Chip DFM welding spot identification and analysis system and method based on artificial intelligence

Abstract

The invention discloses a chip DFM welding spot recognition and analysis system and method based on artificial intelligence, and belongs to the field of welding spot recognition and analysis. Data transmission information in the operation process of a corresponding connection circuit of a welding spot is obtained and imported into a welding spot data anomaly analysis model for welding spot data anomaly analysis; according to the spot welding effect analysis method, the spot welding image data are analyzed to obtain the implicit features reflecting the welding quality in the image, the implicit features are comprehensively analyzed to obtain the welding quality analysis result, and the spot welding effect is analyzed according to the spot welding position anomaly analysis result and the welding spot data anomaly analysis result which are obtained through analysis. And then data transmission analysis at the welding position is integrated, the welding effect of the welding spot is comprehensively evaluated and analyzed, and the accuracy of evaluation of the welding effect of the welding spot is improved.

Description

Technical Field

[0001] The present application belongs to the field of solder joint identification and analysis, and specifically to a chip DFM solder joint identification and analysis system and method based on artificial intelligence. Background Art

[0002] DFM (Design for Manufacturing) plays an important role in solder joint design and manufacturing. Solder joints are a key part in the assembly process of electronic products. Their quality and reliability are crucial to the performance and life of the entire product. DFM solder joints involve the design, manufacturing and quality control of solder joints to ensure that the solder joints meet product requirements and have high reliability. In DFM solder joint design, multiple factors need to be considered, such as the selection of solder joint materials, the selection of welding processes, the design of solder joint structures, etc. After welding, a solder joint identification and analysis system is needed to identify and analyze the welding effect;

[0003] When analyzing welding effects, the prior art usually only analyzes the welding effects through the distortion of the transmitted data, but fails to analyze the spot welding image data, thereby ignoring the implicit features in the image that reflect the welding quality, which results in the inability to comprehensively analyze these implicit features to obtain welding quality analysis results, and ultimately leads to low accuracy in spot welding effect evaluation. Most of the prior art has the above problems.

[0004] In order to solve the problems raised by this background technology, the present application designs a chip DFM solder joint identification and analysis system and method based on artificial intelligence. Summary of the invention

[0005] In view of the deficiencies in the prior art, this application proposes an artificial intelligence-based chip DFM solder joint identification and analysis system and method.

[0006] To achieve the above objectives, the present application provides the following technical solutions: In the first aspect, the present application provides a chip DFM solder joint identification and analysis method based on artificial intelligence, which includes the following specific steps:

[0007] S1, obtaining spot welding image data of each solder joint position of the chip, constructing a three-dimensional model of the solder joint position, and obtaining data transmission information during the operation of the solder joint;

[0008] S2, obtaining the three-dimensional model data of each solder joint position of the chip and importing it into the spot welding position abnormality analysis model to perform spot welding position abnormality analysis;

[0009] S3, obtaining data transmission information of the corresponding connection circuit of the solder joint during operation and importing it into the solder joint data abnormality analysis model to perform solder joint data abnormality analysis;

[0010] S4. Analyze the spot welding effect of the welding spot by analyzing the abnormal analysis results of the spot welding position and the abnormal analysis results of the welding spot data.

[0011] As a preferred technical solution of the chip DFM solder joint identification and analysis method based on artificial intelligence, the specific contents of obtaining the spot welding image data of each solder joint position of the chip, constructing a three-dimensional model of the solder joint position, and obtaining the data transmission information during the operation of the solder joint are:

[0012] S11. Obtain image data of the weld position and standard weld area data of the weld through a weld image acquisition terminal, and simultaneously obtain height data of each pixel corresponding to the weld, and obtain a real-time three-dimensional image of the weld relative to the standard weld area through a three-dimensional construction software, and simultaneously obtain a standard three-dimensional image of the weld, and simultaneously obtain crack data on the surface of the real-time weld. It should be noted that the three-dimensional image of the weld is acquired by using a high-resolution three-dimensional scanner or camera to capture two-dimensional images of the weld at multiple angles, and then synthesizing these images into a three-dimensional model, which is stored in a first storage component. The purpose of acquiring the standard weld three-dimensional image and the real-time weld relative to the standard weld area is to conduct a comprehensive analysis of the weld position and weld image, and to analyze the connection degree of the weld.

[0013] S12. Obtain the current data of the signal passing through the solder joint before and after the solder joint during the operation of the circuit within the test time, and store them in the second storage component; it should be noted that the change of the signal passing through the solder joint is collected here in order to analyze the quality of the solder joint through the transmission distortion of the signal.

[0014] As a preferred technical solution of the chip DFM solder joint identification and analysis method based on artificial intelligence, the three-dimensional model data of the chip solder joint positions is obtained and imported into the spot welding position abnormality analysis model for spot welding position abnormality analysis, which includes the following specific steps:

[0015] S21, obtaining a three-dimensional image of the real-time welding spot relative to the standard welding area, and obtaining a three-dimensional image of the standard welding spot at the same time, obtaining the welding center point at the bottom of the two three-dimensional images, corresponding the welding center point at the bottom of the two three-dimensional images to one point so that the two three-dimensional images partially overlap, obtaining the height value data of each corresponding point, obtaining the height value of the corresponding point, and importing the height value of the corresponding point into the calculation formula of the welding spot displacement abnormal value to calculate the welding spot displacement abnormal value, wherein the calculation formula of the welding spot displacement abnormal value is: Wherein, n is the number of corresponding points on the standard weld spot three-dimensional image, xi is the height of the ith corresponding point on the actual weld spot image, xim is the height of the ith corresponding point on the standard weld spot three-dimensional image, li is the distance from the ith corresponding point to the welding alignment point, c is the distance between the welding alignment points at the bottom of the two three-dimensional images, ck is the average diameter of the bottom of the standard weld spot three-dimensional image, wherein the welding alignment point is the welding ground alignment point, so the closer it is to the welding alignment point, the greater the role of its welding, so the reciprocal of the distance from the corresponding point to the welding alignment point is used to assign weights to corresponding points at different positions, and xixim is the height difference between the two three-dimensional images at point i, which is divided by xim to represent the difference between the two three-dimensional images at point i, and the differences of all points are superimposed to obtain the displacement and shape difference between the two weld spot images. It should be noted that the welding center point here is the point with the smallest standard deviation of the distance to each point on the bottom boundary among any point on the bottom;

[0016] S22, obtaining real-time crack length and width data on the surface of the solder joint, and importing the obtained crack length and width data on the surface of the solder joint into a solder joint strength abnormal value calculation formula to calculate the solder joint strength abnormal value, wherein the solder joint strength abnormal value calculation formula is: Wherein, L is the average value of the shortest distance between cracks, m is the number of cracks, kj is the length of the jth crack, sj is the width of the jth crack, s is the average diameter of the standard solder joint 3D image, and l is the average height of the standard solder joint 3D image;

[0017] S23. Obtain the obtained weld displacement abnormality value and weld strength abnormality value, and substitute them into the spot welding position abnormality value calculation formula to calculate the spot welding position abnormality value, wherein the spot welding position abnormality value calculation formula is: Hc=γHw+(1-γ)Hq, wherein γ is the displacement abnormality ratio coefficient. It should be noted that the welding abnormality of the weld is analyzed here by the weld strength and weld displacement.

[0018] As a preferred technical solution of the chip DFM solder joint identification and analysis method based on artificial intelligence, the data transmission information of the corresponding connection circuit of the solder joint is obtained and imported into the solder joint data anomaly analysis model for solder joint data anomaly analysis, which includes the following specific steps:

[0019] S31, obtaining current data of a signal passing through a welding point before and after the welding point during the circuit operation within a corresponding test time;

[0020] S32, importing the current data of the signal passing through the previous welding point and the current data of the signal passing through the welding point during the circuit operation within the test time into the welding data abnormal value calculation formula to calculate the welding data abnormal value, wherein the welding data abnormal value calculation formula is: Wherein, T is the test time, At is the current data of the signal after passing the welding point at the test time t, Atm is the current data of the signal before passing the welding point at the test time t, and dt is the time integral; in this way, the welding quality can be analyzed by analyzing the abnormality of the passing signal within the test time.

[0021] As a preferred technical solution of the chip DFM solder joint identification and analysis method based on artificial intelligence, the spot welding effect analysis of the solder joints obtained by analyzing the abnormal analysis results of the spot welding position and the abnormal analysis results of the solder joint data includes the following specific contents:

[0022] Obtain the calculated spot welding position abnormal value and welding data abnormal value and substitute them into the welding effect analysis value calculation formula to calculate the welding effect analysis value, wherein the welding effect analysis value calculation formula is: Hz = (1 + Hc) exp (Hs), wherein exp () is the power of the natural constant e;

[0023] The calculated welding effect analysis value is obtained and compared with the welding effect threshold. If the obtained welding effect analysis value is greater than the welding effect threshold, it means that the welding has failed and re-welding is required. If the obtained welding effect analysis value is less than or equal to the welding effect threshold, it means that the welding is successful.

[0024] In the second aspect, the present application provides an artificial intelligence-based chip DFM solder joint identification and analysis system, which is implemented based on the above-mentioned artificial intelligence-based chip DFM solder joint identification and analysis method, and specifically includes a data acquisition module, a position anomaly analysis module, a solder joint data anomaly analysis module and a spot welding effect analysis module;

[0025] The data acquisition module is used to acquire the spot welding image data of each solder joint position of the chip, construct a three-dimensional model of the solder joint position, and acquire the data transmission information during the operation of the solder joint;

[0026] The position anomaly analysis module is used to obtain the three-dimensional model data of the position of each solder joint of the chip and import it into the spot welding position anomaly analysis model to perform spot welding position anomaly analysis;

[0027] The solder point data anomaly analysis module is used to obtain data transmission information during the operation of the corresponding connection circuit of the solder point and import it into the solder point data anomaly analysis model to perform solder point data anomaly analysis;

[0028] The spot welding effect analysis module is used to analyze the spot welding effect of the welding spot by analyzing the abnormal analysis results of the spot welding position and the abnormal analysis results of the welding point data;

[0029] A control module may also be included, and the control module is used to control the operation of the data acquisition module, the position abnormality analysis module, the welding point data abnormality analysis module and the spot welding effect analysis module.

[0030] In a third aspect, the present application provides an electronic device, comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0031] The processor executes the above-mentioned chip DFM solder joint identification and analysis method based on artificial intelligence by calling the computer program stored in the memory.

[0032] In a fourth aspect, the present application provides a computer-readable storage medium storing instructions, which, when executed on a computer, enables the computer to execute the above-mentioned artificial intelligence-based chip DFM solder joint identification and analysis method.

[0033] Compared with the prior art, the beneficial effects of this application are:

[0034] The present application obtains the spot welding image data of each solder joint position of the chip, constructs a three-dimensional model of the solder joint position, and simultaneously obtains the data transmission information during the operation of the solder joint, obtains the three-dimensional model data of each solder joint position of the chip and imports it into the spot welding position abnormality analysis model to perform spot welding position abnormality analysis, obtains the data transmission information during the operation of the corresponding connection circuit of the solder joint and imports it into the solder joint data abnormality analysis model to perform solder joint data abnormality analysis, and performs spot welding effect analysis of the solder joints by analyzing the obtained spot welding position abnormality analysis results and solder joint data abnormality analysis results. The present application analyzes the spot welding image data to obtain implicit features in the image that reflect the welding quality, performs a comprehensive analysis of these implicit features to obtain the welding quality analysis results, and then comprehensively analyzes the data transmission analysis at the welding location, performs a comprehensive evaluation and analysis on the welding effect of the solder joint, thereby improving the accuracy of the evaluation of the solder joint welding effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings.

[0036] Figure 1 This is a schematic diagram of the overall process of the chip DFM solder joint identification and analysis method based on artificial intelligence in this application;

[0037] Figure 2 This is a schematic diagram of step S2 of the chip DFM solder joint identification and analysis method based on artificial intelligence in this application;

[0038] Figure 3 This is a schematic diagram of the overall framework of the chip DFM solder joint identification and analysis system based on artificial intelligence in this application;

[0039] Figure 4 This is a schematic diagram of obtaining the height of corresponding points of a three-dimensional image in this application;

[0040] Figure 5This is a schematic diagram of the names of the various locations of the solder joints in this application. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and is by no means intended to limit the present application and its application or use.

[0042] Example 1

[0043] In order to solve the technical problems raised in the background technology, the present application provides a preferred embodiment: Figure 1-Figure 2 As shown, the chip DFM solder joint identification and analysis method based on artificial intelligence includes the following specific steps:

[0044] S1, obtaining spot welding image data of each solder joint position of the chip, constructing a three-dimensional model of the solder joint position, and obtaining data transmission information during the operation of the solder joint;

[0045] In one specific embodiment, the spot welding image data of each solder joint position of the chip is obtained, a three-dimensional model of the solder joint position is constructed, and the specific content of the data transmission information during the operation of the solder joint is obtained:

[0046] S11. Obtain image data of the weld position and standard weld area data of the weld through a weld image acquisition terminal, and simultaneously obtain height data of each pixel corresponding to the weld, and obtain a real-time three-dimensional image of the weld relative to the standard weld area through a three-dimensional construction software, and simultaneously obtain a standard three-dimensional image of the weld, and simultaneously obtain crack data on the surface of the real-time weld. It should be noted that the three-dimensional image of the weld is acquired by using a high-resolution three-dimensional scanner or camera to capture two-dimensional images of the weld at multiple angles, and then synthesizing these images into a three-dimensional model, which is stored in a first storage component. The purpose of acquiring the standard weld three-dimensional image and the real-time weld relative to the standard weld area is to conduct a comprehensive analysis of the weld position and weld image, and to analyze the connection degree of the weld.

[0047] S12, obtaining the current data of the signal passing through the solder joint before and after the solder joint during the circuit operation within the test time, and storing them in the second storage component; it should be noted that the change of the signal passing through the solder joint is collected here in order to analyze the quality of the solder joint through the transmission distortion of the signal;

[0048] S2, obtaining the three-dimensional model data of each solder joint position of the chip and importing it into the spot welding position abnormality analysis model to perform spot welding position abnormality analysis;

[0049] In one embodiment, obtaining the three-dimensional model data of each solder joint position of the chip and importing it into the spot welding position abnormality analysis model to perform spot welding position abnormality analysis includes the following specific steps:

[0050] S21, such as Figure 4 and Figure 5 As shown, Figure 4 The schematic diagram of obtaining the height of corresponding points of the three-dimensional image specifically includes: obtaining a three-dimensional image of the real-time welding point relative to the standard welding area, obtaining a three-dimensional image of the standard welding point at the same time, obtaining the welding center point at the bottom of the two three-dimensional images, corresponding the welding center points at the bottom of the two three-dimensional images to one point so that the two three-dimensional images partially overlap, and obtaining the height value data of each corresponding point therein; Figure 5 The operation process here is described in detail, among which, Figure 5 Image A in the figure is a three-dimensional image of a standard solder joint. Since the three-dimensional image of a standard solder joint is regular and uniform, such as a standard circular or square image, the soldering center point 1 is the soldering alignment point. Figure 5 Image B in the figure is a three-dimensional image of the real-time weld relative to the standard welding area, and its welding center point 2 is the point with the smallest standard deviation of the distance to each point on the bottom boundary among any points on the bottom. In this way, the welding center points of Figure A and Figure B correspond to one point, so that the two three-dimensional images partially overlap to obtain Image C, and the height values ​​of the corresponding points are obtained and imported into the calculation formula of the weld displacement abnormal value to calculate the weld displacement abnormal value, where the calculation formula of the weld displacement abnormal value is: Wherein, n is the number of corresponding points on the standard weld spot three-dimensional image, xi is the height of the ith corresponding point on the actual weld spot image, xim is the height of the ith corresponding point on the standard weld spot three-dimensional image, li is the distance from the ith corresponding point to the welding alignment point, c is the distance between the welding alignment points at the bottom of the two three-dimensional images, ck is the average diameter of the bottom of the standard weld spot three-dimensional image, wherein the welding alignment point is the alignment point of the welding, so the closer it is to the welding alignment point, the greater the role of the welding, so the reciprocal of the distance from the corresponding point to the welding alignment point is used to assign weights to the corresponding points at different positions, and xixim is the height difference between the two three-dimensional images at point i, which is divided by xim to represent the difference between the two three-dimensional images at point i, and the differences of all points are superimposed to obtain the displacement and shape difference between the two weld spot images. It should be noted that the welding center point here is the point with the smallest standard deviation of the distance to each point on the bottom boundary among any point on the bottom;

[0051] S22, obtaining real-time crack length and width data on the surface of the solder joint, and importing the obtained crack length and width data on the surface of the solder joint into a solder joint strength abnormal value calculation formula to calculate the solder joint strength abnormal value, wherein the solder joint strength abnormal value calculation formula is: Wherein, L is the average value of the shortest distance between cracks, m is the number of cracks, kj is the length of the jth crack, sj is the width of the jth crack, s is the average diameter of the standard solder joint 3D image, and l is the average height of the standard solder joint 3D image;

[0052] S23, obtain the obtained weld point displacement abnormal value and weld point strength abnormal value, substitute them into the spot welding position abnormal value calculation formula to calculate the spot welding position abnormal value, wherein the spot welding position abnormal value calculation formula is: Hc=γHw+(1-γ)Hq, wherein γ is the displacement abnormality ratio coefficient. It should be noted that the welding abnormality of the weld point is analyzed here by the weld point strength and weld point displacement;

[0053] S3, obtaining data transmission information of the corresponding connection circuit of the solder joint during operation and importing it into the solder joint data abnormality analysis model to perform solder joint data abnormality analysis;

[0054] In one embodiment, obtaining data transmission information of a connection circuit corresponding to a solder joint during operation and importing it into a solder joint data anomaly analysis model to perform solder joint data anomaly analysis includes the following specific steps:

[0055] S31, obtaining current data of a signal passing through a welding point before and after the welding point during the circuit operation within a corresponding test time;

[0056] S32, importing the current data of the signal passing through the previous welding point and the current data of the signal passing through the welding point during the circuit operation within the test time into the welding data abnormal value calculation formula to calculate the welding data abnormal value, wherein the welding data abnormal value calculation formula is: Wherein, T is the test time, At is the current data of the signal after the welding point at the test time t, Atm is the current data of the signal before the welding point at the test time t, and dt is the time integral; thus, the welding quality can be analyzed by the abnormality of the passing signal within the test time;

[0057] S4, analyzing the spot welding effect of the welding spot by analyzing the abnormal analysis results of the spot welding position and the abnormal analysis results of the welding spot data;

[0058] In one embodiment, the spot welding effect analysis of the spot welding position abnormality analysis result and the spot welding data abnormality analysis result obtained by analyzing the spot welding position abnormality analysis result includes the following specific contents:

[0059] Obtain the calculated spot welding position abnormal value and welding data abnormal value and substitute them into the welding effect analysis value calculation formula to calculate the welding effect analysis value, wherein the welding effect analysis value calculation formula is: Hz = (1 + Hc) exp (Hs), wherein exp () is the power of the natural constant e;

[0060] The calculated welding effect analysis value is obtained and compared with the welding effect threshold. If the obtained welding effect analysis value is greater than the welding effect threshold, it means that the welding has failed and re-welding is required. If the obtained welding effect analysis value is less than or equal to the welding effect threshold, it means that the welding is successful.

[0061] It should be noted here that the welding effect threshold and the displacement anomaly ratio coefficient are determined in the following way: 500 sets of spot welding image data of chip solder joint positions and data transmission information of solder joints during operation are obtained, and the welding effect analysis value calculation formula is used to calculate the welding effect analysis value, and the expert judgment results on whether the welding of these chip solder joints is qualified are obtained, and the welding effect analysis value and the manual chip solder joint welding judgment results are imported into the fitting software, and the welding effect threshold and the displacement anomaly ratio coefficient that meet the maximum judgment accuracy are output.

[0062] The advantages of this embodiment over the prior art are as follows: obtaining spot welding image data of each solder joint position of the chip, constructing a three-dimensional model of the solder joint position, and obtaining data transmission information during the operation of the solder joint at the same time, obtaining the three-dimensional model data of each solder joint position of the chip and importing it into the spot welding position abnormality analysis model to perform spot welding position abnormality analysis, obtaining the data transmission information during the operation of the corresponding connection circuit of the solder joint and importing it into the solder joint data abnormality analysis model to perform solder joint data abnormality analysis, and performing spot welding effect analysis on the solder joints by analyzing the obtained spot welding position abnormality analysis results and solder joint data abnormality analysis results. This application analyzes the spot welding image data to obtain implicit features in the image that reflect the welding quality, conducts a comprehensive analysis of these implicit features to obtain welding quality analysis results, and then conducts a comprehensive evaluation and analysis of the welding effects of the solder joints by comprehensively analyzing the data transmission analysis at the welding locations, thereby improving the accuracy of the evaluation of the solder joint welding effect.

[0063] Example 2

[0064] like Figure 3 As shown, the chip DFM solder joint identification and analysis system based on artificial intelligence is implemented based on the above-mentioned chip DFM solder joint identification and analysis method based on artificial intelligence, which specifically includes a data acquisition module, a position anomaly analysis module, a solder joint data anomaly analysis module and a spot welding effect analysis module;

[0065] The data acquisition module is used to obtain the spot welding image data of each solder joint position of the chip, build a three-dimensional model of the solder joint position, and obtain the data transmission information during the operation of the solder joint;

[0066] The position anomaly analysis module is used to obtain the three-dimensional model data of the position of each solder joint of the chip and import it into the spot welding position anomaly analysis model to perform spot welding position anomaly analysis;

[0067] A solder point data anomaly analysis module, which is used to obtain data transmission information of the corresponding connection circuit of the solder point during operation and import it into the solder point data anomaly analysis model to perform solder point data anomaly analysis;

[0068] The spot welding effect analysis module is used to analyze the spot welding effect of the welding spot by analyzing the abnormal analysis results of the spot welding position and the abnormal analysis results of the welding point data;

[0069] A control module may also be included, and the control module is used to control the operation of the data acquisition module, the position abnormality analysis module, the welding point data abnormality analysis module and the spot welding effect analysis module.

[0070] Example 3

[0071] This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0072] The processor executes the above-mentioned chip DFM solder joint identification and analysis method based on artificial intelligence by calling the computer program stored in the memory.

[0073] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors and one or more memories, wherein the memory stores at least one computer program, and the computer program is loaded and executed by the processor to implement the chip DFM solder joint identification and analysis method based on artificial intelligence provided by the above method embodiment. The electronic device may also include other components for realizing the functions of the device, for example, the electronic device may also have components such as a wired or wireless network interface and an input and output interface for data input and output. This embodiment will not be described in detail here.

[0074] Example 4

[0075] This embodiment provides a computer-readable storage medium having a rewritable computer program stored thereon;

[0076] When the computer program runs on a computer device, the computer device executes the above-mentioned chip DFM solder joint identification and analysis method based on artificial intelligence.

[0077] For example, the computer readable storage medium can be a read-only memory, a random access memory, a read-only CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0078] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When a computer instruction or computer program is loaded or executed on a computer, a process or function according to an embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from a website site, a computer, a server or a data center to another website site, a computer, a server or a data center through a wired network or / and a wireless network. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or a data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0079] The terms "comprises," "comprising," or any other variations thereof are intended to cover a non-exclusive inclusion such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article, or apparatus.

[0080] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of application involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned application concept. For example, the above features are replaced with (but not limited to) technical features with similar functions applied in the present application.

Claims

1. The chip DFM solder joint identification and analysis method based on artificial intelligence is characterized by: It includes the following specific steps: S1, obtaining spot welding image data of each solder joint position of the chip, constructing a three-dimensional model of the solder joint position, and obtaining data transmission information during the operation of the solder joint; S2, obtaining the three-dimensional model data of each solder joint position of the chip and importing it into the spot welding position abnormality analysis model to perform spot welding position abnormality analysis; S3, obtaining data transmission information of the corresponding connection circuit of the solder joint during operation and importing it into the solder joint data abnormality analysis model to perform solder joint data abnormality analysis; S4. Analyze the spot welding effect of the welding spot by analyzing the abnormal analysis results of the spot welding position and the abnormal analysis results of the welding spot data.

2. The chip DFM solder joint identification and analysis method based on artificial intelligence as claimed in claim 1, characterized in that: The specific contents of obtaining the spot welding image data of each solder joint position of the chip, constructing a three-dimensional model of the solder joint position, and obtaining the data transmission information during the operation of the solder joint are: The image data of the weld position and the standard weld area data of the weld are obtained through the weld image acquisition terminal, and the height data of each pixel corresponding to the weld is obtained at the same time. The real-time three-dimensional image of the weld relative to the standard weld area is obtained through the three-dimensional construction software, and the three-dimensional image of the standard weld is obtained at the same time, and the crack data on the surface of the real-time weld is obtained at the same time; The current data of the signal passing through the welding point before and after the welding point during the circuit operation within the test time are obtained and stored in the second storage component.

3. The chip DFM solder joint identification and analysis method based on artificial intelligence as claimed in claim 1, characterized in that: The step of obtaining the three-dimensional model data of each solder joint position of the chip and importing it into the spot welding position abnormality analysis model to perform spot welding position abnormality analysis includes the following specific steps: A three-dimensional image of a real-time welding spot relative to a standard welding area is obtained, and a three-dimensional image of a standard welding spot is obtained at the same time. The welding center points at the bottom of the two three-dimensional images are obtained, and the welding center points at the bottom of the two three-dimensional images are corresponded to one point so that the two three-dimensional images partially overlap, and the height value data of each corresponding point is obtained. The height values ​​of the corresponding points are obtained and imported into the calculation formula of the welding spot displacement abnormal value to calculate the welding spot displacement abnormal value, wherein the calculation formula of the welding spot displacement abnormal value is: Wherein, n is the number of corresponding points on the standard weld 3D image, xi is the height of the ith corresponding point on the actual weld image, xim is the height of the ith corresponding point on the standard weld 3D image, li is the distance from the ith corresponding point to the welding alignment point, c is the distance between the welding alignment points at the bottom of the two 3D images, and ck is the average diameter of the bottom of the standard weld 3D image.

4. The chip DFM solder joint identification and analysis method based on artificial intelligence as claimed in claim 3, characterized in that: The step of obtaining the three-dimensional model data of the positions of each solder joint of the chip and importing it into the spot welding position abnormality analysis model to perform spot welding position abnormality analysis also includes the following specific steps: The real-time crack length and width data of the solder joint surface are obtained, and the obtained crack length and width data of the solder joint surface are imported into the solder joint strength abnormal value calculation formula to calculate the solder joint strength abnormal value, wherein the solder joint strength abnormal value calculation formula is: Wherein, L is the average value of the shortest distance between cracks, m is the number of cracks, kj is the length of the jth crack, sj is the width of the jth crack, s is the average diameter of the standard solder joint 3D image, and l is the average height of the standard solder joint 3D image; The obtained weld spot displacement abnormal value and weld spot strength abnormal value are substituted into the spot welding position abnormal value calculation formula to calculate the spot welding position abnormal value, wherein the spot welding position abnormal value calculation formula is: Hc=γHw+(1-γ)Hq, wherein γ is the displacement abnormality ratio coefficient.

5. The chip DFM solder joint identification and analysis method based on artificial intelligence as claimed in claim 4, characterized in that: The step of obtaining the data transmission information of the corresponding connection circuit of the solder joint during operation and importing it into the solder joint data abnormality analysis model to perform solder joint data abnormality analysis includes the following specific steps: Obtain current data of the signal passing through the solder joint before and after the solder joint during the circuit operation within the corresponding test time; The current data of the signal passing through the previous welding point and the current data of the signal passing through the welding point during the circuit operation during the test time are imported into the welding data abnormal value calculation formula to calculate the welding data abnormal value, wherein the welding data abnormal value calculation formula is: Wherein, T is the test time, At is the current data of the signal after passing the welding point at the test time t, Atm is the current data of the signal before passing the welding point at the test time t, and dt is the time integral.

6. The chip DFM solder joint identification and analysis method based on artificial intelligence as claimed in claim 5, characterized in that: The spot welding effect analysis of the spot welding position abnormality analysis results and the spot welding data abnormality analysis results obtained by analyzing the spot welding position abnormality analysis results includes the following specific contents: Obtain the calculated spot welding position abnormal value and welding data abnormal value and substitute them into the welding effect analysis value calculation formula to calculate the welding effect analysis value, wherein the welding effect analysis value calculation formula is: Hz = (1 + Hc) exp (Hs), wherein exp () is the power of the natural constant e; The calculated welding effect analysis value is obtained and compared with the welding effect threshold. If the obtained welding effect analysis value is greater than the welding effect threshold, it means that the welding has failed and re-welding is required. If the obtained welding effect analysis value is less than or equal to the welding effect threshold, it means that the welding is successful.

7. An artificial intelligence-based chip DFM solder joint identification and analysis system, which is implemented based on the artificial intelligence-based chip DFM solder joint identification and analysis method according to any one of claims 1 to 6, characterized in that: It specifically includes a data acquisition module, a position anomaly analysis module, a welding point data anomaly analysis module and a spot welding effect analysis module; The data acquisition module is used to acquire the spot welding image data of each solder joint position of the chip, construct a three-dimensional model of the solder joint position, and acquire the data transmission information during the operation of the solder joint; The position anomaly analysis module is used to obtain the three-dimensional model data of the position of each solder joint of the chip and import it into the spot welding position anomaly analysis model to perform spot welding position anomaly analysis; The solder point data anomaly analysis module is used to obtain data transmission information during the operation of the corresponding connection circuit of the solder point and import it into the solder point data anomaly analysis model to perform solder point data anomaly analysis; The spot welding effect analysis module is used to perform spot welding effect analysis on the welding points by analyzing the obtained spot welding position abnormality analysis results and welding point data abnormality analysis results.

8. An electronic device comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; It is characterized in that the processor executes the chip DFM solder joint identification and analysis method based on artificial intelligence as described in any one of claims 1 to 6 by calling the computer program stored in the memory.

9. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer executes the chip DFM solder joint identification and analysis method based on artificial intelligence as described in any one of claims 1 to 6.

Images