JP6828300B2 - Abnormality analysis system and analysis equipment - Google Patents

Description

The present invention relates to an abnormality analysis system and an analysis device used in the abnormality analysis system.

Patent Document 1 describes a method for monitoring grinding burn of a workpiece. During grinding of the workpiece, the grinding load of the grindstone and the rotation speed of the workpiece are detected, and the presence or absence of grinding burn is determined by comparing with the threshold value for the grinding load according to the rotation speed. Here, the threshold value is set based on the grinding load of the grindstone with respect to the rotation speed of the workpiece when the grinding burn of the workpiece occurs.

Patent Document 2 describes that trial grinding is performed and a threshold value is set based on the grinding load in the trial grinding. After that, the presence or absence of a grinding abnormality is determined by comparing the grinding load detected in the actual grinding with the threshold value.

Further, Patent Document 3 describes that a quality abnormality of a product is predicted based on the following quality tendency pattern. For example, when grinding the outer peripheral surface of a workpiece with a grindstone, the dimensional accuracy tends to deteriorate as the number of workpieces increases (see FIG. 4 of Patent Document 3). Further, from the relationship between the grinding time and the grinding resistance in one workpiece, the relationship between the number of workpieces and the average value of the grinding resistance is obtained (see FIGS. 5 and 10 of Patent Document 3). Then, by considering the relationship between the number of workpieces and the dimensional accuracy, it is possible to set a threshold value for the average value of the grinding resistance in the quality tendency pattern showing the relationship between the number of workpieces and the average value of the grinding resistance. That is, by grasping the grinding resistance and the number of workpieces, it is possible to predict the abnormality of the product based on the above-mentioned quality tendency pattern and threshold value.

JP 2013-129027 International Publication No. 2012/098805 Japanese Unexamined Patent Publication No. 2014-154894

In recent years, it is said to be the IoT (Internet of Things) era, and the utilization of big data acquired by connecting a large number of things to the Internet is expected. It is also expected that production equipment will perform anomalous analysis of production objects based on a large amount of information obtained from the production equipment.

In recent years, cloud computing has been known. Cloud computing is a form of using a computer connected via the Internet or the like. For example, instead of using the data and applications stored in the computer at hand, the data stored in the computer connected via the Internet etc. can be used on the computer at hand, or the application of the computer can be used. To do.

It is conceivable to utilize big data of production equipment by using cloud computing. However, in cloud computing, communication congestion may occur because huge amounts of data are being communicated. Furthermore, when the distance to the cloud server is long, the communication time becomes long. For these reasons, it lacks speed when using cloud computing.

If the analysis result can be fed back to the production equipment at an early stage when the abnormality analysis of the production equipment is performed, the effect of suppressing the occurrence of the abnormality of the production object can be expected. Therefore, it is not sufficient to use cloud computing as it is as an abnormality analysis system for production equipment.

An object of the present invention is to provide an anomaly analysis system capable of analyzing based on information of a large number of production facilities and feeding back the analysis results to the production facilities at an early stage, and an analysis device used therefor.

(1. Abnormality analysis system)
The anomaly analysis system according to the present invention is a facility for producing a production object, and is connected to a plurality of production facilities each equipped with one or a plurality of detectors and the plurality of production facilities to construct fog computing. Data analysis is performed based on the first network installed in the predetermined area and the detection information of the detector connected to the first network and acquired via the first network, and the result of the data analysis. It is provided with an analysis device that generates determination information regarding an abnormality of each of the plurality of production facilities or an abnormality of the production object based on the above. Each of the plurality of production facilities includes an abnormality determination device that determines an abnormality of each of the plurality of production facilities or an abnormality of the production object based on the determination information generated by the analysis device.

The detector and the analysis device in the plurality of production facilities are connected to each other via a first network installed in a predetermined area for constructing fog computing. Fog computing is a network-connected system in a smaller area than cloud computing. That is, the first network for constructing fog computing is a network installed in a predetermined area narrower than the area for constructing cloud computing. Therefore, in the data communication between the detector and the analysis device, the occurrence of communication congestion is suppressed. Further, since the first network is constructed in a narrow predetermined area, the communication time between the production equipment and the analysis device can be shortened. Therefore, the analysis device can receive the detection information by the detector at high speed.

Since the analysis device can acquire detection information in a plurality of production facilities at an early stage and perform analysis, the results of the analysis device can be fed back to the production facilities at an early stage. Since the analysis result can be fed back to the production equipment at an early stage, it is possible to suppress the occurrence of an abnormality of the production object earlier and more reliably.

(2. Analytical device)
The analysis device according to the present invention is the analysis device used in the above-mentioned abnormality analysis system. According to the analysis device, the effect of the above-mentioned abnormality analysis system can be obtained.

It is a figure which shows the abnormality analysis system. It is a figure which shows the structure of the grinding machine as an example of the production equipment of FIG. It is a block diagram of a production facility. It is a figure which shows the behavior of the power of the motor of the grindstone with respect to the elapsed time from the start of grinding of one production object. It is a figure which shows the structure of the analysis apparatus of FIG. In the first embodiment, the flow of detailed processing of the abnormality determination device, the analysis device, and the upper analysis device is shown. In the second embodiment, the flow of detailed processing of the abnormality determination device, the analysis device, and the upper analysis device is shown. In the second embodiment, it is a graph which shows the result of the frequency analysis by the abnormality determination apparatus. In the second embodiment, it is the figure which shows the 1st example of the abnormality determination by the abnormality determination apparatus, and is the figure about the peak value (evaluation parameter) of the vibration amplitude in the time zone (specified parameter) of one day. In the second embodiment, it is a figure which shows the 2nd example of the abnormality determination by the abnormality determination apparatus, and is the figure about the peak value (evaluation parameter) of the vibration amplitude at the time of one year (specified parameter). It is a figure explaining the generation of the pattern of the determination information in the 1st example by the analysis apparatus in the 2nd Embodiment. It is a figure explaining the generation of the pattern of the determination information in the 2nd example by the analysis apparatus in 2nd Embodiment. In the third embodiment, the flow of detailed processing of the abnormality determination device, the analysis device, and the upper analysis device is shown. In the third embodiment, it is a figure which shows the abnormality determination by the abnormality determination apparatus, and is the figure about the current value (evaluation parameter) of the power of the motor at the environmental temperature (specified parameter). It is a figure explaining the generation of the pattern of the determination information by an analysis apparatus in the 3rd Embodiment.

<1. First Embodiment>
(1-1. Configuration of anomaly analysis system)
The configuration of the abnormality analysis system 1 of the present embodiment will be described with reference to FIG. As shown in FIG. 1, the abnormality analysis system 1 includes production equipment 11 to 13, other production equipment 21 to 23, a fog network 31 connected to production equipment 11 to 13, and other production equipment 21 to 23. It includes another fog network 32 connected to the fog network 32, a cloud network 40 connected to the fog networks 31 and 32, an analysis device 50, another analysis device 60, and a higher level analysis device 70. Here, the analysis devices 50 and 60 and the upper analysis device 70 can be, for example, an embedded system such as a PLC (Programmable Logic Controller) or a CNC (Computerized Numerical Control) device, or can be a personal computer, a server, or the like. it can.

Production equipment 11 to 13 (corresponding to the production equipment of the present invention) are equipment for producing a predetermined production object. The other production facilities 21 to 23 (corresponding to the other production facilities of the present invention) are facilities for producing a predetermined production object. The production objects produced by the production facilities 11 to 13 and the production objects produced by the other production facilities 21 to 23 may be of the same type or different types.

The production facilities 11 and 21 are, for example, machine tools in charge of the first processing process in the production line, such as a grinding machine for grinding a crankshaft. The production facilities 13 and 23 are machine tools in charge of the second processing process, such as a grinding machine that grinds the crankshaft in the same manner as described above. The production facilities 12 and 22 are a transport machine or the like that transports a production object between the production facilities 11 and 13 or between the production facilities 21 and 23.

Further, the production facilities 11 to 13 are installed in the same building or in a neighboring building. The other production facilities 21 to 23 are installed in the same building or in a neighboring building, and are installed in a building in a place different from the production facilities 11 to 13. For example, when the production facilities 11 to 13 are installed in Japan and the other production facilities 21 to 23 are installed in a country other than Japan, or when the production facilities 11 to 13 and the other production facilities 21 to 23 are different. , Both are installed in Japan, but there are cases where they are installed in distant areas.

That is, the production facilities 11 to 13 are installed in a predetermined area where fog computing described later can be constructed. Similarly, other production facilities 21 to 23 are also installed in a predetermined area where fog computing can be constructed. However, the production facilities 11 to 13 and the other production facilities 21 to 23 are installed in an area where fog computing cannot be constructed.

Here, fog computing is a network-connected system in a narrow area as compared with cloud computing. That is, the network for constructing fog computing is a network installed in a predetermined area narrower than the area for constructing cloud computing. Fog computing is sometimes referred to as edge computing.

The fog network 31 (corresponding to the first network of the present invention) is a network connected to production facilities 11 to 13 and installed in a predetermined area for constructing fog computing. The fog network 31 is installed in the same building as the building where the production facilities 11 to 13 are installed, or is installed in the building where any of the production facilities 11 to 13 is installed and the neighboring building. There is.

The other fog network 32 is a network that is connected to other production facilities 21 to 23 and is installed in a predetermined area for constructing fog computing. The other fog network 32 is installed in the same building as the building in which the other production facilities 21 to 23 are installed, or is in the vicinity of the building in which any of the other production facilities 21 to 23 is installed. It is installed in the building. Further, the other fog network 32 is not directly connected to the fog network 31. Here, the fog networks 31 and 32 can be applied to the Internet, a local area network (LAN), a wide area network (WAN), and the like.

The cloud network 40 (corresponding to the second network of the present invention) is a network connected to the fog networks 31 and 32. The cloud network 40 is a network having a wider area than the fog networks 31 and 32, and is, for example, the Internet. Therefore, the cloud network 40 is a network that connects the production facilities 11 to 13 and the other production facilities 21 to 23.

The analysis device 50 is directly connected to the fog network 31 and is installed in the same building as the building in which the production facilities 11 to 13 are installed or in a nearby building. The analysis device 50 analyzes data based on the detection information acquired from the production equipments 11 to 13. The analysis device 50 acquires, for example, the detection information for one day of the production equipments 11 to 13 and analyzes the data every day. Data analysis can also be learned by repeating it many times. Then, the analysis device 50 stores the determination information regarding the abnormality of the production equipments 11 to 13 or the abnormality of the production object by the production equipments 11 to 13 as the result of the data analysis. Further, the analysis device 50 acquires the result of the upper data analysis by the upper analysis device 70, which will be described later, and determines the determination information based on the result of the data analysis by the analysis device 50 and the result of the upper data analysis by the upper analysis device 70. And memorize.

The other analysis device 60 is directly connected to the fog network 32 and is installed in the same building as the building in which the production facilities 21 to 23 are installed or in a nearby building. The other analysis device 60 analyzes the data based on the detection information acquired from the other production facilities 21 to 23. The other analysis device 60 performs the same processing as the analysis device 50 described above, with the target being another production equipment 21 to 23.

The higher-level analysis device 70 is connected to the cloud network 40 and performs higher-level data analysis based on the acquired information. That is, the higher-level analysis device 70 acquires information from the production facilities 11 to 13 and also acquires information from the other production facilities 21 to 23 via the cloud network 40 and the fog networks 31 and 32, respectively. The higher-level analysis device 70 targets higher-level data analysis that requires a longer time than data analysis by the analysis devices 50 and 60, and targets higher-level data analysis that uses a large amount of information. The upper analyzer 70 acquires the detection information of the production equipments 11 to 13 and other production equipments 21 to 23 for one week, several weeks, one month or several months, and during the acquisition period, for example. Perform data analysis according to the situation. Higher-level data analysis can also be learned by repeating it many times.

(1-2. Configuration of production equipment 11)
Next, an example of the configuration of the production equipment 11 will be described with reference to FIGS. 2 to 4. In the present embodiment, the production equipment 11 is, for example, a grinding machine. As an example of the grinding machine 11, a grindstone traverse type grinding machine that traverses the grindstone table 114 with respect to the bed 111 (movement in the Z-axis direction) will be described as an example. However, the grinding machine 11 can also be applied to a table traverse type grinding machine in which the spindle device 112 traverses the bed 111 (movement in the Z-axis direction).

The object (workpiece) produced by the grinding machine 11 is, for example, a crankshaft W. The grinding portion by the grinding machine 11 is a crank journal of a crankshaft, a crank pin, or the like.

The grinding machine 11 is configured as follows. The bed 111 is fixed to the installation surface, and the spindle device 112 and the tailstock device 113 that rotatably support both ends of the crankshaft W are attached to the bed 111. The crankshaft W is supported by the spindle device 112 and the tailstock device 113 so as to rotate about the crank journal. The spindle device 112 includes a motor 112a that rotationally drives the crankshaft W. A detector (vibration sensor) 112b for detecting the vibration of the spindle is attached to the spindle device 112.

Further, a grindstone base 114 that can move in the Z-axis direction (the axial direction of the crankshaft W) and the X-axis direction (the direction orthogonal to the axis of the crankshaft W) is provided on the bed 111. The grindstone base 114 is moved in the Z-axis direction by the motor 114a, and is moved in the X-axis direction by the motor 114b. Further, the grindstone base 114 is provided with a detector 114c for detecting the Z-direction position of the grindstone base 114 and a detector 114d for detecting the X-direction position of the grindstone base 114. The detectors 114c and 114d are rotary encoders and the like that measure the rotation of the motor 114b and the like, and can also be linear position detectors such as a linear scale.

The grindstone table 114 is rotatably provided with a grindstone 115 for grinding a crank pin or a crank journal. The grindstone 115 is rotationally driven by a motor 115a. Further, the grindstone base 114 is provided with a detector 115b that detects the power of the motor 115a and the like. The detector 115b is, for example, a motor wattmeter, but it can also be a voltmeter or an ammeter that measures the voltage or current of the motor 115a. It should be noted that the electric power, voltage, current, etc. of the motor 115a of the grindstone 115 can indirectly obtain the grinding resistance. In addition to the above, the detector 115b can also be used as a load detector provided on the spindle device 112 or the grindstone base 114 to directly obtain the grinding resistance.

Further, the bed 111 is provided with a sizing device 116 for measuring the outer diameter of the crank pin or the crank journal, which is the grinding portion of the crankshaft W. Further, the bed 111 is provided with a detector 117 for detecting the environmental temperature (outside air temperature). Further, the bed 111 includes a pump 118a for supplying coolant to the ground portion, a valve 118b for switching ON / OFF of the coolant supply, and a detector 118c for detecting the state of the valve 118b. The detector 118c is a flow meter for coolant, but may be a pressure sensor or the like for detecting the pressure of coolant.

Further, the grinding machine 11 includes a CNC device 121, a PLC 122, an abnormality determination device 123, and an operation panel 124. Here, the abnormality determination device 123 can be an embedded system of the CNC device 121 or the PLC 122, or can be a personal computer, a server, or the like.

As shown in FIG. 3, the CNC device 121 controls the motors 112a and 115a that rotate the spindle device 112 and the grindstone 115, and controls the motors 114a and 114b that move the grindstone 115 relative to the crankshaft W. .. The CNC device 121 acquires the detectors 114c and 114d at the position of the grindstone base 114 and the power detector 115b of the motor 115a during control.

The PLC 122 acquires the detection information from the sizing device 116. Further, the PLC 122 controls the supply of coolant by controlling the pump 118a and the valve 118b. During this control, the PLC 122 acquires the detection information of the detector 118c that detects the state of the valve 118b. Further, the PLC 122 acquires the detection information of the detector 117 that detects the environmental temperature.

Here, the sampling cycles of the detectors 112b, 114c, 114d, 115b, 116, 117, 118c are not all the same, but at least a part is different. For example, the sampling cycle of the power detector 115b of the motor 115a is several msec, the sampling cycle of the sizing device 116 is several msec, and the sampling cycle of the valve state detector 118c is several tens of msec. The sampling period of the temperature detector 117 is several tens of msec. Each sampling period is appropriately adjusted by the control method.

The abnormality determination device 123 determines an abnormality of the grinding machine 11 or an abnormality of a production object (workpiece). The abnormality determination device 123 stores the threshold value according to the determination target, and determines the abnormality by comparing the detection information by each detector 112b, 114c, 114d, 115b, 116, 117, 118c with the corresponding threshold value. I do.

For example, as shown in FIG. 4, the abnormality determination device 123 stores in advance the threshold values Th11 and Th12 for comparing one production object (workpiece) with the detection information by the power detector 115b of the motor 115a. doing. The threshold values Th11 and Th12 are set so as to change according to the behavior of the power of the motor 115a with respect to the elapsed time from the start of grinding for one production object (workpiece). The threshold value Th11 is the upper limit value, and the threshold value Th12 is the lower limit value.

The abnormality determination device 123 determines an abnormality of the production object by comparing the power of the motor 115a with the threshold values Th11 and Th12. Specifically, in the abnormality determination device 123, when the power of the motor 115a exceeds the upper limit threshold value Th11 or falls below the lower limit threshold value Th12, a state in which the production object does not satisfy the grinding burn or shape accuracy occurs. If so, it is determined that the production object is abnormal. The power of the motor 115a of the grindstone 115 corresponds to the grinding resistance. Therefore, instead of the power of the motor 115a of the grindstone 115, a grinding resistance detected by another detection method can be adopted. For example, Japanese Patent Application Laid-Open No. 2013-129027 describes a determination as to whether or not a product to be produced has grinding burn or the like by comparing the grinding resistance with the threshold value.

Further, the abnormality determination device 123 determines the abnormality of the drive devices 112a, 114a, 114b, 115a, 118a, 118b to be controlled by the CNC device 121 and the PLC 122. For example, the abnormality determination device 123 compares the actual usage value obtained from information such as the usage status and usage history of the motors 114a and 114b with the threshold value stored in advance, so that the ball screw used in the drive mechanism can be used. Judge abnormalities such as bearings. Further, the abnormality determination device 123 determines the abnormality of the valve 118b by comparing the actual usage value obtained from the information such as the usage state and the usage history of the valve 118b with the threshold value stored in advance. The abnormality of the drive mechanism and the abnormality of the valve 118b are used in the sense that not only the failure of the drive mechanism and the valve 118b but also the life and the state requiring maintenance are included.

Here, the threshold value stored in the abnormality determination device 123 is a value different depending on the target grinding machine 11. Even if the production equipment 11 and the other production equipment 21 produce the same object in FIG. 1, the usage environment may be different or the material composition of the production object may be different. In addition, there may be individual differences in the production equipment 11 and 21. Therefore, even when the same object is produced, the threshold value of the production equipment 11 and the threshold value of the other production equipment 21 may be set to different values.

Further, although the production equipment 11 has been described above, the same applies to the production equipments 13, 21, 23 as a grinding machine. Further, the production facilities 12 and 22 as the transfer device are also provided with the abnormality determination device 123. In this case, the abnormality determination device 123 compares the actual usage value obtained from information such as the usage status and usage history of the production equipments 12 and 22 as the transport device with the threshold value stored in advance, for example, transport. It is possible to determine abnormalities (failures, lifespans, and conditions that require maintenance) of the parts that make up the road. Although the abnormality determination device 123 is provided in the production facility 11 as shown in FIG. 2, it may be provided in the analysis device 50.

(1-3. Configuration of analysis device 50)
Next, the configuration of the analysis device 50 will be described with reference to FIG. The analysis device 50 is connected to the detectors 112b, 114c, 114d, 115b, 116, 117, 118c of the production facilities 11 to 13 via the fog network 31. The analysis device 50 acquires the detection information of each of the detectors 112b, 114c, 114d, 115b, 116, 117, 118c of the production facilities 11 to 13 via the fog network 31. Further, the analysis device 50 is also connected to the CNC device 121 and the PLC 122 of the production facilities 11 to 13. The analysis device 50 acquires various control parameters via the fog network 31.

The fog network 31 is constructed in a narrower area than the cloud network 40. Therefore, the analysis device 50 can acquire the detection information of the detectors 112b, 114c, 114d, 115b, 116, 117, 118c of the production equipments 11 to 13 at an early stage from the detection time.

As shown in FIG. 5, the analysis device 50 includes an analysis unit 51, a display unit 52, and an input unit 53. The analysis unit 51 acquires the detection information of each of the detectors 112b, 114c, 114d, 115b, 116, 117, 118c of the production equipments 11 to 13. Here, the analysis unit 51 acquires all the detection information detected by each of the detectors 112b, 114c, 114d, 115b, 116, 117, and 118c. That is, the analysis unit 51 acquires all of the detection information regardless of the sampling period of each of the detectors 112b, 114c, 114d, 115b, 116, 117, 118c. Here, since the analysis unit 51 acquires all of the detected information, the amount of data is enormous, but since the analysis unit 51 goes through the fog network 31, the delay in communication time does not matter.

Further, the analysis unit 51 acquires various control parameters in the production facilities 11 to 13 in addition to the detection information of each detector 112b, 114c, 114d, 115b, 116, 117, 118c. For example, the control parameters in the production equipments 11 and 13 include grinding process information such as the shape and material of the crankshaft W as a production object, the shape and material of the grindstone 115, the grinding depth, and the flow rate of coolant. ..

The analysis unit 51 analyzes the data based on the acquired detection information and various control parameters. Data analysis is so-called data mining. In particular, the analysis unit 51 includes not only the detection information of each detector 112b, 114c, 114d, 115b, 116, 117, 118c in one production facility 11, but also each detector 112b in a plurality of production facilities 11-13. The detection information and the like of 114c, 114d, 115b, 116, 117, 118c are acquired.

Then, the analysis unit 51 can generate determination information regarding an abnormality of the production target by data analysis, and stores this determination information. For example, the analysis unit 51 generates threshold values Th11 and Th12 (shown in FIG. 4) for determining the presence or absence of grinding burn of the production object by data analysis as one of the determination information. Further, the analysis unit 51 generates a threshold value for determining an abnormality of each component of the production equipments 11 to 13 by data analysis as one of the other determination information. Further, the analysis unit 51 updates the determination information by acquiring new detection information after once generating the determination information.

The display unit 52 displays the determination information as the result of the data analysis by the analysis unit 51, and allows the operator to confirm the result of the data analysis. In addition, the display unit 52 can also display the detection information and various control parameters acquired by the analysis unit 51. For example, the display unit 52 has a threshold value for determining the presence or absence of grinding burn obtained by the analysis unit 51, detection information by the power detector 115b of the motor 115a in the production equipment 11, and the power of the motor 115a in the production equipment 13. The detection information by the detector 115b of the above is superimposed and displayed.

The input unit 53 receives input of determination information and the like by the operator. The input unit 53 can set determination information according to each of the production equipments 11 to 13. The analysis unit 51 can obtain determination information corresponding to each of the production equipments 11 to 13, but the operator can further arbitrarily edit while referring to the obtained determination information. The edited determination information is stored in the analysis unit 51.

Then, the production facilities 11 to 13 acquire and store the determination information stored in the analysis unit 51 via the fog network 31. The abnormality determination device 123 of the production facilities 11 to 13 determines the abnormality of the production facilities 11 to 13 or the abnormality of the production object based on the acquired determination information.

(1-4. Detailed processing of abnormality determination device 123, analysis devices 50, 60, and upper analysis device 70)
Next, detailed processing of the abnormality determination device 123, the analysis devices 50, 60, and the upper analysis device 70 will be described with reference to FIG. The analysis devices 50 and 60 and the upper analysis device 70 acquire the detection information of the detectors 112b, 114c, 114d, 115b, 116, 117, 118c and generate various determination information. However, for ease of explanation, the processing when the detection information of the detector 115b is used will be described below by taking as an example.

The detector 115b detects the power of the motor 115a each time the production object (workpiece) is ground (S1). Subsequently, the abnormality determination device 123 collects data for one production target (S2). This data is, for example, the behavior shown by the solid line in FIG. Then, if the threshold values Th11 and Th12 as the determination information are already stored in the abnormality determination device 123, the abnormality determination device 123 performs the abnormality determination (S3). That is, the abnormality determination device 123 determines whether or not the production object is abnormal by comparing the data for one production object with the already stored threshold values Th11 and Th12. ..

Further, the abnormality determination device 123 collects data for a plurality of production objects (S4). The abnormality determination device 123 collects data for one day's production target, for example. The data of the plurality of production objects collected by the abnormality determination device 123 is transmitted to the analysis devices 50 and 60, for example, once a day via the fog networks 31 and 32. Then, the analyzers 50 and 60 acquire the detection information of the detector 115b for a plurality of production objects, for example, once a day (S5). Here, the analyzers 50 and 60 acquire all of the detection information of the detector 115b.

The analyzers 50 and 60 perform data analysis based on the detection information of the detector 115b for a plurality of production objects (S6). Then, the analysis devices 50 and 60 generate threshold values Th11 and Th12 as determination information by data analysis (S7). Further, when the analysis devices 50 and 60 newly acquire the detection information of the detector 115b, the analysis devices 50 and 60 update the threshold values Th11 and Th12 as the determination information by performing data analysis again (S7). Then, the analysis devices 50 and 60 transmit the threshold values Th11 and Th12 as determination information to the abnormality determination device 123 via the fog networks 31 and 32. Then, the abnormality determination device 123 stores the threshold values Th11 and Th12 as determination information while sequentially updating them (S8).

By the way, the analysis devices 50 and 60 extract only a part of the acquired detection information of the detector 115b in parallel with the data analysis for generating the threshold values Th11 and Th12 as the determination information (S9). .. For example, the analyzers 50 and 60 extract the power P of the motor 115a during steady machining in FIG. The analysis devices 50 and 60 transmit the extracted information to the host analysis device 70 via the cloud network 40. The transmission may be, for example, once a day or once a month.

Then, the host analyzer 70 acquires a part of the detection information of the detector 115b via the cloud network 40 (S10). Further, the higher-level analysis device 70 acquires various control parameters from the analysis devices 50 and 60 as needed. The amount of data of various control parameters is smaller than that of the detection information.

The amount of data communication in the cloud network 40 is much smaller than the amount of data communication in the fog networks 31 and 32. Even if the analysis device 50 and the other analysis device 60 and the upper analysis device 70 are located far away, the problem of delay in communication speed via the cloud network 40 does not occur.

The higher-level analysis device 70 performs higher-level data analysis based on a part of the detection information acquired from the analysis devices 50 and 60 and various control parameters (S11). High-level data analysis is so-called data mining. The upper analysis device 70 analyzes the upper data by using the information of the production equipments 11 to 13 and the production equipments 21 to 23 installed in different areas. Therefore, the higher-level analysis device 70 can perform higher-level data analysis using a large amount of information.

If the installation locations of the production facilities 11 to 13 and the other production facilities 21 to 23 are different, the environmental temperatures of the two may be different. For example, the upper level analysis device 70 can analyze the upper level data in more detail due to the influence of the environmental temperature.

The analysis devices 50 and 60 can acquire the result of the upper data analysis by the upper analysis device 70 via the cloud network 40. Therefore, the analysis devices 50 and 60 update the threshold values Th11 and Th12 as the determination information generated by their own data analysis with reference to the result of the upper data analysis (S7). Then, the analysis devices 50 and 60 transmit the threshold values Th11 and Th12 as the updated determination information to the abnormality determination device 123 via the fog networks 31 and 32. In this way, the abnormality determination device 123 stores the threshold values Th11 and Th12 as determination information in consideration of the result of the upper data analysis while sequentially updating them (S8).

Here, the display unit 52 of the analysis device 50 displays the determination information as the result of the data analysis of the analysis device 50 itself, and also displays the determination information as the result of the upper data analysis of the upper analysis device 70 in an overlapping manner. Can be done. The operator can set the determination information to be used in the production equipments 11 to 13 by the input unit 53 while confirming the determination information of both. The same applies to the analyzer 60.

The analysis devices 50 and 60 can transmit a part or all of the collected data to the upper analysis device 70. The range of data transmitted by the analysis devices 50 and 60 (the range set by the size and time of the value) is the range of the production facilities 11 to 13 in cooperation with the analysis devices 50 and 60 itself or the operation of the operator. You can decide in the near future.

<2. Second Embodiment>
The detailed processing of the abnormality determination device 123, the analysis devices 50, 60, and the upper analysis device 70 in the second embodiment will be described with reference to FIGS. 7 to 12. In the second embodiment, the case where the detection information of the detector 112b is used will be described as an example.

As shown in FIG. 7, the detector 112b detects the vibration of the spindle every time the production object (geographical feature) is ground (S21). Subsequently, the abnormality determination device 123 collects data for one production target (S22). Subsequently, the abnormality determination device 123 performs frequency analysis (corresponding to a predetermined process of the present invention) on vibration data for one production object (S23). The result of frequency analysis is shown in FIG. Then, the abnormality determination device 123 acquires the peak value (corresponding to the processed data of the present invention) of the predetermined frequency band of the vibration data obtained by the frequency analysis.

Here, as shown in FIG. 8, the result of the frequency analysis has a peak value (enclosed by a circle in FIG. 8) in a plurality of frequency bands. These frequency bands correspond to the vibration causes of the spindle. For example, the frequency band differs depending on whether the outer ring of the bearing of the spindle device 112 is damaged, the inner ring is damaged, the rolling element is damaged, or the like. Therefore, the abnormality determination device 123 acquires the peak value of the frequency band corresponding to each vibration cause.

Then, when the abnormality determination device 123 has already stored the threshold values Th21 and Th22 as the determination information pattern, the abnormality determination device 123 performs the abnormality determination (S24). The threshold values Th21 and Th22 as patterns of determination information are, for example, patterns of peak values (evaluation parameters) of frequency analysis of vibration data for a time zone (specified parameter) of one day, as shown in FIG. Here, even in one day, the magnitude of vibration varies depending on the elapsed time from starting the production equipments 11 to 13 and the environmental temperature. Therefore, as shown in FIG. 9, the threshold values Th21 and Th22 as the judgment information pattern have the horizontal axis as the time zone of one day (specified parameter) and the vertical axis as the peak value (evaluation parameter) of the frequency analysis of the vibration data. Expressed as.

That is, the abnormality determination device 123 has an abnormality based on the currently acquired actual time zone (specified parameter), the currently acquired actual peak value (evaluation parameter), and the stored determination information pattern. Is judged. Here, in FIG. 9, the mark (1) is a peak value with respect to the actually acquired time zone. Since the mark (6) is equal to or lower than the upper limit threshold value Th21 and is equal to or higher than the lower limit threshold value Th22, it is determined to be normal.

Further, in the abnormality determination device 123, the threshold values Th31 and Th32 as patterns of other determination information are, for example, as shown in FIG. 10, the peak value (evaluation) of the frequency analysis of the vibration data for the period of one year (specified parameter). The pattern of parameter) is memorized. Here, even in one year, the magnitude of vibration differs due to the influence of the difference in environmental temperature. Therefore, as shown in FIG. 10, for the threshold values Th31 and Th32 as patterns of other determination information, the horizontal axis is the period of one year (specified parameter), and the vertical axis is the peak value (evaluation parameter) of the frequency analysis of the vibration data. ).

That is, the abnormality determination device 123 has an abnormality based on the currently acquired actual time (specified parameter), the currently acquired actual peak value (evaluation parameter), and the stored determination information pattern. Make a judgment. Here, in FIG. 10, the mark ▲ is the peak value with respect to the actual time acquired at present. Since the mark ▲ is equal to or lower than the upper limit threshold value Th31 and is equal to or higher than the lower limit threshold value Th32, it is determined to be normal.

Further, the abnormality determination device 123 collects peak values (post-processed data) of a plurality of production objects (S25). The abnormality determination device 123 collects, for example, the peak value of the production object for one day. The peak values of the plurality of production objects collected by the abnormality determination device 123 are transmitted to the analysis devices 50 and 60, for example, once a day via the fog networks 31 and 32. Then, the analyzers 50 and 60 acquire the peak value of the frequency analysis of the vibration data for a plurality of production objects, for example, once a day (S26). Here, the analyzers 50 and 60 acquire the peak value of a much smaller amount of data than the detection information of the detector 112b.

The analyzers 50 and 60 perform data analysis based on the peak values of a plurality of production objects (S27). For example, the distribution of peak values for two days is shown in FIG. Then, the analyzers 50 and 60 analyze the normal tendency pattern from the peak values for a plurality of days. The normal tendency pattern may be an approximate curve of the distributed data (for example, a least squares approximate curve), or may be a curve having a width including all the distributed data. Then, the analysis devices 50 and 60 generate threshold values Th21 and Th22 as patterns of determination information as shown by the broken line in FIG. 11 based on the normal tendency pattern (S28).

Further, when the analysis devices 50 and 60 newly acquire the detection information of the detector 112b, the analysis devices 50 and 60 update the threshold values Th21 and Th22 as the pattern of the determination information by performing the data analysis again (S28). Then, the analysis devices 50 and 60 transmit the threshold values Th21 and Th22 as the pattern of the determination information to the abnormality determination device 123 via the fog networks 31 and 32. Then, the abnormality determination device 123 stores the threshold values Th21 and Th22 as patterns of determination information while sequentially updating them (S29).

Further, the analyzers 50 and 60 perform data analysis based on the peak values of the production objects for one year (S27). For example, the distribution of peak values for one year is shown in FIG. Then, the analyzers 50 and 60 analyze the normal tendency pattern from the peak value for one year. Then, the analysis devices 50 and 60 generate threshold values Th31 and Th32 as patterns of determination information as shown by the broken line in FIG. 12 based on the normal tendency pattern (S28).

Similarly in this case, when the analysis devices 50 and 60 newly acquire the detection information of the detector 112b, the analysis devices 50 and 60 update the threshold values Th31 and Th32 as the pattern of the determination information by performing the data analysis again (these are the same. S28). Then, the analysis devices 50 and 60 transmit the threshold values Th31 and Th32 as the pattern of the determination information to the abnormality determination device 123 via the fog networks 31 and 32. Then, the abnormality determination device 123 stores the threshold values Th31 and Th32 as patterns of determination information while sequentially updating them (S29).

By the way, the analysis devices 50 and 60 extract only a part of the acquired peak values in parallel with the data analysis for generating the threshold values Th21, Th22, Th31, Th32 as the determination information (S30). .. For example, the analyzers 50 and 60 extract not the peak values of all the production objects but the peak values of some production objects. The analyzers 50 and 60, for example, extract the peak value of one production object from the same lot. The analysis devices 50 and 60 transmit the extracted information to the host analysis device 70 via the cloud network 40. The transmission may be, for example, once a week or once a month.

Then, the upper analysis device 70 acquires a part of the information of the peak value via the cloud network 40 (S31). Further, the higher-level analysis device 70 acquires various control parameters from the analysis devices 50 and 60 as needed. The amount of data of various control parameters is smaller than that of the detection information.

The upper analysis device 70 analyzes the upper data based on a part of the peak values acquired from the analysis devices 50 and 60 and various control parameters (S32). High-level data analysis is so-called data mining. The upper analysis device 70 analyzes the upper data by using the information of the production equipments 11 to 13 and the production equipments 21 to 23 installed in different areas. Therefore, the higher-level analysis device 70 can perform higher-level data analysis using a large amount of information.

The analysis devices 50 and 60 can acquire the result of the upper data analysis by the upper analysis device 70 via the cloud network 40. Therefore, the analysis devices 50 and 60 update the threshold values Th21, Th22, Th31, and Th32 as patterns of the determination information generated by their own data analysis with reference to the result of the upper data analysis (S28). Then, the analysis devices 50 and 60 transmit the threshold values Th21, Th22, Th31, and Th32 as the updated determination information to the abnormality determination device 123 via the fog networks 31 and 32. In this way, the abnormality determination device 123 stores the threshold values Th21, Th22, Th31, and Th32 as determination information in consideration of the result of the upper data analysis while sequentially updating them (S29).

<3. Third Embodiment>
The detailed processing of the abnormality determination device 123, the analysis devices 50, 60, and the upper analysis device 70 in the third embodiment will be described with reference to FIGS. 13 to 15. In the third embodiment, the case where the detection information of the detectors 115b and 117 is used will be described as an example.

As shown in FIG. 13, the detector 115b detects the current value of the power of the motor 115a each time the production object (geographical feature) is ground (S41). In addition, the detector 117 detects the environmental temperature each time the production object is ground (S42). Subsequently, the abnormality determination device 123 collects data for one production object (S43).

Subsequently, the abnormality determination device 123 extracts data during steady machining from the power data of the motor 115a for one production object (corresponding to the predetermined process of the present invention) (corresponding to the predetermined process of the present invention). S44). For example, in FIG. 4, the current value of the power of the motor 115a during steady machining is P. Then, the abnormality determination device 123 acquires the power current value P data and the environmental temperature data (corresponding to the post-processing data of the present invention) obtained by the extraction process.

Then, when the abnormality determination device 123 already stores the threshold values Th41 and Th42 as the determination information pattern, the abnormality determination device 123 performs the abnormality determination (S45). The threshold values Th41 and Th42 as the patterns of the determination information are, for example, as shown in FIG. 14, a pattern of the current value (evaluation parameter) of the power of the motor 115a with respect to the environmental temperature (specified parameter). Here, the current value of the power of the motor 115a changes depending on the environmental temperature. Therefore, as shown in FIG. 14, the threshold values Th41 and Th42 as patterns of determination information are represented by the horizontal axis as the environmental temperature (specified parameter) and the vertical axis as the current value P (evaluation parameter) of the power of the motor 115a.

That is, the abnormality determination device 123 is based on the currently acquired actual environmental temperature (specified parameter), the currently acquired actual power current value P (evaluation parameter), and the stored determination information pattern. Then, the abnormality is judged. Here, in FIG. 14, the mark (6) is the current value P of the power with respect to the actually acquired environmental temperature. Since the mark (6) is equal to or lower than the upper limit threshold value Th41 and equal to or higher than the lower limit threshold value Th42, it is determined to be normal.

Further, the abnormality determination device 123 collects data of a plurality of power current values P and environmental temperature data (processed data) (S46). The abnormality determination device 123 collects, for example, data of the current value P of the power of the production object for one day and data of the environmental temperature. The plurality of data collected by the abnormality determination device 123 are transmitted to the analysis devices 50 and 60 via the fog networks 31 and 32, for example, once a day. Then, the analyzers 50 and 60 acquire power current value P data and environmental temperature data for a plurality of production objects, for example, once a day (S47). Here, the analyzers 50 and 60 acquire data in a much smaller amount of data than all the detection information of the detectors 115b and 117.

The analyzers 50 and 60 perform data analysis based on the data of a plurality of production objects (S48). For example, the distribution of data for a plurality of days with different environmental temperatures is shown in FIG. Then, the analysis devices 50 and 60 analyze the normal tendency pattern from the data for a plurality of days. Then, the analysis devices 50 and 60 generate threshold values Th41 and Th42 as patterns of determination information based on the normal tendency pattern as shown by the broken lines in FIGS. 14 and 15 (S49).

Further, when the analysis devices 50 and 60 newly acquire the detection information of the detectors 115b and 117, the analysis devices 50 and 60 update the threshold values Th41 and Th42 as the pattern of the determination information by performing the data analysis again (S49). .. Then, the analysis devices 50 and 60 transmit the threshold values Th41 and Th42 as the pattern of the determination information to the abnormality determination device 123 via the fog networks 31 and 32. Then, the abnormality determination device 123 stores the threshold values Th41 and Th42 as patterns of determination information while sequentially updating them (S50).

By the way, the analysis devices 50 and 60 extract only a part of the acquired data in parallel with the data analysis for generating the threshold values Th41 and Th42 as the determination information (S51). For example, the analyzers 50 and 60 extract not the data of all the production objects but the data of some production objects. The analyzers 50 and 60, for example, extract data of one production object from the same lot. The analysis devices 50 and 60 transmit the extracted information to the host analysis device 70 via the cloud network 40. The transmission may be, for example, once a week or once a month.

Then, the upper analysis device 70 acquires a part of the information of the data via the cloud network 40 (S52). Further, the higher-level analysis device 70 acquires various control parameters from the analysis devices 50 and 60 as needed. The amount of data of various control parameters is smaller than that of the detection information.

The higher-level analysis device 70 performs higher-level data analysis based on a part of the data acquired from the analysis devices 50 and 60 and various control parameters (S53). High-level data analysis is so-called data mining. The upper analysis device 70 analyzes the upper data by using the information of the production equipments 11 to 13 and the production equipments 21 to 23 installed in different areas. Therefore, the higher-level analysis device 70 can perform higher-level data analysis using a large amount of information.

The analysis devices 50 and 60 can acquire the result of the upper data analysis by the upper analysis device 70 via the cloud network 40. Therefore, the analysis devices 50 and 60 update the threshold values Th41 and Th42 as patterns of the determination information generated by their own data analysis with reference to the result of the upper data analysis (S49). Then, the analysis devices 50 and 60 transmit the threshold values Th41 and Th42 as the updated determination information to the abnormality determination device 123 via the fog networks 31 and 32. In this way, the abnormality determination device 123 stores the threshold values Th41 and Th42 as determination information in consideration of the result of the upper data analysis while sequentially updating them (S50).

<4. Effect of embodiment>
In the first to third embodiments, the anomaly analysis system 1 is a facility for producing an object to be produced, and includes one or a plurality of detectors 112b, 114c, 114d, 115b, 116, 117, 118c, respectively. A fog network (corresponding to the first network) 31 connected to a plurality of production facilities 11 to 13 and a plurality of production facilities 11 to 13 and installed in a predetermined area for constructing fog computing, and 31 connections to the fog network. Data analysis is performed based on the detection information of the detectors 112b, 114c, 114d, 115b, 116, 117, 118c acquired via the fog network 31, and a plurality of production facilities 11 are performed based on the result of the data analysis. It is provided with an analyzer 50 that generates determination information regarding each of the abnormalities of to 13 or the abnormality of the production object. Each of the plurality of production facilities 11 to 13 determines the abnormality of each of the plurality of production facilities 11 to 13 or the abnormality of the production object based on the determination information generated by the analysis device 50.

The detectors 112b, 114c, 114d, 115b, 116, 117, 118c in the plurality of production facilities 11 to 13 and the analysis device 50 are connected via a fog network 31 installed in a predetermined area for constructing fog computing. Has been done. Fog computing is a network-connected system in a smaller area than cloud computing. That is, the fog network 31 for constructing fog computing is a network installed in a predetermined area narrower than the area for constructing cloud computing. Therefore, the occurrence of communication congestion is suppressed in the data communication between the detectors 112b, 114c, 114d, 115b, 116, 117, 118c and the analysis device 50. Further, since the fog network 31 is constructed in a narrow predetermined area, the communication time between the production equipments 11 to 13 and the analysis device 50 can be shortened. Therefore, the analysis device 50 can receive the detection information by the detectors 112b, 114c, 114d, 115b, 116, 117, 118c at high speed.

Since the analysis device 50 can acquire the detection information in the plurality of production facilities 11 to 13 at an early stage and perform data analysis, the result of the analysis device 50 can be fed back to the production facilities 11 to 13 at an early stage. Since the analysis result can be fed back to the production equipments 11 to 13 at an early stage, it is possible to suppress the occurrence of abnormalities in the production object earlier and more reliably.

Further, in the first embodiment, the analysis device 50 acquires all the detection information of the detectors 112b, 114c, 114d, 115b, 116, 117, 118c via the fog network 31 and is based on all of the detection information. And analyze the data. In particular, the plurality of detectors 112b, 114c, 114d, 115b, 116, 117, 118c acquire detection information at different sampling cycles, and the analysis device 50 uses the plurality of detectors 112b, 114c, 114d, 115b, 116. , 117, 118c, respectively, all of the detection information is acquired, and data analysis is performed based on all of the detection information. Even if a large amount of data communication is performed on the fog network 31, the problem of communication delay does not occur. Therefore, the analysis device 50 is designed to acquire all the detection information of the detectors 112b, 114c, 114d, 115b, 116, 117, 118c. Therefore, the analysis device 50 can perform data analysis with high accuracy and in real time.

Further, in the second embodiment and the third embodiment, the abnormality determination device 123 performs predetermined processing on the detection information of the detectors 112b, 114c, 114d, 115b, 116, 117, 118c to generate post-processing data. At the same time, the abnormality is determined based on the determination information. Then, the analysis devices 50 and 60 acquire the processed data via the fog network 31, perform data analysis based on the processed data, and update the determination information based on the result of the data analysis.

The abnormality determination device 123 is performing abnormality determination, and the analysis devices 50 and 60 are updating the determination information. Here, the analyzers 50 and 60 use the processed data obtained by subjecting the detection information of the detectors 112b, 114c, 114d, 115b, 116, 117, 118c to the predetermined processing. That is, the analyzers 50 and 60 do not update the determination information based on all the detection information itself of the detectors 112b, 114c, 114d, 115b, 116, 117, 118c. Therefore, the analysis devices 50 and 60 can process the determination information at a higher speed than when all the detection information itself is used. From the above, the abnormality analysis system 1 can surely update the determination information while performing the abnormality determination.

In particular, the data capacity of the processed data that has been subjected to the predetermined processing by the abnormality determination device 123 is set to be smaller than the detection information before the processing. Therefore, since the communication volume of the fog network 31 can be reduced, the analysis devices 50 and 60 can shorten the time for acquiring data for one day, for example. As a result, the analyzers 50 and 60 can secure a sufficient time for performing the analysis.

Further, in the second embodiment, the abnormality determination device 123 determines the abnormality based on the generated post-processing data and the determination information, and the analysis devices 50 and 60 perform the post-processing used for the determination by the abnormality determination device 123. Judgment information is updated based on the data. That is, the processed data is shared by the abnormality determination device 123 and the analysis devices 50 and 60.

In particular, in the second embodiment, the detector 112b is a vibration detection sensor, and the predetermined processing by the abnormality determination device 123 is frequency analysis for the detection information of the detector 112b. Therefore, the abnormality determination device 123 does not generate the dedicated data for use in the analysis devices 50 and 60, but only generates the data to be used by itself. Therefore, since the abnormality determination device 123 does not require a dedicated process, it is possible to reduce the communication amount of the fog network 31 while increasing the processing speed of the abnormality determination device 123 itself.

Further, in the third embodiment, the predetermined process by the abnormality determination device 123 is a process of extracting specific information from the detection information of the detectors 115b and 117. Also in this case, the abnormality determination device 123 does not generate the dedicated data for use in the analysis devices 50 and 60, but only generates the data to be used by itself. Therefore, since the abnormality determination device 123 does not require a dedicated process, it is possible to reduce the communication amount of the fog network 31 while increasing the processing speed of the abnormality determination device 123 itself.

Further, in the second embodiment and the third embodiment, the analyzers 50 and 60 analyze the normal tendency pattern for the evaluation parameter for the specified parameter by data analysis, and based on the normal tendency pattern, the evaluation parameter for the specified parameter. The pattern of judgment information about is updated. Then, the abnormality determination device 123 acquires the actual specified parameter and the actual evaluation parameter, and determines the abnormality based on the pattern of the determination information, the actual specified parameter, and the actual evaluation parameter.

For example, in the second embodiment, as a first example, the specified parameter is a time zone in one day, and the evaluation parameter is a parameter that changes according to the time zone in one day. Further, in the second embodiment, as a second example, the specified parameter is the time in one year, and the evaluation parameter is a parameter that changes according to the time in one year.

The state of the components of the production facilities 11 to 13 or the state of the production object changes, for example, depending on the elapsed time from the start of the production facilities 11 to 13 and the environmental temperature. The environmental temperature changes depending on the time of day or the time of year. Further, the elapsed time from starting the production equipments 11 to 13 changes depending on the time zone in one day when the production equipments 11 to 13 are started once a day. Therefore, by setting the specified parameters and the evaluation parameters as described above, the state of the production equipments 11 to 13 or the state of the production object can be reliably evaluated.

In particular, the detector 112b shall detect the vibration of the production equipment 11 to 13 or the production object, and the evaluation parameter is the peak value of a predetermined frequency band in the vibration. The amplitude of vibration is a parameter that changes depending on, for example, the elapsed time from starting the production equipments 11 to 13 and the environmental temperature. That is, the peak value is a parameter that changes depending on the elapsed time from starting the production equipments 11 to 13 and the environmental temperature. Therefore, by setting the evaluation parameter to the peak value, it is possible to reliably evaluate the state of the production equipment 11 to 13 or the state of the production object.

Further, in the third embodiment, the specified parameter is the environmental temperature, and the evaluation parameter is a parameter that changes according to the environmental temperature. In this case, by setting the environmental temperature itself as a specified parameter, it is possible to evaluate the state of the production equipment 11 to 13 or the state of the production object by evaluating the parameter that changes according to the environmental temperature.

Further, in the second embodiment and the third embodiment, the analysis devices 50 and 60 collectively acquire the processing results for the plurality of times by the abnormality determination device 123 after the predetermined processing by the abnormality determination device 123 is performed a plurality of times. ing. That is, the analysis devices 50 and 60 do not acquire data from the abnormality determination device 123 every time the abnormality determination device 123 acquires detection information from the detectors 112b, 114c, 114d, 115b, 116, 117, 118c. ..

Here, in the second embodiment and the third embodiment, the abnormality determination device 123 performs predetermined processing on the detection information, and the analysis devices 50 and 60 perform processing in which the amount of data is reduced by the predetermined processing. After getting the data. Therefore, even if the analysis devices 50 and 60 collectively acquire the results for a plurality of times, the communication volume of the fog network 31 can be sufficiently small.

Further, in the first to third embodiments, the predetermined area where the fog network 31 is constructed is in the same building as the building in which any of the plurality of production equipments 11 to 13 is installed, or the production equipment. It is in the building where 11 to 13 are installed and in the neighboring buildings. Therefore, the production equipments 11 to 13 and the analysis device 50 can be reliably configured by the fog network 31.

Further, in the first to third embodiments, the analysis is performed near the production equipments 11 to 13, so that the operator can check the state of the production object and the production equipments 11 to 13 to check for abnormalities or normalities. It is possible to determine the value to be determined (judgment information). Further, when a sudden abnormality occurs in the production equipments 11 to 13 or the production object, the analysis is performed in the vicinity of the production equipments 11 to 13, so that the data can be analyzed in collaboration with the operator and the analysis device 50. Can be performed immediately, and the result can be immediately reflected in the determination information for the target production facilities 11 to 13. Further, in the abnormality determination or the stage before the abnormality determination (a state that is not abnormal but is close to an abnormality) based on the analysis result of the analysis device 50, the production equipments 11 to 13 or the analysis device 50 automatically inform the operator of the abnormality state or automatically. It is possible to stop the operation of the production facilities 11 to 13.

Further, in the first to third embodiments, the analysis device 50 includes a display unit 52 for displaying the result of data analysis and an input unit 53 for receiving input of determination information by the operator. The operator can manually set the determination information for the production equipments 11 to 13. The setting is not limited to manual setting by the operator, but automatic setting by the system is also possible.

Further, in the first to third embodiments, the anomaly analysis system 1 is not directly connected to the fog network 31 and includes other detectors 112b, 114c, 114d, 115b, 116, 117, 118c. Cloud network 40 (in the second network) that is connected to the production facilities 21 to 23 of the above, a plurality of production facilities 11 to 13 and other production facilities 21 to 23, and constructs cloud computing in a wider area than a predetermined area of the fog network 31. The detection information of the detectors 112b, 114c, 114d, 115b, 116, 117, 118c connected to the cloud network 40 and acquired via the cloud network 40 and other detectors 112b, 114c, 114d, 115b, It is provided with a higher-level analyzer 70 that performs higher-level data analysis based on the detection information of 116, 117, and 118c.

The analysis device 50 can also determine and store the determination information based on the result of the data analysis by the analysis device 50 and the result of the upper data analysis by the upper analysis device 70. Therefore, better determination information can be obtained by performing higher-level data analysis using information that cannot be obtained by the production equipments 11 to 13 and feeding back to the production equipments 11 to 13.

Further, in the first to third embodiments, the analysis device 50 acquires all the detection information of the detectors 112b, 114c, 114d, 115b, 116, 117, 118c and analyzes the data. On the other hand, the upper analyzer 70 includes a part of the detection information of the detectors 112b, 114c, 114d, 115b, 116, 117, 118c of the production equipments 11 to 13 and other detectors 112b of the other production equipments 21 to 23. A part of the detection information of the 114c, 114d, 115b, 116, 117, 118c devices is acquired, and the upper data analysis is performed. Even if the higher-level analyzer 70 does not require high-speed processing, all of the detectors 112b, 114c, 114d, 115b, 116, 117, and 118c are sent to the upper-level analysis device 70 via the cloud network 40. If it is transmitted, it may affect others due to the communication delay of the cloud network 40. Therefore, as described above, the data communication amount of the cloud network 40 becomes a part of the detection information, and it is possible to suppress the influence of the communication delay in the cloud network 40.

Further, in the first to third embodiments, the plurality of production facilities 11 to 13 include a grinding machine for grinding the production object, and the determination information is, for example, determination information regarding a grinding abnormality of the production object. .. As a result, in a system including a grinding machine, the occurrence of grinding abnormalities such as grinding burn can be reliably suppressed.

Further, in the first to third embodiments, the determination information may be determination information regarding a component failure, component life, or maintenance necessity of any of the plurality of production facilities 11 to 13. As a result, it is possible to predict the failure of parts of the production equipments 11 to 13, and prepare replacement parts in advance. Also, in the past, parts were often replaced based on the usage period of the parts, but since the parts can be replaced after grasping the life of each part with higher accuracy, the usage period of the parts is extended. be able to. In addition, maintenance of parts can be performed at an appropriate time before the performance of parts deteriorates. As a result, the usage period of the parts can be extended.

1: Abnormality analysis system, 11-13: Production equipment (11: Grinding machine), 21-23: Other production equipment, 31: Fog network (first network), 32: Fog network, 40: Cloud network (second) Network), 50: Analytical unit, 51: Analytical unit, 52: Display unit, 53: Input unit, 60: Other analytical equipment, 70: Upper level analyzer, 112b, 114c, 114d, 115b, 116, 117, 118c: Detector, 121: CNC device, 122: PLC, 123: Abnormality determination device, Th11, Th12, Th21, Th22, Th31, Th32: Threshold, W: Crank shaft (production object)

Claims (5)

Equipment for producing production objects, including multiple production equipments each equipped with one or more detectors, and
A first network connected to the plurality of production facilities and installed in a predetermined area for constructing fog computing,
With other production equipment that is not directly connected to the first network and has other detectors
A second network that is connected to the plurality of production facilities and the other production facilities to construct cloud computing in a wider area than the predetermined area.
An analysis device connected to the first network and performing data analysis based on the detection information of the detector acquired via the first network.
A higher-level analyzer that is connected to the second network and performs higher-level data analysis based on the detection information of the detector and the detection information of the other detectors acquired via the second network.
With
Based on the result of the data analysis by the analysis device and the result of the higher-level data analysis by the higher-level analysis device, the analysis device obtains determination information regarding an abnormality of each of the plurality of production facilities or an abnormality of the production object. Generate and
Each of the plurality of production facilities includes an abnormality determination device that determines an abnormality of each of the plurality of production facilities or an abnormality of the production object based on the determination information generated by the analysis device. Analysis system. The analysis device acquires all the detection information of the detector and analyzes the data.
The abnormality analysis system according to claim 1 , wherein the higher-level analysis device acquires a part of the detection information of the detector and a part of the detection information of the other detector, and performs the higher-level data analysis. The plurality of production facilities include a grinding machine that grinds the production object.
The abnormality analysis system according to claim 1 or 2 , wherein the determination information is determination information regarding a grinding abnormality of the production object. The abnormality analysis system according to any one of claims 1-3 , wherein the determination information is determination information regarding a component failure, component life, or maintenance necessity of any of the plurality of production facilities. The analysis device used in the abnormality analysis system according to any one of claims 1 to 4 .

Images