A PCBA soldering process optimization system based on deep learning

Abstract

The present invention discloses a PCBA soldering process optimization system based on deep learning, belonging to the technical field of printed circuit board assembly. In the present invention, the number of pixel points in the local solder joint depth image whose pixel differences from the pixel points at the corresponding positions of the local solder joint depth image template exceed the set threshold is used as the size feature information of the peeling area of each solder joint, which can accurately characterize the degree of copper foil peeling near each solder joint and can be used as an accurate basis for subsequent parameter optimization; through the solder joint area in the obtained solder joint depth image, the boundary points are cleverly identified and then the boundary of the concave area is formed, so that the size and depth of the concave area can be accurately characterized and can be used as an accurate basis for subsequent parameter optimization; based on the size feature information of the peeling area and the solder joint concave feature information, the soldering temperature, soldering time and soldering pressure can be accurately adjusted to realize the optimization of the soldering process parameters.

Description

Technical Field

[0001] The present invention relates to the technical field of printed circuit board assembly, and particularly to a PCBA soldering process optimization system based on deep learning. Background Art

[0002] A PCB, also known as a printed circuit board or printed wiring board, is an important electronic component, a support for electronic components, and a carrier for electrical connections of electronic components. It serves as a channel for current transmission and signal transfer and is a key electronic interconnection part in electronic products. Printed circuit boards are widely used in high-tech fields such as military, communication, medical, power, automotive, industrial control, smartphones, and wearables. With the development of science and technology, the application scope of printed circuit boards will continue to expand.

[0003] PCBA, i.e., printed circuit board assembly, is based on a PCB (printed circuit board). Through processes such as surface mount technology (SMT) and through-hole technology (DIP), electronic components (such as resistors, capacitors, inductors, chips, etc.) are installed on the PCB, and a series of processes such as soldering and testing are carried out to finally form an electronic component with a specific function.

[0004] During the soldering process, it is very likely that situations such as insufficient solder joints and PCB copper foil peeling will occur. Here, insufficient solder joints mainly refer to the phenomenon of depression in the middle area of the solder joint surface, and PCB copper foil peeling refers to the phenomenon that the adhesion between the copper foil and the PCB substrate is insufficient, resulting in partial or complete separation of the copper foil from the substrate.

[0005] How to optimize the soldering process parameters to avoid the occurrence of the above phenomena is an urgent problem to be solved. For this reason, a PCBA soldering process optimization system based on deep learning is proposed. Summary of the Invention

[0006] The technical problem to be solved by the present invention is: how to better optimize the soldering process parameters to avoid the occurrence of insufficient solder joints and PCB copper foil peeling, and a PCBA soldering process optimization system based on deep learning is provided.

[0007] The present invention solves the above technical problem through the following technical solutions. The present invention includes an initial parameter setting module, a copper foil peeling detection module, a solder joint depression detection module, and a parameter optimization module;

[0008] The initial parameter setting module is used to initialize and set the soldering temperature, soldering time, and soldering pressure during soldering to obtain the initial maximum allowable soldering temperature, the initial maximum allowable soldering time, and the initial maximum allowable soldering pressure;

[0009] The copper foil peeling detection module is used to detect the copper foil peeling phenomenon after each welding and obtain the size feature information of the peeling area;

[0010] The solder joint depression detection module is used to detect the solder joint depression phenomenon after each welding and obtain the solder joint depression feature information;

[0011] The parameter optimization module is used to adjust the welding temperature, welding time, and welding pressure respectively based on the size feature information of the peeling area and the solder joint depression feature information, on the basis of the initial maximum allowable welding temperature, initial maximum allowable welding time, and initial maximum allowable welding pressure, so as to optimize the welding process parameters.

[0012] Furthermore, the copper foil peeling detection module includes a depth image acquisition unit, a solder joint recognition unit, and a peeling area size feature information acquisition unit; the depth image acquisition unit is used to, after each welding, use the RGB-D depth camera installed on the welding head of the welding equipment to photograph the solder joints below, obtain the solder joint depth image and the corresponding solder joint RGB image, and perform noise reduction processing on the solder joint depth image and the solder joint RGB image; the solder joint recognition unit is used to use the trained solder joint target detection model to recognize the solder joints in the solder joint RGB image, and perform outer contour detection processing to obtain the solder joint area position information; the peeling area size feature information acquisition unit is used to process according to the solder joint area position information and the solder joint depth image template to obtain the peeling area size feature information Fi i , where i represents the i-th detection.

[0013] Furthermore, the specific processing process of the solder joint recognition unit is as follows:

[0014] Step S11: Use the target detection model to recognize the solder joints in the solder joint RGB image, and obtain the coordinates of the upper left corner point and the lower right corner point of the solder joint detection frame in the RGB image;

[0015] Step S12: Use the contour detection function in OpenCV to perform outer contour detection on the inside of the solder joint detection frame area, and obtain the solder joint outer contour line and the coordinates of each point on the outer contour line in the solder joint RGB image, that is, obtain the solder joint area position information.

[0016] Furthermore, the specific processing process of the peeling area size feature information acquisition unit is as follows:

[0017] Step S21: Correspondingly obtain the solder joint area in the solder joint depth image according to the solder joint outer contour line and the coordinates of each point on the outer contour line in the solder joint RGB image;

[0018] Step S22: Remove the solder joint areas in the solder joint depth image from the solder joint depth image and the solder joint depth image template, and correspondingly obtain a local solder joint depth image and a local solder joint depth image template. The solder joint depth image template is obtained by taking a picture with an RGB-D depth camera at each solder joint position before welding, and the shooting position is the same as that after welding is completed;

[0019] Step S23: Read the pixel values of the pixel points at the same positions in the local solder joint depth image and the local solder joint depth image template respectively, and calculate the pixel difference between the pixel points of the local solder joint depth image and the local solder joint depth image template at the same position, denoted as PC ij , where j represents the j-th pixel point;

[0020] Step S24: When the pixel difference PC ij is greater than or equal to the preset threshold PC of the pixel difference 0 , it means that the corresponding pixel point in the local solder joint depth image is a peeled pixel point. The peeled pixel point is the pixel point within the copper foil peeling area. Count the number of all peeled pixel points in the local solder joint depth image, denoted as F i , that is, obtain the size feature information of the peeling area.

[0021] Furthermore, the solder joint depression detection module includes a depression area size feature information acquisition unit and a depression depth feature acquisition unit; the depression area size feature information acquisition unit is used to process the solder joint depth image to obtain the boundary of the depression area, and further obtain the size feature information As of the depression area i , and the depression depth feature acquisition unit is used to obtain the pixel values of the pixel points within the depression area boundary line to obtain the depression depth feature information Ad i .

[0022] Furthermore, the specific processing process of the depression area size feature information acquisition unit is as follows:

[0023] Step S31: Obtain the solder joint area in the solder joint depth image in Step S21, and cut out the solder joint area from the solder joint depth image to obtain a solder joint area depth image;

[0024] Step S32: In the solder joint area depth image, calculate the pixel difference between the pixel values of two adjacent pixel points in turn from the outside to the inside. When the pixel difference exceeds the set threshold Ps, the pixel point with the smaller pixel value among the two pixel points is defined as a boundary point;

[0025] Step S33: Obtain all the boundary points, and all the boundary points form the boundary of the depression area;

[0026] Step S34: Count the number of all pixel points within the depression area boundary, denoted as Asi , the size feature information of the concave region is obtained.

[0027] Furthermore, the specific processing procedure of the concave depth feature acquisition unit is as follows:

[0028] Step S41: Read the pixel values of all pixel points within the boundary of the concave region in step S33;

[0029] Step S42: Denote the maximum pixel value as Ad i , that is, the concave depth feature information Ad is obtained i .

[0030] Furthermore, the adjustment process of the welding temperature by the parameter optimization module is as follows:

[0031] Look up according to the size feature information F of the peeling region i in the preset welding temperature adjustment database to obtain the adjustment value Tt of the welding temperature for the next welding i+1 , and subtract the adjustment value Tt from the current welding temperature during the next welding i+1 , until the numerical value of the size feature information F of the peeling region i is 0, then the adjustment work of the welding temperature can be stopped. Among them, the temperature during the first welding is the initial maximum allowable welding temperature, and the numerical value of the size feature information F of the peeling region i has a positive correlation with the numerical value of the adjustment value Tt i+1 , and the corresponding relationship between the size feature information F of the peeling region and the adjustment value Tt i is preset in the welding temperature adjustment database. i+1

[0032] Furthermore, the adjustment process of the welding time by the parameter optimization module is as follows:

[0033] Look up according to the size feature information As of the concave region i in the preset welding time adjustment database to obtain the adjustment value St of the welding time for the next welding i+1 , and subtract the adjustment value St from the current welding time during the next welding i+1 , until the numerical value of the size feature information As of the concave region i is 0, then the adjustment work of the welding time can be stopped. Among them, the time during the first welding is the initial maximum allowable welding time, and the numerical value of the size feature information As of the concave region i has a positive correlation with the numerical value of the adjustment value St i+1 , and the corresponding relationship between the size feature information As of the concave region and the adjustment value St i is preset in the welding time adjustment database. i+1 ​

[0034] Further, the process of the parameter optimization module adjusting the welding pressure is as follows:

[0035] Based on the depression depth feature information Ad i Search in the preset welding pressure adjustment database to obtain the adjustment value Pt of the welding pressure for the next welding i+1 , and subtract the adjustment value Pt from the current welding pressure during the next welding i+1 , until the value of the depression depth feature information Ad i is 0, then the adjustment of the welding pressure can be stopped. Among them, the pressure during the first welding is the initial maximum allowable welding pressure, and the value of the depression depth feature information Ad i has a positive correlation with the value of the adjustment value Pt i+1 , and the corresponding relationship between Pt i+1 and the adjustment value Pt i+1 is preset in the welding pressure adjustment database.

[0036] The present invention has the following advantages compared with the prior art: This PCBA welding process optimization system based on deep learning uses the number of pixel points whose pixel differences between corresponding position pixel points in the local solder joint depth image and the local solder joint depth image template exceed the set threshold as the peeling area size feature information of each solder joint, which can accurately represent the copper foil peeling degree near each solder joint and can be used as an accurate basis for subsequent parameter optimization; through the solder joint area in the obtained solder joint depth image, the boundary points are cleverly identified and then the boundary of the depression area is formed, so that the size and depth of the depression area can be accurately represented and can be used as an accurate basis for subsequent parameter optimization; based on the peeling area size feature information and the solder joint depression feature information, the welding temperature, welding time, and welding pressure can be accurately adjusted to realize the optimization of the welding process parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 is a structural schematic block diagram of the PCBA welding process optimization system based on deep learning in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0038] The following details the embodiments of the present invention. This embodiment is implemented on the premise of the technical solution of the present invention, and provides detailed implementation manners and specific operation processes, but the protection scope of the present invention is not limited to the following embodiments.

[0039] As Figure 1As shown in the figure, this embodiment provides a technical solution: a PCBA soldering process optimization system based on deep learning. Before batch soldering various components, the initially set soldering process parameters (mainly referring to soldering temperature, soldering time, and soldering pressure) are optimized through soldering tests, so as to avoid the occurrence of insufficient solder joints and PCB copper foil peeling during subsequent batch soldering of various components. It includes the following modules: an initial parameter setting module, a copper foil peeling detection module, a solder joint depression detection module, and a parameter optimization module;

[0040] In this embodiment, the initial parameter setting module is used to initialize and set the soldering temperature, soldering time, and soldering pressure during soldering, to obtain the initial maximum allowable soldering temperature, the initial maximum allowable soldering time, and the initial maximum allowable soldering pressure;

[0041] More specifically, the initial maximum allowable soldering temperature is initialized and set according to the type of solder used and the heat resistance of the components. Generally, the melting point of the solder and the recommended temperature range of the components can be referred to for initialization and setting.

[0042] More specifically, the initial maximum allowable soldering time is initialized and set according to the type of solder used and the pin size of the components.

[0043] More specifically, the initial maximum allowable soldering pressure is initialized and set according to the type of circuit board, the type of solder, and the type of components. It should be noted that the thickness, material of the circuit board, and the layout of the solder pads, etc. will affect the soldering pressure. For thick boards or multi-layer boards, the soldering pressure needs to be appropriately increased to ensure that the solder can fully fill the gap between the solder pad and the pin.

[0044] After the initial parameter setting module sets the above initial soldering process parameters, the current components are soldered through a soldering device, and the soldering test work begins.

[0045] In this embodiment, the copper foil peeling detection module is used to detect the copper foil peeling phenomenon after each soldering and obtain the size feature information of the peeling area.

[0046] More specifically, the copper foil peeling detection module includes a depth image acquisition unit, a solder joint recognition unit, and a peeling area size feature information acquisition unit. The depth image acquisition unit is configured to, after each welding is completed, use an RGB-D depth camera installed on the welding head of the welding equipment to capture the solder joints below, obtain the solder joint depth image and the corresponding solder joint RGB image, and perform noise reduction processing on the solder joint depth image and the solder joint RGB image. The solder joint recognition unit is configured to use a trained solder joint target detection model to recognize the solder joints in the solder joint RGB image, and perform outer contour detection processing to obtain the solder joint area position information. The peeling area size feature information acquisition unit is configured to process according to the solder joint area position information and the solder joint depth image template to obtain the peeling area size feature information F i , where i represents the i-th detection, and each solder joint performs a copper foil peeling / solder joint depression detection operation.

[0047] It should be noted that the RGB-D depth camera can not only obtain the two-dimensional image information (RGB image) of an object, but also obtain the depth information (depth image) of the object at the same time, and the RGB image and the depth image have the same specifications. The solder joint depth image and the solder joint RGB image in this embodiment both contain a single complete solder joint and the copper foil near the solder joint.

[0048] It should be noted that the solder joint target detection model is trained based on the SSD target detection network.

[0049] More specifically, the specific processing process of the solder joint recognition unit is as follows:

[0050] Step S11: Use the target detection model to recognize the solder joints in the solder joint RGB image to obtain the coordinates of the upper left corner point and the lower right corner point of the solder joint detection box in the RGB image;

[0051] Step S12: Use the contour detection function in OpenCV to perform outer contour detection on the inside of the solder joint detection box area to obtain the solder joint outer contour line and the coordinates of each point on the outer contour line in the solder joint RGB image, that is, obtain the solder joint area position information.

[0052] More specifically, the specific processing process of the peeling area size feature information acquisition unit is as follows:

[0053] Step S21: Correspondingly obtain the solder joint area in the solder joint depth image according to the solder joint outer contour line and the coordinates of each point on the outer contour line in the solder joint RGB image;

[0054] Step S22: Remove the solder joint area in the solder joint depth image from the solder joint depth image and the solder joint depth image template to correspondingly obtain a local solder joint depth image and a local solder joint depth image template;

[0055] Step S23: Read the pixel values of the corresponding pixels at the same positions in the local solder joint depth image and the local solder joint depth image template respectively, and calculate the pixel difference between the pixel points of the local solder joint depth image and the local solder joint depth image template at the same position, denoted as PC ij , where j represents the j-th pixel point;

[0056] Step S24: When the pixel difference PC ij is greater than or equal to the threshold PC of the preset pixel difference 0 , it means that the corresponding pixel point in the local solder joint depth image is a peeled pixel point. The peeled pixel point is the pixel point within the copper foil peeling area. Count the number of all peeled pixel points in the local solder joint depth image, denoted as F i , that is, obtain the size feature information of the peeling area.

[0057] It should be noted that in this embodiment, the solder joint depth image template is obtained by shooting with the above RGB-D depth camera before welding at each solder joint position, and the shooting position is the same as the shooting position after welding; moreover, after each welding is completed, the RGB-D depth camera shoots each solder joint of the lower PCB at the same set height.

[0058] In the present invention, by using the number of pixel points in the local solder joint depth image whose pixel difference from the corresponding pixel points in the local solder joint depth image template exceeds the set threshold as the size feature information of the peeling area of each solder joint, it can accurately characterize the degree of copper foil peeling near each solder joint and can be used as an accurate basis for subsequent parameter optimization.

[0059] In this embodiment, the solder joint depression detection module is used to detect the solder joint depression phenomenon after each welding is completed and obtain the solder joint depression feature information.

[0060] More specifically, the solder joint depression detection module includes a depression area size feature information acquisition unit and a depression depth feature acquisition unit; the depression area size feature information acquisition unit is used to process the solder joint depth image to obtain the depression area boundary, and further obtain the depression area size feature information As i , and the depression depth feature acquisition unit is used to obtain the pixel values of the pixel points within the depression area boundary line to obtain the depression depth feature information Ad i .

[0061] More specifically, the specific processing process of the depression area size feature information acquisition unit is as follows:

[0062] Step S31: Obtain the solder joint area in the solder joint depth image in Step S21, and cut the solder joint area from the solder joint depth image to obtain the solder joint area depth image;

[0063] Step S32: In the depth image of the solder joint area, calculate the pixel difference between the pixel values of two adjacent pixel points in sequence from the outside to the inside. When the pixel difference exceeds the set threshold Ps, the pixel point with the smaller pixel value among the two pixel points is defined as the boundary point;

[0064] Step S33: Obtain all the boundary points, and all the boundary points form the boundary of the concave area;

[0065] Step S34: Count the number of all pixel points within the boundary of the concave area, denoted as As i , that is, the size feature information of the concave area is obtained.

[0066] More specifically, the specific processing process of the concave depth feature acquisition unit is as follows:

[0067] Step S41: Read the pixel values of all pixel points within the boundary of the concave area in Step S33;

[0068] Step S42: Denote the maximum pixel value as Ad i , that is, the concave depth feature information Ad is obtained i .

[0069] In the present invention, through the solder joint area in the obtained solder joint depth image, the boundary points are skillfully identified and then the boundary of the concave area is formed, so that the size and depth of the concave area can be accurately characterized.

[0070] In this embodiment, the parameter optimization module is used to adjust the welding temperature, welding time, and welding pressure respectively according to the size feature information of the peeling area and the concave feature information of the solder joint, so as to optimize the welding process parameters.

[0071] More specifically, the specific processing process of the parameter optimization module is as follows:

[0072] According to the size feature information F of the peeling area i Search in the preset welding temperature adjustment database to obtain the adjustment value Tt of the welding temperature for the next welding i+1 , and subtract the adjustment value Tt from the current welding temperature for the next welding i+1 , until the numerical value of the size feature information F of the peeling area i is 0, then the adjustment work of the welding temperature can be stopped. Among them, the temperature for the first welding is the initial maximum allowable welding temperature, and the numerical value of the size feature information F of the peeling area i is positively correlated with the numerical value of the adjustment value Tt i+1 , and the welding temperature adjustment database presets the size feature information F of the peeling area i and the adjustment value Tti+1 The corresponding relationship;

[0073] According to the size feature information As of the concave region i Search in the preset welding time adjustment database to obtain the adjustment value St of the welding time for the next welding i+1 , and subtract the adjustment value St from the current welding time during the next welding i+1 , until the numerical value of the size feature information As of the concave region i is 0, then the adjustment work of the welding time can be stopped. Among them, the time for the first welding is the initial maximum allowable welding time, and the numerical value of the size feature information As of the concave region i has a positive correlation with the numerical value of the adjustment value St i+1 . There is a preset corresponding relationship between the size feature information As of the concave region i and the adjustment value St i+1 in the welding time adjustment database;

[0074] According to the concave depth feature information Ad i Search in the preset welding pressure adjustment database to obtain the adjustment value Pt of the welding pressure for the next welding i+1 , and subtract the adjustment value Pt from the current welding pressure during the next welding i+1 , until the numerical value of the concave depth feature information Ad i is 0, then the adjustment work of the welding pressure can be stopped. Among them, the pressure for the first welding is the initial maximum allowable welding pressure, and the numerical value of the concave depth feature information Ad i has a positive correlation with the numerical value of the adjustment value Pt i+1 . There is a preset corresponding relationship between Pt i+1 and the adjustment value Pt i+1 in the welding pressure adjustment database.

[0075] It should be noted that during the welding process, the main factor for copper foil peeling is excessive welding temperature, so it is gradually adjusted downward based on the initial maximum allowable welding temperature; similarly, the main factors for solder joint depression are excessive welding time and excessive welding pressure. Among them, excessive welding time mainly affects the size of the concave region, and the larger the welding time, the larger the concave region, so it is gradually adjusted downward based on the initial maximum allowable welding time. Excessive welding pressure mainly affects the depth of the concave region, and the larger the welding pressure, the deeper the concave region, so it is gradually adjusted downward based on the initial maximum allowable welding pressure.

[0076] In this embodiment, for the testing process of a single component, the optimization of the welding process parameters of the current component can be completed through 5 - 8 rounds of detection and optimization processes.

[0077] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A PCBA welding process optimization system based on deep learning, characterized in that: It includes initial parameter setting module, copper foil peeling detection module, solder joint sag detection module and parameter optimization module; The initial parameter setting module is used to initialize the welding temperature, welding time and welding pressure during welding to obtain the initial maximum allowable welding temperature, the initial maximum allowable welding time and the initial maximum allowable welding pressure; The copper foil peeling detection module is used to detect the copper foil peeling phenomenon after each welding is completed, and obtain the size characteristic information of the peeling area; The solder joint depression detection module is used to detect the solder joint depression phenomenon after each welding is completed to obtain solder joint depression feature information; The parameter optimization module is used to adjust the welding temperature, welding time and welding pressure respectively based on the initial maximum allowable welding temperature, initial maximum allowable welding time and initial maximum allowable welding pressure according to the stripping area size feature information and the solder joint depression feature information, so as to optimize the welding process parameters; The copper foil peeling detection module includes a depth image acquisition unit, a solder joint recognition unit and a peeling area size feature information acquisition unit; the depth image acquisition unit is used to use the RGB-D depth camera installed on the welding head of the welding equipment to shoot the solder joint below after each welding, obtain the solder joint depth image and the corresponding solder joint RGB image, and perform noise reduction processing on the solder joint depth image and the solder joint RGB image; The solder joint recognition unit is used to use the trained solder joint target detection model to recognize the solder joints in the solder joint RGB image, and perform outer contour detection processing to obtain the solder joint area position information; the stripping area size feature information acquisition unit is used to process according to the solder joint area position information and the solder joint depth image template to obtain the stripping area size feature information F i , where i represents the i-th detection.

2. According to a PCBA welding process optimization system based on deep learning according to claim 1, it is characterized in that: The specific processing process of the solder joint identification unit is as follows: Step S11: using the target detection model to identify the solder joints in the solder joint RGB image, and obtaining the coordinates of the upper left corner point and the lower right corner point of the solder joint detection frame in the RGB image; Step S12: Use the contour detection function in OpenCV to perform outer contour detection on the inside of the solder joint detection frame area, obtain the outer contour line of the solder joint and the coordinates of each point on the outer contour line in the solder joint RGB image, that is, obtain the position information of the solder joint area.

3. According to a PCBA welding process optimization system based on deep learning according to claim 2, it is characterized in that: The specific processing process of the stripping area size feature information acquisition unit is as follows: Step S21: Obtaining the solder joint area in the solder joint depth image according to the solder joint outer contour line and the coordinates of each point on the outer contour line in the solder joint RGB image; Step S22: removing the solder joint area in the solder joint depth image from the solder joint depth image and the solder joint depth image template, and correspondingly obtaining a local solder joint depth image and a local solder joint depth image template, wherein the solder joint depth image template is obtained by photographing at each solder joint position by using an RGB-D depth camera before welding, and the photographing position is the same as the photographing position after welding. Step S23: Read the pixel values ​​of the pixels at the same position in the local solder joint depth image and the local solder joint depth image template respectively, and calculate the pixel difference between the pixels at the same position in the local solder joint depth image and the local solder joint depth image template, recorded as PC ij , where j represents the jth pixel; Step S24: When the pixel difference PC ij If the pixel difference value is greater than or equal to the preset pixel difference threshold PC0, it means that the corresponding pixel point in the local solder joint depth image is a peeled pixel point. The peeled pixel point is the pixel point in the copper foil peeling area. The number of all peeled pixels in the local solder joint depth image is counted and recorded as F i , that is, obtaining the characteristic size information of the peeling area.

4. According to a PCBA welding process optimization system based on deep learning according to claim 3, it is characterized in that: The solder joint dent detection module includes a dent area size feature information acquisition unit and a dent depth feature acquisition unit; the dent area size feature information acquisition unit is used to process the solder joint depth image to obtain the dent area boundary, and then obtain the dent area size feature information As i The concave depth feature acquisition unit is used to obtain the pixel value of the pixel point within the concave area boundary line to obtain the concave depth feature information Ad i .

5. According to a PCBA welding process optimization system based on deep learning according to claim 4, it is characterized in that: The specific processing process of the recessed area size feature information acquisition unit is as follows: Step S31: obtaining a solder joint area in the solder joint depth image in step S21, and cutting out the solder joint area from the solder joint depth image to obtain a solder joint area depth image; Step S32: in the depth image of the solder joint area, the pixel difference between the pixel values ​​of two adjacent pixels is calculated from the outside to the inside. When the pixel difference exceeds the set threshold value Ps, the pixel with the smaller pixel value of the two pixels is defined as a boundary point. Step S33: Acquire all boundary points, and all boundary points form the boundary of the concave area; Step S34: Count the number of all pixels within the concave area boundary, denoted as As i , that is, the size characteristic information of the concave area is obtained.

6. A PCBA welding process optimization system based on deep learning according to claim 5, characterized in that: The specific processing process of the concave depth feature acquisition unit is as follows: Step S41: reading the pixel values ​​of all pixels within the boundary of the concave area in step S33; Step S42: Record the maximum pixel value as Ad i , that is, the concave depth feature information Ad is obtained i .

7. According to a PCBA welding process optimization system based on deep learning according to claim 4, it is characterized in that: The parameter optimization module adjusts the welding temperature as follows: According to the peeling area size characteristic information F i Search in the preset welding temperature adjustment database to obtain the welding temperature adjustment value Tt for the next welding i+1 In the next welding, the adjustment value Tt is subtracted from the current welding temperature. i+1 , until the stripping area size feature information F i When the value is 0, the adjustment of welding temperature can be stopped. The temperature of the first welding is the initial maximum allowable welding temperature. The stripping area size feature information F i The value of the adjustment value Tt i+1 The numerical value of is positively correlated, and the welding temperature adjustment database is preset with the peeling area size feature information F i With adjustment value Tt i+1 The corresponding relationship.

8. According to a PCBA welding process optimization system based on deep learning according to claim 4, it is characterized in that: The parameter optimization module adjusts the welding time as follows: According to the concave area size characteristic information As i Search in the preset welding time adjustment database to obtain the welding time adjustment value St for the next welding. i+1 In the next welding, the adjustment value St is subtracted from the current welding time. i+1 , until the concave area size characteristic information As i When the value is 0, the adjustment of welding time can be stopped. The time of the first welding is the initial maximum allowable welding time. The size characteristic information of the concave area As i The value of the adjustment value St i+1 The numerical value of is positively correlated, and the welding time adjustment database is preset with the concave area size feature information As i With adjustment value St i+1 The corresponding relationship.

9. The PCBA welding process optimization system based on deep learning according to claim 4, characterized in that: The parameter optimization module adjusts the welding pressure as follows: According to the concave depth feature information Ad i Search in the preset welding pressure adjustment database to obtain the welding pressure adjustment value Pt for the next welding i+1 In the next welding, the adjustment value Pt is subtracted from the welding pressure of this time. i+1 , until the depression depth feature information Ad i When the value is 0, the welding pressure adjustment can be stopped. The pressure during the first welding is the initial maximum allowable welding pressure. The concave depth characteristic information Ad i The value of the adjustment value Pt i+1 The numerical value of is positively correlated, and the welding pressure adjustment database is preset with Pt i+1 With adjustment value Pt i+1 The corresponding relationship.

Images