Integrated electronic product accessories parameter testing system based on computer automatic analysis

Abstract

The present invention relates to the field of parameter testing technology, and more specifically to an integrated electronic product accessory parameter testing system based on computer automatic analysis. The system, through the mutual cooperation between multiple modules, can implement the following steps: obtaining a target infrared image corresponding to the integrated electronic product to be tested, and extracting target accessory areas representing different target accessories; clustering the target accessory areas; determining the initial radiation anomaly index corresponding to each target accessory area, and screening out abnormal candidate accessory areas; determining the own heat source anomaly index and other heat source influence indexes corresponding to each abnormal candidate accessory area; screening out real abnormal accessory areas; and performing parameter testing on the accessories represented by each real abnormal accessory area. The present invention screens out accessories with abnormal operation represented by the real abnormal accessory area, and excludes normal accessories that do not need to be parameter tested, thereby improving the efficiency of parameter testing of integrated electronic product accessories.

Description

Technical Field

[0001] The present invention relates to the technical field of parameter testing, and in particular to an integrated electronic product accessory parameter testing system based on computer automatic analysis. Background Art

[0002] With the rapid advancement of technology, integrated electronic products are becoming increasingly common in everyday life, such as smartphones and home appliances. Therefore, parameter testing of components within these products is crucial. Components within these products often generate heat at their center during operation, such as resistors and capacitors. Currently, manual testing is commonly used to perform parameter testing on these components.

[0003] However, when manually testing the parameters of components in integrated electronic products, the following technical problems often occur:

[0004] When performing parameter testing on accessories in integrated electronic products manually, since each parameter of each accessory in the integrated electronic product often needs to be tested manually, the efficiency of the parameter testing is often poor. Summary of the Invention

[0005] In order to solve the technical problem of low efficiency in parameter testing of integrated electronic product accessories, the present invention proposes an integrated electronic product accessory parameter testing system based on computer automatic analysis.

[0006] In a first aspect, the present invention provides an integrated electronic product accessory parameter testing system based on computer automatic analysis, the system comprising:

[0007] An image acquisition and extraction module is used to acquire a target infrared image corresponding to the integrated electronic product to be inspected, and to extract target accessory areas representing different target accessories from the target infrared image;

[0008] A region clustering module is used to cluster all target accessory regions according to their corresponding major axis distances and minor axis distances to obtain target clusters;

[0009] a determination and screening module, configured to determine an initial radiation anomaly index corresponding to each target accessory region based on a difference in grayscale distribution change between each target accessory region and other target accessory regions in its target cluster, and to screen out abnormal candidate accessory regions from all target accessory regions based on all initial radiation anomaly indicators;

[0010] A self-heat source anomaly index determination module is used to determine the self-heat source anomaly index corresponding to each abnormal candidate accessory region based on the grayscale disorder degree corresponding to each abnormal candidate accessory region and the grayscale difference between the centroid of each abnormal candidate accessory region and the edge pixels of the corresponding preset windows of different sizes;

[0011] Other heat source impact index determination module, used to determine other heat source impact index corresponding to each abnormal candidate accessory area based on the distance and high temperature difference between each abnormal candidate accessory area and other abnormal candidate accessory areas;

[0012] A region screening module is used to screen out the real abnormal accessory regions from all abnormal candidate accessory regions based on their own heat source abnormality indicators and other heat source impact indicators;

[0013] The parameter testing module is used to perform parameter testing on the accessories represented by each real abnormal accessory area.

[0014] In combination with the first aspect above, in a possible implementation, extracting target accessory regions representing different target accessories from the target infrared image includes:

[0015] Acquire a target RGB image corresponding to the integrated electronic product to be inspected;

[0016] Filtering reference accessory regions representing different target accessories from the target RGB image;

[0017] According to the correspondence between the target RGB image and the target infrared image, an accessory region corresponding to each reference accessory region is screened out from the target infrared image as a target accessory region.

[0018] In combination with the first aspect above, in a possible implementation, clustering all target accessory regions according to the major axis distances and minor axis distances corresponding to all target accessory regions to obtain target clusters includes:

[0019] The distance between each two edge pixels on each target accessory area is determined as a reference distance, and a reference distance set corresponding to each target accessory area is obtained;

[0020] Determine the maximum value in the reference distance set corresponding to each target accessory area as the long axis distance corresponding to each target accessory area;

[0021] Determine the minimum value in the reference distance set corresponding to each target accessory area as the short-axis distance corresponding to each target accessory area;

[0022] The long axis distance and the short axis distance corresponding to each target accessory area are used to form a binary vector corresponding to each target accessory area;

[0023] The target accessory areas whose Euclidean distance between corresponding binary vectors is less than a preset distance threshold are divided into the same cluster, and each obtained cluster is determined as the target cluster.

[0024] In conjunction with the first aspect above, in one possible implementation, determining the initial radiation anomaly indicator corresponding to each target accessory region based on the difference in grayscale distribution change between each target accessory region and other target accessory regions in its target cluster includes:

[0025] The variance of the grayscale values ​​corresponding to all pixels in each target accessory area is determined as the grayscale disorder degree corresponding to each target accessory area;

[0026] The mean of the grayscale values ​​corresponding to all pixels in each target accessory area is determined as the grayscale representative factor corresponding to each target accessory area;

[0027] Determine the grayscale distribution eigenvalue corresponding to each target accessory area based on the grayscale disorder degree and grayscale representative factor corresponding to each target accessory area, wherein the grayscale disorder degree is positively correlated with the grayscale distribution eigenvalue, and the grayscale representative factor is negatively correlated with the grayscale distribution eigenvalue;

[0028] The initial radiation anomaly index corresponding to each target accessory region is determined according to the difference between the grayscale distribution eigenvalue corresponding to each target accessory region and the grayscale distribution eigenvalues ​​corresponding to other target accessory regions in the target cluster to which it belongs.

[0029] In conjunction with the first aspect above, in one possible implementation, determining the initial radiation anomaly index corresponding to each target accessory region based on a difference between the grayscale distribution eigenvalue corresponding to each target accessory region and the grayscale distribution eigenvalues ​​corresponding to other target accessory regions in the target cluster to which it belongs includes:

[0030] The average of the grayscale values ​​corresponding to all pixels in the preset rectangular window corresponding to each pixel in each target accessory area is determined as the overall grayscale factor corresponding to each pixel in each target accessory area;

[0031] The maximum value of the overall grayscale factors corresponding to all pixels in each target accessory area is determined as the overall representative grayscale index corresponding to each target accessory area;

[0032] The initial radiation anomaly index corresponding to each target accessory area is determined based on the absolute value of the difference between the grayscale distribution eigenvalue corresponding to each target accessory area and the grayscale distribution eigenvalues ​​corresponding to other target accessory areas in the target cluster to which it belongs, as well as the difference between the overall representative grayscale index corresponding to each target accessory area and the overall representative grayscale index corresponding to other target accessory areas in the target cluster to which it belongs.

[0033] In conjunction with the first aspect above, in a possible implementation, the formula corresponding to the initial radiation anomaly index corresponding to the target accessory area is:

[0034] ;in, It is The target cluster The initial radiation anomaly index corresponding to the target accessory area; is the sequence number of the target cluster; and It is The sequence numbers of different target accessory areas in a target cluster; is the normalization function; It is The number of target accessory regions in a target cluster; It is the absolute value function; It is The target cluster The grayscale confusion degree corresponding to each target accessory area; It is The target cluster The grayscale confusion degree corresponding to each target accessory area; It is The target cluster The grayscale representative factor corresponding to the target accessory area; It is The target cluster The grayscale representative factor corresponding to the target accessory area; It is The target cluster Grayscale distribution eigenvalues ​​corresponding to the target accessory area; It is The target cluster Grayscale distribution eigenvalues ​​corresponding to the target accessory area; It is The target cluster The overall representative grayscale index corresponding to the target accessory area; It is The target cluster The overall representative grayscale index corresponding to the target accessory area.

[0035] In combination with the first aspect above, in a possible implementation, screening out abnormal candidate accessory areas from all target accessory areas based on all initial radiation anomaly indicators includes:

[0036] If the initial radiation anomaly index corresponding to the target accessory area is greater than a preset initial anomaly threshold, the target accessory area is determined as an abnormal candidate accessory area.

[0037] In combination with the first aspect above, in a possible implementation, the formula corresponding to the abnormal heat source abnormality index of the abnormal candidate accessory area is:

[0038] ;in, It is The abnormal heat source abnormality index corresponding to the abnormal candidate accessory area; is the sequence number of the abnormal candidate accessory area; It is The grayscale disorder degree corresponding to the abnormal candidate accessory area is equal to The variance of the grayscale values ​​corresponding to all pixels in the abnormal candidate accessory area; is the number of preset windows of different sizes; It is the serial number of the preset windows of different sizes; is a natural exponential function; It is The centroid of the abnormal candidate accessory area and the corresponding The maximum value of the Euclidean distances between the edge pixels of preset windows of different sizes; is the normalization function; It is Gray value corresponding to the centroid of each abnormal candidate accessory area; It is The centroid of the abnormal candidate accessory area corresponds to the The mean of the grayscale values ​​corresponding to all edge pixels of preset windows of different sizes.

[0039] In combination with the first aspect above, in a possible implementation, the formula corresponding to other heat source impact indicators corresponding to the abnormal candidate accessory area is:

[0040] ;in, It is Other heat source impact indicators corresponding to the abnormal candidate accessory areas; and is the sequence number of different abnormal candidate accessory areas; is the number of abnormal candidate accessory regions; is a natural exponential function; It is The high temperature point in the abnormal candidate accessory area is The Euclidean distance between the high-temperature points in the abnormal candidate accessory area; the high-temperature point in the abnormal candidate accessory area is the pixel with the largest overall grayscale factor in the abnormal candidate accessory area; is the normalization function; It is The overall representative grayscale index corresponding to the abnormal candidate accessory area is used to represent the Local high temperature conditions in the abnormal candidate accessory area; It is The overall representative grayscale index corresponding to the abnormal candidate accessory area is used to represent the The local high temperature situation of the abnormal candidate accessory area.

[0041] In conjunction with the first aspect above, in one possible implementation, screening out the truly abnormal accessory regions from all abnormal candidate accessory regions based on the corresponding inherent heat source abnormality indicators and other heat source impact indicators of all abnormal candidate accessory regions includes:

[0042] According to the own heat source abnormality index and other heat source impact indexes corresponding to each abnormal candidate accessory area, the target abnormality index corresponding to each abnormal candidate accessory area is determined, wherein the own heat source abnormality index is positively correlated with the target abnormality index, and the other heat source impact index is negatively correlated with the target abnormality index;

[0043] If the target abnormality index corresponding to the abnormal candidate accessory area is greater than the preset target abnormality threshold, the abnormal candidate accessory area is determined to be a real abnormal accessory area.

[0044] In a second aspect, the present invention provides a method for testing parameters of integrated electronic product accessories based on computer automatic analysis, implemented by an integrated electronic product accessory parameter testing system based on computer automatic analysis, the method comprising:

[0045] Acquire a target infrared image corresponding to the integrated electronic product to be inspected, and extract target accessory regions representing different target accessories from the target infrared image;

[0046] All target accessory regions are clustered according to their corresponding major axis distances and minor axis distances to obtain target clusters;

[0047] Determine the initial radiation anomaly index corresponding to each target accessory region based on the difference in grayscale distribution changes between each target accessory region and other target accessory regions in its target cluster, and screen out abnormal candidate accessory regions from all target accessory regions based on all initial radiation anomaly indices;

[0048] Determine the heat source anomaly index corresponding to each abnormal candidate accessory region based on the grayscale disorder degree corresponding to each abnormal candidate accessory region and the grayscale difference between the centroid of each abnormal candidate accessory region and the edge pixels of the corresponding preset windows of different sizes;

[0049] Determine other heat source impact indicators corresponding to each abnormal candidate accessory area based on the distance and high temperature difference between each abnormal candidate accessory area and other abnormal candidate accessory areas;

[0050] According to the corresponding heat source abnormality indicators and other heat source impact indicators of all abnormal candidate accessory areas, the real abnormal accessory areas are screened out from all abnormal candidate accessory areas;

[0051] Parameter tests are performed on the accessories represented by each real abnormal accessory region.

[0052] In a third aspect, a server is provided, comprising a memory and a processor. The memory is configured to store executable program code, and the processor is configured to retrieve and execute the executable program code from the memory, so that the device executes the above-mentioned integrated electronic product accessory parameter testing method based on computer automatic analysis.

[0053] In a fourth aspect, a computer program product is provided, which includes: computer program code, which, when running on a computer, enables the computer to execute the above-mentioned integrated electronic product accessory parameter testing method based on computer automatic analysis.

[0054] In a fifth aspect, a computer-readable storage medium is provided, which stores a computer program code. When the computer program code runs on a computer, the computer executes the above-mentioned integrated electronic product accessory parameter testing method based on computer automatic analysis.

[0055] The present invention has the following beneficial effects:

[0056] The integrated electronic product accessory parameter testing system of the present invention, which is based on computer automatic analysis, screens out accessories with abnormal operation represented by the real abnormal accessory area, excludes normal accessories that do not need to be parameter tested, and solves the technical problem of low efficiency in parameter testing of integrated electronic product accessories, thereby improving the efficiency of parameter testing of integrated electronic product accessories. Compared with manual parameter testing of accessories in integrated electronic products, the present invention comprehensively considers multiple indicators related to abnormal operation of accessories in the process of parameter testing of accessories in integrated electronic products, such as initial radiation abnormality indicators, self-heat source abnormality indicators and other heat source influence indicators, thereby screening out abnormal accessories that need to be parameter tested represented by the real abnormal accessory area, reducing the time wasted due to parameter testing of normal accessories to a certain extent, thereby improving the efficiency of parameter testing of integrated electronic product accessories. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0058] Figure 1 Schematic diagram of the structure of the integrated electronic product accessories parameter testing system based on computer automatic analysis of the present invention;

[0059] Figure 2 Schematic diagram of the flow of the integrated electronic product accessory parameter testing method based on computer automatic analysis of the present invention;

[0060] Figure 3 The figure is a structural diagram of a computer device of the present invention. DETAILED DESCRIPTION

[0061] To further illustrate the technical means and effects employed by the present invention to achieve its intended objectives, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail the specific implementations, structures, features, and effects of the technical solutions proposed by the present invention. In the following description, references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0062] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0063] refer to Figure 1 , shows a schematic structural diagram of an integrated electronic product accessory parameter testing system based on computer automatic analysis according to the present invention. The integrated electronic product accessory parameter testing system based on computer automatic analysis includes:

[0064] The image acquisition and extraction module 101 is used to acquire a target infrared image corresponding to the integrated electronic product to be inspected, and extract target accessory regions representing different target accessories from the target infrared image.

[0065] The integrated electronic product to be inspected may be an integrated electronic product for which accessory parameter testing is to be performed. An integrated electronic product may be an electronic device that integrates multiple electronic components and systems into a compact module or product. The electronic components in an integrated electronic product are also called accessories in an integrated electronic product. These products are generally characterized by smaller size, lower power consumption, higher integration, and higher efficiency. Integrated electronic products are widely used in consumer electronics, communications equipment, automotive electronics, industrial control, and other fields. The target infrared image may be an infrared image of the integrated electronic product to be inspected. The electronic components on the surface of the integrated electronic product to be inspected may be arranged in a single row. The target accessory may be an electronic component that exhibits central heating during operation. For example, the target accessory may be, but is not limited to, a resistor and a capacitor. The target accessory area may be the area where the target accessory is mapped into the target infrared image.

[0066] As an example, this step may include the following steps:

[0067] The first step is to obtain the target infrared image and target RGB image corresponding to the above-mentioned integrated electronic product to be detected.

[0068] The target RGB image can be an RGB (Red, Green, Blue) image of the surface of the integrated electronic product to be inspected. The target infrared image and the target RGB image can be of the same size, and the same position within them can represent the same component.

[0069] For example, a camera can capture an RGB image of the surface of the integrated electronic product to be inspected before operation as the target RGB image, and an infrared thermal imager can capture an infrared image of the integrated electronic product to be inspected at the current moment during operation as the target infrared image. During image acquisition, the camera and infrared thermal imager can be placed in the same position and have the same shooting angle. The current moment can be the current time during the operation of the integrated electronic product to be inspected.

[0070] In the second step, reference accessory regions representing different target accessories are screened out from the above target RGB image.

[0071] The reference accessory region may be a region where the target accessory is mapped to the target RGB image.

[0072] For example, a region representing each target accessory can be screened out from the target RGB image through threshold segmentation or neural network recognition technology as a reference accessory region.

[0073] In the third step, based on the correspondence between the target RGB image and the target infrared image, the accessory region corresponding to each reference accessory region is screened out from the target infrared image as the target accessory region.

[0074] For example, an area having the same position as the reference accessory area may be screened out from the target infrared image as the target accessory area.

[0075] Optionally, regions representing different target accessories may be directly extracted from the target infrared image through threshold segmentation or neural network recognition technology as target accessory regions.

[0076] It should be noted that when electronic products are running, part of the electrical energy will be scattered as heat radiation due to the current passing through the resistor. This may cause the edges of the areas representing the accessories of the electronic products in the infrared image to be blurred and the boundaries to be unclear. At this time, directly extracting the accessory areas representing different accessories from the infrared image may lead to inaccurate edge division of the accessory areas. Therefore, the accessory areas are indirectly extracted through the RGB image, thereby improving the accuracy of identifying the target accessory areas.

[0077] The region clustering module 102 is configured to cluster all target accessory regions according to the major axis distances and minor axis distances corresponding to all target accessory regions to obtain target clusters.

[0078] As an example, this step may include the following steps:

[0079] In the first step, the distance between every two edge pixels on each target accessory area is determined as the reference distance, and a reference distance set corresponding to each target accessory area is obtained.

[0080] The reference distance set corresponding to the target accessory area may include: the distances between all edge pixels on the target accessory area.

[0081] In the second step, the maximum value in the reference distance set corresponding to each target accessory area is determined as the long axis distance corresponding to each target accessory area.

[0082] In the third step, the minimum value in the reference distance set corresponding to each target accessory area is determined as the short-axis distance corresponding to each target accessory area.

[0083] In the fourth step, the major axis distance and minor axis distance corresponding to each target accessory area are used to form a binary vector corresponding to each target accessory area.

[0084] The major axis distance and the minor axis distance may be elements of a binary vector, and the major axis distance may be the first element of the binary vector, and the minor axis distance may be the second element of the binary vector.

[0085] In the fifth step, the target accessory areas whose Euclidean distance between the corresponding binary vectors is less than a preset distance threshold are divided into the same cluster, and each obtained cluster is determined as the target cluster.

[0086] The binary vectors corresponding to the target accessory regions in the target cluster are relatively similar. The preset distance threshold may be a preset threshold for clustering, which may be 1.

[0087] It's important to note that integrated electronic products often incorporate numerous components, and these components often exist in isolation. For example, multiple resistors are often present in an integrated electronic product. Regions containing the same component often have similar major and minor axis distances. Therefore, the target component regions within the same target cluster often represent the same component.

[0088] The determination and screening module 103 is used to determine the initial radiation anomaly index corresponding to each target accessory area according to the difference in grayscale distribution changes between each target accessory area and other target accessory areas in the target cluster to which it belongs, and based on all the initial radiation anomaly indicators, screen out abnormal candidate accessory areas from all target accessory areas.

[0089] As an example, this step may include the following steps:

[0090] In the first step, the variance of the grayscale values ​​corresponding to all pixels in each target accessory area is determined as the grayscale chaos degree corresponding to each target accessory area.

[0091] In the second step, the mean of the grayscale values ​​corresponding to all pixels in each target accessory area is determined as the grayscale representative factor corresponding to each target accessory area.

[0092] In the third step, the grayscale distribution characteristic value corresponding to each target accessory area is determined according to the grayscale disorder degree and grayscale representative factor corresponding to each target accessory area.

[0093] The grayscale disorder degree may be positively correlated with the grayscale distribution characteristic value, and the grayscale representative factor may be negatively correlated with the grayscale distribution characteristic value.

[0094] The fourth step, based on the difference between the grayscale distribution characteristic value corresponding to each target accessory region and the grayscale distribution characteristic values ​​corresponding to other target accessory regions in the target cluster to which it belongs, determines the initial radiation anomaly index corresponding to each target accessory region, which may include the following sub-steps:

[0095] In the first sub-step, the average of the grayscale values ​​corresponding to all pixels in a preset rectangular window corresponding to each pixel in each target accessory area is determined as the overall grayscale factor corresponding to each pixel in each target accessory area.

[0096] The preset rectangular window may be a pre-set rectangular area. For example, the preset rectangular window may be a 3×3 window. The pixel point may be located at the center of its corresponding preset rectangular window.

[0097] In the second sub-step, the maximum value of the overall grayscale factors corresponding to all pixels in each target accessory area is determined as the overall representative grayscale index corresponding to each target accessory area.

[0098] In the third sub-step, the initial radiation anomaly index corresponding to each target accessory area is determined based on the absolute value of the difference between the grayscale distribution characteristic value corresponding to each target accessory area and the grayscale distribution characteristic value corresponding to other target accessory areas in the target cluster to which it belongs, and the difference between the overall representative grayscale index corresponding to each target accessory area and the overall representative grayscale index corresponding to other target accessory areas in the target cluster to which it belongs.

[0099] For example, the formula for determining the initial radiation anomaly index corresponding to the target accessory area can be:

[0100] ;in, It is The target cluster The initial radiation anomaly indicators corresponding to the target accessory areas. is the sequence number of the target cluster. and It is The sequence numbers of different target accessory areas in a target cluster. is the normalization function. It is The number of target accessory regions in a target cluster. It is the absolute value function. It is The target cluster The grayscale chaos degree corresponding to the target accessory area. It is The target cluster The grayscale chaos degree corresponding to the target accessory area. It is The target cluster The grayscale corresponding to each target accessory area represents the factor. It is The target cluster The grayscale corresponding to each target accessory area represents the factor. It is The target cluster The grayscale distribution eigenvalues ​​corresponding to the target accessory area. It is The target cluster The grayscale distribution eigenvalues ​​corresponding to the target accessory area. It is The target cluster The overall representative grayscale index corresponding to the target accessory area. It is The target cluster The overall representative grayscale index corresponding to the target accessory area.

[0101] It should be noted that, in actual situations, during operation, the thermal radiation emitted by normal accessories of the same type is often similar, and their grayscale expressions in infrared images are often relatively similar. In addition, the embodiments of the present invention are mainly used to implement real-time abnormality monitoring of integrated electronic product accessories. During the real-time abnormality monitoring process, abnormal accessories are often discovered relatively promptly. Therefore, during the real-time abnormality monitoring process, the number of abnormal accessories that can be monitored each time is often small. Therefore, during the real-time abnormality monitoring process, if the thermal radiation emitted by a certain accessory is not similar to the thermal radiation emitted by most accessories of the same type, it often indicates that the accessory is likely to have a thermal abnormality, and it often indicates that parameter testing should be performed for subsequent maintenance. The smaller the time, the more likely it is that Target accessory area and The more similar the overall grayscale distribution is between the target accessory areas, the more likely it is that the The target accessory region represents the accessories and the The more similar the overall thermal radiation distribution is between the accessories represented by the target accessory area. The smaller the time, the more likely it is that Target accessory area and The more similar the overall maximum grayscale is between the target accessory regions, the more likely it is that the The target accessory region represents the accessories and the The more similar the local heat sources between the accessories represented by the target accessory regions are, the more similar the local heat sources between the accessories represented by the target accessory regions are. The larger the The more dissimilar the thermal radiation distribution and local heat source distribution between the accessories represented by the first target accessory area and most accessories of the same type are, the more likely it is that the The more likely the accessories represented by the target accessory area are to have thermal anomalies, the more likely the accessories are to have thermal anomalies. The more target accessory areas a component represents, the more likely it is that there is an operational abnormality.

[0102] In the fifth step, if the initial radiation anomaly index corresponding to the target accessory area is greater than the preset initial anomaly threshold, the target accessory area is determined as an abnormal candidate accessory area.

[0103] The preset initial abnormal threshold may be a pre-set threshold for roughly screening abnormal accessory regions, which may be 0.5. Abnormal candidate accessory regions are often real thermally abnormal accessory regions or normal accessory regions affected by abnormal thermal radiation from other abnormal accessories.

[0104] The self-heat source abnormality index determination module 104 is used to determine the self-heat source abnormality index corresponding to each abnormal candidate accessory area based on the grayscale confusion degree corresponding to each abnormal candidate accessory area and the grayscale difference between the centroid of each abnormal candidate accessory area and the edge pixels of the corresponding preset windows of different sizes.

[0105] The centroid of the abnormal candidate accessory region is the center of the abnormal candidate accessory region. The preset window can be a pre-set window of different sizes. For example, there can be four preset windows of different sizes: a 3×3 window, a 5×5 window, a 7×7 window, and a 9×9 window. The centroid can be located at the center of its corresponding preset window. The edge pixels of a preset window are the outermost pixels within the preset window.

[0106] As an example, the formula for determining the abnormal heat source index corresponding to the abnormal candidate accessory area can be:

[0107] ;in, It is The abnormal heat source abnormality index corresponding to the abnormal candidate accessory area. It is the sequence number of the abnormal candidate accessory area. It is The grayscale disorder degree corresponding to the abnormal candidate accessory area is equal to The variance of the grayscale values ​​corresponding to all pixels in the abnormal candidate accessory area. is the number of preset windows of different sizes. It is the sequence number of the preset windows of different sizes. is a natural exponential function. It is The centroid of the abnormal candidate accessory area and the corresponding The maximum value of the Euclidean distances between each edge pixel point of preset windows of different sizes. is the normalization function. It is The grayscale value corresponding to the centroid of the abnormal candidate accessory area. It is The centroid of the abnormal candidate accessory area corresponds to the The mean of the grayscale values ​​corresponding to all edge pixels of preset windows of different sizes.

[0108] It should be noted that in actual situations, due to abnormal heat generation during operation of abnormal accessories, the heat distribution is often relatively chaotic. The larger the The more chaotic the grayscale distribution of the abnormal candidate accessory area is, the more likely it is that the The more likely the accessories represented by the first abnormal candidate accessory area are to have abnormal heat distribution, the more likely the accessories are to have abnormal heat distribution. The more abnormal candidate accessory regions a component represents, the more likely it is that there is an operational abnormality. Can be used as When The smaller the time, the more likely it is that The smaller the size of the preset window of different sizes, the smaller the The smaller the distance between the centroid of the abnormal candidate accessory area and the edge pixel point that needs to be compared in grayscale. The larger the The higher the grayscale of the centroid of the abnormal candidate accessory area is, the higher the grayscale of the The grayscale of the edge pixels of the preset windows of different sizes often indicates the The heat represented by the centroid of the abnormal candidate accessory area is higher than the heat represented by the surrounding edge pixels. In actual situations, the target accessory is often heated at the center. When an abnormality occurs, the heat at the center of the component often increases suddenly. Therefore, the heat at the center of the component is often much higher than the surrounding heat. The larger the The higher the heat of the center of the accessory represented by the abnormal candidate accessory area is, the higher the heat is than the heat at a shorter distance from it, which often indicates that the The more abnormal candidate accessory regions represent, the more likely abnormal sudden increases in the heat of the accessory center will occur. The larger the The more likely the accessories represented by the first abnormal candidate accessory area are to have thermal anomalies, the more likely the accessories are to have thermal anomalies. The more abnormal candidate accessory regions a component represents, the more likely it is that the component is operating abnormally.

[0109] The other heat source impact index determination module 105 is used to determine other heat source impact indexes corresponding to each abnormal candidate accessory region according to the distance and high temperature difference between each abnormal candidate accessory region and other abnormal candidate accessory regions.

[0110] As an example, the formula for determining other heat source impact indicators corresponding to the abnormal candidate accessory area can be:

[0111] ;in, It is Other heat source impact indicators corresponding to the abnormal candidate accessory areas. and It is the sequence number of different abnormal candidate accessory areas. is the number of abnormal candidate accessory regions. is a natural exponential function. It is The high temperature point in the abnormal candidate accessory area is The Euclidean distance between the high-temperature points in the abnormal candidate accessory area. The high-temperature point in the abnormal candidate accessory area can be the pixel with the largest overall grayscale factor in the abnormal candidate accessory area. is the normalization function. It is The overall representative grayscale index corresponding to the abnormal candidate accessory area can be used to represent the The local high temperature situation of the abnormal candidate accessory area. It is The overall representative grayscale index corresponding to the abnormal candidate accessory area can be used to represent the The local high temperature situation of the abnormal candidate accessory area.

[0112] It should be noted that, in practice, heat is radiative. Therefore, when a normal component experiences thermal anomalies in surrounding components, the abnormal heat from the surrounding components often radiates to the normal component, potentially misidentifying it as an abnormal component. Therefore, quantifying the thermal impact of surrounding components can, to a certain extent, reduce the misidentification of truly abnormal components. yes When The smaller the time, the more likely it is that The high temperature area of ​​the component represented by the abnormal candidate accessory area is The smaller the distance between the high temperature areas of the components represented by the abnormal candidate parts areas, the smaller the distance between the high temperature areas of the components represented by the abnormal candidate parts areas. The more likely the part represented by the abnormal candidate accessory area is to be affected by the The thermal impact of the component is characterized by the abnormal candidate assembly area. The larger the The higher the local high temperature of the component represented by the first abnormal candidate accessory area is, the higher the The abnormal candidate accessory area represents the local high temperature of the component; it often indicates that the The parts represented by the abnormal candidate accessory regions, The more abnormal candidate parts are represented, the more likely they are to have thermal anomalies; The more likely the thermal anomaly of the component represented by the abnormal candidate accessory area is to radiate and affect the Therefore, when The larger the The thermal anomaly displayed by the component represented by the abnormal candidate accessory area is more likely to be caused by the thermal anomaly of the surrounding components.

[0113] The region screening module 106 is configured to screen out real abnormal accessory regions from all abnormal candidate accessory regions based on their own heat source abnormality indicators and other heat source impact indicators corresponding to all abnormal candidate accessory regions.

[0114] As an example, this step may include the following steps:

[0115] In the first step, the target abnormality index corresponding to each abnormal candidate accessory area is determined according to the own heat source abnormality index and other heat source influence indexes corresponding to each abnormal candidate accessory area.

[0116] Among them, the self-heat source abnormality index can be positively correlated with the target abnormality index, and the other heat source impact index can be negatively correlated with the target abnormality index.

[0117] For example, the formula for determining the target anomaly index corresponding to the abnormal candidate accessory area can be:

[0118] ;in, It is The target anomaly indicator corresponding to the abnormal candidate accessory area. It is the sequence number of the abnormal candidate accessory area. is the normalization function. It is The abnormal heat source abnormality index corresponding to the abnormal candidate accessory area. is a natural exponential function. It is Other heat source impact indicators corresponding to the abnormal candidate accessory areas.

[0119] It should be noted that when The larger the The more likely the accessories represented by the first abnormal candidate accessory area are to have thermal anomalies, the more likely the accessories are to have thermal anomalies. The more abnormal candidate accessory regions represent, the more likely the accessories are to operate abnormally. The larger the The thermal anomaly of the component represented by the abnormal candidate accessory area is more likely to be caused by the thermal anomaly of the surrounding components. The larger the The more likely the accessories represented by the first abnormal candidate accessory area are to have thermal anomalies, and the The more likely the thermal anomaly of the accessory represented by the first abnormal candidate accessory area is to be caused by itself, the more likely it is that the first The more likely the accessories represented by the first abnormal candidate accessory area are to have abnormal operation, the more likely it is that the first The accessories represented by the abnormal candidate accessory area are tested for parameters to facilitate subsequent maintenance.

[0120] In the second step, if the target abnormality index corresponding to the abnormal candidate accessory area is greater than the preset target abnormality threshold, the abnormal candidate accessory area is determined to be a real abnormal accessory area.

[0121] The preset target abnormality threshold may be a preset threshold for screening real abnormal accessory areas, which may be 0.7.

[0122] The parameter testing module 107 is used to perform parameter testing on the accessories represented by each real abnormal accessory area.

[0123] As an example, performing parameter testing on an accessory represented by a real abnormal accessory region may include the following steps:

[0124] The first step is to individually connect the accessories represented by the real abnormal accessories area, and use multi-dimensional electronic testing software to collect multi-dimensional and comprehensive information on the accessories represented by the real abnormal accessories area.

[0125] In the second step, the collected comprehensive information is transmitted to the computer, and the difference between the test information of the accessories represented by the real abnormal accessories area and the normal test information of the accessories of the same model is analyzed through template matching, and the difference is determined as the abnormal difference corresponding to the real abnormal accessories area.

[0126] The third step is to analyze the abnormal parameters of the accessories represented by the real abnormal accessory area through the abnormal differences corresponding to the real abnormal accessory area, and record them.

[0127] Optionally, parameter testing of the accessories represented by the actual abnormal accessory region may also be achieved by the following steps:

[0128] The first step is to place the accessories represented by the real abnormal accessories area in the standard fixture, scan the barcode of the accessories represented by the real abnormal accessories area and register them.

[0129] The second step is to send the test instructions pre-stored in the computer to the standard fixture according to the test requirements.

[0130] In the third step, after the control board in the standard fixture receives the test instructions for the accessories representing the real abnormal accessories area, it starts the test of the accessories representing the real abnormal accessories area and displays the test results in the multi-function meter. The multi-function meter synchronizes the test results to the computer for the computer to perform comparative analysis and form an analysis report.

[0131] refer to Figure 2 Based on the same inventive concept as the above method embodiment, the present invention provides a method for testing parameters of integrated electronic product accessories based on computer automatic analysis, comprising the following steps:

[0132] Step 201 : obtaining a target infrared image corresponding to the integrated electronic product to be inspected, and extracting target accessory regions representing different target accessories from the target infrared image.

[0133] Step 202 : Clustering all target accessory regions according to their corresponding major axis distances and minor axis distances to obtain target clusters.

[0134] Step 203 , determining an initial radiation anomaly index corresponding to each target accessory region based on the grayscale distribution change difference between each target accessory region and other target accessory regions in the target cluster to which it belongs, and screening out abnormal candidate accessory regions from all target accessory regions based on all initial radiation anomaly indicators.

[0135] Step 204 , based on the grayscale disorder degree corresponding to each abnormal candidate accessory region and the grayscale difference between the centroid of each abnormal candidate accessory region and the edge pixels of its corresponding preset windows of different sizes, determines the corresponding heat source abnormality index of each abnormal candidate accessory region.

[0136] Step 205 : determining other heat source impact indicators corresponding to each abnormal candidate accessory region based on the distance and high temperature difference between each abnormal candidate accessory region and other abnormal candidate accessory regions.

[0137] Step 206 , based on the corresponding self-heat source abnormality indicators and other heat source impact indicators of all abnormal candidate accessory regions, the real abnormal accessory regions are screened out from all abnormal candidate accessory regions.

[0138] Step 207 : Perform parameter testing on each accessory represented by the actual abnormal accessory region.

[0139] Figure 3 FIG. 1 is a schematic diagram of the structure of a computer device provided by an embodiment of the present invention. For example, Figure 3 As shown, the computer device 300 includes: a memory 301, a processor 302, and a computer program 303 stored in the memory 301 and running on the processor 302, wherein when the processor 302 executes the computer program 303, the computer device can execute the aforementioned integrated electronic product accessory parameter testing method based on computer automatic analysis.

[0140] Based on the same inventive concept as the above-described method embodiment, the present invention provides a server comprising a memory and a processor. The memory is configured to store executable program code, and the processor is configured to retrieve and execute the executable program code from the memory, thereby enabling the device to perform the above-described method for testing parameters of integrated electronic product accessories based on computer-automated analysis.

[0141] Based on the same inventive concept as the above-mentioned method embodiment, the present invention provides a computer program product, which includes: computer program code, which, when running on a computer, enables the computer to execute the above-mentioned integrated electronic product accessory parameter testing method based on computer automatic analysis.

[0142] Based on the same inventive concept as the above-mentioned method embodiment, the present invention provides a computer-readable storage medium, which stores computer program code. When the computer program code runs on a computer, the computer executes the above-mentioned integrated electronic product accessory parameter testing method based on computer automatic analysis.

[0143] In summary, compared with manual parameter testing of accessories in integrated electronic products, the present invention comprehensively considers multiple indicators related to abnormal operation of accessories in the process of parameter testing of accessories in integrated electronic products, such as initial radiation abnormality indicators, self-heat source abnormality indicators and other heat source impact indicators, thereby screening out abnormal accessories that need to be parameter tested in the real abnormal accessory area representation, reducing to a certain extent the time waste caused by parameter testing of normal accessories, thereby improving the efficiency of parameter testing of accessories of integrated electronic products.

[0144] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention 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 scope of the technical solutions of the embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. An integrated electronic product accessory parameter testing system based on computer automatic analysis, characterized in that: The system comprises: An image acquisition and extraction module is used to acquire a target infrared image corresponding to the integrated electronic product to be inspected, and to extract target accessory areas representing different target accessories from the target infrared image; A region clustering module is used to cluster all target accessory regions according to their corresponding major axis distances and minor axis distances to obtain target clusters; a determination and screening module, configured to determine an initial radiation anomaly index corresponding to each target accessory region based on a difference in grayscale distribution change between each target accessory region and other target accessory regions in its target cluster, and to screen out abnormal candidate accessory regions from all target accessory regions based on all initial radiation anomaly indicators; A self-heat source anomaly index determination module is used to determine the self-heat source anomaly index corresponding to each abnormal candidate accessory region based on the grayscale disorder degree corresponding to each abnormal candidate accessory region and the grayscale difference between the centroid of each abnormal candidate accessory region and the edge pixels of the corresponding preset windows of different sizes; Other heat source impact index determination module, used to determine other heat source impact index corresponding to each abnormal candidate accessory area based on the distance and high temperature difference between each abnormal candidate accessory area and other abnormal candidate accessory areas; A region screening module is used to screen out the real abnormal accessory regions from all abnormal candidate accessory regions based on their own heat source abnormality indicators and other heat source impact indicators; A parameter testing module is used to perform parameter testing on each accessory represented by the real abnormal accessory area; The target accessory regions are clustered according to the major axis distances and minor axis distances corresponding to all target accessory regions to obtain target clusters, including: The distance between each two edge pixels on each target accessory area is determined as a reference distance, and a reference distance set corresponding to each target accessory area is obtained; Determine the maximum value in the reference distance set corresponding to each target accessory area as the long axis distance corresponding to each target accessory area; Determine the minimum value in the reference distance set corresponding to each target accessory area as the short-axis distance corresponding to each target accessory area; The long axis distance and the short axis distance corresponding to each target accessory area are used to form a binary vector corresponding to each target accessory area; The target accessory areas whose Euclidean distance between corresponding binary vectors is less than a preset distance threshold are divided into the same cluster, and each obtained cluster is determined as the target cluster; The formula corresponding to the abnormal heat source abnormality index of the abnormal candidate accessory area is: ;in, It is The abnormal heat source abnormality index corresponding to the abnormal candidate accessory area; is the sequence number of the abnormal candidate accessory area; It is The grayscale disorder degree corresponding to the abnormal candidate accessory area is equal to The variance of the grayscale values ​​corresponding to all pixels in the abnormal candidate accessory area; is the number of preset windows of different sizes; It is the serial number of the preset windows of different sizes; is a natural exponential function; It is The centroid of the abnormal candidate accessory area and the corresponding The maximum value of the Euclidean distances between the edge pixels of preset windows of different sizes; is the normalization function; It is Gray value corresponding to the centroid of each abnormal candidate accessory area; It is The centroid of the abnormal candidate accessory area corresponds to the The mean of the grayscale values ​​corresponding to all edge pixels of preset windows of different sizes; The method of screening out the real abnormal accessory regions from all abnormal candidate accessory regions based on the corresponding self-heat source abnormality indicators and other heat source impact indicators of all abnormal candidate accessory regions includes: According to the own heat source abnormality index and other heat source impact indexes corresponding to each abnormal candidate accessory area, the target abnormality index corresponding to each abnormal candidate accessory area is determined, wherein the own heat source abnormality index is positively correlated with the target abnormality index, and the other heat source impact index is negatively correlated with the target abnormality index; If the target abnormality index corresponding to the abnormal candidate accessory area is greater than the preset target abnormality threshold, the abnormal candidate accessory area is determined to be a real abnormal accessory area.

2. The integrated electronic product accessory parameter testing system based on computer automatic analysis according to claim 1, characterized in that: The step of extracting target accessory regions representing different target accessories from the target infrared image includes: Acquire a target RGB image corresponding to the integrated electronic product to be inspected; Filtering reference accessory regions representing different target accessories from the target RGB image; According to the correspondence between the target RGB image and the target infrared image, an accessory region corresponding to each reference accessory region is screened out from the target infrared image as a target accessory region.

3. The integrated electronic product accessory parameter testing system based on computer automatic analysis according to claim 1, characterized in that: The determining of the initial radiation anomaly index corresponding to each target accessory region according to the grayscale distribution change difference between each target accessory region and other target accessory regions in the target cluster to which it belongs includes: The variance of the grayscale values ​​corresponding to all pixels in each target accessory area is determined as the grayscale disorder degree corresponding to each target accessory area; The mean of the grayscale values ​​corresponding to all pixels in each target accessory area is determined as the grayscale representative factor corresponding to each target accessory area; Determine the grayscale distribution eigenvalue corresponding to each target accessory area based on the grayscale disorder degree and grayscale representative factor corresponding to each target accessory area, wherein the grayscale disorder degree is positively correlated with the grayscale distribution eigenvalue, and the grayscale representative factor is negatively correlated with the grayscale distribution eigenvalue; The initial radiation anomaly index corresponding to each target accessory region is determined according to the difference between the grayscale distribution eigenvalue corresponding to each target accessory region and the grayscale distribution eigenvalues ​​corresponding to other target accessory regions in the target cluster to which it belongs.

4. The integrated electronic product accessory parameter testing system based on computer automatic analysis according to claim 3, characterized in that: Determining the initial radiation anomaly index corresponding to each target accessory region according to the difference between the grayscale distribution characteristic value corresponding to each target accessory region and the grayscale distribution characteristic values ​​corresponding to other target accessory regions in the target cluster to which it belongs includes: The average of the grayscale values ​​corresponding to all pixels in the preset rectangular window corresponding to each pixel in each target accessory area is determined as the overall grayscale factor corresponding to each pixel in each target accessory area; The maximum value of the overall grayscale factors corresponding to all pixels in each target accessory area is determined as the overall representative grayscale index corresponding to each target accessory area; The initial radiation anomaly index corresponding to each target accessory area is determined based on the absolute value of the difference between the grayscale distribution eigenvalue corresponding to each target accessory area and the grayscale distribution eigenvalues ​​corresponding to other target accessory areas in the target cluster to which it belongs, as well as the difference between the overall representative grayscale index corresponding to each target accessory area and the overall representative grayscale index corresponding to other target accessory areas in the target cluster to which it belongs.

5. The integrated electronic product accessory parameter testing system based on computer automatic analysis according to claim 4, characterized in that: The formula for the initial radiation anomaly index corresponding to the target accessory area is: ;in, It is The target cluster The initial radiation anomaly index corresponding to the target accessory area; is the sequence number of the target cluster; and It is The sequence numbers of different target accessory areas in a target cluster; is the normalization function; It is The number of target accessory regions in a target cluster; It is the absolute value function; It is The target cluster The grayscale confusion degree corresponding to each target accessory area; It is The target cluster The grayscale confusion degree corresponding to each target accessory area; It is The target cluster The grayscale representative factor corresponding to the target accessory area; It is The target cluster The grayscale representative factor corresponding to the target accessory area; It is The target cluster Grayscale distribution eigenvalues ​​corresponding to the target accessory area; It is The target cluster Grayscale distribution eigenvalues ​​corresponding to the target accessory area; It is The target cluster The overall representative grayscale index corresponding to the target accessory area; It is The target cluster The overall representative grayscale index corresponding to the target accessory area.

6. The integrated electronic product accessory parameter testing system based on computer automatic analysis according to claim 1, characterized in that: Based on all initial radiation anomaly indicators, abnormal candidate accessory areas are screened out from all target accessory areas, including: If the initial radiation anomaly index corresponding to the target accessory area is greater than a preset initial anomaly threshold, the target accessory area is determined as an abnormal candidate accessory area.

7. The integrated electronic product accessory parameter testing system based on computer automatic analysis according to claim 4, characterized in that: The formulas corresponding to other heat source impact indicators corresponding to abnormal candidate accessory areas are: ;in, It is Other heat source impact indicators corresponding to the abnormal candidate accessory areas; and is the sequence number of different abnormal candidate accessory areas; is the number of abnormal candidate accessory regions; is a natural exponential function; It is The high temperature point in the abnormal candidate accessory area is The Euclidean distance between the high-temperature points in the abnormal candidate accessory area; the high-temperature point in the abnormal candidate accessory area is the pixel with the largest overall grayscale factor in the abnormal candidate accessory area; is the normalization function; It is The overall representative grayscale index corresponding to the abnormal candidate accessory area is used to represent the Local high temperature conditions in the abnormal candidate accessory area; It is The overall representative grayscale index corresponding to the abnormal candidate accessory area is used to represent the The local high temperature situation of the abnormal candidate accessory area.

Images