is a storage device that stores the computer program executed by the control unit 32 and the learning model generated by the model generation unit 32a. The memory unit 33 is realized, for example, by a semiconductor memory, but is not limited to this.

[1-2. Operation of the Inkjet System]
Next, the operation of the inkjet system 1 as described above will be described with reference to Fig. 8 and Fig. 9. First, the method of generating a learning model by the model generating unit 32a will be described with reference to Fig. 8. Fig. 8 is a flowchart showing the method of generating a learning model according to the present embodiment. The flowchart shown in Fig. 8 is executed before the operation of outputting a waveform signal of the inkjet system 1 (the operation shown in Fig. 9) is performed.

As shown in FIG. 8, the control unit 32 applies a waveform signal to eject ink from the inkjet head 13 (S11). Specifically, the control unit 32 transmits a control signal to the inkjet device 10, thereby causing the signal generator 15 to apply a waveform signal to the drive unit 14. The waveform signal applied here may be any waveform signal.

The signal generator 15 of the inkjet device 10 applies a waveform signal to the drive unit 14 based on a control signal from the server device 30, thereby causing ink to be ejected from the nozzle 13c. The signal generator 15 ejects ink continuously, for example, by repeatedly applying a waveform signal such as that shown in FIG. 3. The droplet camera 17 continuously captures images of the flight state of the ink droplets I ejected continuously from the nozzle 13c. The droplet camera 17 captures images multiple times for one waveform signal (for example, one ink droplet I).

The control unit 32 acquires from the droplet camera 17 a group of ink shape data, which is a plurality of image data obtained by photographing ink droplets I successively in time by the droplet camera 17 (S12). The control unit 32 may store the group of ink shape data in the memory unit 33.

Next, the model generation unit 32a determines whether mist is generated based on the group of shape data (S13). The model generation unit 32a may determine whether mist is captured in the image data by, for example, pattern matching. Note that the method of image analysis is not particularly limited, and any existing technology may be used.

The model generation unit 32a may, for example, determine that mist is occurring if mist is captured in at least one of the shape data groups, and may determine that mist is not occurring if mist is not captured in any of the shape data groups. The model generation unit 32a may also, for example, determine that mist is occurring if the number of image data pieces in which mist is captured in the shape data group is equal to or greater than a predetermined number, and may determine that mist is not occurring if the number of image data pieces in which mist is captured in the shape data group is less than the predetermined number. The result of determining whether or not mist is occurring is an example of the probability of mist occurring. In other words, step S13 is an example of obtaining the probability of mist occurring in the shape data group.

The model generation unit 32a may also calculate the probability of mist occurring in the shape data group, for example, by tallying up the number of image data pieces that contain mist in the shape data group.

The model generating unit 32a also has a reception unit (not shown) that receives input from the operator, and may receive input of the probability of mist generation from the user for each image data. In other words, the model generating unit 32a does not need to determine whether or not mist is being generated. In this case, when the model generating unit 32a receives input indicating that mist is not being generated via the reception unit, it determines that mist is not being generated, and when the model generating unit receives input indicating that mist is being generated via the reception unit, it determines that mist is being generated. Note that the reception unit is, for example, but is not limited to, a touch panel, a keyboard, a mouse, a button, etc.

If mist is not occurring in the shape data group (No in S13), the model generation unit 32a stores the shape data group acquired in step S12 in the storage unit 33 as a shape data group in a state where mist is not occurring (S14). In addition, if mist is occurring in the shape data group (Yes in S13), the model generation unit 32a stores the shape data group acquired in step S12 in the storage unit 33 as a shape data group in a state where mist is occurring (S15).

The processes from steps S11 to S15 may be repeated. For example, the waveform signal to be applied may be changed, a shape data group corresponding to the changed waveform signal may be obtained, and the processes from step S12 onward may be performed. For example, the processes from steps S11 to S15 may be repeated until the number of teacher data required for learning is obtained.

Note that, for example, at least one of the following is changed in the waveform signal: the time from the second time t2 to the third time t3 shown in FIG. 3, the differential voltage between the third voltage V3 and the fourth voltage V4, and the unit time change in voltage from the third time t3 to the fourth time t4. For example, at least one of the following may be changed in the waveform signal: the time from the second time t2 to the third time t3 shown in FIG. 3, the differential voltage between the third voltage V3 and the fourth voltage V4, the unit time change in voltage from the third time t3 to the fourth time t4, the unit time change in voltage from the first time t1 to the second time t2, and the differential voltage between the second voltage V2 and the first voltage V1. Note that the pre-processing portion of the waveform signal is not changed.

In addition, when the number of shape data groups in a state where mist is generated is small, the model generation unit 32a may, for example, set a waveform signal that is likely to generate mist and perform the processing from step S11 onwards.

Next, the model generation unit 32a generates a learning model by machine learning the relationship between the shape data group and the probability of mist occurrence (S16). The model generation unit 32a uses the shape data group and the presence or absence of mist occurrence as training data, inputs the shape data group into a neural network, and learns the parameters of the neural network so that the probability of mist occurrence is output from the neural network. The parameters are, for example, the weights of each neuron.

In the above, an example has been described in which the model generation unit 32a generates a learning model using a group of shape data obtained by photographing ink droplets I in both a state in which mist is generated and a state in which mist is not generated, but this is not limiting. For example, the model generation unit 32a may generate a learning model using a group of shape data obtained by photographing ink droplets I in either a state in which mist is generated or a state in which mist is not generated. For example, the model generation unit 32a may generate a learning model that outputs the probability of mist being generated from the inkjet head 13 by machine learning the relationship between a group of shape data obtained by photographing ink droplets I in a state in which mist is not generated and the probability that mist is not generated (for example, 100%).

In the above, an example was described in which the learning model is a model that outputs the occurrence probability of mist generation, but it may also be a model that outputs the probability of mist not occurring.

Next, the model generation unit 32a stores the generated learning model in the storage unit 33 (S17). This generates a learning model that can output the probability of mist generation for a group of shape data newly acquired from the inkjet device 10.

Next, the operation of the inkjet system 1 to output a waveform signal will be described with reference to FIG. 9. FIG. 9 is a flow chart showing the operation of the inkjet system 1 according to the present embodiment to output a waveform signal. The operation shown in FIG. 9 is performed in the server device 30, and is performed before the actual start of production (mass production), for example, when setting the conditions for the inkjet device 10. Note that the processing of steps S21 and S22 is similar to steps S11 and S12 shown in FIG. 8, and a description thereof will be omitted. Note that in step S21, a shape data group is obtained that includes multiple shape data that are continuous in time, and is the shape data of ink continuously ejected from the inkjet head 13 by applying a waveform signal.

As shown in FIG. 9, the determination unit 32b inputs the group of shape data acquired in step S22 into a learning model, and acquires the probability of mist generation from the inkjet head 13 output from the learning model (S23). That is, in step S23, the learning model outputs the probability of mist generation. This probability corresponds to the group of shape data acquired in step S22, i.e., the flight state of the ink droplet I.

Next, the determination unit 32b determines whether the probability of mist generation output from the learning model is equal to or greater than a predetermined value (S24). The determination unit 32b performs the determination in step S24, for example, by reading a predetermined value from the storage unit 33 and comparing the read predetermined value with the probability of mist generation output from the learning model. If the probability of mist generation is smaller than the predetermined value (No in S24), the determination unit 32b outputs the waveform signal corresponding to the shape data group acquired in step S22, that is, the waveform signal instructed in step S21, to the inkjet device 10 as a waveform signal that does not generate mist (S25). Specifically, the determination unit 32b transmits a control signal including information indicating the waveform signal to the inkjet device 10. The information indicating the waveform signal may be, for example, the waveform signal itself, identification information for identifying the waveform signal, or information indicating that production may be started with the waveform signal instructed in step S21.

If the probability of mist generation is equal to or greater than a predetermined value (Yes in S24), the determination unit 32b determines whether the probability of mist generation is lower than the previous time (S26). In step S26, the probability of mist generation for the current waveform signal is compared with the probability of mist generation for the previous waveform signal. Note that the probability of mist generation for the previous waveform signal is stored in the memory unit 33, for example.

When the probability of mist generation for the current waveform signal is lower than the probability of mist generation for the previous waveform signal (Yes in S26), the determination unit 32b stores the current waveform signal in the storage unit 33 as a waveform signal in which mist generation is suppressed (S27). It can also be said that the determination unit 32b updates the waveform signal in which mist generation is suppressed. Furthermore, when the probability of mist generation for the current waveform signal is equal to or higher than the probability of mist generation for the previous waveform signal (No in S26), the operation of step S27 is not performed.

Next, the determination unit 32b determines whether there is a waveform signal that has not been determined (S28). For example, the determination unit 32b determines that there is a waveform signal that has not been determined when at least one of the time from the second time t2 to the third time t3 shown in FIG. 3, the differential voltage between the third voltage V3 and the fourth voltage V4, and the unit time change amount of the voltage from the third time t3 to the fourth time t4 has not yet been changed. The determination unit 32b may also determine that there is a waveform signal that has not been determined when the above three parameters have been changed and when at least one of the differential voltage between the third voltage V3 and the fourth voltage V4, and the unit time change amount of the voltage from the third time t3 to the fourth time t4 has not yet been changed.

If there is a waveform signal that has not been judged (Yes in S28), the judgment unit 32b changes the waveform signal (S29). In step S29, the judgment unit 32b changes at least one of the time from the second time t2 to the third time t3, the differential voltage between the third voltage V3 and the fourth voltage V4, the unit time change in voltage from the third time t3 to the fourth time t4, the unit time change in voltage from the first time t1 to the second time t2, and the differential voltage between the second voltage V2 and the first voltage V1 to generate the next waveform signal. The judgment unit 32b may also change a combination of two or more of the above five parameters to be changed to generate the next waveform signal.

In this embodiment, the determination unit 32b changes at least one of the following with priority: the time from the second time t2 to the third time t3, the differential voltage between the third voltage V3 and the fourth voltage V4, and the amount of change in voltage per unit time from the third time t3 to the fourth time t4. This causes the waveform signal to be changed while maintaining the volume and initial velocity of the ink ejected, so that it is possible to determine with priority whether or not there is a waveform signal that can suppress the generation of mist while maintaining the volume of the ink applied, etc.

The determination unit 32b may also change at least one of the above five parameters, for example, using a table that associates the probability of mist generation with the change points in the waveform signal.

Then, the control unit 32 transmits a control signal including the modified waveform signal generated in step S29 to the inkjet device 10, thereby applying the modified waveform signal to the inkjet head 13 and ejecting ink. In other words, the steps from step S21 are repeatedly executed. In other words, the control unit 32 checks whether there is a waveform signal that does not generate mist or can further suppress the generation of mist.

Furthermore, if there are no waveform signals that have not been determined (No in S28), the determination unit 32b outputs the waveform signal stored in step S27 to the inkjet device 10 as a waveform signal that suppresses the generation of mist. The determination unit 32b transmits a control signal to the inkjet device 10 that includes information indicating the waveform signal and information indicating that there was no waveform signal that did not generate mist. This makes it possible to inform the operator that there was no waveform signal that did not generate mist.

As a result, when the inkjet device 10 is used, the waveform signal to be applied to the inkjet head 13 is automatically determined. For example, even if the operator of the inkjet device 10 is not an experienced person, the waveform signal to be applied to the inkjet head 13 can be easily determined.

The timing of the process shown in FIG. 9 is not particularly limited, but may be performed, for example, every time the type or lot of ink is changed, or may be performed periodically, such as at the start of work inspection.

[1-3. Effects, etc.]
As described above, the waveform signal control method according to the present embodiment is a method for controlling a waveform signal applied to inkjet head 13 included in inkjet device 10, in which the first waveform signal is set to a second voltage higher than the first voltage at the first time at a second time after the first time, a third voltage higher than the first voltage at a third time after the second time, and a fourth voltage lower than the third voltage at a fourth time after the third time, and by applying the first waveform signal to inkjet head 13, ink is continuously discharged from inkjet head 13. the shape data indicating the shape of the ink ejected from the inkjet head (the shape of the ink droplet I) being acquired (S22), the shape data group including a plurality of shape data that are continuous in time, outputting the probability of mist generation from the inkjet head 13 based on the shape data group (S23), and if the output probability is equal to or greater than a predetermined value, outputting to the inkjet device 10 information indicating a second waveform signal obtained by changing at least one of the time from the second time to the third time, the differential voltage between the third voltage and the fourth voltage, and the amount of change per unit time of the voltage from the third time to the fourth time, of the first waveform signal.

As a result, when mist occurs in the first waveform signal, information indicating a second waveform signal in which at least one of the parameters related to suppression of mist in the waveform signal, the time from the second time to the third time, the differential voltage between the third voltage and the fourth voltage, and the voltage drop rate from the third time t3 to the fourth time t4, is changed from the first waveform signal can be output to the inkjet device 10. By changing the time from the second time to the third time or the differential voltage between the third voltage and the fourth voltage, the volume of the extension part of the ink droplet I, which is the source of mist generation, is reduced, so that the generation of mist can be suppressed. In addition, by appropriately changing the voltage drop rate from the third time t3 to the fourth time t4 according to the magnitude of the vibration of the meniscus part, the vibration of the meniscus part can be stabilized in a shorter time, so that the generation of mist can be suppressed. Therefore, according to the control method of the waveform signal according to the present embodiment, the generation of mist can be suppressed.

Furthermore, by applying such a second waveform signal to the inkjet head 13 of the inkjet device 10, the generation of mist can be suppressed compared to when the first waveform signal is applied.

The second waveform signal is also generated by changing at least one of the amount of change per unit time of the voltage from the first time to the second time and the differential voltage between the second voltage and the first voltage.

As a result, the second waveform signal is modified from the first waveform signal in at least one of the amount of voltage change per unit time from the first time to the second time and the differential voltage between the second voltage and the first voltage, thereby further suppressing the generation of mist from the inkjet head 13.

The probability of mist generation is output by inputting the acquired group of shape data into a learning model that is trained to receive a group of shape data and output the probability of mist generation.

This makes it possible to output the probability of mist generation without obtaining the probability of mist generation from an external source such as a worker.

As described above, the server device 30 according to this embodiment is a server device 30 that controls a waveform signal applied to the inkjet head 13 of the inkjet device 10, and the first waveform signal is a signal in which a second voltage higher than the first voltage at the first time is set at a second time after the first time, a third voltage higher than the first voltage at a third time after the second time, and a fourth voltage lower than the third voltage at a fourth time after the third time is set, and by applying the first waveform signal to the inkjet head 13, ink is discharged from the inkjet head 13. The communication unit 31 acquires a shape data group including multiple shape data that are continuous in time, the shape data indicating the shape of continuously ejected ink; a control unit 32 outputs the probability that mist will be generated from the inkjet head 13 based on the shape data group; and when the output probability is equal to or greater than a predetermined value, the communication unit 31 outputs to the inkjet device 10 information indicating a second waveform signal in which at least one of the time from the second time to the third time, the differential voltage between the third voltage and the fourth voltage, and the amount of change in voltage per unit time from the third time to the fourth time has been changed from the first waveform signal.

The server device 30 is an example of a control device. The communication unit 31 functions as an acquisition unit and an output unit.

This achieves the same effect as the waveform signal control method described above.

(Embodiment 2)
[2-1. Configuration of Inkjet System]
First, the configuration of the inkjet system according to the present embodiment will be described with reference to Fig. 10. Fig. 10 is a diagram showing an example of a waveform signal condition table according to the present embodiment. The inkjet system according to the present embodiment differs from the inkjet system 1 according to the first embodiment mainly in that a waveform signal condition table is stored in the storage unit 33. The functional configuration of the inkjet system according to the present embodiment is similar to that of the inkjet system 1 according to the first embodiment, and a description thereof will be omitted. In the following description, the inkjet system according to the present embodiment will be described using the functional configuration shown in Fig. 3.

Note that FIG. 10 shows the voltage corresponding to time as a parameter for multiple waveform steps in a waveform signal. By connecting the time and voltage data for each step with lines, a waveform signal such as that shown in FIG. 3 can be obtained.

The memory unit 33 stores a condition table in which parameters of a waveform signal are set to determine a waveform signal that suppresses the generation of mist, as shown in FIG. 10. S1 to S5 shown in FIG. 10 correspond to positions S1 to S5 shown in FIG. 3. Note that time is shown with the time point of position S1 as the reference (zero). Also, FIG. 10 shows an example in which the condition table contains 100 conditions. In other words, 100 waveform patterns are set in the condition table of FIG. 10. Note that there is no particular limit to the number of conditions included in the condition table.

The control unit 32 transmits a control signal including the waveform signal for each condition to the inkjet device 10 in order to apply each waveform signal for each condition included in the condition table to the drive unit 14, and obtains a group of shape data for each waveform signal from the droplet camera 17.

The determination unit 32b obtains the probability of mist generation for each waveform signal of each condition included in the condition table, and transmits the waveform signal for which the probability of mist generation is smaller than a predetermined value to the inkjet device 10. For example, the determination unit 32b may transmit the waveform signal for which the probability of mist generation is the lowest to the inkjet device 10.

[2-2. Operation of the Inkjet System]
Next, the operation of the inkjet system 1 as described above will be described with reference to Fig. 11 and Fig. 12. Fig. 11 is a flow chart showing the operation of the inkjet system 1 according to this embodiment for outputting a waveform signal. The method of generating a learning model by the model generating unit 32a is the same as that in the first embodiment, and the description thereof will be omitted. Also, the predetermined value used in the determination in step S45 will be described as 60%, but the predetermined value is not limited to this.

As shown in Fig. 11, the control unit 32 sets the condition number k in the condition table to k = 1 (S41), reads out the waveform signal of the condition number k from the storage unit 33, and applies it to the inkjet head 13 to eject ink (S42). Specifically, the control unit 32 transmits a control signal including information indicating the waveform signal corresponding to the condition number k = 1 to the inkjet device 10, thereby causing the signal generator 15 to apply the waveform signal to the drive unit 14.

The processing from step S43 to S45 is the same as steps S32 to S34 in FIG. 9, and the description will be omitted. Note that the determination unit 32b may store the probability of mist generation output from the learning model in the memory unit 33.

If the probability of mist generation is less than a predetermined value (No in S45), the determination unit 32b determines that the waveform signal of condition number k=1 is a waveform signal that does not generate mist (S46). In this embodiment, the determination unit 32b outputs, for example, a flag indicating that the waveform signal does not generate mist. Also, if the probability of mist generation is equal to or greater than a predetermined value (Yes in S45), the determination unit 32b determines that the waveform signal of condition number k=1 is a waveform signal that generates mist (S47). In this embodiment, the determination unit 32b does not output, for example, a flag indicating that the waveform signal does not generate mist.

Next, the determination unit 32b stores the probability of mist generation for condition number k in the storage unit 33 (S48). In this embodiment, the determination unit 32b stores, for example, the probability of mist generation and the determination result of the determination unit 32b in association with each other in the storage unit 33. Specifically, the determination unit 32b updates the condition table shown in FIG. 10 based on the probability of mist generation and a flag indicating that mist will not be generated. FIG. 12 is a diagram showing an example of an updated condition table according to this embodiment.

As shown in FIG. 12, the determination unit 32b may store in the memory unit 33 a correspondence between the waveform signal applied to the inkjet head 13 and information indicating the probability of mist generation and whether or not mist is generated. For example, when the waveform signal has condition number k=1, the probability of mist generation is 80%, and the determination unit 32b determines that mist is generated. Also, when the waveform signal has condition number k=3, the probability of mist generation is 55%, and the determination unit 32b determines that mist is not generated.

Next, when the condition table contains N conditions, the determination unit 32b determines whether or not the condition number k=N (S49). That is, the determination unit 32b determines whether or not the processing of steps S42 to S47 has been performed for all conditions (all waveform patterns) in the condition table shown in FIG. 10. When the condition number k=N, that is, when processing has been completed for all conditions in the condition table (Yes in S49), the determination unit 32b outputs the waveform signal of the condition number with the lowest probability of mist generation to the inkjet device 10 as the optimal condition (S50). In the example of FIG. 12, the waveform signal of condition number 3 is output to the inkjet device 10 as the optimal condition. Note that, when there are multiple waveform signals determined to be non-mist generation, the determination unit 32b may output the multiple waveform signals to the inkjet device 10. This allows the operator of the inkjet device 10 to select a waveform signal.

If the condition number k is not equal to N, that is, if there is a condition that has not been processed (No in S49), the determination unit 32b sets k to k+1 (S51) and performs the processing from step S42 onwards for the next condition.

Note that, although the above describes an example in which the processing shown in FIG. 11 is performed for all conditions in the condition table, this is not limiting.

For example, when the tank 11 of the inkjet device 10 is refilled (e.g., replaced) with a second ink of a different type from the first ink used, the determination unit 32b may obtain the probability of mist generation in the second ink by using the waveform signal of the first ink. The determination unit 32b may obtain the probability of mist generation by inputting a shape data group for the waveform signal of the first ink, which is a shape data group for the second ink, into the learning model, and may output the waveform signal of the first ink to the inkjet device 10 as the optimal condition for the second ink (corresponding to S50) when the obtained probability of mist generation is smaller than a predetermined value (corresponding to No in S45). Furthermore, when the obtained probability of mist generation is equal to or greater than a predetermined value (corresponding to Yes in S45), the determination unit 32b may execute the process shown in FIG. 11. This can simplify the process for determining the waveform conditions, thereby reducing the power consumption of the server device 30. In addition, since ink can be smoothly replaced in production, the effect of improving productivity can be expected.

In addition, for example, if the probability of mist generation desired by the operator is set in advance, when a condition with a lower probability of mist generation is detected, the determination unit 32b may output a waveform signal of that condition number to the inkjet device 10 as the optimal condition (corresponding to S50). In other words, when a waveform signal that satisfies the probability of mist generation desired by the operator is detected, the processing from step S42 onwards does not need to be performed for the remaining conditions. This makes it possible to output waveform conditions that satisfy the conditions desired by the user with less processing effort.

[2-3. Effects, etc.]
As described above, the waveform signal control method according to the present embodiment is a method for controlling a waveform signal applied to the inkjet head 13 included in the inkjet device 10, and includes inputting a shape data group including a plurality of time-contiguous shape data pieces that indicate the shape of ink continuously ejected from the inkjet head 13 into a learning model that has been trained to output the probability of mist generation from the inkjet head 13, and acquiring a shape data group for each of one or more waveform signals including a plurality of time-contiguous shape data pieces that indicate the shape of ink continuously ejected from the inkjet head 13 by applying one or more waveform signals to the inkjet head 13, thereby acquiring a probability of mist generation from the inkjet head 13 for each of the one or more waveform signals (S44), and outputting information indicating a waveform signal among the one or more waveform signals for which the acquired probability is smaller than a predetermined value to the inkjet device 10 (S50).

As a result, even if the parameters related to suppressing the generation of mist in the waveform signal cannot be identified, information indicating a waveform signal in which the probability of mist generation is smaller than a predetermined value can be output to the inkjet device 10. Therefore, the waveform signal control method according to the present embodiment can suppress the generation of mist.

In addition, by applying such a waveform signal to the inkjet head 13 of the inkjet device 10, the generation of mist can be suppressed compared to when a waveform signal with a probability equal to or greater than a predetermined value is applied.

The one or more waveform signals include a first waveform signal and a second waveform signal different from the first waveform signal, and when a first probability is a probability of being output by inputting a group of shape data when the first waveform signal is applied to the inkjet head 13 into the learning model, and a second probability is a probability of being output by inputting a group of shape data when the second waveform signal is applied to the inkjet head 13 into the learning model, when the second probability is smaller than a predetermined value and smaller than the first probability, information indicating the second waveform signal is output to the inkjet device 10 (S50).

This allows information indicating a waveform signal with a lower probability of mist generation to be output to the inkjet device 10, thereby further suppressing the generation of mist.

As described above, the method for generating a learning model according to this embodiment is a method for generating a learning model used to control the waveform signal applied to the inkjet head 13, and involves applying a waveform signal to the inkjet head 13 to obtain a shape data group including a plurality of time-continuous shape data pieces, and obtaining the probability of mist occurrence (probability of mist occurrence) in the shape data group (S13). The relationship between the shape data group and the occurrence probability is machine-learned to generate a learning model that takes the shape data group as input and outputs the probability of mist occurrence from the inkjet head 13 (S16).

This makes it possible to generate a learning model that is trained to use a group of shape data as input and output the probability of mist being generated from the inkjet head 13. By using such a learning model to output the probability of mist being generated, it becomes possible to automatically obtain the probability of mist being generated.

As described above, the server device 30 according to this embodiment is a server device 30 that controls the waveform signal applied to the inkjet head 13 equipped in the inkjet device 10, and includes a control unit 32 that acquires the probability of mist generation from the inkjet head 13 for each of the one or more waveform signals by inputting a shape data group including a plurality of shape data that are continuous in time, which is shape data indicating the shape of ink continuously ejected from the inkjet head 13, obtained by applying one or more waveform signals to the inkjet head 13, and which includes a plurality of shape data that are continuous in time, to a learning model that has been trained to output the probability of mist generation from the inkjet head 13, and a communication unit 31 that outputs information indicating which of the one or more waveform signals has a probability smaller than a predetermined value to the inkjet device 10.

The server device 30 is an example of a control device. The communication unit 31 functions as an output unit.

This achieves the same effect as the waveform signal control method described above.

(Embodiment 3)
[3-1. Configuration of Inkjet System]
First, the configuration of inkjet system 1a according to the present embodiment will be described with reference to Fig. 13. Fig. 13 is a block diagram showing the functional configuration of inkjet system 1a according to the present embodiment. Inkjet system 1a according to the present embodiment differs from inkjet system 1 according to embodiment 1 mainly in that inkjet system 1a according to the present embodiment includes a display device 160. In inkjet system 1a according to the present embodiment, components similar to those in inkjet system 1 according to embodiment 1 are denoted by the same reference numerals, and descriptions thereof will be omitted or simplified.

As shown in FIG. 13, the inkjet system 1a includes an inkjet device 110, a network 20, a server device 30, and a display device 160.

The inkjet device 110 does not have a droplet camera 17, unlike the inkjet device 10 of the first embodiment. In other words, in this embodiment, the server device 30 determines whether mist is generated from the inkjet head 13 without using a group of shape data obtained by continuously photographing the flight state of the ink droplets I over time. Specifically, the server device 30 acquires shape data including image data of the entire workpiece 50 on which ink has been applied from the workpiece camera 18, and determines whether mist is generated based on the shape data acquired from the workpiece camera 18. The shape data including image data of the entire workpiece 50 is an example of state data that indicates the state of the ink applied to the workpiece 50.

In the following, an example will be described in which the server device 30 makes a judgment based on one piece of image data, but the judgment may also be made based on multiple pieces of image data. For example, the server device 30 may acquire a shape data group including multiple pieces of image data capturing the entirety of each of multiple workpieces 50 to which ink has been applied from the work camera 18, and judge whether or not mist will be generated based on the shape data group acquired from the work camera 18.

The work camera 18 captures image data used to output the probability of mist generation from the inkjet head 13 in the server device 30. Specifically, it captures the workpiece 50 coated with ink ejected from the inkjet head 13. The work camera 18 may capture the entire workpiece 50 in multiple separate images, or may capture the image in one single image. When the entire workpiece 50 is captured in multiple separate images, the multiple image data are combined to generate one image data capturing the entire workpiece 50. In this embodiment, the work camera 18 is an example of a detector that acquires shape data of the workpiece 50 coated with ink ejected from the inkjet head 13.

In addition, the inkjet system 1a may include the inkjet device 10 according to the first embodiment instead of the inkjet device 110. In other words, the inkjet system 1a may include a droplet camera 17.

The model generation unit 32a of the server device 30 is a processing unit for generating a learning model that is trained to input shape data acquired from the work camera 18 and output the probability of mist being generated from the inkjet head 13. In other words, the learning model outputs the probability of mist being generated from the inkjet head 13 based on the state of ink applied to the workpiece 50, which is the object to be printed. The model generation unit 32a generates the above learning model in advance. The learning model is, for example, composed of a neural network, but is not limited to this. The state of the ink includes at least one of the shape, position, and color of the ink.

The model generation unit 32a generates a learning model by, for example, machine learning the relationship between the shape data acquired from the work camera 18 and the probability of mist generation in the shape data. For example, in the machine learning, teacher data that represents the shape data acquired from the work camera 18 in association with the probability of mist generation in the shape data is used. For example, the probability of mist generation may be determined by the result of determining whether or not mist is generated in the shape data. In this way, the learning model is trained by, for example, supervised learning, but may also be trained by other learning methods such as unsupervised learning. In addition, the learning model may be a learning model that is trained to input the shape data acquired from the work camera 18 and output the presence or absence of mist generation from the inkjet head 13.

The learning model trained in this way can output the probability of mist being generated from the inkjet head 13 based on image data of the workpiece 50 to which ink has actually been applied, in the event that mist is generated while the inkjet device 110 is producing using a set waveform signal. In other words, the learning model according to this embodiment is a model for detecting mist generated during production (while the inkjet device 110 is printing).

The determination unit 32b determines whether mist will occur using the learning model generated by the model generation unit 32a and shape data of the workpiece 50 on which ink has been applied, newly acquired by the workpiece camera 18. Specifically, the determination unit 32b determines whether mist will occur based on the probability of mist occurrence, which is the output obtained by inputting the shape data into the learning model. The determination unit 32b determines that mist will occur, for example, if the probability of occurrence is equal to or greater than a predetermined probability.

In addition, if the learning model is trained to output whether or not mist is generated, the determination unit 32b may obtain the presence or absence of mist generation, which is an output obtained by inputting shape data into the learning model. This is also included in the determination by the determination unit 32b of whether or not mist is generated.

The display device 160 is connected to the inkjet device 110 and the server device 30 via the network 20, and displays information received from the inkjet device 110 and the server device 30 to the worker. For example, the display device 160 may display information indicating whether printing on the workpiece 50 was performed normally, that is, whether the workpiece 50 after printing is a good product, based on information from the inkjet device 110. The display device 160 may also display a recommendation to adjust the waveform signal applied to the inkjet head 13, based on information from the server device 30, for example.

The display device 160 is realized, for example, by a liquid crystal panel, but may also be realized by other display panels such as an organic EL panel. The display device 160 may also be equipped with a backlight.

The display device 160 may be provided in the inkjet device 110, or may be a display unit of a terminal device (e.g., a tablet terminal) owned by an operator.

The display device 160 is an example of a presentation device that presents information indicating that the waveform signal is a waveform signal that generates mist from the inkjet head 13. Note that the presentation mode of the presentation device is not limited to display. The presentation device may include a device that presents information using at least one of sound, light, vibration, etc., together with the display device 160 or in place of the display device 160.

According to the inkjet system 1a as described above, even if the generated mist cannot be directly detected, it is possible to determine whether or not mist is generated based on the shape data of the workpiece 50 to which the ink is applied. A case in which the mist cannot be directly detected is, for example, when the inkjet device 110 does not have a droplet camera 17.

[3-2. Operation of the Inkjet System]
Next, the operation of the inkjet system 1a as described above will be described with reference to Fig. 14 to Fig. 16. Fig. 14 is a flowchart showing a method for generating a learning model according to the present embodiment. The flowchart shown in Fig. 14 is performed before production (mass production) is started in the inkjet device 110.

As shown in FIG. 14, the control unit 32 applies a waveform signal to eject ink from the inkjet head 13 and apply ink to the workpiece 50 (S61). Specifically, the control unit 32 transmits a control signal to the inkjet device 110, thereby causing the signal generator 15 to apply a waveform signal to the drive unit 14. The waveform signal applied here may be any waveform signal.

The signal generator 15 of the inkjet device 110 applies a waveform signal to the drive unit 14 based on a control signal from the server device 30, and ejects ink from the nozzle 13c to apply ink to the workpiece 50. This fills the cells of the workpiece 50 with ink. The workpiece camera 18 photographs the state of the ink on the workpiece 50 where the ink droplets I have landed.

The control unit 32 acquires shape data of the workpiece 50, which is image data obtained by photographing the workpiece 50 to which ink has been applied, from the workpiece camera 18 (S62). The control unit 32 may store the ink shape data in the memory unit 33.

Next, the model generating unit 32a determines whether or not mist is generated in the shape data of the workpiece 50 (S63). In other words, the model generating unit 32a determines whether or not mist is generated from the inkjet head 13.

The model generating unit 32a may determine whether mist is generated from the inkjet head 13, for example, by determining whether ink is applied to areas other than the ink application areas on the workpiece 50 by image analysis. The image analysis method is not particularly limited, and any existing technology may be used. The model generating unit 32a may determine that mist is generated when ink is applied to areas other than the ink application areas of the workpiece 50, for example, and may determine that mist is not generated when ink is not applied to areas other than the ink application areas of the workpiece 50. The model generating unit 32a may also determine that mist is generated when the number of inks applied to areas other than the ink application areas of the workpiece 50 is equal to or greater than a predetermined number, and may determine that mist is not generated when the number of inks applied to areas other than the ink application areas of the workpiece 50 is less than a predetermined number. Determining whether mist is generated is an example of obtaining the probability of mist generation.

Figure 15A is a diagram showing the workpiece 50 when no mist is generated according to this embodiment. Figure 15B is a diagram showing the workpiece 50 when mist is generated according to this embodiment. Note that Figures 15A and 15B show the case where the workpiece 50 is a substrate used in an organic EL display. Walls 51 for forming cells are formed on the workpiece 50. The walls 51 are made of, for example, a resin containing fluorine. There are also three types of light-emitting layers corresponding to the three colors RGB, which are represented by light-emitting layers 51R, 51G, and 51B, respectively. The light-emitting layers 51R, 51G, and 51B are formed by ink applied onto the workpiece 50. In this case, the ink is a solution in which the light-emitting layer material is dissolved in a solvent.

In Figures 15A and 15B, the light-emitting layers 51R, 51G, and 51B are filled with the corresponding inks from left to right on the paper. The same ink is filled in the scanning direction, which is the vertical direction on the paper. The work camera 18 may, for example, take images of each row (pixel row) in which cells are lined up in the sub-scanning direction, which is the horizontal direction on the paper. The image data shown in Figures 15A and 15B is a single image data including the entire work 50, synthesized from multiple image data taken for each row.

As shown in FIG. 15A, when no mist is generated, for example, no ink is applied to the wall portion 51. The area of the wall portion 51 in a plan view is an example of an area other than the applied area.

As shown in FIG. 15B, cell X in the upper left shows a state in which mist has been generated, causing ink to be applied outside of cell X. Cell Y in the lower right shows a state in which mist has been generated, causing ink that should have been dropped into an adjacent cell to get mixed in. Note that cells X and Y of workpiece 50 are examples of application areas.

The determination unit 32b may determine that mist is occurring, for example, based on the position of the ink applied on the workpiece 50. The determination unit 32b may determine that mist is occurring, for example, when ink is applied outside the area of cell X. The determination unit 32b may also determine that mist is occurring, based on the colors of the light-emitting layers 51R, 51G, and 51B. For example, when at least one of the light-emitting layers 51R, 51G, and 51B is not the desired color, the determination unit 32b may determine that mist is occurring because there is a possibility that ink that should not be dropped into that cell has been mixed in. For example, it is assumed that ink that should be dropped into an adjacent cell has been mixed in.

When the determination unit 32b determines whether mist is being generated based on the colors of the light-emitting layers 51R, 51G, and 51B, the work camera 18 is, for example, a color camera.

The model generating unit 32a has a receiving unit (not shown) that receives input from the user, and may receive input from the user regarding the presence or absence of mist generation in the image data. In other words, the model generating unit 32a does not need to determine whether or not mist is being generated. In this case, when the model generating unit 32a receives input indicating that mist generation is not occurring via the receiving unit, it determines that mist is not being generated, and when the model generating unit receives input indicating that mist generation is occurring via the receiving unit, it determines that mist is being generated. The receiving unit is, for example, but is not limited to, a touch panel, a keyboard, a mouse, a button, etc.

Referring again to FIG. 14, if mist is not occurring in the shape data of the workpiece 50 (No in S63), the model generation unit 32a stores the shape data acquired in step S62 in the storage unit 33 as shape data in a state where mist is not occurring (S64). Also, if mist is occurring in the shape data (Yes in S63), the model generation unit 32a stores the shape data acquired in step S62 in the storage unit 33 as shape data in a state where mist is occurring (S65).

The processes from steps S61 to S65 may be repeated. For example, the waveform signal to be applied may be changed, shape data corresponding to the changed waveform signal may be obtained, and the processes from step S62 onward may be performed. For example, the processes from steps S61 to S65 may be repeated until the number of teacher data required for learning is obtained.

Next, the model generation unit 32a generates a learning model by machine learning the relationship between the shape data and the probability of mist occurrence (S66). The model generation unit 32a uses the shape data and the probability of mist occurrence as training data, inputs the shape data into a neural network, and learns the parameters of the neural network so that the probability of mist occurrence is output from the neural network. The parameters are, for example, the weights of each neuron.

In the above, an example has been described in which the model generation unit 32a generates a learning model using shape data of the workpiece 50 in both a state in which mist is generated and a state in which mist is not generated, but this is not limiting. For example, the model generation unit 32a may generate a learning model using shape data of one of the workpieces 50 in a state in which mist is generated and a state in which mist is not generated. For example, the model generation unit 32a may generate a learning model that outputs the probability of mist being generated from the inkjet head 13 by machine learning the relationship between the shape data of the workpiece 50 in a state in which mist is not generated and the probability of mist being generated (e.g., 0%).

In the above, an example was described in which the learning model is a model that outputs the occurrence probability of mist generation, but it may also be a model that outputs the probability of mist not occurring.

Next, the model generation unit 32a stores the generated learning model in the storage unit 33 (S67). This generates a learning model that can output the probability of mist generation for the shape data newly acquired from the inkjet device 110.

Next, the operation of outputting a waveform signal of the inkjet system 1a will be described with reference to FIG. 16. FIG. 16 is a flow chart showing the operation of outputting a waveform signal of the inkjet system 1a according to this embodiment. Note that the operation shown in FIG. 16 is an operation performed in the server device 30. Also, the operation shown in FIG. 16 is performed, for example, after production (mass production) by the inkjet device 110 has started. Also, the operation shown in FIG. 16 is performed for each of the workpieces 50, which are the objects to be printed by the inkjet device 110.

As shown in FIG. 16, the control unit 32 applies a waveform signal to eject ink from the inkjet head 13 and apply ink to the workpiece 50 (S71). Specifically, the control unit 32 transmits a control signal to the inkjet device 110, causing the signal generator 15 to apply a waveform signal to the drive unit 14. The waveform signal applied here may be, for example, a waveform signal determined before production according to embodiment 1 or 2.

The signal generator 15 of the inkjet device 110 applies a waveform signal to the drive unit 14 based on a control signal from the server device 30, thereby ejecting ink from the nozzle 13c and applying the ink to the workpiece 50. The workpiece camera 18 photographs the state of the ink on the workpiece 50 where the ink droplets I have landed.

The control unit 32 acquires shape data of the workpiece 50, which is image data obtained by photographing the workpiece 50 to which ink has been applied, from the workpiece camera 18 (S72). The control unit 32 may store the shape data of the workpiece 50 in the memory unit 33.

Next, the determination unit 32b inputs the shape data acquired in step S72 into the learning model (S73) to acquire the probability that mist will be generated from the inkjet head 13 output from the learning model. This probability corresponds to the shape data acquired in step S72, i.e., the ink application position, application shape, or ink color in the application area.

Next, the determination unit 32b determines whether the probability of mist generation obtained from the learning model is equal to or greater than a predetermined value (S74). The predetermined value is set in advance and is stored, for example, in the storage unit 33. If the probability of mist generation is equal to or greater than the predetermined value (Yes in S74), the determination unit 32b ejects the workpiece 50 as a defective product (S75). Then, the determination unit 32b outputs a recommendation to adjust the waveform signal applied to the inkjet head 13 to the display device 160 (S76). Specifically, the determination unit 32b displays the information by outputting information indicating that the waveform signal should be adjusted or information indicating that mist is being generated to the display device 160. This allows the operator of the inkjet device 110 to adjust the waveform parameters (for example, the voltage or time at positions S1 to S5 shown in FIG. 3) as appropriate in response to the recommendation.

If the probability of mist generation is less than a predetermined value (No in S74), the determination unit 32b supplies the workpiece 50 to the next process (S77). In other words, if the result in step S74 is No, production of the workpiece 50 by applying ink continues.

Conventionally, the printing condition has been checked, for example, when setting the conditions for the inkjet device 110 or during random inspection during production. However, because mist is not reproducible, there is a possibility that the occurrence of mist may be overlooked with conventional inspections.

In contrast, the inkjet system 1a according to this embodiment performs the operation shown in FIG. 16 for each workpiece 50, making it possible to detect the occurrence of mist that is not reproducible. Therefore, it is possible to detect the occurrence of mist more accurately and automatically than in the past.

In addition, the inkjet system 1a can display a recommendation indicating that the waveform signal applied to the inkjet head 13 needs to be adjusted, so that if mist occurs, the operator can be notified immediately. The operator can take measures to suppress the mist based on the recommendation, thereby suppressing the generation of mist from the inkjet head 13.

In addition, when the inkjet system 1a includes the droplet camera 17, after displaying the recommendation in step S76, the inkjet system 1a may perform processing to control the waveform signal in which the generation of mist is suppressed based on the waveform signal control method described in the first or second embodiment. Specifically, the determination unit 32b may perform the operation shown in FIG. 9 or FIG. 11 after step S76.

[3-3. Effects, etc.]
As described above, the information processing method according to this embodiment includes inputting status data indicating the state of ink on workpiece 50 to which ink ejected from inkjet head 13 has been applied, and inputting status data acquired by applying a waveform signal to inkjet head 13 into a learning model trained to output the probability of mist being generated from inkjet head 13, thereby acquiring the probability of mist being generated from inkjet head 13 in a state in which the waveform signal is applied (S73), and if the acquired probability is equal to or greater than a predetermined value (Yes in S74), outputting information indicating that the waveform signal is a waveform signal that generates mist from inkjet head 13 to display device 160 (S76).

The display device 160 is an example of a presentation device.

As a result, even if the mist from the inkjet head 13 cannot be directly detected in the inkjet device 110 equipped with the inkjet head 13, the presence or absence of mist generation can be determined by acquiring status data of the workpiece 50 on which ink has been applied. If mist is generated, it is possible to prompt the user to adjust the waveform signal applied to the inkjet head 13. Information indicating that the waveform signal generates mist is displayed on the display device 160, and the operator of the inkjet device 110 can take measures to suppress the mist, thereby suppressing the generation of mist from the inkjet head 13.

The status data is also image data obtained by photographing the workpiece 50.

As a result, by acquiring image data of the workpiece 50, it is possible to determine whether mist is occurring. For example, if the inkjet device 110 is equipped with a camera for detecting the printing state of the workpiece 50, it is possible to determine whether mist is occurring using image data captured by the camera. In other words, it is possible to determine whether mist is occurring without requiring any additional device.

As described above, the method for generating a learning model according to this embodiment is a method for generating a learning model used to control the waveform signal applied to the inkjet head 13, and includes obtaining status data indicating the state of the ink on the workpiece 50 onto which the ink ejected from the inkjet head 13 is applied by applying a waveform signal to the inkjet head 13 (S62), obtaining the probability of mist generation in the status data (S63), and generating a learning model that takes the status data as input and outputs the probability of mist generation from the inkjet head 13 by machine learning the relationship between the status data and the occurrence probability (S66).

This makes it possible to generate a learning model that is trained to use status data as input and output the probability of mist generation from the inkjet head 13. By using such a learning model to output the probability of mist generation, it becomes possible to automatically obtain the probability of mist generation.

As described above, the server device 30 according to this embodiment is equipped with a control unit 32 that inputs status data indicating the state of the ink on the workpiece 50 to which the ink ejected from the inkjet head 13 has been applied, and acquires the probability of mist being generated from the inkjet head 13 when the waveform signal is applied by inputting status data acquired by applying a waveform signal to the inkjet head 13 into a learning model that has been trained to output the probability of mist being generated from the inkjet head 13, and a communication unit 31 that outputs information indicating that the waveform signal is a waveform signal that generates mist from the inkjet head 13 to a display device 160 when the acquired probability is equal to or greater than a predetermined value.

The server device 30 is an example of a control device, and the display device 160 is an example of a presentation device. The communication unit 31 functions as an output unit.

This achieves the same effect as the waveform signal control method described above.

(Other embodiments)
Although each embodiment (hereinafter also referred to as "embodiments") has been described above, the present disclosure is not limited to such embodiments.

For example, the inkjet device in the above-mentioned embodiments can be used in an inkjet device that applies liquid to various objects using an inkjet head capable of ejecting liquid. The object can be made of any material, as long as it can be applied with ink (including, for example, a liquid containing ink), and may be, for example, paper, a substrate, plastic, film, textile, metal, etc. Furthermore, the inkjet device may be mounted on any device that has the function of applying ink.

In addition, in the above embodiment, an example has been described in which image data for generating the learning model and image data for determining whether mist is generated are obtained from the same inkjet device, but this is not limiting. Image data for generating the learning model may be obtained, for example, using an inkjet device different from the inkjet device that controls the waveform signal (for example, an inkjet device with similar device specifications to the inkjet device that controls the waveform signal).

In addition, in the above embodiment and the like, the inkjet device is an example of a circulation type inkjet device that circulates ink between the tank and the inkjet head, but the present invention is not limited to this. The inkjet device may be configured not to circulate ink.

In addition, in the above-mentioned third embodiment, a case where the inkjet system does not include a droplet camera has been described, but the present invention is not limited to this. The inkjet system according to the third embodiment may include a droplet camera. In this case, the inkjet system may determine whether or not mist is generated from the inkjet head based on image data captured by at least one of the droplet camera and the work camera. The inkjet system may determine whether or not mist is generated from the inkjet head based on image data captured by both the droplet camera and the work camera. For example, the inkjet system may determine that mist is generated from the inkjet head when at least one of the determination result of whether or not mist is generated based on the image data captured by the droplet camera and the determination result of whether or not mist is generated based on the image data captured by the work camera indicates that mist is generated.

The division of functional blocks in the block diagrams shown in Figures 2 and 13 is merely an example, and multiple functional blocks may be realized as one functional block, one functional block may be divided into multiple blocks, or some functions may be transferred to other functional blocks. In addition, the functions of multiple functional blocks having similar functions may be processed in parallel or in a time-shared manner by a single piece of hardware or software.

In the above embodiments, the inkjet device and the server device are each realized as a single device, but they may be realized as multiple devices connected to each other. Also, at least some of the functions of the server device may be provided by the inkjet device. For example, the inkjet device may have all of the functional configuration of the server device. In other words, the inkjet device may have the functions of the server device built in.

Furthermore, the communication method between the devices in the inkjet system in the above-described embodiment is not particularly limited. Either wireless communication or wired communication may be performed between the devices.

The order in which each step in the flowchart is executed is merely an example to specifically explain the present disclosure, and orders other than those described above may also be used. For example, some of the steps may be executed simultaneously (in parallel) with other steps, or may be executed in a different order than the other steps.

In addition, some or all of the components of the inkjet system in the above embodiments may be configured from a single system LSI (Large Scale Integration).

A system LSI is an ultra-multifunctional LSI manufactured by integrating multiple components onto a single chip, and specifically, is a computer system that includes a microprocessor, ROM, RAM, etc. Computer programs are stored in the ROM. The system LSI achieves its functions when the microprocessor operates according to the computer program.

Note that although the term system LSI is used here, it may also be called IC, LSI, super LSI, or ultra LSI depending on the level of integration. Furthermore, the method of integration is not limited to LSI, but may be realized with a dedicated circuit or a general-purpose processor. It is also possible to use an FPGA (Field Programmable Gate Array) that can be programmed after LSI manufacture, or a reconfigurable processor that can reconfigure the connections and settings of circuit cells inside the LSI.

Furthermore, if an integrated circuit technology that can replace LSI emerges due to advances in semiconductor technology or other derived technologies, it is natural that such technology can be used to integrate functional blocks. The application of biotechnology, etc. is also a possibility.

An aspect of the present disclosure may be a computer program that causes a computer to execute each of the characteristic steps included in the waveform signal control method. An aspect of the present disclosure may be a computer-readable non-transitory recording medium on which such a computer program is recorded.

In the above embodiments, each component may be configured with dedicated hardware, or may be realized by executing a software program suitable for each component. Each component may be realized by a program execution unit such as a CPU or processor reading and executing a software program recorded on a recording medium such as a hard disk or semiconductor memory.

In addition, the present invention also includes forms obtained by applying various modifications to the embodiments that a person skilled in the art may conceive, or forms realized by arbitrarily combining the components and functions of each embodiment within the scope of the spirit of the present invention.

This disclosure is useful for controlling a waveform signal applied to an inkjet head of an inkjet device.

REFERENCE SIGNS LIST 1, 1a Inkjet system 10, 110 Inkjet device 10a, 32 Control unit 11 Tank 12 Flow path 12a Pump 13 Inkjet head 13a Main body 13b Pressure chamber 13c Nozzle 14 Driving unit 15 Signal generator 16 Light source 17 Droplet camera (detector)
18 Work camera (detector)
19 Communication unit 20 Network 30 Server device (control device)
31 Communication unit (acquisition unit, output unit)
32a Model generation unit 32b Determination unit 33 Memory unit 40 Scanning stage 50 Workpiece 51 Wall unit 51R, 51G, 51B Light-emitting layer 160 Display device (presentation device)
A: Imaging surface I, I1, I2, I3: Droplets S1 to S5: Position T: Interval T1 to T9: Time t1: First time t2: Second time t3: Third time t4: Fourth time t5: Fifth time V1: First voltage V2: Second voltage V3: Third voltage V4: Fourth voltage V5: Fifth voltage X, Y: Cell

Claims (6)

A method for controlling a waveform signal applied to an inkjet head of an inkjet device, comprising the steps of:
the first waveform signal is set to a second voltage higher than a first voltage at a second time point after a first time point, a third voltage higher than the first voltage at a third time point after the second time point, and a fourth voltage lower than the third voltage at a fourth time point after the third time point,
acquiring a shape data group including a plurality of shape data that are continuous in time, the shape data being indicative of a shape of ink continuously ejected from the inkjet head by applying the first waveform signal to the inkjet head;
outputting a probability of mist generation from the inkjet head based on the group of shape data, the probability being based on the group of shape data ;
outputting, when the output probability is equal to or greater than a predetermined value, information indicating a second waveform signal obtained by changing at least one of the time from the second time to the third time, the differential voltage between the third voltage and the fourth voltage, and the amount of change in voltage per unit time from the third time to the fourth time, of the first waveform signal to the inkjet device;
A method for controlling a waveform signal. A method for controlling a waveform signal applied to an inkjet head of an inkjet device, comprising the steps of:
the first waveform signal is set to a second voltage higher than a first voltage at a second time point after a first time point, a third voltage higher than the first voltage at a third time point after the second time point, and a fourth voltage lower than the third voltage at a fourth time point after the third time point,
acquiring a shape data group including a plurality of shape data that are continuous in time, the shape data being indicative of a shape of ink continuously ejected from the inkjet head by applying the first waveform signal to the inkjet head;
outputting a probability of mist generation from the inkjet head based on the group of shape data;
outputting, when the output probability is equal to or greater than a predetermined value, information indicating a second waveform signal obtained by changing at least one of the time from the second time to the third time and the amount of change in voltage per unit time from the third time to the fourth time, of the first waveform signal to the inkjet device;
A method for controlling a waveform signal. the second waveform signal is generated by changing at least one of a change amount per unit time of a voltage from the first time point to the second time point and a differential voltage between the second voltage and the first voltage.
3. A method for controlling a waveform signal according to claim 1 or 2 . The probability of mist generation is output by inputting the acquired shape data group into a learning model that is trained to input the shape data group and output the probability of mist generation.
The method for controlling a waveform signal according to any one of claims 1 to 3 . A control device for controlling a waveform signal applied to an inkjet head of an inkjet device,
the first waveform signal is set to a second voltage higher than a first voltage at a second time point after a first time point, a third voltage higher than the first voltage at a third time point after the second time point, and a fourth voltage lower than the third voltage at a fourth time point after the third time point;
an acquisition unit that acquires a shape data group including a plurality of shape data that are continuous in time, the shape data being indicative of a shape of ink continuously ejected from the inkjet head by applying the first waveform signal to the inkjet head;
a control unit that outputs a probability of mist generation from the inkjet head based on the group of shape data, the probability being based on the group of shape data ;
an output unit that outputs, when the output probability is equal to or greater than a predetermined value, information indicating a second waveform signal obtained by changing at least one of the time from the second time to the third time, the differential voltage between the third voltage and the fourth voltage, and the amount of change in voltage per unit time from the third time to the fourth time, of the first waveform signal, to the inkjet device;
Control device. A control device for controlling a waveform signal applied to an inkjet head of an inkjet device,
the first waveform signal is set to a second voltage higher than a first voltage at a second time point after a first time point, a third voltage higher than the first voltage at a third time point after the second time point, and a fourth voltage lower than the third voltage at a fourth time point after the third time point,
an acquisition unit that acquires a shape data group including a plurality of shape data that are continuous in time, the shape data being indicative of a shape of ink continuously ejected from the inkjet head by applying the first waveform signal to the inkjet head;
a control unit that outputs a probability of mist being generated from the inkjet head based on the group of shape data;
an output unit that outputs, when the output probability is equal to or greater than a predetermined value, information indicating a second waveform signal obtained by changing at least one of the time from the second time to the third time and the amount of change in voltage per unit time from the third time to the fourth time, of the first waveform signal, to the inkjet device;
Control device.

Images