TWI866486B - Artificial intelligence (ai) desoldering device for laser removal of substrate resist layers - Google Patents

Abstract

An artificial intelligence (AI) desoldering device for laser removal of substrate resist layers includes an AI system, a control processing module, a camera module, and a laser desoldering module. The AI system includes a database unit, a leaming and training unit, a parameter setting optimization unit, a condition limiting unit, and an AI model processing unit. The AI system is used to learn and pre-train the type of substrates, the size of substrate, the thickness of substrate, the color of solder masks, the thickness of solder masks, and the depth of the area around soldering pads, and automatically optimize and set up all processing parameters according to the characteristics of the substrates to be processed. The laser desoldering module is controlled by the AI system to perform laser desoldering on the substrates according to a first control command and a circuit layout diagram.

Description

Intelligent desoldering device that uses artificial intelligence-driven laser to remove the solder mask of substrates

A substrate desoldering device, in particular an intelligent desoldering device that uses an artificial intelligence-driven laser to remove the solder mask of a substrate.

According to the general solder mask process of circuit boards, after the printed circuit is set up, a photosensitive solder mask is applied to the surface of the circuit board to form a solder mask layer, which is pre-baked to semi-cured, and then the mask is used for exposure and development technology to cure the solder mask layer outside the solder pad in the circuit, and then the uncured part of the solder mask layer is removed to expose the solder mask layer on the solder pad. Due to the necessary errors caused by exposure energy and development, the accuracy is limited, and the solder pad distance (pitch) cannot be reduced; there is also the introduction of direct imaging technology, which reduces the mask cost, but the equipment cost is extremely high, and the technology also faces the same problem.

However, the circuit board and the photomask will be affected by the environmental conditions such as temperature and humidity in the exposure part of the exposure device, causing the position accuracy of the positioning marks on the circuit board and the photomask and the position accuracy of the exposure pattern to change, resulting in the problem of not being able to form a high-precision pattern, and the problem of the solder pad not being able to correctly expose the solder mask. Furthermore, circuit boards with different solder pad positions must first be made with masks that match the circuit board, which increases the manufacturing cost of the circuit board. In addition, the solder mask process of general circuit boards often requires the use of different inks, making the ink cost high. Moreover, the semi-cured solder mask is not hard enough or has stickiness, which is easy to cause scrap during the operation.

Therefore, how to solve the above problems and deficiencies of existing technologies is a topic that relevant industries are eager to research and develop.

The present invention provides an intelligent solder removal device for removing a solder mask layer of a substrate by laser driven by artificial intelligence. The device processes at least one substrate placed on a laser processing machine by laser with controllable energy. Each substrate corresponds to a board production material number, and at least one solder pad is provided on the surface of the substrate, and a solder mask is covered on the surface of the substrate and the solder pad, wherein the solder mask is a shielding portion facing the surface of the substrate, and the solder mask is a cleaning portion facing the solder pad. The intelligent solder removal device for removing a solder mask layer of a substrate by laser driven by artificial intelligence includes an artificial intelligence (AI) system, a control processing module, a photographic imaging module, and a laser solder removal module. The artificial intelligence system includes a database unit, a learning and training unit, a parameter optimization setting unit, a condition restriction unit and an AI model processing unit. The artificial intelligence (AI) system is used to learn and pre-train the types of the substrates, the sizes of the substrates, the thickness of the substrates, the color of the solder mask, the thickness of the solder mask and the depth around the pads, and automatically optimize all processing parameters according to the characteristics of the substrate to be processed. The database unit has relevant data on the types of the substrates, the sizes of the substrates, the thickness of the substrates, the color of the solder mask, the thickness of the solder mask and the depth around the pads, wherein the database unit is connected to a cloud platform via the Internet to update the relevant data online. A learning and training unit, which is connected to the database unit, and the learning and training unit performs learning and pre-training through a substrate deep learning algorithm and according to relevant data in the database unit. A parameter optimization setting unit, which is connected to the database unit, and the parameter optimization setting unit is used to optimize the settings of multiple processing parameters according to the relevant data of the types of the substrates, the sizes of the substrates, the thickness of the substrates, the color of the solder mask, the thickness of the solder mask, and the depth around the solder pads. A condition restriction unit is connected to the learning and training unit, and the condition restriction unit is used to limit the learning deviation of the artificial intelligence (AI) system by setting multiple conditions. The AI model processing unit is connected to the learning and training unit and the parameter optimization setting unit. The AI model processing unit learns and trains an AI model through the learning and training unit, wherein the AI model processing unit is the AI brain of the artificial intelligence system. The control processing module is connected to the AI model processing unit of the artificial intelligence system. The control processing module generates a first control instruction, a second control instruction and a third control instruction according to the instructions and related data transmitted by the AI model processing unit to perform processing operations on the substrate. A photographic imaging module is connected to the control processing module. The photographic imaging module photographs or captures the substrate according to the first control instruction transmitted by the control processing module, wherein the photographic imaging module reads the rapid response matrix of the board production material number on the substrate, and transmits it back to the AI model processing unit to identify the characteristics of the substrate and perform pre-processing preparation for parameter optimization settings. A laser desoldering module is connected to the control processing module. The laser desoldering module performs laser desoldering on the substrate according to the first control instruction transmitted by the control processing module and a circuit layout diagram. The laser desoldering module uses a laser beam and performs a stripping operation on the removal portion according to a construction drawing to form at least one hollow portion of the solder mask layer, wherein the circuit layout diagram imports the data of the solder mask layer, and then converts the data of the solder mask layer into a positive image, a negative image or a graphic conversion process to obtain the construction drawing.

In one embodiment of the present invention, the artificial intelligence (AI) system predicts or adjusts the laser spot size and shape based on the processing path, the construction pattern and the energy required by the material.

In one embodiment of the present invention, the artificial intelligence (AI) system adjusts different laser spot sizes and different laser firing numbers for different areas of the same surface of the substrate through the parameter optimization setting unit according to the calculated results.

In one embodiment of the present invention, the intelligent solder removal device for removing the solder mask layer of the substrate by laser driven by artificial intelligence further includes a positioning module. The positioning module is connected to the control processing module, and the positioning module aligns the substrate to be processed according to a third control instruction transmitted by the control processing module and through an infrared light to further adjust the increase and decrease amplitude of the construction pattern, wherein the infrared light is used to see through the solder mask layer, wherein the artificial intelligence (AI) system analyzes and excludes inappropriate positioning point images, and calculates the deformation direction and degree of the substrate.

In one embodiment of the present invention, the four corners around the substrate each have a pair of points.

In one embodiment of the present invention, the four corners around the substrate each have a pair of alignment points and the central area of the substrate has at least two alignment points.

In one embodiment of the present invention, after obtaining the construction drawing, the control processing module calculates the overlapping area size of the laser spot according to the laser spot size and energy of the laser desoldering module, and then translates it into a laser dot matrix.

In one embodiment of the present invention, the substrate is photographed by the photographic imaging module and a substrate processing picture is taken out, and the substrate processing picture is compared and judged whether it is the same as the circuit layout diagram. If they are the same, the substrate processing operation is completed.

In one embodiment of the present invention, in the step of comparing and judging whether the substrate processing image is the same as the circuit layout image, if they are not the same, the laser beam will then perform a stripping operation on the cleaning portion at the different locations.

In one embodiment of the present invention, the substrate is divided into a plurality of areas to be processed by the circuit layout diagram, and then the laser beam performs a stripping operation on the clearing portion of each of the areas to be processed according to a preset rule.

In one embodiment of the present invention, the laser light emitted by the laser beam is a high-frequency laser beam above the millisecond level.

In one embodiment of the present invention, the type of laser beam is at least one of carbon dioxide (CO2) laser, Yag laser, green laser and ultraviolet light according to the characteristics of the material, so as to achieve the effect of removing solder mask without residue or carbonization.

In one embodiment of the present invention, the laser desoldering module has multiple sets of laser light sources to emit the laser beams respectively, which respectively perform the stripping operation on the cleaning part of the substrate according to the first control instruction and the circuit layout diagram, wherein each laser light source is responsible for a different area.

In summary, the intelligent solder removal device for removing the solder mask layer of the substrate by laser driven by artificial intelligence disclosed in the present invention can achieve the following effects: 1. Greatly shorten the steps of the processing process; 2. Improve the process yield; 3. Have a laser beam with controllable energy; 4. Improve the pattern accuracy of the processing process; 5. Circuit substrates with different solder pad positions no longer need to be made into masks that meet the circuit substrates in advance; 6. There will be no influence of environmental conditions such as temperature and humidity; 7. No need to develop with large Significantly reduce wastewater pollution and save energy at the same time; 8. No restrictions on inks, reducing ink costs; 9. Use at least one of carbon dioxide (CO2) laser, Yag laser, green laser and ultraviolet light to achieve the effect of removing solder mask without residue or carbonization; 10. Solve the problem of semi-cured solder mask in previous technologies that is not hard enough or sticky, which is easy to cause scrapping during operation; and 11. Reduce environmental damage, meet ESG standards, and contribute to sustainable development

The following detailed description is based on specific embodiments, which will make it easier to understand the purpose, technical content, features and effects of the present invention.

100: Intelligent desoldering device that uses artificial intelligence-driven laser to remove the solder mask of substrates

110: Artificial Intelligence (AI) System

111: Database unit

112: Learning and training unit

113: Parameter optimization setting unit

114: Conditional unit

115: AI model processing unit

120: Control processing module

130: Photography and imaging module

140, 141, 142, 143: Laser desoldering module

150: Alignment module

200: Substrate

210: Welding pad

220: Solder mask

222: Shielding part

224: Clearing Department

226: Hollow Section

300: Cloud Platform

ACS: Intelligent Control Instructions

CS1: First control instruction

CS2: First control instruction

CS3: First control instruction

P1, P2: Alignment points

NT: Internet

MT: Laser processing machine

SC: Screen

L1, L2, L3, L4: Laser beam

TA: Circuit layout diagram

DC: Substrate processing pictures

RL: Infrared light

The first figure is a schematic diagram of an intelligent desoldering device that uses an artificial intelligence-driven laser to remove the solder mask layer of a substrate.

The second figure is a side view of the substrate of the present invention.

The third figure is a side view of the substrate covered with solder mask of the present invention.

The fourth figure is a schematic diagram of the first embodiment of the substrate with multiple alignment points of the present invention.

The fifth figure is a schematic diagram of the second embodiment of the substrate with multiple alignment points of the present invention.

The sixth figure is a three-dimensional schematic diagram of the intelligent desoldering device of the present invention processing a substrate.

Figure 7 is a schematic diagram of the photographic imaging module of the present invention capturing an image of a substrate.

Figure 8 is a schematic diagram of the present invention comparing the circuit layout diagram with the substrate processing diagram.

Figure 9 is a schematic diagram of the translated laser dot matrix of the present invention.

Figure 10 is a schematic diagram of the multi-light source laser processing of a substrate of the present invention.

In order to solve the many problems of the existing circuit substrate solder mask process, the inventor has improved the shortcomings of existing products after years of research and development. The following will introduce in detail how the invention uses an intelligent solder removal device that removes the substrate solder mask layer by laser driven by artificial intelligence to achieve the most efficient functional requirements. In addition, the disclosure content is to avoid the traditional chemical process development is not clean, and the traditional laser ablation due to thermal effects to produce carbon residues, which must be secondary processing or directly lead to scrap.

Please refer to Figures 1 to 3, 6, 7, and 9 simultaneously. Figure 1 is a schematic diagram of the structure of an intelligent desoldering device that uses an artificial intelligence-driven laser to remove the solder mask layer of a substrate. Figure 2 is a side view of a substrate of the present invention. Figure 3 is a side view of a substrate covered with a solder mask layer of the present invention. Figure 6 is a three-dimensional schematic diagram of the intelligent desoldering device of the present invention processing a substrate. Figure 7 is a schematic diagram of the photographic imaging module of the present invention capturing an image of a substrate. Figure 9 is a schematic diagram of the translated laser dot matrix of the present invention. As shown in the first figure, the intelligent solder removal device 100 driven by artificial intelligence to remove the solder mask of the substrate by laser is to perform processing operations on all or part of a substrate through a laser with controllable energy, rather than just using lasers manually to optimize the local or single point of the circuit substrate. In the embodiment of the present invention, the intelligent solder removal device 100 driven by artificial intelligence to remove the solder mask of the substrate by laser is mainly used to replace the complicated process under the previous technology and reduce environmental pollution, which meets the ESG standard. ESG is the abbreviation of environmental protection (E, Environmental), social responsibility (S, Social) and corporate governance (G, governance).

As shown in the figure, the intelligent solder removal device 100 for removing the solder mask layer of a substrate by laser driven by artificial intelligence of the present invention processes at least one substrate 200 placed on a laser processing machine MT through a laser with controllable energy, each of the substrates 200 corresponds to a board production material number, and at least one solder pad 210 is disposed on the surface of the substrate 200 and a solder mask 220 (e.g., green paint) is covered on the surface of the substrate 200 and the solder pad 210, wherein the solder mask 220 is a shielding portion 222 facing the surface of the substrate 200, and the solder mask 220 is a cleaning portion 224 facing the solder pad 210. In detail, the intelligent solder removal device 100 for removing the solder mask of the substrate by laser driven by artificial intelligence includes an artificial intelligence (AI) system 110, a control processing module 120, a photographic imaging module 130 and a laser solder removal module 140. The artificial intelligence system 110 includes a database unit 111, a learning and training unit 112, a parameter optimization setting unit 113, a condition restriction unit 114 and an AI model processing unit 115. The artificial intelligence (AI) system 110 is mainly used to learn and pre-train the types of the substrates 200, the sizes of the substrates 200, the thickness of the substrates 200, the color of the solder mask 220, the thickness of the solder mask 220, and the depth around the pads 210, and automatically optimize all processing parameters according to the characteristics of the substrate 200 to be processed. The database unit 111 has data related to the types of the substrates 200, the sizes of the substrates 200, the thickness of the substrates 200, the color of the solder mask 220, the thickness of the solder mask 220, and the depth around the pads 210. The database unit 111 is connected to the Internet NT through a wireless network unit (not shown) and further connected to a cloud platform 300 to update the relevant data or substrate deep learning algorithm online (for use by the learning and training unit 112).

Furthermore, the learning and training unit 112 is connected to the database unit 111. The learning and training unit 112 performs learning and pre-training based on the relevant data in the database unit 111 through a substrate deep learning algorithm to identify which processing parameter settings are required for different substrate characteristics for laser desoldering. The parameter optimization setting unit 113 is connected to the database unit 111. The parameter optimization setting unit 113 is used to optimize the setting of multiple processing parameters according to the data related to the types of the substrates 200, the sizes of the substrates 200, the thickness of the substrates 200, the color of the solder mask 220, the thickness of the solder mask 220, and the depth around the pads 210. The condition restriction unit 114 is connected to the learning and training unit 112. The condition restriction unit 114 is used to limit the learning deviation or operation error of the artificial intelligence (AI) system by setting multiple conditions. The designer can introduce at least one condition into the condition restriction unit 114 according to actual needs. The AI model processing unit 115 is connected to the learning and training unit 112 and the parameter optimization setting unit 113. The AI model processing unit 115 learns and trains the AI model through the learning and training unit 112. The AI model processing unit 115 is the AI brain of the artificial intelligence system 110. At this time, the AI model processing unit 115 has been pre-trained by a large number of data or big data of practical operations, so it can give optimized settings according to different substrate characteristics. Therefore, before any operation or any process parameter input, it must first be analyzed, judged and decided by the AI model processing unit 115 to avoid manual input errors or back-end laser equipment operation errors.

In addition, in the present invention, the control processing module 120 is connected to the AI model processing unit 115 of the artificial intelligence system 110, and the control processing module 120 generates a first control instruction CS1, a second control instruction CS2, and a third control instruction CS3 according to the intelligent control instruction ACS and related data transmitted by the AI model processing unit 115, so as to perform processing operations on the substrate 200. It should be noted that the intelligent control instruction ACS includes a plurality of processing parameters calculated and optimized by the AI model processing unit 115, as well as the best construction path and construction rules, that is, the AI model processing unit 115 will command the control processing module 120 how to control all operations of the photography and imaging module 130, the laser desoldering module 140, and the alignment module 150. The photographic imaging module 130 is connected to the control processing module 120. The photographic imaging module 130 photographs or captures the substrate 200 according to the first control instruction CS1 transmitted by the control processing module 120. The control processing module 120 photographs the substrate 200 and takes out the substrate processing picture through the photographic imaging module 130. The number of photographic imaging modules 130 is not limited to one. The photographic imaging module 130 can photograph and take out the picture of one unit or processed area of the substrate 200, or the entire substrate 200, and this is performed according to a preset rule. Furthermore, the photographic imaging module 130 reads the rapid response matrix of the board production material number on the substrate 200 and transmits it back to the AI model processing unit 115 to identify the characteristics of the substrate 200 and perform pre-processing preparation for parameter optimization settings.

The laser desoldering module 140 is connected to the control processing module 120. The laser desoldering module 140 performs laser desoldering on the substrate 200 according to the first control instruction CS1 and a circuit layout diagram TA transmitted by the control processing module 120, and divides the substrate 200 into a plurality of areas to be processed through the circuit layout diagram TA, and then the laser beam performs a stripping operation on the cleaning portion 224 of each of the areas to be processed according to a preset rule. The above-mentioned circuit layout diagram TA refers to the output through the computer-aided design (CAD, Computer-Aided Design)/computer-aided manufacturing system (CAM, Computer-aided Manufacturing), which is a graphic-oriented automation system for automatic design, drafting, and display.

Furthermore, before the laser desoldering process is officially performed on the substrate 200, the operator will introduce process parameters, such as ink type, color, thickness, moving area or other parameter values, to allow the AI model processing unit 115 of the artificial intelligence system 110 to calculate the required laser spot size and number of laser shots to achieve the optimization effect. Because the AI model processing unit 115 has been pre-trained with a large amount of data or big data from practical operations, it can provide optimized settings based on different substrate characteristics. Next, the laser solder removal module 140 removes the removal portion 224 on the substrate 200 through a laser beam L1 and according to a construction pattern, so that the solder mask 220 forms at least one hollow portion 226, wherein the circuit layout diagram TA imports the data of the solder mask 220, and then converts the data of the solder mask 220 into a positive image, a negative image or a graphic conversion process to obtain the construction pattern. In the present invention, after obtaining the construction pattern, the control processing module 120 calculates the overlapping area size of the laser spot according to the laser spot size and energy of the laser solder removal module 140, and then translates a laser dot matrix, as shown in the ninth figure. In Figure 9, three types of graphics are used to illustrate the resolution of the laser dot matrix, which can be set by the designer or operator.

It should be noted that the laser light emitted by the laser beam L1 is a high-frequency laser beam (milliseconds, microseconds, nanoseconds or picoseconds) above the millisecond level. The type of laser beam L1 can be selected according to the characteristics of the material, and at least one of carbon dioxide (CO2) laser, Yag laser, green laser and ultraviolet light is used to achieve the effect of removing solder mask without residue or carbonization. In the embodiment of the present invention, for example, the laser beam L1 is a picosecond laser beam, and the time that the picosecond laser beam stays on the substrate 200 is very short, that is, it will not over-etch or remove the pad 210 under the solder mask 220. In addition, the artificial intelligence (AI) system 110 in the present invention will predict or adjust the laser spot size and shape according to the processing path, the construction pattern and the energy required by the material. Furthermore, the artificial intelligence (AI) system 110 adjusts different laser spot sizes and different laser firing numbers for different areas of the same surface of the substrate 200 through the parameter optimization setting unit 113 according to the calculated results, so as to achieve the goal of vaporizing the surface.

Please refer to Figures 1 to 5 at the same time. Figure 4 is a schematic diagram of the first embodiment of the substrate with multiple alignment points of the present invention. Figure 5 is a schematic diagram of the second embodiment of the substrate with multiple alignment points of the present invention. Before laser processing, the substrate 200 is usually flattened and aligned. The following will further explain how the present invention performs alignment, and the flattening of the substrate will not be repeated here. Under the prior art, the positioning pins on the positioning sleeve of the plate on the workbench only have a positioning function and are unable to solve the problem of deformation and expansion of the plate, so it often leads to the scrapping of the plate. However, the present invention can solve such a problem, which will be described in detail below. As shown in the fourth figure, in one implementation, the four corners around the substrate 200 each have a pair of points P1, and in another implementation, the four corners around the substrate 200 each have a pair of points P1 and the central area of the substrate has at least two alignment points P2, as shown in the fifth figure. The intelligent solder removal device 100 for removing the solder mask of the substrate by laser driven by artificial intelligence of the present invention further includes an alignment module 150. The alignment module 150 is connected to the control processing module 120, and the alignment module 150 aligns the substrate 200 to be processed according to a third control instruction CS3 transmitted by the control processing module 120 and through an infrared light RL, so as to further adjust the expansion and contraction amplitude of the construction pattern. Furthermore, because the solder mask 220 will cover the alignment point P1 or P2, the infrared light RL needs to first see through the solder mask 220 to accurately capture the image of the alignment point P1 or P2, and the artificial intelligence (AI) system 110 can be used to analyze and exclude the inappropriate alignment point P1 or P2 image before alignment. After the alignment is completed, the artificial intelligence (AI) system 110 calculates the deformation direction and degree of the substrate 200, that is, it will adjust the growth and contraction deformation according to the actual object, and then generate the deformed output construction drawing through CAM (Computer Aided Manufacturing).

Next, please refer to the first to eighth figures at the same time. The eighth figure is a schematic diagram of comparing the circuit layout diagram with the substrate processing picture of the present invention. After the laser solder removal module 140 removes the cleaning portion 224 on the substrate 200 through a laser beam L1 and according to a construction pattern, the control processing module 120 controls the photography module 130 to photograph the substrate 200 and take out a substrate processing picture DC, and compare and determine whether the substrate processing picture DC is the same as the circuit layout diagram TA. On the screen SC of the eighth figure, it can be seen that the substrate processing picture DC is being compared with the circuit layout diagram TA. If they are the same, the substrate processing operation is completed. If they are not the same, the laser desoldering module 140 will emit the laser beam L1 again for the different places to perform the stripping operation on the cleaning part 224. Accordingly, since the intelligent desoldering device 100 for removing the substrate solder mask by laser driven by artificial intelligence of the present invention does not use a mask at all, the circuit substrate 200 with different solder pad 210 positions no longer needs to make a mask that conforms to the circuit substrate in advance. In addition, the intelligent desoldering device 100 for removing the substrate solder mask by laser driven by artificial intelligence does not use an exposure device at all, so it will not be affected by the environmental conditions such as temperature and humidity in the exposure part of the exposure device, so the position accuracy of the positioning mark on the circuit substrate and the mask and the position accuracy of the exposure pattern will not change. The control processing module 120, the imaging module 130 and the alignment module 150 mentioned above can be regarded as a laser device.

Finally, please refer to the first figure and the tenth figure. The tenth figure is a schematic diagram of the multi-light source laser processing of the substrate of the present invention. The laser processing machine MT has multiple laser desoldering modules 141, 142 and 143, which are the same as the laser desoldering module 140 in the first figure. The laser desoldering modules 141, 142 and 143 are respectively connected to the control processing module 120 to perform multiple operations. In addition, the multiple laser desoldering modules 141, 142 and 143 respectively emit laser beams L2, L3 and L4 according to the circuit layout diagram TA and sequentially perform ablation or stripping operations on the cleaning portion 224 on the substrate 200, wherein the laser light source of each laser desoldering module is responsible for a different area, which helps to further improve the efficiency of the processing process. In this embodiment, three laser desoldering modules 141, 142 and 143 are used as examples for illustration, but in actual application, the number is not limited to three. The laser beams L2, L3 and L4 can be high-frequency laser beams above the millisecond level (milliseconds, microseconds, nanoseconds or picoseconds).

In summary, the laser solder mask removal process method disclosed in the present invention can achieve the following effects: 1. Greatly shorten the steps of the processing process; 2. Improve the process yield; 3. Have a laser beam with controllable energy; 4. Improve the pattern accuracy of the processing process; 5. Circuit substrates with different solder pad positions no longer need to first make a mask that meets the circuit substrate; 6. There will be no impact of environmental conditions such as temperature and humidity; 7. No need for development to greatly reduce waste water 8. No restrictions on ink, reducing ink costs; 9. Use at least one of CO2 laser, Yag laser, green laser and ultraviolet light to achieve the effect of removing solder mask without residue or carbonization; 10. Solve the problem of semi-cured solder mask being insufficient in hardness or sticky, which is easy to cause waste during operation; and 11. Reduce environmental damage, meet ESG standards, and contribute to sustainable development.

However, the above is only a preferred embodiment of the present invention and is not intended to limit the scope of implementation of the present invention. Therefore, all equivalent changes or modifications based on the features and spirit described in the scope of the present invention should be included in the scope of the patent application of the present invention.

100: Intelligent desoldering device that uses artificial intelligence-driven laser to remove the solder mask of substrates

110: Artificial Intelligence (AI) System

111: Database unit

112: Learning and training unit

113: Parameter optimization setting unit

114: Conditional unit

115: AI model processing unit

120: Control processing module

130: Photography and imaging module

140: Laser desoldering module

150: Alignment module

200: Substrate

300: Cloud Platform

ACS: Intelligent Control Instructions

CS1: First control instruction

CS2: First control instruction

CS3: First control instruction

NT: Internet

Claims (13)

An intelligent solder removal device for removing a substrate solder mask layer by laser driven by artificial intelligence is used to process at least one substrate placed on a laser processing machine through a laser with controllable energy, each of the substrates corresponds to a board production material number, and at least one solder pad is disposed on the surface of the substrate and a solder mask is covered on the surface of the substrate and the solder pad, wherein the solder mask is a shielding portion facing the surface of the substrate, and the solder mask is facing the The solder pad is a removal unit. The intelligent solder removal device for removing the solder mask layer of the substrate by laser driven by artificial intelligence includes: an artificial intelligence (AI) system for learning and pre-training the types of the substrates, the sizes of the substrates, the thickness of the substrates, the color of the solder mask, the thickness of the solder mask and the depth around the solder pads, and automatically optimizing all the multiple processing parameters according to the characteristics of the substrate to be processed. The artificial intelligence system comprises: a database unit having data related to the types of the substrates, the sizes of the substrates, the thickness of the substrates, the color of the solder mask, the thickness of the solder mask and the depth around the solder pads, wherein the database unit is connected to a cloud platform via the Internet to update the related data online; a learning and training unit connected to the database unit, the learning and training unit The unit learns and pre-trains through a substrate deep learning algorithm and according to the relevant data in the database unit; a parameter optimization setting unit is connected to the database unit, and the parameter optimization setting unit is used to optimize the processing parameters according to the relevant data of the types of the substrates, the sizes of the substrates, the thickness of the substrates, the color of the solder mask, the thickness of the solder mask, and the depth around the solder pads. a condition restriction unit connected to the learning and training unit, the condition restriction unit is used to limit the learning deviation of the artificial intelligence (AI) system by setting multiple conditions; and an AI model processing unit connected to the learning and training unit and the parameter optimization setting unit, the AI model processing unit learns and trains an AI model through the learning and training unit, wherein the AI model The AI model processing unit is the AI brain of the artificial intelligence system; a control processing module is connected to the AI model processing unit of the artificial intelligence system, and the control processing module generates a first control instruction, a second control instruction and a third control instruction according to the instructions and related data transmitted by the AI model processing unit to perform processing operations on the substrate; a photography module is connected to the control processing module, and the photography module The module photographs or captures the substrate according to the first control instruction transmitted by the control processing module, wherein the photographic imaging module reads the rapid response matrix of the board production material number on the substrate and returns it to the AI model processing unit to identify the characteristics of the substrate and perform pre-processing preparation for parameter optimization setting; and a laser desoldering module, which is connected to the control processing module, and the laser desoldering module performs pre-processing preparation according to the control processing module. The laser desoldering module performs laser desoldering on the substrate according to the first control instruction and a circuit layout diagram transmitted by the processing module, wherein the laser desoldering module performs a stripping operation on the removal portion through a laser beam and according to a construction drawing, so that the solder mask layer forms at least one hollow portion, wherein the circuit layout drawing imports the data of the solder mask layer, and then the data of the solder mask layer is processed into a positive image, a negative image or a graphic conversion to obtain the construction drawing. As described in claim 1, an intelligent solder removal device for removing the solder mask layer of a substrate by laser driven by artificial intelligence, wherein the artificial intelligence (AI) system predicts or adjusts the size and shape of the laser spot according to the processing path, the construction pattern and the energy required by the material. As described in claim 1, an intelligent solder removal device for removing the solder mask layer of a substrate by laser driven by artificial intelligence, wherein the artificial intelligence (AI) system adjusts different laser spot sizes and different laser firing numbers for different areas of the same board surface of the substrate through the parameter optimization setting unit according to the calculated results. The intelligent solder removal device for removing the solder mask layer of the substrate by laser driven by artificial intelligence as described in claim 1 further includes: a positioning module connected to the control processing module, the positioning module aligns the substrate to be processed according to a third control instruction transmitted by the control processing module and through an infrared light to further adjust the increase and decrease amplitude of the construction pattern, wherein the infrared light is used to see through the solder mask, wherein the artificial intelligence (AI) system analyzes and excludes inappropriate positioning point images, and calculates the deformation direction and degree of the substrate. As described in claim 4, an intelligent solder removal device for removing the solder mask layer of a substrate by laser driven by artificial intelligence, wherein each of the four corners around the substrate has a pair of points. An intelligent solder removal device for removing the solder mask layer of a substrate by laser driven by artificial intelligence as described in claim 4, wherein each of the four corners around the substrate has a pair of points and the central area of the substrate has at least two alignment points. As described in claim 1, the intelligent solder removal device for removing the solder mask layer of the substrate by laser driven by artificial intelligence, wherein after obtaining the construction pattern, the control processing module calculates the overlapping area size of the laser spot according to the laser spot size and energy of the laser solder removal module, and then translates it into a laser dot matrix. As described in claim 1, the intelligent solder removal device for removing the solder mask layer of the substrate by laser driven by artificial intelligence, wherein the substrate is photographed by the photographic imaging module and a substrate processing picture is taken out, and the substrate processing picture is compared and judged whether it is the same as the circuit layout diagram. If they are the same, the substrate processing operation is completed. As described in claim 8, in the step of comparing and judging whether the substrate processing image and the circuit layout image are the same, the intelligent solder removal device for removing the substrate solder mask layer by laser driven by artificial intelligence, if they are not the same, the laser beam will then perform a stripping operation on the cleaning portion for the different parts. As described in claim 1, the intelligent solder removal device for removing the solder mask layer of the substrate by laser driven by artificial intelligence, wherein the substrate is divided into a plurality of areas to be processed by the circuit layout diagram, and then the laser beam performs a stripping operation on the removal portion of each of the areas to be processed according to a preset rule. As described in claim 1, an intelligent solder removal device for removing the solder mask layer of a substrate by using an artificial intelligence-driven laser, wherein the laser light emitted by the laser beam is a high-frequency laser beam of more than milliseconds. As described in claim 1, the intelligent solder removal device for removing the solder mask layer of the substrate by laser driven by artificial intelligence, wherein the type of the laser beam adopts at least one of carbon dioxide (CO2) laser, Yag laser, green laser and ultraviolet light according to the characteristics of the material, so as to achieve the effect of removing the solder mask without residue or carbonization. As described in claim 1, the intelligent solder removal device for removing the solder mask layer of the substrate by laser driven by artificial intelligence, wherein the laser solder removal module has multiple sets of laser light sources to emit the laser beams respectively, and the removal operation is performed on the cleaning part of the substrate according to the first control instruction and the circuit layout diagram, wherein each laser light source is responsible for a different area.

Images