Method, device and equipment for detecting wiring quality of server PCBA mainboard and medium

Abstract

The invention relates to the technical field of mainboard quality detection, and discloses a server PCBA mainboard wiring quality detection method and device, equipment and a medium, a target image segmentation model and a corresponding preset reference image are obtained based on a target model and a wiring arrangement category of a server PCBA mainboard, and further, the target image segmentation model and the corresponding preset reference image are obtained. The target image segmentation model is utilized to segment the wiring image and extract the image to obtain the area image, the area image is compared with the preset reference image to detect the wiring quality, the overall wiring quality condition of the server PCBA mainboard is obtained, the efficiency of detection work is improved, and the accuracy of a detection result is improved.

Description

Technical Field

[0001] The present application relates to the technical field of motherboard quality detection, and in particular to a method, device, equipment and medium for detecting the wiring quality of a server PCBA motherboard. Background Art

[0002] With the development of computer technology, server products are of various types and functions. Correspondingly, server motherboards are also different, and the component wiring and terminal wiring of the motherboard are becoming more and more complicated. Therefore, server production and assembly are facing increasingly complex situations. For example, different models of motherboards have different types and quantities of components, and different requirements for components and terminal wiring. The connected chassis components also have their own different wiring requirements.

[0003] In the related art, the method for detecting the wiring of the motherboard is mainly to detect the wiring quality manually with the naked eye, but abnormal wiring problems will still be found during the power-on test phase. At this time, it is necessary to manually disassemble the machine for troubleshooting and reassemble the wiring. It can be seen that the accuracy of wiring quality detection in the related art needs to be improved. Summary of the invention

[0004] The present application provides a method, device, equipment and medium for detecting the wiring quality of a server PCBA motherboard, which solves the technical problem in the related art that the accuracy of wiring quality detection needs to be improved, and can reduce the probability of needing to disassemble the machine for troubleshooting after power-on testing due to abnormal wiring.

[0005] In order to achieve the above objectives, the main technical solutions adopted in this application include:

[0006] In a first aspect, an embodiment of the present application provides a method for detecting the wiring quality of a server PCBA motherboard, the method comprising:

[0007] Obtaining a wiring image of a server PCBA mainboard, as well as a target model and wiring arrangement category of the server PCBA mainboard; wherein the wiring arrangement category is used to characterize the wiring conditions between the server PCBA mainboard and functional components in a server chassis;

[0008] Calling a target image segmentation model according to the wiring arrangement category and the target model, and obtaining N preset reference images corresponding to the target model; wherein the value of N is greater than or equal to 1;

[0009] Using the target image segmentation model to segment and extract images from the wiring image, to obtain N regional images; wherein the regional images correspond one to one with the preset reference images;

[0010] Wiring quality detection is performed according to the N regional images and the N preset reference images to obtain the overall wiring quality of the server PCBA mainboard.

[0011] Optionally, the wiring arrangement category includes a dense wiring mode and a sparse wiring mode; and calling the target image segmentation model according to the wiring arrangement category and the target model includes:

[0012] If the wiring arrangement category is a dense wiring mode, in the image segmentation model corresponding to the target model, a first image segmentation model corresponding to the dense wiring mode is called;

[0013] If the wiring arrangement category is a sparse wiring mode, in the image segmentation model corresponding to the target model, a second image segmentation model corresponding to the sparse wiring mode is called.

[0014] Optionally, if the wiring arrangement category indicates that the wiring situation belongs to a dense wiring mode, N is greater than 1, and each of the preset reference images is a partial correct image obtained by pre-dividing the correct wiring image of the server PCBA mainboard; the wiring quality detection is performed according to the N regional images and the N preset reference images to obtain the overall wiring quality of the server PCBA mainboard, including:

[0015] Performing image detection and comparison based on each regional image and a portion of correct images corresponding to each regional image to obtain a regional wiring detection result of each regional image;

[0016] The overall wiring quality is obtained by integrating the regional wiring detection results of each regional image.

[0017] Optionally, if the wiring arrangement category indicates that the wiring situation belongs to a sparse wiring mode, N is equal to 1, and the preset reference image is a correct wiring image of the server PCBA mainboard; the wiring quality detection is performed according to the N regional images and the N preset reference images to obtain the overall wiring quality of the server PCBA mainboard, including:

[0018] Extracting features from an image of the region to obtain sparse wiring features;

[0019] Extracting features from one of the correct wiring images to obtain correct wiring features;

[0020] The overall wiring quality is obtained by comparing the sparse wiring features with the correct wiring features.

[0021] Optionally, obtaining a wiring image of a server PCBA mainboard includes:

[0022] An orientation wiring image of the server PCBA mainboard at a preset shooting angle is obtained; the preset reference image is obtained by photographing the correctly wired server PCBA mainboard at the preset shooting angle in advance.

[0023] Optionally, the method further comprises:

[0024] If the overall wiring quality indicates that there is an abnormal wiring area, an abnormal area mark is displayed on the wiring image; wherein the abnormal area mark is used to indicate the location of the abnormal wiring area.

[0025] Optionally, the target model and wiring arrangement category of the server PCBA mainboard are determined in the following manner:

[0026] Before the server chassis starts wiring, the server PCBA mainboard is photographed to obtain an initial image of the server PCBA mainboard; model recognition is performed based on the initial image to obtain a target model of the server PCBA mainboard;

[0027] After the server chassis is wired, the wiring density is identified based on the wiring image to obtain the wiring arrangement category of the server PCBA mainboard.

[0028] In a second aspect, an embodiment of the present application provides a wiring quality detection device for a server PCBA motherboard, the device comprising:

[0029] A wiring image acquisition module, used to acquire a wiring image of a server PCBA mainboard, as well as a target model and wiring arrangement category of the server PCBA mainboard; wherein the wiring arrangement category is used to characterize the wiring condition between the server PCBA mainboard and the functional components in the server chassis;

[0030] A segmentation model calling module, used to call a target image segmentation model according to the wiring arrangement category and the target model, and obtain N preset reference images corresponding to the target model; wherein the value of N is greater than or equal to 1;

[0031] An image segmentation and extraction module, used to segment and extract the wiring image using the target image segmentation model to obtain N regional images; wherein the regional images correspond one-to-one to the preset reference images;

[0032] The wiring quality detection module is used to perform wiring quality detection according to the N regional images and the N preset reference images to obtain the overall wiring quality of the server PCBA mainboard.

[0033] In a third aspect, an embodiment of the present application provides a computer device, including:

[0034] A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method described in any of the above embodiments by executing the computer instructions.

[0035] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to enable a computer to execute the method described in any of the above embodiments.

[0036] In the embodiment of the present application, firstly, different types of server PCBA motherboards correspond to different wiring methods. Secondly, even the same type of server PCBA motherboards will correspond to different wiring methods due to manufacturing batches, configuration options, etc. Therefore, in the present application, firstly, the target model and wiring arrangement category of the server PCBA motherboard are comprehensively considered; and a matching image segmentation model is pre-trained for different combinations of the target model and the wiring arrangement category, so that the target image segmentation model matching the wiring arrangement category and the target model can be called; secondly, different numbers of preset reference images are obtained for different combinations of the target model and the wiring arrangement category; then, the target image segmentation model is used to segment and extract the wiring image wiring, and a regional image corresponding to the meaning of the preset reference image is obtained, so that accurate regional images and preset reference images are provided for image comparison, so that the wiring quality can be detected according to N regional images and N preset reference images, and the overall wiring quality of the server PCBA motherboard can be obtained. It can be seen that compared with the use of artificial naked eyes in the related art to detect the wiring condition of the server PCBA motherboard, the efficiency of the detection work is improved, and the accuracy of the detection results is also improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0038] Figure 1 A schematic diagram of a scenario for detecting the quality of PCBA motherboard wiring of a server provided in an embodiment of this specification;

[0039] Figure 2 A flow chart of a method for detecting the quality of PCBA motherboard wiring of a server provided in an embodiment of this specification;

[0040] Figure 3 A flow chart of a method for detecting the quality of PCBA motherboard wiring of a server provided in an embodiment of this specification;

[0041] Figure 4 A flow chart of a method for detecting the quality of PCBA motherboard wiring of a server provided in an embodiment of this specification;

[0042] Figure 5 A flow chart of a method for detecting the quality of PCBA motherboard wiring of a server provided in an embodiment of this specification;

[0043] Figure 6 A flow chart of a method for detecting the quality of PCBA motherboard wiring of a server provided in an embodiment of this specification;

[0044] Figure 7 A schematic diagram of a server PCBA motherboard wiring quality detection device provided in an embodiment of this specification;

[0045] Figure 8 A schematic diagram of the structure of a computer device provided in an embodiment of this specification. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0047] In the related art, the wiring assembly of the server PCBA board is mainly done manually, and the staff assembles the wiring of the server PCBA board according to the SOP. However, due to long-term work and momentary negligence, it is inevitable that the wiring will be wrongly connected, missed, or not properly plugged in.

[0048] Furthermore, the method for detecting the wiring of the motherboard is to first detect the wiring quality by human eyes. After the detection is passed, the server is powered on to test whether there are any functional abnormalities. However, the accuracy of the wiring quality detection by human eyes cannot be guaranteed, and the process is relatively complicated and inefficient. If there are omissions when the wiring quality is detected by human eyes, abnormal wiring is found during the power-on test, and the machine needs to be manually disassembled for troubleshooting and the wiring needs to be reassembled, which further reduces work efficiency.

[0049] Therefore, the present application provides a scenario example of a method for detecting the wiring quality of a server PCBA motherboard, which is applied to Figure 1In the application scenario shown. Among them, the application scenario includes a computer device 101 and multiple cameras 102. The computer device 101 is in communication connection with each camera 102. On the production assembly line, the server chassis after wiring arrives at the predetermined area through transmission, and the server PCBA motherboard wiring can be photographed by multiple cameras 102, and each camera 102 takes pictures at a different angle. After taking pictures of the PCBA motherboard of the server to be inspected to obtain an image, the correct wiring image pre-stored in the computer device 101 can be used as a preset reference image for comparison to confirm whether the wiring of the PCBA motherboard of the server to be inspected is correct.

[0050] It is understandable that the wiring of some models of server PCBA motherboards is a relatively simple situation, and only one image is needed to determine whether the wiring is correct. The wiring of some models of server PCBA motherboards is a relatively complex situation, and multiple images of different angles and orientations are required to determine whether the wiring is correct. When formulating a wiring detection strategy for any model of server PCBA motherboard, according to its wiring conditions, such as the density of wiring, the distribution of wiring, etc., it is determined from which angles and orientations to take pictures. Then the server of the target model with correct wiring is placed in the predetermined area of ​​the production line, and the clear image of the corresponding angle and orientation is stored in the computer device 101 as a preset reference image. Furthermore, when the image to be detected is detected, if the wiring condition of the server PCBA motherboard of this model is relatively simple, an image to be detected can be directly compared with a preset reference image to determine the wiring quality of the server PCBA motherboard to be detected. If the wiring situation of the PCBA motherboard of this model of server is relatively complicated, multiple images to be tested at different angles and orientations can be compared with preset reference images at corresponding angles and orientations to obtain the wiring quality test results of each image. Finally, the wiring quality test results of all images can be combined to obtain the wiring quality test results of the entire server PCBA motherboard.

[0051] In the above scenario example, the server PCBA mainboard wiring is first photographed by a camera to obtain an image of the wiring to be tested. Then, different methods and preset reference images are used for comparison in simple and complex wiring situations to determine whether the wiring quality of the server PCBA mainboard to be tested is qualified. This realizes automated image comparison detection of the server PCBA mainboard wiring. Compared with using the naked eye to detect the quality of the server PCBA mainboard wiring, it not only improves the efficiency of the detection work, but also improves the accuracy of the detection results.

[0052] It should be emphasized that this scenario example does not simply use image comparison technology directly, but combines the model of the server PCBA motherboard with the wiring arrangement category, and pre-trains different image segmentation models for different combinations of PCBA motherboard models and wiring arrangement categories. Therefore, when inspecting the wiring quality of the server PCBA motherboard, the target model and wiring arrangement category of the server PCBA motherboard can be determined first, and then the corresponding target image segmentation model can be called.

[0053] According to an embodiment of the present application, an embodiment of a method for detecting the wiring quality of a server PCBA motherboard is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0054] See also Figure 2 The wiring quality detection method of the server PCBA motherboard provided in the embodiment of the present application comprises the following steps:

[0055] S110, obtaining a wiring image of the server PCBA mainboard, as well as a target model and wiring arrangement category of the server PCBA mainboard.

[0056] Among them, the wiring image of the server PCBA motherboard is an image obtained by photographing the wiring of the server PCBA motherboard through a camera when the server chassis is transmitted to the predetermined area on the production assembly line. It should be noted that the number and angle of the wiring images required to be taken for server PCBA motherboards of different target models may be different, which may be determined by the wiring conditions of the server PCBA motherboard of this model and the corresponding image detection strategy. For example, when the wiring condition of the server PCBA motherboard of model A is relatively simple, only one positive image is needed to determine the accuracy of its wiring, so only one positive image is needed for the wiring of the server PCBA motherboard of model A. For another example, when the wiring condition of the server PCBA motherboard of model B is relatively complex, images of five directions, including the positive position and the front, back, left and right, are required to determine the accuracy of its wiring, so five images of different directions are needed for the wiring of the server PCBA motherboard of model B. It should also be noted that the number and angle of the wiring images required to be taken for the server PCBA motherboard of the same target model may also be different, because the PCBA motherboard of the same target model may have wiring methods of different complexity, which may be caused by different manufacturing batches, configuration options or specific application requirements.

[0057] The target model of the server PCBA motherboard can be a unique identifier that provides clear identification and classification for the server PCBA motherboard. There are many ways to obtain it. For example, an identification code that can identify the motherboard model can be pasted at a certain position on the motherboard. Before the server chassis enters the predetermined area of ​​the captured image, the target model of the motherboard is obtained by scanning the identification code.

[0058] The wiring arrangement category is used to characterize the wiring conditions between the server PCBA motherboard and the functional components in the server chassis. It can be used to distinguish the wiring differences of the server PCBA motherboards of the same target model due to different manufacturing batches, configuration options or specific application requirements. For example, the server PCBA motherboard of the target model D has two different configurations, high and low. In the high-configuration server, there are 4 SSD disks, each SSD disk is connected to the server PCBA motherboard through a data cable and a power cable; in the low-configuration server, there is only 1 SSD disk, and the SSD disk is also connected to the server PCBA motherboard through a data cable and a power cable. Then the wiring arrangement category of the PCBA motherboard of the high-configuration server can be recorded as "wiring arrangement category 1", and the wiring arrangement category of the PCBA motherboard of the low-configuration server can be recorded as "wiring arrangement category 2", or other methods can be used to distinguish different wiring arrangement categories.

[0059] S120 , calling a target image segmentation model according to the wiring arrangement category and the target model, and obtaining N preset reference images corresponding to the target model.

[0060] The target image segmentation model may be a model for segmenting the wiring image of the server PCBA motherboard to be inspected. The computer device 101 stores the correspondence between the server PCBA motherboard target model, wiring arrangement category and the target image segmentation model. After the server PCBA motherboard target model and wiring arrangement category are obtained, the target image segmentation model is obtained according to the correspondence and called.

[0061] The preset reference image can be the original image obtained after shooting the correctly wired server PCBA motherboard, and these original images will be stored in the computer device 101 for reference in subsequent image comparison detection. In addition, the preset reference image can also be an image obtained by some preprocessing of the original image, and the processed image will also be stored in the computer device 101. Exemplarily, firstly, an image detection strategy is formulated according to the target model and wiring arrangement category of the server PCBA motherboard, such as which angles and directions need to be photographed, and whether one image or multiple images are used for image recognition; then the correctly wired server chassis is placed in the predetermined area of ​​the production line, and the image is photographed according to the image detection strategy; finally, the photographed image is preprocessed and then stored in the computer device 101 as a preset reference image. The angle and orientation information of the photographed image can also be stored in the computer device 101. When it is necessary to detect the wiring condition of the PCBA motherboard of the target model and wiring arrangement category, after the server chassis to be detected reaches the predetermined area, the camera 102 also takes an image from the angle and orientation stored in the computer device 101. For example, the wiring conditions of PCBA mainboards of some target models and wiring arrangement categories are relatively simple, and only one image is needed to detect the wiring conditions. In this case, only one preset reference image may be saved in the computer device 101. The wiring conditions of PCBA mainboards of some target models and wiring arrangement categories are relatively complex, and multiple images of different angles and orientations are needed to detect the wiring conditions. In this case, multiple preset reference images of corresponding angles and orientations may be saved in the computer device 101.

[0062] S130 , using the target image segmentation model to segment and extract the wiring image to obtain N regional images.

[0063] Among them, the regional image can be an image of a specific area or object extracted from the original image, and can be obtained through image segmentation and image extraction technology. The regional image corresponds to the preset reference image one by one. Image segmentation can be to use the image segmentation model to obtain the mask image of the area where each component, terminal socket, plug-in interface, etc. in the image is located according to the shape characteristics of different components on the server PCBA motherboard and the characteristics of the dense wiring arrangement. Image extraction can be to use the mask image obtained by image segmentation to extract the area containing relevant key information such as the characteristics of each component, terminal socket, plug-in interface, etc. from the original image.

[0064] Specifically, some server PCBA mainboards have fewer components and a relatively simple wiring arrangement, so one image can be used for image segmentation and image extraction to obtain a regional image; some server PCBA mainboards have more components and a relatively dense wiring arrangement. When one image is used for image segmentation and image extraction, the image can be segmented and feature extracted according to the shape features of different components and the dense wiring arrangement features to obtain multiple regional images. It can be understood that when the target image segmentation model performs image segmentation and image extraction on the image to be detected, it uses the same parameters as when performing image segmentation and image extraction on the corresponding correct wiring image, so the obtained regional image and the preset reference image are one-to-one corresponding.

[0065] S140, performing wiring quality detection according to the N regional images and the N preset reference images to obtain the overall wiring quality of the server PCBA mainboard.

[0066] Specifically, some server PCBA motherboards have fewer components and a relatively simple wiring arrangement. A regional image can be compared with a preset reference image for wiring quality detection. If the detection passes, the overall wiring quality of the server PCBA motherboard is determined to be qualified. Some server PCBA motherboards have more components and a relatively dense wiring arrangement. N (N>1) regional images can be compared with the corresponding N preset reference images for wiring quality detection. If all N regional images pass the detection, the overall wiring quality of the server PCBA motherboard is determined to be qualified, otherwise the overall wiring quality is determined to be unqualified.

[0067] In the above embodiment, firstly, different types of server PCBA motherboards correspond to different wiring methods. Secondly, even the same type of server PCBA motherboards will correspond to different wiring methods due to manufacturing batches, configuration options, etc. Therefore, in this application, firstly, the target model and wiring arrangement category of the server PCBA motherboard are comprehensively considered; and a matching image segmentation model is pre-trained for different combinations of the target model and wiring arrangement category, so that the target image segmentation model matching the wiring arrangement category and the target model can be called; secondly, different numbers of preset reference images are obtained for different combinations of the target model and wiring arrangement category; then, the target image segmentation model is used to segment and extract the wiring image wiring, and a regional image corresponding to the meaning of the preset reference image is obtained, so that accurate regional images and preset reference images are provided for image comparison, so that the wiring quality can be detected according to N regional images and N preset reference images, and the overall wiring quality of the server PCBA motherboard can be obtained. It can be seen that compared with the use of artificial naked eyes in the related art to detect the wiring condition of the server PCBA motherboard, the accuracy of the detection is improved.

[0068] In some embodiments, the wiring arrangement category includes a dense wiring mode and a sparse wiring mode; calling the target image segmentation model according to the wiring arrangement category and the target model may include any of the following situations:

[0069] If the wiring arrangement category is a dense wiring mode, in the image segmentation model corresponding to the target model, a first image segmentation model corresponding to the dense wiring mode is called.

[0070] If the wiring arrangement category is a sparse wiring mode, in the image segmentation model corresponding to the target model, a second image segmentation model corresponding to the sparse wiring mode is called.

[0071] Among them, the first image segmentation model is a model used when the wiring arrangement type is a dense wiring method. After image segmentation and image extraction are performed on an image, the number of regional images obtained is relatively large, generally more than one. The second image segmentation model is a model used when the wiring arrangement type is a sparse wiring method. After image segmentation and image extraction are performed on an image, the number of regional images obtained is relatively small, which can be one.

[0072] Specifically, server PCBA motherboards of the same target model may have different wiring due to different manufacturing batches, configuration options or specific application requirements. For example, for server PCBA motherboards of the same target model, the server PCBA motherboards in the previous manufacturing batches need to connect fewer components, while the server PCBA motherboards in the later manufacturing batches need to connect more components, resulting in the wiring arrangement category of the previous manufacturing batch being a sparse wiring method, and the wiring arrangement category of the later manufacturing batch being a dense wiring method.

[0073] Exemplarily, when taking a photo of the wiring of the PCBA motherboard of the server to be inspected, the original silk-screen identification model can be first extracted from the first image taken to obtain the target model of the server PCBA motherboard. The image is then input into the wiring density classification model for classification to obtain the wiring arrangement category of the PCBA motherboard of the server to be inspected: dense wiring method or sparse wiring method. Then, if the wiring arrangement category is a dense wiring method, then in the image segmentation model corresponding to the target model, the first image segmentation model is called; if the wiring arrangement category is a sparse wiring method, in the image segmentation model corresponding to the target model, the second image segmentation model is called. It should be emphasized that a model can correspond to multiple image segmentation models, and a suitable or matching first image segmentation model or second image segmentation model is selected from these multiple image segmentation models using a dense wiring method or a sparse wiring method.

[0074] In the above embodiment, for the wiring of the PCBA mainboard of the server to be inspected with the same target model, when the wiring arrangement category is a dense wiring method, the first image segmentation model corresponding to the dense wiring method is called; when the wiring arrangement category is a sparse wiring method, the second image segmentation model corresponding to the sparse wiring method is called. Different wiring arrangement categories call different image segmentation models, which improves the pertinence and accuracy of image detection.

[0075] In some embodiments, see Figure 3 , if the wiring arrangement category indicates that the wiring situation belongs to a dense wiring mode, N is greater than 1, and each preset reference image is a partial correct image obtained by pre-dividing the correct wiring image of the server PCBA motherboard; wiring quality detection is performed according to N regional images and N preset reference images to obtain the overall wiring quality of the server PCBA motherboard, and the steps include:

[0076] S310 , performing image detection and comparison based on each regional image and a portion of correct images corresponding to each regional image, to obtain a regional wiring detection result for each regional image.

[0077] S320 , integrating the regional wiring detection results of each regional image to obtain the overall wiring quality status.

[0078] The partially correct image may be an image obtained by directly dividing the original image of the correctly wired server PCBA motherboard, or may be an image obtained by preprocessing the original image of the correctly wired server PCBA motherboard and then dividing it. The regional wiring detection result may be a detection result of the wiring quality in each regional image.

[0079] Specifically, feature extraction is performed on each partially correct image to obtain partially correct image wiring features; feature extraction is performed on each regional image to obtain regional image features; similarity calculation is performed between each partially correct image wiring feature and the corresponding regional image feature, and if the calculation result exceeds the similarity threshold, the regional image detection passes. If all N regional images pass the detection, the overall wiring quality of the server PCBA motherboard is determined to be qualified, otherwise the overall wiring quality is determined to be unqualified.

[0080] In the above embodiment, for the server PCBA mainboard wiring whose wiring arrangement category belongs to the dense wiring mode, image comparison detection is performed based on each regional image and the partial correct image corresponding to each regional image, and the regional wiring detection result of each regional image is obtained. Based on the integration of the regional wiring detection results of each regional image, the overall wiring quality is obtained, which improves the accuracy of the image detection results of the dense wiring mode.

[0081] In some embodiments, see Figure 4 If the wiring arrangement category indicates that the wiring situation belongs to a sparse wiring mode, N is equal to 1, and the preset reference image is the correct wiring image of the server PCBA motherboard. The wiring quality detection is performed based on N regional images and N preset reference images to obtain the overall wiring quality of the server PCBA motherboard, and the steps include:

[0082] S410: extract features from a region image to obtain sparse connection features.

[0083] S420: extract features from a correct wiring image to obtain correct wiring features.

[0084] S430: Compare the sparse wiring features with the correct wiring features to obtain the overall wiring quality.

[0085] Specifically, the sparse wiring features and the correct wiring features are compared, and the cosine similarity or Euclidean distance between the two features can be calculated. If the calculation result exceeds the predetermined similarity threshold, the regional image detection passes, and the overall wiring quality of the server PCBA motherboard is judged to be qualified, otherwise it is judged to be unqualified.

[0086] In the above embodiment, for the server PCBA mainboard wiring whose wiring arrangement category belongs to the sparse wiring mode, sparse wiring features are obtained based on feature extraction of a regional image, correct wiring features are obtained based on feature extraction of a correct wiring image, and the overall wiring quality is obtained based on comparison of the sparse wiring features and the correct wiring features, thereby improving the accuracy of the sparse wiring mode image detection results.

[0087] In some embodiments, obtaining a wiring image of a server PCBA mainboard may include: obtaining an orientation wiring image of the server PCBA mainboard at a preset shooting angle; the preset reference image is obtained by photographing a correctly wired server PCBA mainboard at a preset shooting angle in advance.

[0088] Among them, the preset shooting angle can be determined according to factors such as the number of components on any server PCBA mainboard, the density of wiring arrangement, etc., and the image detection of the server PCBA mainboard wiring can be performed by obtaining the azimuth wiring image from these shooting angles.

[0089] Specifically, it is possible to first formulate an image detection strategy based on the number of components of the server PCBA motherboard, the density of the wiring arrangement, etc., such as the shooting angle, whether to use one image or multiple images for image recognition, etc.; then place the correctly wired server chassis in the predetermined area of ​​the production line, and use the camera 102 to shoot the image at the preset shooting angle; finally, store the shot image in the computer device 101 as a preset reference image, or the shot image may be pre-processed and then stored in the computer device 101 as a preset reference image. The angle and orientation information of the shot image may also be stored in the computer device 101. When it is necessary to detect the wiring condition of the PCBA motherboard of the target model and wiring arrangement category, after the server chassis arrives at the predetermined area, the camera 102 shoots an image of the chassis from the preset shooting angle stored in the computer device 101.

[0090] In the above embodiment, a sample of a correctly wired server PCBA motherboard is photographed based on a preset shooting angle, and an image is obtained as a preset reference image. Furthermore, a sample of a server PCBA motherboard to be inspected for wiring is photographed based on a preset shooting angle, and the obtained image is compared with the preset reference image at the corresponding angle to obtain the overall wiring quality, thereby providing reliable image data for inspecting the wiring quality of the server PCBA motherboard using image comparison.

[0091] In some embodiments, the method may further include: if the overall wiring quality indicates that there is an abnormal wiring area, displaying an abnormal area mark on the wiring image.

[0092] The abnormal area mark is used to indicate the location of the abnormal wiring area. The abnormal wiring may be caused by wrong connection, missing connection or loose connection of the connection line, which may cause abnormal server function.

[0093] In some examples, if the wiring arrangement is a sparse wiring method, a wiring area image is compared with a corresponding preset reference image. If the comparison results are different, the difference is the wiring abnormality area, and the abnormal area mark is made at the corresponding position on the wiring image. In some other examples, if the wiring arrangement is a dense wiring method, multiple wiring area images are compared with corresponding multiple preset reference images respectively. If the comparison results of any preset image are different, the difference is the wiring abnormality area, and the abnormal area mark is made at the corresponding position on the wiring image.

[0094] For some more examples, see Figure 5After taking a wiring image of the server PCBA motherboard, the image is analyzed to obtain the motherboard model and wiring arrangement category, and the target image segmentation model is called to extract features according to the motherboard model and wiring arrangement category; further, the detection result is obtained after analysis and comparison with the preset reference image features. If there is no abnormality in the detection result, the detection passes; if there is a wiring abnormality in the detection result, an abnormal information notification can be displayed on the display screen of the computer device 101, and the speaker of the computer device 101 can emit a warning sound. After correcting the abnormal features, the server PCBA motherboard wiring image is re-taken, and the detection is performed again according to the above process until the detection passes.

[0095] In the above embodiment, based on the abnormal wiring area existing in the overall wiring quality situation, the abnormal area mark is displayed on the wiring image, and the occurrence of the abnormality can be warned through the computer display and speaker, which helps to manually locate the wiring abnormality quickly and correct and re-detect it, thereby improving the work efficiency of PCBA motherboard wiring quality detection.

[0096] In some embodiments, see Figure 6 , determine the target model and wiring arrangement category of the server PCBA motherboard in the following ways:

[0097] S610: Before the server chassis starts wiring, the server PCBA mainboard is photographed to obtain an initial image of the server PCBA mainboard; model recognition is performed based on the initial image to obtain a target model of the server PCBA mainboard.

[0098] The initial image may include a server PCBA motherboard, soldered or installed components, and original silk screen printing, and sometimes some logos pasted on.

[0099] Specifically, an identification code that can identify the motherboard model can be pasted at a certain position on the motherboard, and the identification code can be identified on the initial image of the server PCBA motherboard according to the position, shape characteristics, etc., and then the target model of the server PCBA motherboard can be obtained. Alternatively, after taking an image of the server PCBA motherboard, the target model can be identified by the original silk-screen identification model on the server PCBA motherboard. Alternatively, after taking a wiring image of the server PCBA motherboard, the target model of the server PCBA motherboard can be identified by the color and appearance size of the motherboard, the characteristics of related components, the layout of components, etc.

[0100] S620: After the server chassis is wired, the wiring density is identified based on the wiring image to obtain the wiring arrangement category of the server PCBA mainboard.

[0101] Specifically, after the server chassis is wired, the camera 102 is used to capture a wiring image, and the wiring image is input into a wiring density classification model for classification to obtain a wiring arrangement category of the PCBA mainboard of the server to be tested: dense wiring or sparse wiring.

[0102] In the above embodiment, based on the recognition of the server PCBA mainboard image before wiring, the target model of the server PCBA mainboard is obtained, and based on the recognition of the server PCBA mainboard image after wiring, the wiring arrangement category of the server PCBA mainboard is obtained. The combination of the target model and wiring arrangement category of the PCBA mainboard can determine the correct preset reference image for the wiring quality using image comparison detection.

[0103] In some embodiments, see Figure 7 , a wiring quality detection device 700 for a server PCBA motherboard, comprising:

[0104] The information acquisition module 701 is used to acquire the wiring image of the server PCBA mainboard, as well as the target model and wiring arrangement category of the server PCBA mainboard; wherein the wiring arrangement category is used to characterize the wiring conditions between the server PCBA mainboard and the functional components in the server chassis;

[0105] The segmentation model calling module 702 is used to call the target image segmentation model according to the wiring arrangement category and the target model, and obtain N preset reference images corresponding to the target model; wherein the value of N is greater than or equal to 1;

[0106] The image segmentation and extraction module 703 is used to segment and extract the wiring image using the target image segmentation model to obtain N regional images; wherein the regional images correspond to the preset reference images one by one;

[0107] The wiring quality detection module 704 is used to perform wiring quality detection based on N regional images and N preset reference images to obtain the overall wiring quality of the server PCBA motherboard.

[0108] In some embodiments, the wiring arrangement category includes a dense wiring method and a sparse wiring method, and the segmentation model calling module 702 also includes a function for calling a first image segmentation model corresponding to the dense wiring method in the image segmentation model corresponding to the target model if the wiring arrangement category is a dense wiring method; or, if the wiring arrangement category is a sparse wiring method, calling a second image segmentation model corresponding to the sparse wiring method in the image segmentation model corresponding to the target model.

[0109] In some embodiments, if the wiring arrangement category indicates that the wiring situation belongs to a dense wiring method, N is greater than 1, and each preset reference image is a partial correct image obtained by pre-dividing the correct wiring image of the server PCBA motherboard. The wiring quality detection module 704 is also used to perform image detection and comparison based on each regional image and the partial correct image corresponding to each regional image to obtain the regional wiring detection result of each regional image; the regional wiring detection results of each regional image are integrated to obtain the overall wiring quality situation.

[0110] In some embodiments, if the wiring arrangement category indicates that the wiring situation belongs to a sparse wiring mode, N is equal to 1, and the preset reference image is the correct wiring image of the server PCBA motherboard. The wiring quality detection module 704 is also used to extract features from a regional image to obtain sparse wiring features; extract features from a correct wiring image to obtain correct wiring features; and compare the sparse wiring features with the correct wiring features to obtain the overall wiring quality.

[0111] In some embodiments, the server PCBA mainboard wiring quality detection device 700 further includes a server PCBA mainboard wiring image acquisition module for acquiring an azimuth wiring image of the server PCBA mainboard at a preset shooting angle.

[0112] In some embodiments, the wiring quality detection device 700 of the server PCBA mainboard also includes an abnormal area marking module, which is used to display an abnormal area mark on the wiring image if the overall wiring quality indicates that there is a wiring abnormal area; wherein the abnormal area mark is used to indicate the location of the wiring abnormal area.

[0113] In some embodiments, the wiring quality detection device 700 for the server PCBA mainboard further includes a target model acquisition module and a wiring arrangement category acquisition module:

[0114] The target model acquisition module is used to photograph the server PCBA mainboard before the server chassis starts wiring to obtain an initial image of the server PCBA mainboard; perform model recognition based on the initial image to obtain the target model of the server PCBA mainboard;

[0115] The wiring arrangement category acquisition module is used to identify the wiring density based on the wiring image after the server chassis is wired, and obtain the wiring arrangement category of the server PCBA mainboard.

[0116] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0117] In this embodiment, a wiring quality detection device for a server PCBA motherboard is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0118] See also Figure 8 , Figure 8 is a schematic diagram of the structure of a computer device provided in an embodiment of the present application, such as Figure 8 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 8 A processor 10 is taken as an example.

[0119] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0120] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0121] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0122] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0123] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 8 The example of connecting through bus is taken in the following.

[0124] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0125] The embodiment of the present application also provides a computer-readable storage medium. The above method according to the embodiment of the present application can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0126] The embodiment of the present application provides a computer program product, which includes computer instructions, which are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method of any embodiment of the present application.

[0127] Although the embodiments of the present application are described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations are all within the scope defined by the appended claims.

[0128] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0129] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0130] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0131] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0132] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0133] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0134] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device 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, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0135] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0136] The above is only the embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

[0137] Although the embodiments of the present application have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for detecting the wiring quality of a server PCBA motherboard, characterized in that: The method comprises: Obtaining a wiring image of a server PCBA mainboard, as well as a target model and wiring arrangement category of the server PCBA mainboard; wherein the wiring arrangement category is used to characterize the wiring conditions between the server PCBA mainboard and functional components in a server chassis; Calling a target image segmentation model according to the wiring arrangement category and the target model, and obtaining N preset reference images corresponding to the target model; wherein the value of N is greater than or equal to 1; Using the target image segmentation model to segment and extract the wiring image, and obtain N regional images; wherein the regional images correspond one to one with the preset reference images; Wiring quality detection is performed according to the N regional images and the N preset reference images to obtain the overall wiring quality of the server PCBA mainboard.

2. The method according to claim 1, characterized in that The wiring arrangement category includes a dense wiring mode and a sparse wiring mode; and calling the target image segmentation model according to the wiring arrangement category and the target model includes: If the wiring arrangement category is a dense wiring mode, in the image segmentation model corresponding to the target model, a first image segmentation model corresponding to the dense wiring mode is called; If the wiring arrangement category is a sparse wiring mode, in the image segmentation model corresponding to the target model, a second image segmentation model corresponding to the sparse wiring mode is called.

3. The method according to claim 2, characterized in that If the wiring arrangement category indicates that the wiring situation belongs to a dense wiring mode, the N is greater than 1, and each of the preset reference images is a partial correct image obtained by pre-dividing the correct wiring image of the server PCBA mainboard; the wiring quality detection is performed according to the N regional images and the N preset reference images to obtain the overall wiring quality of the server PCBA mainboard, including: Performing image detection and comparison based on each regional image and a portion of correct images corresponding to each regional image to obtain a regional wiring detection result of each regional image; The overall wiring quality is obtained by integrating the regional wiring detection results of each regional image.

4. The method according to claim 2, characterized in that: If the wiring arrangement category indicates that the wiring situation belongs to a sparse wiring mode, N is equal to 1, and the preset reference image is a correct wiring image of the server PCBA mainboard; the wiring quality detection is performed according to the N regional images and the N preset reference images to obtain the overall wiring quality of the server PCBA mainboard, including: Extracting features from an image of the region to obtain sparse wiring features; Extracting features from one of the correct wiring images to obtain correct wiring features; The overall wiring quality is obtained by comparing the sparse wiring features with the correct wiring features.

5. The method according to any one of claims 1 to 4, characterized in that: The obtaining of the wiring image of the server PCBA mainboard includes: An orientation wiring image of the server PCBA mainboard at a preset shooting angle is obtained; the preset reference image is obtained by photographing the correctly wired server PCBA mainboard at the preset shooting angle in advance.

6. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: If the overall wiring quality indicates that there is an abnormal wiring area, an abnormal area mark is displayed on the wiring image; wherein the abnormal area mark is used to indicate the location of the abnormal wiring area.

7. The method according to any one of claims 1 to 4, characterized in that: Determine the target model and wiring arrangement category of the server PCBA motherboard in the following way: Before the server chassis starts wiring, the server PCBA mainboard is photographed to obtain an initial image of the server PCBA mainboard; model recognition is performed based on the initial image to obtain a target model of the server PCBA mainboard; After the server chassis is wired, the wiring density is identified based on the wiring image to obtain the wiring arrangement category of the server PCBA mainboard.

8. A wiring quality detection device for a server PCBA motherboard, characterized in that: The device comprises: A wiring image acquisition module, used to acquire a wiring image of a server PCBA mainboard, as well as a target model and wiring arrangement category of the server PCBA mainboard; wherein the wiring arrangement category is used to characterize the wiring condition between the server PCBA mainboard and the functional components in the server chassis; A segmentation model calling module, used to call a target image segmentation model according to the wiring arrangement category and the target model, and obtain N preset reference images corresponding to the target model; wherein the value of N is greater than or equal to 1; An image segmentation and extraction module, used to segment and extract the wiring image using the target image segmentation model to obtain N regional images; wherein the regional images correspond one-to-one to the preset reference images; The wiring quality detection module is used to perform wiring quality detection according to the N regional images and the N preset reference images to obtain the overall wiring quality of the server PCBA mainboard.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 7.

Images