PCB defect automatic detection method based on machine vision

Abstract

The invention is suitable for the technical field of PCB defect detection, and particularly relates to a PCB defect automatic detection method based on machine vision, and the method comprises the steps: obtaining control parameters and plate information, and carrying out the analysis according to the control parameters and the plate information, and obtaining the interval time; the control device controls the purging device to perform first operation on the PCB based on the control parameters; in response to the first operation, the image acquisition device acquires a first image based on the interval time; according to the first image and the board information, whether short circuit and open circuit conditions exist in the PCB is judged; if the short circuit and the open circuit exist in the PCB, the control device controls the blowing device to carry out second operation, and the image acquisition device acquires a second image after the interval time; and performing analysis according to the first image, the second image and the interval time to obtain a defect detection result. According to the PCB defect automatic detection method based on machine vision provided by the invention, the defect detection efficiency of the PCB can be improved, and the yield can be improved.

Description

Technical Field

[0001] The present application belongs to the technical field of PCB defect detection, and in particular relates to a method for automatic PCB defect detection based on machine vision. Background Art Machine vision-based automated PCB defect detection uses image processing and pattern recognition techniques to detect defects such as open circuits, short circuits, trace offsets, and missing pads on the PCB surface. This technology is widely used in the PCB production process and enables rapid screening of visible surface defects.

[0002] In related technologies, the trend toward greater sophistication and miniaturization of electronic products has significantly increased the circuit density and integration of PCBs. However, conventional industrial cameras are limited by their resolution (10-20μm / pixel), making it difficult to detect invisible defects smaller than 50μm. Furthermore, existing machine vision inspection technology primarily relies on visual features of the PCB surface (such as color, texture, and geometry) to identify defects. Its detection principle is essentially two-dimensional image analysis of visible surface defects. For defects hidden within the PCB board (such as interlayer conductive residue that has not penetrated the surface), microcracks within the conductor (circuit damage that is not completely broken and covered by the surface coating), etching residue or over-etching of inner layer circuits (which does not affect the integrity of the surface copper coating), etc., since these defects are not directly reflected on the PCB board surface and do not cause obvious changes in surface visual characteristics (such as color value and morphology), after the surface appearance defects of the PCB board are initially screened by machine vision, it is necessary to directly verify the electrical performance of the PCB board by applying current or voltage to the PCB board. However, during the initial screening process, due to hidden defects within the PCB board substrate, between multi-layer circuits, or under the conductor coating, the electrical performance of the PCB board may be abnormal when applying current or voltage to the PCB board for electrical performance testing due to hidden small defects such as short circuits. This may cause damage to the PCB board or electronic components, ultimately leading to reduced detection efficiency of PCB board defects and increased product scrap rate. Summary of the Invention

[0003] The embodiment of the present application provides a method for automatic PCB defect detection based on machine vision, which can improve the problems of reduced detection efficiency and increased product scrap rate in PCB board defect detection.

[0004] In a first aspect, an embodiment of the present application provides a method for automatic detection of PCB defects based on machine vision, comprising: Acquiring control parameters and plate information, and analyzing the control parameters and the plate information to obtain an interval time; wherein the control parameters are used to reflect the wind speed of the purge device, the plate information is used to reflect the process parameters of the PCB board, and the interval time is used to reflect the time it takes for the ion wind blown by the purge device to completely cover the PCB board; The control device controls the purge device to perform a first operation on the PCB based on the control parameter; wherein the first operation is used to reflect that the purge device uses an ion wind with tracer particles to purge the PCB in a direction parallel to the surface of the PCB; In response to the first operation, the image acquisition device acquires a first image based on the interval time; wherein the first image is used to reflect the color distribution of the tracer particles on the surface of the PCB board; Determine whether the PCB board has a short circuit according to the first image and the board information; If a short circuit exists on the PCB, the control device controls the purging device to perform a second operation, and the image acquisition device acquires a second image after the interval time; wherein the second operation is used to instruct the purging device to stop purging the PCB, and the second image is used to reflect the color distribution of the tracer particles on the surface of the PCB; An analysis is performed based on the first image, the second image, and the interval time to obtain a defect detection result; wherein the defect detection result is used to reflect the short circuit and open circuit conditions of the PCB board.

[0005] The above technical solutions in the embodiments of the present application have at least the following technical effects: The machine vision-based automatic PCB defect detection method provided in an embodiment of the present application first obtains a control parameter for reflecting the wind speed of a purge device and plate information for reflecting the process parameters of the PCB board. Then, a control device controls the purge device based on the control parameter to perform a first operation on the PCB board, reflecting that the purge device uses ion wind with tracer particles to purge the PCB board in a direction parallel to the surface of the PCB board. In response to the first operation, an image acquisition device acquires a first image based on an interval time, reflecting the color distribution of the tracer particles on the surface of the PCB board. Then, based on the first image and the plate information, it is determined whether the PCB board has a short circuit or a short circuit. If the PCB board has a short circuit or a short circuit, the control device controls the purge device to perform a second operation for instructing the PCB purge device to stop purge the PCB board. The image acquisition device acquires the color distribution of the PCB tracer particles on the surface of the PCB board after an interval time. Finally, an analysis is performed based on the first image, the second image, and the interval time to obtain a defect detection result reflecting the short circuit or the short circuit of the PCB board.

[0006] This method can effectively sweep tracer particles onto the PCB surface in the form of ionized wind using a purge device. By obtaining the color distribution of the tracer particles on the PCB surface under different detection conditions, the method can exploit hidden defects within the PCB to create different color distributions of the tracer particles on the PCB surface. Furthermore, by creating differential adsorption of the tracer particles at the defects on the PCB surface, the color distributions of the first and second images at the defect locations differ. This method eliminates the need to apply current or voltage to the PCB, thereby improving the safety of PCB inspection conditions. This method can enhance the efficiency of PCB defect detection and improve the yield rate.

[0007] In a possible implementation of the first aspect, analyzing the control parameter and the plate information to obtain the interval time includes: Obtaining a passing length from the plate information; wherein the passing length is used to reflect the distance swept by the ion wind when passing through the surface of the PCB board; The control parameter and the passing length are processed to obtain the interval time.

[0008] In a possible implementation of the first aspect, determining whether the PCB has a short circuit or open circuit according to the first image and the plate information includes: Analyze the plate information to obtain an etched area and a non-etched area; wherein the etched area is used to reflect the area of the PCB board where the copper foil is dissolved and removed by the etching liquid, and the non-etched area is used to reflect the area of the PCB board where the copper foil is not dissolved and removed by the etching liquid; A determination result is obtained by analyzing the etching area, the non-etching area, and the first image.

[0009] In a possible implementation of the first aspect, the analyzing the etched area, the non-etched area, and the first image to obtain a determination result includes: Matching the etched area with the first image to obtain a first color value; wherein the first color value is used to reflect the color value of the etched area; According to the matching of the non-etched area with the first image, a plurality of second color values are obtained; wherein the second color values are used to reflect the color value of the non-etched area; A determination result is determined based on a comparison result of the first color value and a plurality of the second color values.

[0010] In a possible implementation of the first aspect, determining a determination result based on a comparison result of the first color value and the plurality of second color values includes: When the first color value is equal to a plurality of the second color values, it is determined that there is no short circuit on the PCB board; When the first color value is not equal to the second color values, it is determined that a short circuit exists on the PCB board.

[0011] In a possible implementation of the first aspect, the analyzing the first image, the second image, and the interval time to obtain a defect detection result includes: Analyzing the first image and the second image to obtain a first change condition and a second change condition; wherein the first change condition is used to reflect the difference between the color values of the first image and the second image at the defect in the non-etched area, and the second change condition is used to reflect the difference between the color values of the first image and the second image at the non-defect in the non-etched area; An analysis is performed based on the first change condition, the second change condition, and the interval time to obtain a defect detection result.

[0012] In a possible implementation of the first aspect, analyzing the first image and the second image to obtain the first change status and the second change status includes: Determine the second color value that is unequal to the first color value among the plurality of second color values in the first image and is located at a position on the PCB as a difference point, and determine the second color value that is equal to the first color value among the plurality of second color values in the first image and is located at a position on the PCB as a non-difference point; Analyze the first color value, the difference point, and the second image to obtain a first change condition; A second change condition is obtained by analyzing the non-difference point, the first image, and the second image.

[0013] In a possible implementation of the first aspect, analyzing the first color value, the difference point, and the second image to obtain the first change status includes: Based on the difference point, obtaining a third color value from the second image; wherein the third color value is used to reflect the color value of the difference point in the second image; A first change condition is obtained by processing the first color value and the third color value.

[0014] In a possible implementation of the first aspect, analyzing the indifference point, the first image, and the second image to obtain the second change condition includes: marking the second color value at the non-difference point in the first image as a fourth color value; wherein the fourth color value is used to reflect the color value at the non-difference point among the plurality of second color values in the first image; Based on the non-difference point, obtaining a fifth color value from the second image; wherein the fifth color value is used to reflect the color value of the non-difference point in the second image; The second change condition is obtained by processing according to the fourth color value and the fifth color value.

[0015] In a possible implementation of the first aspect, the analyzing the first change condition, the second change condition, and the interval time to obtain a defect detection result includes: Obtaining a calibration curve, and matching the calibration curve with the first change condition and the second change condition, respectively, to obtain a first potential change and a second potential change; wherein the calibration curve is used to reflect a corresponding relationship curve between the color value of the tracer particle and the potential, the first potential change is used to reflect the potential change value corresponding to the first change condition and the calibration curve, and the second potential change is used to reflect the potential change value corresponding to the second change condition and the calibration curve; Processing the first potential change and the interval time to obtain a first time constant; wherein the first time constant is used to quantify the decay rate of the nuclear charge at the defect of the PCB board under ion wind blowing; Processing the second potential change and the interval time to obtain a second time constant; wherein the second time constant is used to quantify the decay rate of the nuclear charge at a non-defective portion of the PCB board that is not under ion wind blowing; Comparing the first time constant with the second time constant to obtain a comparison status; wherein the comparison status is used to reflect the difference between the first time constant and the second time constant; If the comparison condition is less than 0, the defect detection result is a short circuit defect, and if the comparison condition is greater than 0, the defect detection result is an open circuit defect.

[0016] In a second aspect, an embodiment of the present application provides a PCB defect automatic detection system based on machine vision, comprising: an acquisition and analysis module, configured to acquire control parameters and plate information, and perform analysis based on the control parameters and the plate information to obtain an interval time; wherein the control parameters reflect the wind speed of the purge device, the plate information reflects the process parameters of the PCB, and the interval time reflects the time it takes for the ion wind blown by the purge device to completely cover the PCB; a first control module configured to control the purge device to perform a first operation on the PCB based on the control parameter; wherein the first operation is configured to reflect that the purge device purges the PCB using an ion wind with tracer particles in a direction parallel to the surface of the PCB; an acquisition module, configured to, in response to the first operation, acquire, by an image acquisition device, a first image based on the interval; wherein the first image is used to reflect the color distribution of the tracer particles on the surface of the PCB; A judgment module, configured to judge whether the PCB board has a short circuit or open circuit according to the first image and the board information; a second control module, configured to, if a short circuit exists on the PCB board, cause the control device to control the purging device to perform a second operation, and for the image acquisition device to acquire a second image after the interval; wherein the second operation is used to instruct the purging device to stop purging the PCB board, and the second image is used to reflect the color distribution of the tracer particles on the surface of the PCB board; An analysis module is used to analyze the first image, the second image and the interval time to obtain a defect detection result; wherein the defect detection result is used to reflect the short circuit and open circuit conditions of the PCB board.

[0017] In a third aspect, embodiments of the present application provide a machine vision-based automatic PCB defect detection device, comprising a purge device, an image acquisition device, a placement table, and a control device. The purge device and the image acquisition device are electrically connected to the control device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When executed by the processor, the computer program implements the method described in any one of the first aspects above.

[0018] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of the first aspects above is implemented.

[0019] In a fifth aspect, an embodiment of the present application provides a computer program. When the computer program is run on a machine vision-based PCB defect automatic detection device, the machine vision-based PCB defect automatic detection device enables the machine vision-based PCB defect automatic detection method described in any one of the machine vision-based PCB defect automatic detection methods described in the first aspect above.

[0020] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0022] Figure 1 This is a flow chart of a method for automatic PCB defect detection based on machine vision provided in one embodiment of the present application; Figure 2 This is a schematic diagram of the implementation process of the machine vision-based PCB defect automatic detection method provided in one embodiment of the present application; Figure 3 1 is a schematic structural diagram of a machine vision-based PCB defect automatic detection system provided in one embodiment of the present application; Figure 4 This is a structural diagram of a control device for a machine vision-based PCB defect automatic detection device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0023] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0024] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0025] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0026] As used in this specification and the appended claims, the term "if" can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0027] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0028] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0029] With the increasing sophistication and miniaturization of electronic products, the circuit density and integration of PCBs have increased significantly. However, conventional industrial cameras are limited by their resolution (10-20μm / pixel), making it difficult to detect invisible defects smaller than 50μm. Furthermore, existing machine vision inspection technology primarily relies on visual features of the PCB surface (such as color, texture, and geometry) to identify defects. Its detection principle is essentially two-dimensional image analysis of visible surface defects. For defects hidden within the PCB board (such as interlayer conductive residues that have not penetrated the surface), micro-cracks within the conductor (circuit damage that is not completely broken and covered by the surface coating), etching residue or over-etching of inner-layer circuits (without affecting the integrity of the surface copper coating), etc., since these defects are not directly reflected on the PCB board surface and do not cause obvious changes in surface visual characteristics (such as color value and morphology), after the surface appearance defects of the PCB board are initially screened by machine vision, it is necessary to directly verify and test the electrical performance of the PCB board by applying current or voltage to the PCB board. However, during the initial screening process, hidden defects may exist within the PCB board substrate, between multi-layer circuits, or under the conductor coating. When applying current or voltage to the PCB board for electrical performance testing, electrical performance abnormalities may be caused by hidden small defects such as short circuits. This may cause damage to the PCB board or electronic components, ultimately leading to reduced detection efficiency of PCB board defects and increased product scrap rates.

[0030] To address the aforementioned issues, embodiments of the present application provide a machine vision-based automatic PCB defect detection method. The method first obtains a control parameter reflecting the wind speed of a purge device and plate information reflecting process parameters of the PCB board. A control device, based on the control parameter, controls the purge device to perform a first operation on the PCB board, reflecting the purge device's use of ionized air with tracer particles in a direction parallel to the PCB board surface. In response to the first operation, an image acquisition device acquires a first image reflecting the color distribution of the tracer particles on the PCB board surface based on an interval. The PCB board then determines whether a short circuit or open circuit exists based on the first image and the plate information. If a short circuit or open circuit exists on the PCB board, the control device controls the purge device to perform a second operation instructing the PCB purge device to stop purge the PCB board. An image acquisition device acquires the color distribution of the PCB tracer particles on the PCB board surface after an interval. Finally, an analysis is performed based on the first and second images and the interval to obtain a defect detection result reflecting the short circuit or open circuit on the PCB board.

[0031] The machine vision-based automatic PCB defect detection method provided in the embodiment of the present application can be applied to a machine vision-based automatic PCB defect detection device. In this case, the machine vision-based automatic PCB defect detection device is the executor of the machine vision-based automatic PCB defect detection method provided in the embodiment of the present application. The embodiment of the present application does not impose any restrictions on the specific type of the machine vision-based automatic PCB defect detection device.

[0032] The machine vision-based automatic PCB defect detection equipment includes a purge device, an image acquisition device, a placement table, and a control device. The purge device and the image acquisition device are electrically connected to the control device. The purge device is used to blow tracer particles toward the PCB board in the form of ion wind. The purge device can be a micro-purge gun, a blower, or an air gun. The image acquisition device is used to capture a surface image of the PCB board from a top-down perspective. The image acquisition device is positioned directly above the placement table. The image acquisition device can be an optical imaging camera or a microscope camera. The placement table provides a placement area for the PCB board. The placement table can be an assembly line transfer platform or an electric translation stage. The control device is used to monitor and control the PCB defect detection process. For example, the control device can be a single-chip microcomputer, a microcontroller, an application-specific integrated circuit, etc.

[0033] In order to better understand the automatic PCB defect detection method based on machine vision provided in the embodiment of the present application, the specific implementation process of the automatic PCB defect detection method based on machine vision provided in the embodiment of the present application is exemplarily introduced below.

[0034] Figure 1 and Figure 2A schematic flow chart of the automatic PCB defect detection method based on machine vision provided by an embodiment of the present application is shown. Figure 1 and Figure 2 , the automatic detection method of PCB defects based on machine vision includes: S100, obtain control parameters and plate information, and analyze them based on the control parameters and plate information to obtain the interval time; wherein the control parameters are used to reflect the wind speed of the purge device, the plate information is used to reflect the process parameters of the PCB board, and the interval time is used to reflect the time it takes for the ion wind blown by the purge device to completely cover the PCB board.

[0035] As you can understand, a PCB is a circuit board made by chemically etching the non-etch-resistant copper foil from the bare PCB to create conductive circuitry. Board information includes board size and production process information. Board size refers to the shape and size of the PCB. Production process information refers to the structural distribution of the PCB after etching.

[0036] For example, the interval time can be obtained by obtaining the distance swept by the ion wind as it passes over the PCB surface from the board information, and then processing the distance and control parameters. Alternatively, the interval time can be obtained by capturing the interval time between the image where the tracer particles appear and the image where the tracer particles are completely covered, using an image acquisition device. The interval time is the difference between the first acquisition time for capturing the image where the tracer particles appear and the second acquisition time for capturing the image where the tracer particles are completely covered.

[0037] In a possible implementation, in step S100, the interval time is obtained by analyzing the control parameters and the plate information, including: S110, obtaining a passing length from the board information; wherein the passing length is used to reflect the distance swept by the ion wind when passing through the surface of the PCB board.

[0038] It is understood that the passing length is the length or width of the PCB board. The passing length can be obtained by matching the placement posture of the PCB board in the detection device with the board information.

[0039] For example, when the PCB board is placed parallel to the detection device, the passing length is the length of the PCB board; when the PCB board is placed crosswise to the detection device, the passing length is the width of the PCB board.

[0040] S120, performing processing according to the control parameter and the passing length to obtain the interval time.

[0041] It can be understood that interval time = pass length ÷ control parameter.

[0042] For example, if the passing length is 200 mm and the control parameter is 0.5 m / s, the interval time is 0.4 s, and so on.

[0043] With this setup, by extracting the passing length reflecting the ion wind blowing distance from the board information and combining it with the control parameters for calculation and processing, the interval time of the blowing action can be accurately determined, and the dynamic matching of the ion wind blowing range and time parameters on the PCB board surface can be achieved, providing a basis for the subsequent analysis of defect detection results.

[0044] S200, the control device controls the purge device to perform a first operation on the PCB board based on the control parameters; wherein the first operation is used to reflect that the purge device uses ion wind with tracer particles to purge the PCB board in a direction parallel to the surface of the PCB board.

[0045] It can be understood that the tracer particles are made of materials with high light scattering properties (such as silver-coated polystyrene microspheres), which enables the tracer particles to reflect or scatter enough light under the light source of the machine vision, so that they can be clearly captured by the image acquisition device. The control device starts the purge device according to the preset control parameters, so that the purge device blows out an ion wind flow containing tracer particles. The ion wind blows the PCB board in a directional path parallel to the surface of the PCB board. The ion wind carrying the tracer particles is set at a height of 5cm-12cm from the PCB board. The ion concentration of the tracer particles is 0.05mg / m 3 Up to 0.1 mg / m 3 .

[0046] S300, in response to the first operation, the image acquisition device acquires a first image based on the interval time; wherein the first image is used to reflect the color distribution of the tracer particles on the surface of the PCB board.

[0047] It is understood that the first image is captured when the control device detects that the first operation has been triggered and then controls the image capture device to directly capture the first image. When the first operation is triggered, after the interval has passed, it can be seen that the ion wind carrying the tracer particles will completely cover the PCB.

[0048] S400: Determine whether there is a short circuit or open circuit on the PCB board based on the first image and the board information.

[0049] It's understandable that a short circuit can be caused by surface irregularities (such as the sharp corners of a solder bridge) that trap tracer particles at the short defect, leading to a difference in tracer particle concentration between the short defect and the surrounding area. Furthermore, the sharp edge curvature (and strong tip effect) at a break (such as a fracture) leads to a concentrated local electric field, which in turn increases the attraction for charged particles (i.e., tracer particles), ultimately causing tracer particles to aggregate at the break. This ultimately manifests as a higher tracer particle concentration at the defect site on the PCB, resulting in a darker color at the defect site in the first image.

[0050] For example, the plate information can be analyzed to obtain areas in the PCB board that reflect where the copper foil has been dissolved and removed by the etching liquid, and areas in the PCB board that reflect where the copper foil has not been dissolved and removed by the etching liquid. Then, the short circuit and open circuit conditions of the PCB board can be judged based on the areas in the PCB board that have been dissolved and removed by the etching liquid, the areas in the PCB board that reflect where the copper foil has not been dissolved and removed by the etching liquid, and the first image.

[0051] In a possible implementation, in step S400, determining whether a short circuit exists on the PCB board according to the first image and the board information includes: S410, analyzing the plate information to obtain an etched area and a non-etched area; wherein the etched area is used to reflect the area of the PCB board where the copper foil is dissolved and removed by the etching liquid, and the non-etched area is used to reflect the area of the PCB board where the copper foil is not dissolved and removed by the etching liquid.

[0052] It can be understood that the etching area and the non-etching area of the PCB board can be directly obtained from the production process information in the board information.

[0053] For example, the board information can be read from the production process information for areas of the copper surface that are not covered by resist or accessible to etching liquid, and this area can be defined as an etching area. Similarly, areas on the PCB board that are not defined as etching areas will be defined as non-etching areas. Alternatively, the board information can be read from the design file for areas of copper foil covered by resist (photoresist or dry film) or protected by a physical mask, and this area can be marked as a non-etching area. Other areas on the PCB board that are not defined as non-etching areas can be marked as etching areas.

[0054] S420 , analyzing the etched area, the non-etched area, and the first image to obtain a determination result.

[0055] It can be understood that the charge distribution of the non-etched area and the etched area of the defect-free PCB board is uniform and electrically neutral, so that the ion wind carrying the tracer particles is evenly distributed on the surface of the PCB board.

[0056] For example, the etched area can be matched with the first image, and the color value in the etched area of the first image can be arbitrarily selected. The non-etched area can then be matched with the first image to obtain multiple color values reflecting the non-etched area. The judgment result is then determined based on the comparison results of the color value of the etched area with multiple color values of the non-etched area. The color value can be a three-channel RGB value.

[0057] The image acquisition device can also be used to acquire the surface image of the PCB board in real time after the first operation is triggered, thereby obtaining an image set, and then analyzing the color value change of the surface image based on the image set, and then dividing the color value change into the etching area color value change and the non-etching area color value change based on the etching area and the non-etching area. Then, the color value change of the etching area and the color value change of the non-etching area are synchronously compared to obtain a synchronous comparison result, and then a judgment result is obtained based on the synchronous comparison result.

[0058] With this setting, the etched area and non-etched area of the PCB board can be accurately divided by analyzing the board information, and matching analysis can be performed in combination with the first image actually collected. This can automatically make a preliminary judgment on whether a defect exists. When it is determined that the defect does not exist, the defect judgment of the next PCB board can be carried out, thereby improving the defect recognition capability and defect detection efficiency.

[0059] In a possible implementation, in step S420, the determination result is obtained by analyzing the etched area, the non-etched area, and the first image, including: S421 , matching the etched area with the first image to obtain a first color value; wherein the first color value is used to reflect the color value of the etched area.

[0060] For example, the first image may be matched with the etched area to obtain a color value of the etched area in the first image, ie, the first color value.

[0061] S422 , matching the non-etched area with the first image to obtain a plurality of second color values; wherein the second color values are used to reflect the color values of the non-etched area.

[0062] It is understandable that, because not all areas in the non-etched area (ie, the conductive circuit) have differences, it is necessary to obtain all second color values in the non-etched area, thereby obtaining multiple second color values.

[0063] For example, the first image may be matched with the non-etched area to obtain a color value of the non-etched area in the first image, ie, the second color value.

[0064] S423: Determine a determination result based on a comparison result of the first color value and the plurality of second color values.

[0065] For example, when the plurality of second color values are all equal to the first color value, it indicates that there is no short circuit on the PCB board. Conversely, when a second color value among the plurality of second color values is not equal to the first color value, it indicates that there is a short circuit on the PCB board. A determination result can also be obtained by using the synchronous comparison results in step S420. When the synchronous comparison results show that the color value changes in the etched area and the color value changes in the non-etched area change synchronously, it indicates that there is no short circuit on the PCB board. Conversely, when the synchronous comparison results show that the color value changes in the etched area and the color value changes in the non-etched area do not change synchronously, it indicates that there is a short circuit on the PCB board.

[0066] With this arrangement, by matching the color values of the etched area and the non-etched area of the PCB board with the actual first image, a first color value and multiple second color values reflecting the characteristics of different areas are extracted from the first image. Based on the comparison results of the two, it is possible to efficiently and accurately determine whether there is a short circuit defect in the PCB board.

[0067] In a possible implementation, in step S423, determining a determination result based on a comparison result of the first color value and the second color value includes: S4231: When the first color value is equal to the plurality of second color values, it is determined that there is no short circuit on the PCB board.

[0068] It can be understood that when the multiple second color values are all equal to the first color value, it means that there is no color difference in the first image, that is, the charge distribution on the surface of the PCB board is uniform, which can reflect that there is no short circuit on the PCB board, that is, the output judgment result is that there is no short circuit on the PCB board.

[0069] S4232: When the first color value is not equal to the plurality of second color values, it is determined that a short circuit exists on the PCB board.

[0070] It can be understood that when there is a second color value that is not equal to the first color value in the multiple second color values, it indicates that there is a color difference in the first image, that is, the distribution of charge on the surface of the PCB board is uneven, which can reflect the existence of a short circuit on the PCB board, that is, the output judgment result is that there is a short circuit on the PCB board.

[0071] This setup allows for quantitative comparison of the first color value of the etched area of the PCB with multiple second color values of the non-etched area. Following the standardized inspection rule of "equal color values indicate a short circuit, unequal color values indicate no defect," circuit defects caused by copper foil residue (short circuit) or abnormal removal (open circuit) during the etching process can be efficiently and automatically identified. This provides an objective and rapid quantitative determination solution for PCB quality inspection, improving the efficiency and reliability of defect detection.

[0072] S500: If a short circuit exists on the PCB, the control device controls the purging device to perform a second operation, and the image acquisition device acquires a second image after an interval. The second operation is used to instruct the purging device to stop purging the PCB, and the second image is used to reflect the color distribution of the tracer particles on the surface of the PCB.

[0073] It can be understood that when the control device detects the second operation, after an interval time has passed, it can be indicated that the ion wind carrying the tracer particles does not cover the PCB board.

[0074] S600: Analyze the first image, the second image, and the interval time to obtain a defect detection result; wherein the defect detection result is used to reflect the short circuit and open circuit conditions of the PCB board.

[0075] For example, the first image and the second image can be analyzed to obtain the difference between the color values reflecting the defects in the non-etching area of the first image and the second image, and the difference between the color values reflecting the non-defects in the non-etching area of the first image and the second image, respectively. Then, analysis is performed based on the difference between the color values reflecting the defects in the non-etching area of the first image and the second image, the difference between the color values reflecting the non-defects in the non-etching area of the first image and the second image, and the interval time to obtain the defect detection result.

[0076] Defect detection results can also be obtained by training an analysis model. Specifically, the first image, the second image, and the interval are input into the analysis model, which then outputs the corresponding defect detection results. The analysis model training process can use the processed data of the first image, the second image, the interval, and the corresponding defect detection results as the training dataset for the analysis model. This training dataset is then input into the analysis model for training and learning, ultimately yielding the analysis model.

[0077] With this setup, by using ion wind carrying tracer particles to display internal hidden defects in an externally detectable perspective, machine vision can be used to detect defects in PCB boards that have no defects on the surface but have functional hidden dangers inside, thereby improving the accuracy of PCB defect detection.

[0078] In a possible implementation, in step S600, analyzing the first image, the second image, and the interval time to obtain a defect detection result includes: S610, analyzing the first image and the second image to obtain a first change condition and a second change condition; wherein the first change condition is used to reflect the difference between the color values of the first image and the second image at the defect in the non-etching area, and the second change condition is used to reflect the difference between the color values of the first image and the second image at the non-defect in the non-etching area.

[0079] Exemplarily, the position of the PCB board at which a second color value equal to the first color value among multiple second color values in the first image is located can be determined as a defect point, and the position of the PCB board at which a second color value equal to the first color value among multiple second color values in the first image is determined as a non-defect point, and then analysis is performed based on the first color value, the defective point and the second image to obtain a first change condition, and then analysis is performed based on the non-defective point, the first image and the second image to obtain a second change condition.

[0080] Alternatively, a position on the PCB board where a second color value equal to the first color value among the plurality of second color values in the first image is located may be determined as a defective point, and a position on the PCB board where a second color value equal to the first color value among the plurality of second color values in the first image is determined as a non-defective point. After a second operation, a surface image of the PCB board immediately after the second operation is triggered and a surface image of the PCB board after an interval are acquired by an image acquisition device. A first change condition is obtained by analyzing the defective point, the surface image of the PCB board immediately after the second operation is triggered, and the surface image of the PCB board after the interval are acquired. Furthermore, a second change condition is obtained by analyzing the non-defective point, the surface image of the PCB board immediately after the second operation is triggered, and the surface image of the PCB board after the interval are acquired.

[0081] In a possible implementation, in step S610, analyzing the first image and the second image to obtain the first change status and the second change status includes: S611: A second color value unequal to the first color value among the plurality of second color values in the first image is identified as a difference point at a location on the PCB board, and a second color value equal to the first color value among the plurality of second color values in the first image is identified as a non-difference point at a location on the PCB board.

[0082] It can be understood that when the second color value is not equal to the first color value, it can be indicated that there is a defect at the position of the second color value on the PCB board, and the position is determined as a defect point, that is, a difference point.

[0083] S612: Analyze the first color value, the difference point, and the second image to obtain a first change condition.

[0084] Exemplarily, the color value reflecting the position of the difference point in the second image can be obtained from the second image through the difference point, and then processed according to the first color value and the color value reflecting the position of the difference point in the second image to obtain the first change condition.

[0085] The difference point can also be used to obtain the first-moment color value corresponding to the position of the difference point from the surface image of the PCB board at the moment when the second operation is just triggered, and at the same time, the difference point can be used to obtain the second-moment color value corresponding to the position of the difference point from the surface image of the PCB board after an interval time, thereby obtaining the first change condition, which is the difference between the color value at the first moment and the color value at the second moment.

[0086] In a possible implementation, in step S612, analyzing the first color value, the difference point, and the second image to obtain a first change condition includes: S6121: Based on the difference point, obtain a third color value from the second image; wherein the third color value is used to reflect the color value of the difference point in the second image.

[0087] For example, the specific position of the difference point in the second image can be located through image comparison technology (such as pixel difference, feature matching and other algorithms), and then the color value corresponding to the difference point is extracted from the pixel matrix of the second image based on the coordinate position of the difference point, and the obtained color value is defined as the third color value.

[0088] S6122: Process the first color value and the third color value to obtain a first change condition.

[0089] It can be understood that the first change condition = the first color value - the third color value.

[0090] For example, if the first color value is 150 and the third color value is 100, then the first change condition is 50 (150-100), and so on.

[0091] With this setup, by locating the difference points between the second image and the first image and extracting the third color value, and then performing comparative analysis based on the standard first color value of the etched area, the color change conditions at the difference points can be accurately quantified, effectively identifying short circuit defects that may exist during the etching process, and providing a directional and parameterized evaluation method for the refined detection of PCB board etching quality, thereby improving the accuracy and adaptability of defect detection under complex structures.

[0092] S613: Analyze the non-difference points, the first image, and the second image to obtain a second change condition.

[0093] Exemplarily, the second color value at the non-difference point in the first image can be marked as a color value reflecting the non-difference point among multiple second color values in the first image, and then based on the non-difference point, a color value reflecting the non-difference point of the second image is obtained from the second image. Finally, the second change condition is obtained by processing the color value reflecting the non-difference point among multiple second color values in the first image and the color value reflecting the non-difference point of the second image.

[0094] Alternatively, a color value at a third moment corresponding to the position of the non-difference point may be obtained from the surface image of the PCB board at the moment the second operation is just triggered, and a color value at a fourth moment corresponding to the position of the non-difference point may be obtained from the surface image of the PCB board after an interval, thereby obtaining the second change condition, which is the difference between the color value at the third moment and the color value at the fourth moment.

[0095] With this setup, by mapping the color value differences in the PCB board image to specific physical locations, accurately identifying the difference points (abnormal areas) and non-difference points (normal areas), and combining the two images to analyze the color value changes, the degree of abnormality in the defective area and the difference in the normal area can be quantified, thereby achieving accurate positioning and detection of short circuit defects in the PCB board, thereby improving the comprehensiveness of PCB board defect identification.

[0096] In a possible implementation, in step S613, analyzing the non-difference point, the first image, and the second image to obtain the second change condition includes: S6131: Mark a second color value at a non-difference point in the first image as a fourth color value; wherein the fourth color value is used to reflect a color value at a non-difference point among a plurality of second color values in the first image.

[0097] For example, the second color value that is equal to the first color value among the second color values may be marked as the fourth color value.

[0098] S6132: Based on the non-difference point, obtain a fifth color value from the second image; wherein the fifth color value is used to reflect the color value of the non-difference point of the second image.

[0099] For example, the specific position of the non-difference point in the second image can be located through image comparison technology (such as pixel difference, feature matching and other algorithms), and then the color value corresponding to the non-difference point is extracted from the pixel matrix of the second image based on the coordinate position of the non-difference point, and the obtained color value is defined as the fifth color value.

[0100] S6133: Process according to the fourth color value and the fifth color value to obtain a second change condition.

[0101] It can be understood that, because not all areas in the non-etched area (ie, the conductive line) have differences, the second color value = the fourth color value - the fifth color value.

[0102] For example, if the fourth color value is 200 and the fifth color value is 170, the second change condition is 30 (200-170), and so on.

[0103] With this setup, by accurately comparing and analyzing the standard color value (fourth color value) of the non-etched area of the PCB board with the color value (fifth color value) of the corresponding position in the second image, the color change status (second change status) of the non-defective area can be quantitatively evaluated and used as a reference comparison value. This can provide basic comparison data for defect detection and improve the accuracy of defect identification during the production process.

[0104] S620: Analyze the first change condition, the second change condition, and the interval time to obtain a defect detection result.

[0105] Exemplarily, a correspondence curve between the color value and the electric potential reflecting the tracer particles can be obtained, and then matched with the first change condition and the second change condition based on the correspondence curve, thereby obtaining a potential change value corresponding to the first change condition and the correspondence curve and a potential change value corresponding to the second change condition and the correspondence curve. Then, the potential change value and the interval time corresponding to the first change condition and the correspondence curve are processed to obtain a nuclear charge decay rate for quantifying defects at PCB boards under ion wind blowing. At the same time, the potential change value and the interval time corresponding to the second change condition and the correspondence curve are processed to obtain a nuclear charge decay rate for quantifying non-defective areas of the PCB board that are not under ion wind blowing. Finally, based on the comparison results between the two nuclear charge decay rates, a defect detection result is obtained.

[0106] A calibration model for tracer particle concentration and color value is established. An exponential mapping relationship between tracer particle concentration and electric potential is then established based on the Boltzmann distribution. Combined with the charged properties of the ion wind carrying the tracer particles, the local electric potential is calculated. This calibration model can be established by designing an experimental plan to uniformly spray tracer particles of varying concentrations onto a defect-free standard PCB. An industrial camera is then used to capture surface images of the defect-free standard PCB, extracting the average surface color value. Curve fitting is then used to construct a model based on the experimentally obtained data set of tracer particle concentration and average surface color value, ultimately yielding a calibration model for tracer particle concentration and color value. The Boltzmann distribution model is used to describe the probability distribution of particles at different energy states.

[0107] With this setup, by analyzing the color value differences between the first and second images at the defective and non-defective areas in the non-etched area (i.e., the first and second change conditions), and combining them with the interval time parameter for comprehensive judgment, the defect location and defect type on the PCB surface can be accurately identified, achieving automated detection of defect types and improving PCB defect accuracy.

[0108] In a possible implementation, in step S620, analyzing the first change condition, the second change condition, and the interval time to obtain a defect detection result includes: S621, obtain a calibration curve, and match the calibration curve with the first change condition and the second change condition respectively to obtain a first potential change and a second potential change; wherein, the calibration curve is used to reflect the correspondence curve between the color value and the potential of the tracer particles, the first potential change is used to reflect the potential change value corresponding to the first change condition and the calibration curve, and the second potential change is used to reflect the potential change value corresponding to the second change condition and the calibration curve.

[0109] It is understood that the standard curve can be manually input. Alternatively, corresponding data can be obtained from a variation database, and then the standard curve can be constructed based on this data. The variation database refers to a database containing the potential changes corresponding to changes in different color values. This data can be obtained through laboratory experiments, on-site measurements and monitoring, and previous experience. Once obtained, the collected data is organized, classified, and archived to extract useful information and patterns. The relevant data is then stored in a database to form a variation database.

[0110] S622: Process the first potential change and the interval time to obtain a first time constant; wherein the first time constant is used to quantify the decay rate of the nuclear charge at the defect of the PCB board under the ion wind.

[0111] It can be understood that the relationship between the first potential change, the interval time and the first time constant is: ,in, is the first potential change, is a natural constant, is the sum of the interval time and the analysis time, The analysis time is the time it takes for the machine vision-based PCB defect automatic detection device to determine whether there is a short circuit or open circuit on the PCB board according to the first image and the board information in step S400. The analysis time can be directly obtained by the machine vision-based PCB defect automatic detection device, and then the analysis time and the interval time are processed to obtain The time interval between the acquisition time of the first image in step S300 and the acquisition time of the second image in step S500 can also be calculated by adding a timer to the PCB defect automatic detection device based on machine vision, and the time interval is determined as .

[0112] For example, if the first potential change is 0.264 and the interval time is 0.4s, the first time constant is 0.3; if the first potential change is 0.875 and the interval time is 0.4s, the first time constant is 3, and so on.

[0113] S623: Process the second potential change and the interval time to obtain a second time constant; wherein the second time constant is used to quantify the decay rate of the nuclear charge at the non-defective portion of the PCB board not under ion wind blowing.

[0114] It can be understood that the relationship between the second potential change, the interval time and the second time constant is: ,in, is the second potential change, is a natural constant, is the second time constant.

[0115] For example, if the second potential change is 0.819 and the interval time is 0.4 s, the second time constant is 2, and so on.

[0116] S624 : Compare the first time constant with the second time constant to obtain a comparison status; wherein the comparison status is used to reflect the difference between the first time constant and the second time constant.

[0117] It can be understood that the comparison condition=first time constant-second time constant.

[0118] For example, if the first time constant is 0.3 and the second time constant is 2, the contrast condition is less than 0; if the first time constant is 3 and the second time constant is 2, the contrast condition is greater than 0, and so on.

[0119] S625, if the comparison condition is less than 0, the defect detection result is a short circuit defect, and if the comparison condition is greater than 0, the defect detection result is an open circuit defect.

[0120] It can be understood that short-circuit defects on PCBs (such as solder bridges and metal debris) create low-impedance conductive paths on the board, causing the potential at the short-circuit defect to drop rapidly, increasing the charge decay rate and making the time constant of the short-circuit defect shorter than that of a non-defective area. On the other hand, open-circuit defects (such as cracks and cold solder joints) on PCBs create infinite impedance in the charge migration path, decreasing the charge decay rate and making the time constant of the open-circuit defect longer than that of a non-defective area. Based on this principle, the presence of a short or open circuit at the defect location can be determined by comparing the positive and negative results.

[0121] This setup converts color value changes into potential changes, amplifying PCB defect detection from a microscopic perspective. The system also calculates the decay time constant of the nuclear charge at defective and non-defective locations based on the interval time. By comparing the decay rate differences between the two, the defect type can be automatically determined. This improves the accuracy of PCB short-circuit defect detection results.

[0122] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0123] Corresponding to the automatic PCB defect detection method based on machine vision described in the above embodiment, the embodiment of the present application also provides an automatic PCB defect detection system based on machine vision. The various modules of the automatic PCB defect detection system based on machine vision can implement the various steps of the automatic PCB defect detection method based on machine vision. Figure 3 A structural block diagram of a machine vision-based PCB defect automatic detection system provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0124] Reference Figure 3 , the PCB defect automatic detection system based on machine vision includes: The acquisition and analysis module is used to obtain control parameters and plate information, and analyze the control parameters and plate information to obtain the interval time; among them, the control parameters are used to reflect the wind speed of the purge device, the plate information is used to reflect the shape and size of the PCB board, and the interval time is used to reflect the time it takes for the ion wind blown by the purge device to completely cover the PCB board.

[0125] The first control module is used to control the device to control the purging device to perform a first operation on the PCB board based on the control parameters; wherein the first operation is used to reflect that the purging device uses ion wind with tracer particles to purge the PCB board in a direction parallel to the surface of the PCB board.

[0126] The acquisition module is used to respond to the first operation, and the image acquisition device acquires a first image based on the interval time; wherein the first image is used to reflect the color distribution of the tracer particles on the surface of the PCB board.

[0127] The judgment module is used to judge whether there is a short circuit on the PCB board according to the first image and the board information.

[0128] The second control module is configured to control the purge device to perform a second operation if a short circuit exists on the PCB board, and the image acquisition device to acquire a second image after an interval; wherein the second operation is used to instruct the purge device to stop purging the PCB board, and the second image is used to reflect the color distribution of the tracer particles on the surface of the PCB board.

[0129] The analysis module is used to analyze the first image, the second image and the interval time to obtain a defect detection result; wherein the defect detection result is used to reflect the short circuit and open circuit conditions of the PCB board.

[0130] It should be noted that the information interaction, execution process, etc. between the above-mentioned systems / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment section and will not be repeated here.

[0131] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0132] An embodiment of the present application also provides an automatic PCB defect detection device based on machine vision. The automatic PCB defect detection device based on machine vision includes a purging device, an image acquisition device, a placement table and a control device. The purging device, the image acquisition device and the control device are electrically connected. Figure 4 This is a schematic diagram of the structure of the control device 4 provided in one embodiment of the present application. Figure 4 As shown, the control device 4 of this embodiment includes: at least one processor 40 ( Figure 4Only one is shown), at least one memory 41 ( Figure 4 Only one is shown in the figure) and a computer program 42 stored in the at least one memory 41 and executable on the at least one processor 40. When the processor 40 executes the computer program 42, the control device 4 implements the steps of any of the above-mentioned embodiments of the automatic PCB defect detection method based on machine vision, or implements the functions of each module / unit in each embodiment of the above-mentioned system.

[0133] For example, the computer program 42 may be divided into one or more modules / units, which are stored in the memory 41 and executed by the processor 40 to implement the present application. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program 42 in the control device 4.

[0134] The control device 4 can be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The control device 4 can include, but is not limited to, a processor 40 and a memory 41. Those skilled in the art will understand that Figure 4 This is merely an example of the control device 4 and does not constitute a limitation on the control device 4. The control device 4 may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, buses, etc.

[0135] The processor 40 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor may be a microprocessor or any conventional processor.

[0136] In some embodiments, the memory 41 may be an internal storage unit of the control device 4, such as a hard drive or memory of the control device 4. In other embodiments, the memory 41 may also be an external storage device of the control device 4, such as a plug-in hard drive, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. equipped on the control device 4. Furthermore, the memory 41 may include both the internal storage unit of the control device 4 and an external storage device. The memory 41 is used to store an operating system, application programs, a boot loader, data, and other programs, such as the program code of the computer program. The memory 41 may also be used to temporarily store data that has been output or is about to be output.

[0137] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0138] An embodiment of the present application provides a computer program product. When the computer program product is run on a machine vision-based automatic PCB defect detection device, the machine vision-based automatic PCB defect detection device implements the steps in any of the above-mentioned method embodiments.

[0139] If the integrated unit is implemented as a software functional unit and sold or used as a standalone product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the process steps in the above-mentioned method embodiments can be implemented by a computer program instructing the relevant hardware. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, an executable file, or some intermediate form. The computer-readable medium can include at least any entity or device capable of carrying the computer program code to the machine vision-based PCB defect automatic inspection equipment, a recording medium, computer memory, read-only memory (ROM), random access memory (RAM), an electrical carrier signal, a telecommunications signal, and a software distribution medium. Examples include a USB flash drive, a removable hard drive, a magnetic disk, or an optical disk.

[0140] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0141] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0142] In the embodiments provided in the present application, it should be understood that the disclosed automatic PCB defect detection system based on machine vision and the automatic PCB defect detection device based on machine vision can be implemented in other ways. For example, the embodiment of the automatic PCB defect detection system based on machine vision described above is merely schematic. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0143] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0144] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A method for automatic detection of PCB defects based on machine vision, characterized in that: include: Acquiring control parameters and plate information, and analyzing the control parameters and the plate information to obtain an interval time; wherein the control parameters are used to reflect the wind speed of the purge device, the plate information is used to reflect the process parameters of the PCB board, and the interval time is used to reflect the time it takes for the ion wind blown by the purge device to completely cover the PCB board; The control device controls the purge device to perform a first operation on the PCB based on the control parameter; wherein the first operation is used to reflect that the purge device uses an ion wind with tracer particles to purge the PCB in a direction parallel to the surface of the PCB; In response to the first operation, the image acquisition device acquires a first image based on the interval time; wherein the first image is used to reflect the color distribution of the tracer particles on the surface of the PCB board; Determine whether the PCB board has a short circuit according to the first image and the board information; If a short circuit exists on the PCB, the control device controls the purging device to perform a second operation, and the image acquisition device acquires a second image after the interval time; wherein the second operation is used to instruct the purging device to stop purging the PCB, and the second image is used to reflect the color distribution of the tracer particles on the surface of the PCB; An analysis is performed based on the first image, the second image, and the interval time to obtain a defect detection result; wherein the defect detection result is used to reflect the short circuit and open circuit conditions of the PCB board.

2. The method for automatic PCB defect detection based on machine vision according to claim 1, wherein: The analyzing the control parameters and the plate information to obtain the interval time includes: Obtaining a passing length from the plate information; wherein the passing length is used to reflect the distance swept by the ion wind when passing through the surface of the PCB board; The control parameter and the passing length are processed to obtain the interval time.

3. The method for automatic PCB defect detection based on machine vision according to claim 1, wherein: The determining, based on the first image and the plate information, whether the PCB board has a short circuit or open circuit condition includes: Analyze the plate information to obtain an etched area and a non-etched area; wherein the etched area is used to reflect the area of the PCB board where the copper foil is dissolved and removed by the etching liquid, and the non-etched area is used to reflect the area of the PCB board where the copper foil is not dissolved and removed by the etching liquid; A determination result is obtained by analyzing the etching area, the non-etching area, and the first image.

4. The method for automatic PCB defect detection based on machine vision according to claim 3, wherein: The analyzing the etched area, the non-etched area, and the first image to obtain a determination result includes: Matching the etched area with the first image to obtain a first color value; wherein the first color value is used to reflect the color value of the etched area; According to the matching of the non-etched area with the first image, a plurality of second color values are obtained; wherein the second color values are used to reflect the color value of the non-etched area; A determination result is determined based on a comparison result of the first color value and a plurality of the second color values.

5. The method for automatic PCB defect detection based on machine vision according to claim 4, wherein: The determining a determination result based on a comparison result of the first color value and the plurality of second color values includes: When the first color value is equal to a plurality of the second color values, it is determined that there is no short circuit on the PCB board; When the first color value is not equal to the second color values, it is determined that a short circuit exists on the PCB board.

6. The method for automatic PCB defect detection based on machine vision according to claim 5, wherein: The analyzing the first image, the second image, and the interval time to obtain a defect detection result includes: Analyzing the first image and the second image to obtain a first change condition and a second change condition; wherein the first change condition is used to reflect the difference between the color values of the first image and the second image at the defect in the non-etched area, and the second change condition is used to reflect the difference between the color values of the first image and the second image at the non-defect in the non-etched area; An analysis is performed based on the first change condition, the second change condition, and the interval time to obtain a defect detection result.

7. The method for automatic PCB defect detection based on machine vision according to claim 6, wherein: The analyzing the first image and the second image to obtain a first change condition and a second change condition includes: Determine the second color value that is unequal to the first color value among the plurality of second color values in the first image and is located at a position on the PCB as a difference point, and determine the second color value that is equal to the first color value among the plurality of second color values in the first image and is located at a position on the PCB as a non-difference point; Analyze the first color value, the difference point, and the second image to obtain a first change condition; A second change condition is obtained by analyzing the non-difference point, the first image, and the second image.

8. The method for automatic PCB defect detection based on machine vision according to claim 7, wherein: The analyzing the first color value, the difference point, and the second image to obtain a first change condition includes: Based on the difference point, obtaining a third color value from the second image; wherein the third color value is used to reflect the color value of the difference point in the second image; A first change condition is obtained by processing the first color value and the third color value.

9. The method for automatic PCB defect detection based on machine vision according to claim 7, wherein: The analyzing the non-difference point, the first image, and the second image to obtain a second change condition includes: marking the second color value at the non-difference point in the first image as a fourth color value; wherein the fourth color value is used to reflect the color value at the non-difference point among the plurality of second color values in the first image; Based on the non-difference point, obtaining a fifth color value from the second image; wherein the fifth color value is used to reflect the color value of the non-difference point in the second image; The second change condition is obtained by processing according to the fourth color value and the fifth color value.

10. The method for automatic PCB defect detection based on machine vision according to claim 7, wherein: The analyzing the first change condition, the second change condition, and the interval time to obtain a defect detection result includes: Obtaining a calibration curve, and matching the calibration curve with the first change condition and the second change condition, respectively, to obtain a first potential change and a second potential change; wherein the calibration curve is used to reflect a corresponding relationship curve between the color value of the tracer particle and the potential, the first potential change is used to reflect the potential change value corresponding to the first change condition and the calibration curve, and the second potential change is used to reflect the potential change value corresponding to the second change condition and the calibration curve; Processing the first potential change and the interval time to obtain a first time constant; wherein the first time constant is used to quantify the decay rate of the nuclear charge at the defect of the PCB board under ion wind blowing; Processing the second potential change and the interval time to obtain a second time constant; wherein the second time constant is used to quantify the decay rate of the nuclear charge at a non-defective portion of the PCB board that is not under ion wind blowing; Comparing the first time constant with the second time constant to obtain a comparison status; wherein the comparison status is used to reflect the difference between the first time constant and the second time constant; If the comparison condition is less than 0, the defect detection result is a short circuit defect, and if the comparison condition is greater than 0, the defect detection result is an open circuit defect.

Images