PCB panel conducting circuit defect detection method and system

Abstract

The invention provides a PCB panel conducting circuit defect detection method and system, and relates to the technical field of PCB panel defect detection.The method comprises the steps that end information of a conducting circuit is obtained through an end detection model; obtaining an end part smooth value, an end part density value and an end part width reduction value based on the end part information of the conductive circuit; based on the end part smooth value, the end part density value and the end part width reduction value, carrying out circuit break defect detection on the conductor wire preliminarily; obtaining an end distance value and a tangent included angle value based on the end information of the conductive circuit; performing open circuit defect detection on the conductive circuit again based on the end distance value and the tangent included angle value; and performing comprehensive judgment based on the preliminary detection result and the secondary detection result, and obtaining a repair path based on a comprehensive judgment result. Defects of the conductive circuit are detected in a mode of combining deep learning and machine vision, and the problem that open circuit defects of an existing conductive circuit cannot be found in time and cannot be repaired in time is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of PCB panel defect detection, and in particular to a method and system for detecting defects in conductive lines of a PCB panel. Background Art

[0002] The production and manufacturing of PCB (Printed Circuit Board) panels is complex and tedious. Various product defects are easily introduced during the manufacturing process, and the types of product defects vary.

[0003] In the actual production line quality control process, for the sake of overall product yield, it is necessary to evaluate the severity of product defects and determine the defect type to which the product defects belong. The defect types include acceptable product defects and unacceptable product defects. For unacceptable product defects, the PCB panel needs to be scrapped. For acceptable product defects, the PCB panel can be sent to the back-end process for processing. Therefore, accurate defect detection of PCB panels and accurate assessment of defect severity based on defect detection results are crucial for factory cost control.

[0004] At present, the detection of conductive line break defects in PCB panels is mainly carried out by power-on detection, which is mainly carried out in the later stage of PCB panel production. Therefore, it is impossible to detect and repair them in time. Summary of the invention

[0005] The present invention provides a method and system for detecting defects in conductive lines of a PCB panel, which solves the problem that the conductive line open circuit defects of the existing PCB panel cannot be discovered and repaired in time.

[0006] In a first aspect, an embodiment of the present invention provides a method for detecting defects in conductive lines of a PCB panel, the method comprising the following process:

[0007] Input the PCB panel image to be inspected into the pre-trained end detection model to obtain the end information of the conductive line;

[0008] Calculating the end smoothness, end density, and end width reduction based on the end information of the conductive line to obtain an end smoothness value, an end density value, and an end width reduction value;

[0009] Preliminary detection of disconnection defects of the conductive line is performed based on the end smoothing value, the end density value and the end width reduction value to obtain a preliminary detection result of the disconnection defect;

[0010] Calculating the distance between the ends and the tangent angle between the ends based on the end information of the conductive line to obtain the end distance value and the tangent angle value;

[0011] Based on the end distance value and the tangent angle value, the conductive line disconnection defect detection is performed again to obtain a secondary detection result of the disconnection defect;

[0012] A comprehensive determination of the short circuit defect of the conductive line is performed based on the preliminary detection result and the secondary detection result to obtain a comprehensive determination result of the short circuit defect, and a repair path between the ends is obtained based on the comprehensive determination result of the short circuit defect.

[0013] In the above embodiment, the present invention adopts a combination of deep learning and machine vision to detect defects in conductive circuits. First, deep learning technology is used to detect the end of the conductive circuit, and then machine vision technology is used to analyze the structural characteristics and geometric characteristics of the conductive circuit end when the circuit is broken, so as to obtain preliminary detection results and secondary detection results. Finally, the preliminary detection results and secondary detection results are comprehensively judged in combination with the actual abnormal judgment criteria, so as to timely discover the circuit break defects and provide timely repair suggestions.

[0014] As some optional implementations of the present application, the process of inputting the PCB panel image to be detected into the pre-trained end detection model to obtain the end information of the conductive line is as follows:

[0015] Input the PCB panel image to be inspected into the pre-trained end detection model to obtain the end defect frame;

[0016] The end defect frame is subjected to contour extraction processing and pixel extraction processing to obtain a contour image and a pixel image of the end and the conductive line at the end connection position.

[0017] In the above embodiment, the present invention uses deep learning technology to quickly locate end defects, and based on the end defect location, it can obtain the contour image and pixel image of the end and the conductive line at the end connection position.

[0018] As some optional implementations of the present application, before the PCB panel image to be inspected is input into the pre-trained end detection model, the PCB panel image to be inspected needs to be filtered and gray-scaled.

[0019] In the above embodiment, the present invention can filter out noise interference by filtering and grayscale processing the PCB panel image to be inspected, thereby ensuring that the end detection model can quickly and accurately obtain the end defect frame.

[0020] As some optional implementations of the present application, the process of calculating the end smoothness, end density and end width reduction based on the end information of the conductive line to obtain the end smoothness value, end density value and end width reduction value is as follows:

[0021] Calculating the end smoothness based on the coordinate point information of the end contour image to obtain an end smoothness value;

[0022] Performing end density calculation based on the pixel value of the pixel image of the end to obtain an end density value;

[0023] Based on the contour image of the end and the contour image of the conductive circuit at the end connection position, the difference between the lateral width of the end and the conductive circuit at the end connection position is calculated to obtain the reduced value of the width of the end.

[0024] In the above embodiment, the present invention combines the structural characteristics that the ends corresponding to the conductive line break defects generally have poor smoothness, low density, and a large difference in the width of the ends and the width of the adjacent conductive lines, and can accurately obtain relevant parameters for preliminary detection.

[0025] As some optional implementations of the present application, the process of preliminarily performing a conductive line open circuit defect detection based on the end smoothing value, the end density value, and the end width reduction value to obtain a preliminary detection result of the open circuit defect is as follows:

[0026] Obtain smoothing weighted values, density weighted values, and width reduction weighted values;

[0027] The reciprocal of the end smoothing value, the reciprocal of the end density value and the end width reduction value are multiplied and added with the smoothing weighted value, the density weighted value and the width reduction weighted value respectively to obtain a preliminary weighted determination value.

[0028] In the above embodiment, the present invention adopts a weighted method to perform weighted calculation on the end smoothing value, the end density value and the end width reduction value, which can weigh the influence of each structural feature on the short circuit defect detection.

[0029] As some optional implementations of the present application, the distance between the ends and the tangent angle between the ends are calculated based on the end information of the conductive line to obtain the end distance value and the tangent angle value. The process is as follows:

[0030] Calculating the distance between any two ends based on the coordinate information of the contour image of the end to obtain an end distance value between the ends;

[0031] The tangent angle between any two ends is calculated based on the contour image of the end and the coordinate information of the contour image of the conductive line at the end connection position to obtain the tangent angle value.

[0032] In the above embodiment, the present invention combines the geometric characteristics that the distance between the two ends corresponding to the conductive line short circuit defect is small and the tangent angles of the ends are very similar, so as to accurately obtain the relevant parameters of the secondary detection.

[0033] As some optional implementations of the present application, the process of performing the conductive line disconnection defect detection again based on the end distance value and the tangent angle value to obtain the secondary detection result of the disconnection defect is as follows:

[0034] Get the distance weighted value and the tangent angle weighted value;

[0035] The reciprocal of the end distance value and the reciprocal of the tangent angle value are respectively multiplied and added with the distance weighted value and the tangent angle weighted value to obtain a secondary weighted judgment value.

[0036] In the above embodiment, the present invention adopts a weighted method to perform weighted calculation on the end distance value and the tangent angle value, which can weigh the influence of various geometric features on the short circuit defect detection.

[0037] As some optional implementations of the present application, a comprehensive determination of the disconnection defect of the conductive line is performed based on the preliminary detection results and the secondary detection results to obtain a comprehensive determination result of the disconnection defect, and a process of obtaining a repair path between the ends based on the comprehensive determination result of the disconnection defect is as follows:

[0038] Obtaining a weighted decision threshold, and adding the initial weighted decision value and the secondary weighted decision value to obtain a weighted decision value;

[0039] Determine whether the weighted judgment value is greater than the weighted judgment threshold value. If so, determine that there are disconnection defects at the two ends, and obtain the coordinate information of the corresponding two ends;

[0040] A repair path between the ends is constructed based on the coordinate information of the two ends.

[0041] In the above embodiment, the present invention can timely discover the circuit breaker defect and provide timely repair suggestions by making a comprehensive judgment on the preliminary weighted judgment value and the secondary weighted judgment value.

[0042] And the repair path acquisition can timely detect circuit breaker defects and provide timely repair suggestions

[0043] In a second aspect, the present invention provides a PCB panel conductive line defect detection system, the system comprising:

[0044] An end information acquisition unit, the end information acquisition unit is used to input the PCB panel image to be detected into a pre-trained end detection model to obtain the end information of the conductive line;

[0045] A structural information calculation unit, wherein the structural information calculation unit calculates end smoothness, end density, and end width reduction based on the end information of the conductive line to obtain an end smoothness value, an end density value, and an end width reduction value;

[0046] A preliminary defect detection unit, wherein the preliminary defect detection unit performs preliminary detection of a conductive line open circuit defect based on an end smoothing value, an end density value, and an end width reduction value to obtain a preliminary detection result of the open circuit defect;

[0047] A geometric information calculation unit, wherein the geometric information calculation unit calculates the distance between the ends and the tangent angle between the ends based on the end information of the conductive line to obtain an end distance value and a tangent angle value;

[0048] A defect secondary detection unit, wherein the defect secondary detection unit performs a conductive line disconnection defect detection again based on the end distance value and the tangent angle value to obtain a secondary detection result of the disconnection defect;

[0049] A defect comprehensive detection unit performs a comprehensive determination of the short circuit defect of the conductive line based on the preliminary detection result and the secondary detection result to obtain a comprehensive determination result of the short circuit defect, and obtains a repair path between the ends based on the comprehensive determination result of the short circuit defect.

[0050] In a third aspect, the present invention provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method for detecting defects in conductive circuits of a PCB panel when executing the computer program.

[0051] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for detecting defects in conductive circuits of a PCB panel is implemented.

[0052] In a fifth aspect, the present invention provides a computer program product, including a computer program, which implements the method for detecting defects in conductive lines of a PCB panel when executed by a processor.

[0053] The beneficial effects of the present invention are as follows: the present invention adopts a combination of deep learning and machine vision to detect conductive line defects. First, deep learning technology is used to detect the end of the conductive line, and then machine vision technology is used to analyze the structural characteristics and geometric characteristics of the conductive line end when the circuit is broken, so as to obtain preliminary detection results and secondary detection results. Finally, the preliminary detection results and secondary detection results are comprehensively judged in combination with actual abnormal judgment standards, so as to timely discover the circuit breaking defects and provide timely repair suggestions. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0055] Figure 1 is a schematic diagram of the computer device structure of the hardware operating environment described in the embodiment of the present invention;

[0056] Figure 2 is a flow chart of a method for detecting defects in conductive circuits of a PCB panel according to an embodiment of the present invention;

[0057] Figure 3 It is a structural block diagram of a PCB panel conductive circuit defect detection system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0058] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0059] In order to solve the problem that the conductive circuit break defects of the existing PCB panel cannot be discovered and repaired in time, the present application provides a PCB panel conductive circuit defect detection method and system. Before introducing the specific technical solution of the present application, the hardware operating environment involved in the embodiment of the present application is first introduced.

[0060] See also Figure 1 , Figure 1 A schematic diagram of the computer device structure of the hardware operating environment involved in the embodiment of the present application.

[0061] like Figure 1 As shown, the computer device may include: a processor, such as a central processing unit (CPU), a communication bus, a user interface, a network interface, and a memory. Among them, the communication bus is used to realize the connection and communication between these components. The user interface may include a display screen (Display), an input unit such as a keyboard (Keyboard), and optionally, the user interface may also include a standard wired interface and a wireless interface. The network interface may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity interface). The memory may be a high-speed random access memory (Random Access Memory, RAM) memory, or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory may optionally be a storage device independent of the aforementioned processor.

[0062] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the computer device, and may include more or less components than shown in the figure, or combine some components, or arrange the components differently.

[0063] like Figure 1 As shown, the memory as a storage medium may include an operating system, a data storage module, a network communication module, a user interface module and an electronic program module.

[0064] exist Figure 1 In the computer device shown, the network interface is mainly used for data communication with the network server; the user interface is mainly used for data interaction with the user; the processor and memory in the computer device of the present application can be set in the computer device, and the computer device calls the computer program product stored in the electronic program module through the processor, and executes the PCB panel conductive line defect detection method provided in the embodiment of the present application.

[0065] Based on the hardware environment of the aforementioned embodiment, the embodiment of the present application provides a method for detecting defects in conductive lines of a PCB panel. Figure 2 , Figure 2 The flowchart of the method for detecting defects in conductive lines of a PCB panel is as follows:

[0066] (1) Inputting the PCB panel image to be detected into the pre-trained end detection model to obtain the end information of the conductive line. Specifically, before inputting the PCB panel image to be detected into the pre-trained end detection model, the PCB panel image to be detected needs to be filtered and gray-scaled.

[0067] In an embodiment of the present invention, the process of inputting the PCB panel image to be detected into the pre-trained end detection model to obtain the end information of the conductive line is as follows:

[0068] (1.1) Input the PCB panel image to be inspected into the pre-trained end detection model to obtain an end defect frame; wherein the end detection model is a deep neural network model, including but not limited to a convolution layer, a pooling layer, and a fully connected layer. Specifically, the end defect frame is a rectangular positioning frame containing end image information and position information, which can realize the preliminary positioning of the end defect.

[0069] (1.2) Performing contour extraction and pixel extraction processing on the end defect frame to obtain a contour image and a pixel image of the end and the conductive line at the end connection position; wherein the contour extraction processing can use an edge detection algorithm to collect the image contour; and the pixel extraction processing can use a traversal image algorithm to collect the image pixels.

[0070] Specifically, before using the end detection model to perform contour extraction and pixel extraction processing on the PCB panel image to be inspected, the end detection model needs to be trained to obtain a pre-trained end detection model; wherein, the model training requires that the end-annotated PCB panel image of the history be subjected to end labeling processing, and then the end-annotated PCB panel image be input into the end detection model for feature learning, so that the end detection model has the ability to locate the end face.

[0071] (2) Based on the end information of the conductive line, the end smoothness, end density and end width reduction are calculated to obtain the end smoothness value, end density value and end width reduction value.

[0072] In an embodiment of the present invention, during the PCB panel production process, the smoothness of the ends corresponding to general conductive circuit open defects is generally poor, the density is small, and the end width is greatly different from the width distance of the adjacent conductive circuit. Therefore, preliminary detection of open defects can be performed based on the end smoothness, end density and end width reduction.

[0073] Specifically, the process of calculating the end smoothness, end density and end width reduction based on the end information of the conductive line is as follows:

[0074] (2.1) The end smoothness is calculated based on the coordinate point information of the contour image of the end to obtain the end smoothness value.

[0075] (2.2) The end density is calculated based on the pixel value of the pixel image of the end to obtain the end density value.

[0076] (2.3) Based on the contour image of the end and the contour image of the conductive line at the end connection position, the difference between the lateral width of the end and the conductive line at the end connection position is calculated to obtain the reduced value of the end width.

[0077] (3) Based on the end smoothing value, the end density value and the end width reduction value, preliminary detection of the conductive line open circuit defect is performed to obtain a preliminary detection result of the open circuit defect.

[0078] In an embodiment of the present invention, the process of initially performing conductive line disconnection defect detection based on the end smoothing value, the end density value, and the end width reduction value is as follows:

[0079] (3.1) Obtain a smoothing weighted value, a density weighted value, and a width reduction weighted value, wherein the smoothing weighted value, the density weighted value, and the width reduction weighted value can be set according to actual conditions, and the embodiment of the present invention does not limit this.

[0080] (3.2) The inverse of the end smoothing value, the inverse of the end density value and the end width reduction value are multiplied and added with the smoothing weighted value, the density weighted value and the width reduction weighted value respectively to obtain a preliminary weighted judgment value; this preliminary weighted judgment value can be combined with the subsequent secondary weighted judgment value.

[0081] (4) Based on the end information of the conductive line, the distance between the ends and the tangent angle between the ends are calculated to obtain the end distance value and the tangent angle value.

[0082] In an embodiment of the present invention, during the PCB panel production process, the distance between the two ends corresponding to a general conductive circuit open defect is relatively small, and the tangent angles at the ends are also very similar. Therefore, secondary detection of the open defect can be performed based on the end information of the conductive circuit based on the distance between the ends and the tangent angle between the ends.

[0083] In an embodiment of the present invention, the process of calculating the distance between the ends and the tangent angle between the ends based on the end information of the conductive line is as follows:

[0084] (4.1) The distance between any two ends is calculated based on the coordinate information of the contour image of the end to obtain the end distance value between the ends.

[0085] (4.2) The tangent angle between any two ends is calculated based on the contour image of the end and the coordinate information of the contour image of the conductive line at the end connection position to obtain the tangent angle value.

[0086] (5) Based on the end distance value and the tangent angle value, the conductive line open circuit defect detection is performed again to obtain a secondary detection result of the open circuit defect.

[0087] In an embodiment of the present invention, the process of performing the conductive line disconnection defect detection again based on the end distance value and the tangent angle value is as follows:

[0088] (5.1) Obtaining a distance weighted value and a tangent angle weighted value, wherein the distance weighted value and the tangent angle weighted value can be set according to actual conditions, and the embodiment of the present invention does not limit this.

[0089] (5.2) The reciprocal of the end distance value and the reciprocal of the tangent angle value are multiplied and added with the distance weighted value and the tangent angle weighted value respectively to obtain a secondary weighted judgment value; this secondary weighted judgment value can be combined with the aforementioned preliminary weighted judgment value.

[0090] (6) Based on the preliminary detection results and the secondary detection results, a comprehensive determination of the short circuit defect of the conductive line is performed to obtain a comprehensive determination result of the short circuit defect, and a repair path between the ends is obtained based on the comprehensive determination result of the short circuit defect.

[0091] In an embodiment of the present invention, a comprehensive determination of the disconnection defect of the conductive line is performed based on the preliminary detection result and the secondary detection result to obtain a comprehensive determination result of the disconnection defect, and a process of obtaining a repair path between the ends based on the comprehensive determination result of the disconnection defect is as follows:

[0092] (6.1) Obtain a weighted decision threshold, and add the preliminary weighted decision value and the secondary weighted decision value to obtain a weighted decision value; wherein the weighted decision threshold can be set according to actual conditions, and the embodiment of the present invention does not limit this.

[0093] (6.2) Determine whether the weighted judgment value is greater than the weighted judgment threshold. If so, determine that there are disconnection defects at the two ends, and obtain the coordinate information corresponding to the two ends.

[0094] (6.3) A repair path between the two ends is constructed based on the coordinate information of the two ends. That is, the straight path from one end to the other end is the repair path that can be used as a reference for preliminary positioning.

[0095] In summary, the present invention adopts a combination of deep learning and machine vision to detect defects in conductive circuits. First, deep learning technology is used to detect the end of the conductive circuit, and then machine vision technology is used to analyze the structural characteristics and geometric characteristics of the conductive circuit end when the circuit is broken, so as to obtain preliminary detection results and secondary detection results. Finally, the preliminary detection results and secondary detection results are comprehensively judged in combination with the actual abnormal judgment criteria, so as to timely discover the circuit break defects and provide timely repair suggestions.

[0096] In addition, in one embodiment, based on the same inventive concept as the above embodiment, the embodiment of the present invention provides a PCB panel conductive line defect detection system, and the system corresponds to the method of embodiment 1 one by one, please refer to Figure 3 , Figure 3 The structure block diagram of the PCB panel conductive line defect detection system is as follows:

[0097] An end information acquisition unit, the end information acquisition unit is used to input the PCB panel image to be detected into a pre-trained end detection model to obtain the end information of the conductive line;

[0098] A structural information calculation unit, wherein the structural information calculation unit calculates end smoothness, end density, and end width reduction based on the end information of the conductive line to obtain an end smoothness value, an end density value, and an end width reduction value;

[0099] A preliminary defect detection unit, wherein the preliminary defect detection unit performs preliminary detection of a conductive line open circuit defect based on an end smoothing value, an end density value, and an end width reduction value to obtain a preliminary detection result of the open circuit defect;

[0100] A geometric information calculation unit, wherein the geometric information calculation unit calculates the distance between the ends and the tangent angle between the ends based on the end information of the conductive line to obtain an end distance value and a tangent angle value;

[0101] A defect secondary detection unit, wherein the defect secondary detection unit performs a conductive line disconnection defect detection again based on the end distance value and the tangent angle value to obtain a secondary detection result of the disconnection defect;

[0102] A defect comprehensive detection unit performs a comprehensive determination of the short circuit defect of the conductive line based on the preliminary detection result and the secondary detection result to obtain a comprehensive determination result of the short circuit defect, and obtains a repair path between the ends based on the comprehensive determination result of the short circuit defect.

[0103] It should be noted that each unit in the PCB panel conductive circuit defect detection system in this embodiment corresponds one-to-one to each step in the PCB panel conductive circuit defect detection method in the aforementioned embodiment. Therefore, the specific implementation method and technical effects achieved by this embodiment can refer to the implementation method of the aforementioned PCB panel conductive circuit defect detection method, which will not be repeated here.

[0104] In addition, in one embodiment, the present application also provides a computer device, which includes a processor, a memory, and a computer program stored in the memory, and the computer program implements the method in the aforementioned embodiment when executed by the processor.

[0105] In addition, in one embodiment, the present application further provides a computer storage medium, on which a computer program is stored, and the computer program implements the method in the aforementioned embodiment when executed by a processor.

[0106] In some embodiments, the computer readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or various devices including one or any combination of the above memories. The computer may be various computing devices including intelligent terminals and servers.

[0107] In some embodiments, executable instructions may be in the form of a program, software, software module, script or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine or other unit suitable for use in a computing environment.

[0108] As an example, executable instructions may, but need not, correspond to a file in a file system, may be stored as part of a file that stores other programs or data, such as in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files storing one or more modules, subroutines, or code portions).

[0109] By way of example, executable instructions may be deployed to be executed on one computing device, or on multiple computing devices located at one site, or on multiple computing devices distributed across multiple sites and interconnected by a communication network.

[0110] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0111] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0112] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a multimedia terminal device (which can be a mobile phone, a computer, a television receiver, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0113] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for detecting defects in conductive lines of a PCB panel, characterized in that: The method The following processes are included: Input the PCB panel image to be inspected into the pre-trained end detection model to obtain the end information of the conductive line; Calculating the end smoothness, end density, and end width reduction based on the end information of the conductive line to obtain an end smoothness value, an end density value, and an end width reduction value; Preliminary detection of disconnection defects of the conductive line is performed based on the end smoothing value, the end density value and the end width reduction value to obtain a preliminary detection result of the disconnection defect; Calculating the distance between the ends and the tangent angle between the ends based on the end information of the conductive line to obtain the end distance value and the tangent angle value; Based on the end distance value and the tangent angle value, the conductive line disconnection defect detection is performed again to obtain a secondary detection result of the disconnection defect; A comprehensive determination of the short circuit defect of the conductive line is performed based on the preliminary detection result and the secondary detection result to obtain a comprehensive determination result of the short circuit defect, and a repair path between the ends is obtained based on the comprehensive determination result of the short circuit defect.

2. A PCB panel conductive line defect detection method according to claim 1, characterized in that: The process of inputting the PCB panel image to be inspected into the pre-trained end detection model to obtain the end information of the conductive line is as follows: Input the PCB panel image to be inspected into the pre-trained end detection model to obtain the end defect frame; The contour extraction process and the pixel extraction process of the end image are performed based on the end defect frame to obtain the contour image and the pixel image of the end and the conductive line at the end connection position.

3. A PCB panel conductive line defect detection method according to claim 1, characterized in that: Before inputting the PCB panel image to be inspected into the pre-trained end detection model, the PCB panel image to be inspected needs to be filtered and gray-scaled.

4. A PCB panel conductive line defect detection method according to claim 2, characterized in that: The process of calculating the end smoothness, end density and end width reduction based on the end information of the conductive line to obtain the end smoothness value, end density value and end width reduction value is as follows: Calculating the end smoothness based on the coordinate point information of the end contour image to obtain an end smoothness value; Performing end density calculation based on the pixel value of the pixel image of the end to obtain an end density value; Based on the contour image of the end and the contour image of the conductive circuit at the end connection position, the difference between the lateral width of the end and the conductive circuit at the end connection position is calculated to obtain the reduced value of the width of the end.

5. A PCB panel conductive line defect detection method according to claim 1, characterized in that: The process of preliminarily performing the detection of the conductive line disconnection defect based on the end smoothing value, the end density value and the end width reduction value to obtain the preliminary detection result of the disconnection defect is as follows: Obtain smoothing weighted values, density weighted values, and width reduction weighted values; The reciprocal of the end smoothing value, the reciprocal of the end density value and the end width reduction value are multiplied and added with the smoothing weighted value, the density weighted value and the width reduction weighted value respectively to obtain a preliminary weighted determination value.

6. A method for detecting defects in conductive lines of a PCB panel according to claim 2, characterized in that: The process of calculating the distance between the ends and the tangent angle between the ends based on the end information of the conductive line to obtain the end distance value and the tangent angle value is as follows: Calculating the distance between any two ends based on the coordinate information of the contour image of the end to obtain an end distance value between the ends; The tangent angle between any two ends is calculated based on the contour image of the end and the coordinate information of the contour image of the conductive line at the end connection position to obtain the tangent angle value.

7. A PCB panel conductive line defect detection method according to claim 1, characterized in that: The process of performing the conductive line disconnection defect detection again based on the end distance value and the tangent angle value to obtain the secondary detection result of the disconnection defect is as follows: Get the distance weighted value and the tangent angle weighted value; The reciprocal of the end distance value and the reciprocal of the tangent angle value are respectively multiplied and added with the distance weighted value and the tangent angle weighted value to obtain a secondary weighted judgment value.

8. A method for detecting defects in conductive lines of a PCB panel according to claim 1, characterized in that: Based on the preliminary detection results and the secondary detection results, a comprehensive determination of the disconnection defect of the conductive line is performed to obtain a comprehensive determination result of the disconnection defect, and the process of obtaining a repair path between the ends based on the comprehensive determination result of the disconnection defect is as follows: Obtaining a weighted decision threshold, and adding the initial weighted decision value and the secondary weighted decision value to obtain a weighted decision value; Determine whether the weighted judgment value is greater than the weighted judgment threshold value. If so, determine that there are disconnection defects at the two ends, and obtain the coordinate information of the corresponding two ends; A repair path between the ends is constructed based on the coordinate information of the two ends.

9. A PCB panel conductive line defect detection system, characterized in that: The system comprises: An end information acquisition unit, the end information acquisition unit is used to input the PCB panel image to be detected into a pre-trained end detection model to obtain the end information of the conductive line; A structural information calculation unit, wherein the structural information calculation unit calculates end smoothness, end density, and end width reduction based on the end information of the conductive line to obtain an end smoothness value, an end density value, and an end width reduction value; A preliminary defect detection unit, wherein the preliminary defect detection unit performs preliminary detection of a conductive line open circuit defect based on an end smoothing value, an end density value, and an end width reduction value to obtain a preliminary detection result of the open circuit defect; A geometric information calculation unit, wherein the geometric information calculation unit calculates the distance between the ends and the tangent angle between the ends based on the end information of the conductive line to obtain an end distance value and a tangent angle value; A defect secondary detection unit, wherein the defect secondary detection unit performs a conductive line disconnection defect detection again based on the end distance value and the tangent angle value to obtain a secondary detection result of the disconnection defect; A defect comprehensive detection unit performs a comprehensive determination of the short circuit defect of the conductive line based on the preliminary detection result and the secondary detection result to obtain a comprehensive determination result of the short circuit defect, and obtains a repair path between the ends based on the comprehensive determination result of the short circuit defect.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for detecting defects in conductive lines of a PCB panel as described in any one of claims 1 to 8 is implemented.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for detecting defects in conductive lines of a PCB panel as described in any one of claims 1 to 8 is implemented.

12. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, a method for detecting defects in conductive lines of a PCB panel as described in any one of claims 1 to 8 is implemented.

Images