A method and system for detecting surface defects of a liquid cooling plate

Abstract

The present invention relates to the field of image processing technology, and particularly relates to a method and system for detecting surface defects of a liquid cooling plate. The method includes: collecting a surface image of the liquid cooling plate and dividing it into a reflective area and a non-reflective area; for the non-reflective area, taking the mean of the gray-scale defect degree and the texture defect degree of each pixel point as the comprehensive defect degree of each pixel point, and taking the mean of the comprehensive defect degrees of all pixel points as the defect degree of the non-reflective area; for the reflective area, extracting all scratched areas, and taking the ratio of the total area of all scratched areas to the total area of the reflective area as the defect degree of the reflective area; combining the defect degree of the non-reflective area and the defect degree of the reflective area to determine the total defect degree of the surface of the liquid cooling plate, and performing defect detection according to the magnitude of the total defect degree. This detection method overcomes the interference caused by the influence of light and the texture of the surface of the liquid cooling plate itself, and improves the accuracy of defect detection.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing. Specifically, it relates to a method and system for detecting surface defects of a liquid cooling plate. Background Art

[0002] As a key component of a liquid cooling radiator, the liquid cooling plate plays a crucial role in the battery thermal management system of new energy vehicles. The manufacturing of the liquid cooling plate requires multiple processes such as cutting, welding, grinding, and polishing. If the process control is improper, its surface is prone to scratching. The surface scratching will damage the protective layer and increase the risk of coolant leakage. The coolant leakage not only reduces the heat dissipation efficiency but may also damage electronic devices. Therefore, strict inspection must be carried out before the liquid cooling plate leaves the factory.

[0003] Currently, when detecting surface defects of a liquid cooling plate through traditional image processing methods, there are the following deficiencies: On the one hand, the flow channels on the surface of the liquid cooling plate are convex, and under light conditions, there will be a reflection phenomenon. This reflection will interfere with the image acquisition process, making the brightness of some areas in the acquired image extremely high. In these over-bright areas, if there are scratching defects, the details of the scratches will be masked due to the over-brightness, affecting the accuracy of defect detection. On the other hand, the surface of the liquid cooling plate itself has certain textures, which will interfere with the detection process. The surface textures of the liquid cooling plate and the scratching defects often appear in the form of lines or stripes, and it is easy to be confused with each other, resulting in difficulty in distinguishing normal textures and scratching defects, and the surface defect detection result is inaccurate.

[0004] In summary, when detecting surface defects of a liquid cooling plate through traditional image processing methods, due to the influence of light and the interference of the surface textures of the liquid cooling plate itself, the detection result of the scratching defects is inaccurate and cannot meet the quality inspection requirements of liquid cooling plate manufacturing. Summary of the Invention

[0005] To solve the problem that the detection result of scratching defects is inaccurate due to the influence of light and the interference of the surface textures of the liquid cooling plate itself when detecting surface defects of a liquid cooling plate by traditional image processing methods, the present invention proposes a method and system for detecting surface defects of a liquid cooling plate.

[0006] On the one hand, the present invention provides a method for detecting surface defects of a liquid cooling plate, including:

[0007] Collect the surface image of the liquid cooling plate for preprocessing, and divide the reflective area and the non-reflective area;

[0008] For each non-reflective area:

[0009] Determine the gray - scale defect degree of each pixel point based on the local gray - scale fluctuation degree of each pixel point and the contrast of each non - reflective area; determine the texture defect degree of each pixel point according to the gradient consistency of each pixel point and the edge regularity of each non - reflective area; the edge regularity of each non - reflective area is the mean value after normalizing the curvature change values of all edge pixel points in each non - reflective area;

[0010] Take the mean value of the gray - scale defect degree and the texture defect degree of each pixel point as the comprehensive defect degree of each pixel point, and take the mean value of the comprehensive defect degrees of all pixel points as the defect degree of each non - reflective area;

[0011] For each reflective area: extract all scratched areas in each reflective area, and take the ratio of the total area of all scratched areas to the total area of each reflective area as the defect degree of each reflective area;

[0012] Integrate the defect degree of each non - reflective area and the defect degree of each reflective area to determine the total defect degree of the liquid - cooled plate, and determine the defect detection result on the surface of the liquid - cooled plate according to the magnitude of the total defect degree of the liquid - cooled plate.

[0013] The above - mentioned technical solution can effectively remove the noise introduced by factors such as the accuracy limitation of the image acquisition device and unstable environmental light through pre - processing the surface image of the liquid - cooled plate, and at the same time highlight the detailed features in the image, providing a more accurate data basis for subsequent analysis. The division of reflective areas and non - reflective areas is because these two types of areas show completely different characteristics due to the influence of light and their own properties. Separated processing can avoid mutual interference and significantly improve the pertinence of detection. And further, for non - reflective areas, from the gray - scale perspective, scratched defects will break the normal gray - scale distribution law, causing local gray - scale fluctuations, and then changing the overall contrast of non - reflective areas; from the texture perspective, there are obvious differences between the gradient consistency of scratched defects and the edge irregularity of non - reflective areas and normal textures. Considering these two perspectives comprehensively can depict the characteristics of each pixel point comprehensively and meticulously, making up for the deficiency of analyzing only from a single gray - scale or texture feature, and making the evaluation of the defect degree of non - reflective areas more accurate and comprehensive. And further, for reflective areas, in view of the significant change in gray - scale values in scratched areas, determining the defect degree by calculating the area ratio can intuitively reflect the severity of defects in reflective areas. And further, integrating the defect degrees of non - reflective areas and reflective areas to determine the total defect degree of the liquid - cooled plate improves the accuracy of defect detection on the surface of the liquid - cooled plate.

[0014] Further, the gray - scale defect degree of each pixel point satisfies the following formula:

[0015] ;

[0016] In the formula, is the th gray defect degree of the th pixel of the th non-reflective area, is the normalization function, and are the weights of and respectively, is the contrast of the th non-reflective area, is the local gray fluctuation degree of the

[0017] th pixel of the

[0018] The above technical solution can more comprehensively reflect the difference between the pixel and the normal state from the gray level perspective by analyzing the severity of the overall gray level change in the non-reflective area and the fluctuation of the gray level values in the local area around the pixel points in the non-reflective area, and judge whether there is a gray defect, improving the judgment accuracy of the gray defect of the pixel point.

[0019] ;

[0020] In the formula, is the texture defect degree of the th pixel of the th non-reflective area, is the normalization function, and are both weights, is the gradient value of the th pixel of the th non-reflective area, is the maximum value function, is the absolute value of the maximum gradient value corresponding to all pixel points in the th non-reflective area, is the edge regularity of the th non-reflective area, is the absolute value symbol.

[0021] The above technical solution comprehensively considers two key texture features, gradient consistency and edge regularity. Compared with judging only based on a single texture feature, it can more accurately identify the scratched defect pixels in the non-reflective area. By quantifying the influence of these two features on the texture defect degree, it reduces the misjudgment caused by texture similarity and improves the recognition ability of small or scratched defects with inconspicuous texture features.

[0022] Further, the total defect degree of the liquid cooling plate is determined based on the following relational expression:

[0023] ;

[0024] In the formula, is the total defect degree of the liquid cooling plate, is the weight of ; is the weight of ; is the mean value after normalization of the defect degrees of all non-reflective regions, is the mean value after normalization of the defect degrees of all reflective regions.

[0025] The above technical solution incorporates the mean value after normalization of the defect degrees of non-reflective regions and the mean value after normalization of the defect degrees of reflective regions, which means that when evaluating the total defect degree of the liquid cooling plate, the defect information of different characteristic regions on the surface of the liquid cooling plate is considered, so as to more comprehensively and accurately reflect the overall defect condition of the surface of the liquid cooling plate.

[0026] Further, the method for dividing the reflective region and the non-reflective region is as follows:

[0027] Perform region growing on the surface image to obtain multiple initial regions. If the average gray value of all pixel points in a certain initial region is greater than or equal to a preset gray threshold, this initial region is used as a reflective region; if the average gray value of all pixel points in a certain initial region is less than the preset gray threshold, this initial region is used as a non-reflective region;

[0028] If the edge regularity of a certain reflective region is less than or equal to a preset edge regularity threshold, this reflective region is also divided into a non-reflective region.

[0029] The above technical solution initially divides the reflective region and the non-reflective region through the region growing algorithm, and then optimizes the initial division result by calculating the curvature change value of the edge pixel points of the reflective region, avoiding the error that is likely to exist when dividing regions only by gray value, and making the division results of the reflective region and the non-reflective region more accurate.

[0030] Further, the local gray fluctuation degree of each pixel point is determined based on the variance of the gray values of the eight-neighborhood pixel points of each pixel point.

[0031] Further, the method for obtaining the contrast of each non-reflective region is as follows:

[0032] Obtain the gray-level co-occurrence matrices of each non-reflective region in the directions of 0°, 45°, 90°, 135°, and 180° to obtain the average gray-level co-occurrence matrix;

[0033] Calculate the contrast of the non-reflective area based on the average gray-level co-occurrence matrix:

[0034]

[0035] In the formula, is the contrast of the th non-reflective area, is the total number of gray levels in the average gray-level co-occurrence matrix, and are both gray levels, is the element at the position of the average gray-level co-occurrence matrix. The value of the element is the probability that the gray-level combination composed of gray values and appears in the th non-reflective area.

[0036] Furthermore, the method for extracting all scratched areas in each reflective area is as follows:

[0037] Perform binarization on each reflective area to obtain a binary image of each reflective area. Mark the connected regions of the pixel points with a gray value of 1 in the binary image, perform edge detection on each marked connected region, and take the closed region surrounded by the edge of each connected region as the scratched area.

[0038] Furthermore, the method for determining the defect detection result of the surface of the liquid cooling plate according to the total defect degree is as follows:

[0039] Preset the first threshold, the second threshold, and the third threshold of the total defect degree, and the first threshold is less than the second threshold, and the second threshold is less than the third threshold;

[0040] When the total defect degree is less than or equal to the first threshold, there is no defect on the surface of the liquid cooling plate; when the total defect degree is greater than the first threshold and less than or equal to the second threshold, there are minor defects on the surface of the liquid cooling plate; when the total defect degree of the liquid cooling plate is greater than the second threshold and less than or equal to the third threshold, there are moderate defects on the surface of the liquid cooling plate; when the total defect degree of the liquid cooling plate is greater than the third threshold, there are severe defects on the surface of the liquid cooling plate.

[0041] On the other hand, the present invention also provides a surface defect detection system for a liquid cooling plate. The surface defect detection system includes a memory and a processor. A computer program is stored on the memory, and the processor executes the computer program to implement the steps of any one of the above-mentioned surface defect detection methods.

[0042] The present invention has the following effects:

[0043] Through image acquisition and preprocessing, accurately dividing the reflective area and non-reflective area, and then analyzing the defect degree of different areas from multiple feature angles such as gray scale and texture, finally comprehensively obtaining the total defect degree of the liquid cooling plate, and judging whether there is a scratch defect on the surface of the liquid cooling plate according to the size of the total defect degree, which overcomes the problems of light interference and surface texture interference, and improves the accuracy of surface defect detection of the liquid cooling plate. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a schematic flow chart of the method of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention.

[0046] Referring to Figure 1 , a method for detecting surface defects of a liquid cooling plate provided by the present invention includes steps S1-S5:

[0047] S1: Collect the surface image of the liquid cooling plate and perform preprocessing.

[0048] Use a high-resolution camera to vertically photograph the surface of the liquid cooling plate to avoid distortion of the surface image of the liquid cooling plate due to the shooting angle problem. And considering that during the image acquisition process, factors such as equipment performance differences and environmental changes may cause noise to be mixed into the image, and the noise will interfere with the subsequent feature analysis work on the surface of the liquid cooling plate. Therefore, preprocess the collected surface image of the liquid cooling plate, including: first perform grayscale processing on the surface image, then use the median filtering algorithm to remove the noise in the surface image, then use the histogram equalization algorithm to enhance the contrast, so that the grayscale distribution of the surface image is more uniform, and finally perform sharpening processing to enhance the edges and details of the surface image.

[0049] An accurate and reliable surface image is obtained through the operation of this step.

[0050] S2: Divide the reflective area and non-reflective area in the surface image.

[0051] First, analyze the inherent texture characteristics of the non-reflective area on the surface of the liquid cooling plate: The non-reflective area on the surface of the liquid cooling plate presents a specific texture pattern, showing a texture of black and white dots interlaced with each other. This texture has a high complexity and shows frequent gray value fluctuations at the gray value level. Although the fluctuation frequency of the gray value is high, its fluctuation amplitude is relatively small. From the perspective of the gradient value, it also shows the characteristic of frequent fluctuation changes. This inherent texture characteristic of the non-reflective area provides a basic reference for subsequent identification of abnormal situations (such as scratch defects).

[0052] When there are scratches in the non-reflective area on the surface of the liquid cooling plate, the texture characteristics of the scratches are:

[0053] From the grayscale performance point of view, the color of the scratches is similar to the reflective area on the surface of the liquid cooling plate, which means that in the surface image, the grayscale value of the scratched area is higher and the grayscale value of the reflective area is also higher. Therefore, from the grayscale performance point of view, the scratched area in the non-reflective area presents a similar grayscale performance to the reflective area.

[0054] From the perspective of morphology, the scratched area usually presents a relatively long and thin shape, and the edge of the scratched area is not smooth and continuous, but has burrs, and the overall shape is irregular. This is an intuitive description of the visual morphology of scratches, which is consistent with the general understanding of scratches on the surface of objects. For example, common metal surface scratches in life are often long and thin with irregular edges.

[0055] From the perspective of gradient, in the non-reflective area, the gradient value of the pixel point in the scratch area fluctuates less than the gradient value of the normal texture pixel point in the non-reflective area. Because in the image, the gradient reflects the rate of change of the grayscale value of the pixel point. Due to its own complex structure (such as the interlacing of black and white dots), the grayscale value of the normal texture pixel point in the non-reflective area changes frequently, so the fluctuation of the gradient value is also large. The scratch area is often a highlight area, and the change of the grayscale value is relatively small, resulting in a smaller fluctuation of its gradient value. Therefore, by analyzing the fluctuation of the gradient value, it is helpful to distinguish the normal texture pixel points in the non-reflective area from the pixel points in the scratch area.

[0056] In one embodiment, the method of dividing the reflective area and the non-reflective area is:

[0057] First, a region growing algorithm is performed on the surface image to generate multiple initial regions. A grayscale threshold is preset to 125 (empirical value). For each initial region, the average grayscale value of all its pixels is calculated. If the average grayscale value of an initial region is greater than or equal to 125, the initial region will be judged as a reflective region; if the average grayscale value is less than 125, it will be regarded as a non-reflective region. This method preliminarily completes the division of reflective and non-reflective regions based on the region growing algorithm and the grayscale values ​​of the pixels.

[0058] However, there are various reasons why the reflective areas obtained by the preliminary division have large grayscale values. On the one hand, it may be due to normal reflection phenomenon that causes the grayscale value to be high; on the other hand, the scratched area also shows high grayscale performance characteristics similar to the reflective area. Therefore, it is necessary to conduct further analysis on all the reflective areas obtained by the preliminary division.

[0059] From the perspective of physical properties, reflection usually occurs at the edges of the raised texture of the liquid cooling plate, so the edge shape of the area with a larger gray value due to reflection is relatively regular. However, due to the randomness of the scratching process, the scratched area will have burrs on the edge and the overall shape is relatively irregular.

[0060] Therefore, in order to effectively distinguish these two situations, the erosion and dilation algorithm is first used to process the surface image. The erosion operation can remove isolated pixels and small burrs at the edge of the object in the image, while the dilation operation can restore important edge information that may be lost due to erosion, while further highlighting the main part of the object. After the processing is completed, the Sobel operator is used to obtain all edge pixels in each reflective area in the surface image.

[0061] Next, take the pixel point at the lower left corner of the surface image as the coordinate origin, set the horizontal right direction as the horizontal axis, and set the vertical upward direction as the vertical axis to construct a two-dimensional coordinate system. For each reflective area, according to the curvature calculation formula, use the coordinates of each edge pixel point in the coordinate system to calculate the curvature value of each edge pixel point. Then, subtract the curvature value of each edge pixel point from the mean of the curvature values ​​of all edge pixels in the reflective area, and the difference value (absolute value of the difference) obtained is the curvature change value of the edge pixel point. Normalize the curvature change values ​​of all edge pixels in the reflective area so that the curvature change value of each edge pixel point is between 0 and 1, and then calculate the average value, which is used as the edge regularity of the reflective area.

[0062] The preset edge regularity threshold is 0.5 (empirical value). If the edge regularity of a reflective area is less than or equal to 0.5, it means that the edge irregularity of the area is relatively high, which is more consistent with the characteristics of a scratched area, so the reflective area is reclassified as a non-reflective area.

[0063] Through this series of rigorous operating procedures, the reflective area and non-reflective area in the surface image of the liquid cooling plate can be divided more accurately.

[0064] S3: Determine the defect degree of each non-reflective area according to the grayscale defect degree and the texture defect degree of each pixel point in each non-reflective area.

[0065] S31: Analyze the grayscale defect level of each pixel.

[0066] For a pixel in a non-reflective area, the greater the fluctuation of the grayscale value in the local area of ​​the pixel, and the more drastic the overall grayscale value change of all pixels in the non-reflective area where the pixel is located, it means that the pixel is more likely to have a grayscale defect.

[0067] Therefore, the gray-level co-occurrence matrix of each non-reflective region is obtained, and the contrast of each non-reflective region is calculated according to the gray-level co-occurrence matrix. The contrast of each non-reflective region reflects the severity of the gray-level value change of all pixel points in the non-reflective region as a whole. For each pixel point in each non-reflective region, the variance of the gray-level values of the pixel points in its eight-neighborhood is obtained to reflect the fluctuation of the gray-level values in the local region of the pixel point.

[0068] In one embodiment, the method for obtaining the contrast of the non-reflective region is as follows:

[0069] Obtain the gray-level co-occurrence matrices of each non-reflective region in the directions of 0 degrees, 45 degrees, 90 degrees, 135 degrees, and 180 degrees to obtain the average gray-level co-occurrence matrix.

[0070] Calculate the contrast of the non-reflective region based on the average gray-level co-occurrence matrix:

[0071]

[0072] In the formula, is the contrast of the th non-reflective region, is the total number of gray levels in the average gray-level co-occurrence matrix, and are both gray levels, is the element at the position of the average gray-level co-occurrence matrix, and the value of the element is the probability that the gray-level combination composed of the gray-level values and appears in the th non-reflective region.

[0073] In one embodiment, the gray-level defect degree of each pixel point in each non-reflective region satisfies the following formula:

[0074]

[0075] In the formula, is the gray-level defect degree of the th pixel point in the th non-reflective region. This value is used to quantify the likelihood of a defect in the gray level of the pixel point. The larger the value, the higher the likelihood of a gray-level defect in the pixel point. is the normalization function, and are the weights of and respectively. For each pixel point, the local gray-level fluctuation degree of the pixel point and the contrast of the non-reflective region where the pixel point is located are equally important for measuring the gray-level defect degree. is the contrast of the th non-reflective area, which is obtained by calculating the gray-level co-occurrence matrix of this non-reflective area. It reflects the severity of the gray-level value changes of all pixel points in this non-reflective area as a whole. The higher the contrast, the greater the difference in gray-level values of the pixel points in this non-reflective area, and the more severe the overall gray-level change. is the th non-reflective area's th pixel point's local gray-level fluctuation degree, which is calculated by obtaining the variance of the gray-level values of the pixel points in the eight-neighborhood of this pixel point. The larger the variance, the greater the gray-level value fluctuation in the local area of this pixel point.

[0076] This formula comprehensively considers the overall gray-level change situation of the non-reflective area where the pixel point is located and the local gray-level fluctuation situation of this pixel point itself. These two factors are linearly combined according to a certain weight and, after normalization processing, the gray-level defect degree of this pixel point is obtained. This comprehensive consideration conforms to the judgment logic mentioned above, that is, when the gray-level value fluctuation in the local area of a pixel point is greater and the gray-level value changes of all pixel points in the non-reflective area where it is located are more severe as a whole, this pixel point is more likely to have a gray-level defect.

[0077] S32: Analyze the texture defect degree of each pixel point.

[0078] For a pixel point in a non-reflective area, when the gradient of this pixel point has a large consistency with the gradient of the non-reflective area where it is located, it indicates that the gradient direction of this pixel point is relatively consistent with the gradient directions of other pixel points in this non-reflective area, and it is more in line with the gradient characteristics of the pixel points in the scratched area, that is, this pixel point is more likely to be in the scratched area. If the edge regularity of the non-reflective area where this pixel point is located is small and the edge is more irregular, this also increases the possibility that this pixel point is located in the scratched area.

[0079] In one embodiment, the texture defect degree of each pixel point in each non-reflective area satisfies the following formula:

[0080]

[0081] In the formula, is the th non-reflective area's th pixel point's texture defect degree. The larger the value, the more likely the th non-reflective area's th pixel point is located in the scratched area. is the normalization function, and are both weights, , It is The non-reflective area The gradient value of a pixel, To obtain the maximum value function, It is The absolute value of the maximum gradient value corresponding to all pixels in a non-reflective area is used to measure the maximum range of the gradient values ​​of the pixels in the non-reflective area. By comparing it with the gradient value of a single pixel, it can reflect the relative gradient size of the pixel in the area. It is The edge regularity of a non-reflective area is used to measure whether the edge of the non-reflective area is regular. For areas with defects, their edges are usually irregular. The smaller the value, the more irregular the edge of the non-reflective area is, and the more likely it is that there will be texture defects. is the absolute value symbol.

[0082] In this formula, Reflects the The non-reflective area pixels and Therefore, in a non-reflective area, the maximum gradient value of all pixels is usually the case where the grayscale changes most dramatically in a certain direction. For example, in the non-reflective area on the surface of the liquid cooling plate, if there are some long and thin textures or scratches, these features will make the grayscale changes of pixels along their length more obvious, then a larger gradient value may appear in this direction. At this time, the direction corresponding to the maximum gradient value is likely to represent the main direction of the texture or structure in the area, that is, the main gradient direction. The non-reflective area pixels and The greater the gradient consistency of the non-reflective area, the The closer the gradient value of a pixel is to the maximum gradient value of the non-reflective area.

[0083] In summary, this step comprehensively considers the key factors of the pixel's own gradient value, the maximum gradient value of the non-reflective area (used to determine the gradient direction consistency), and the edge regularity of the non-reflective area when analyzing the texture defect degree of the pixel in the non-reflective area. Through the combination of these factors, the possibility of the pixel having defects in the texture angle can be determined. When the gradient direction consistency factor is large, at the same time, if the edge regularity corresponding to the non-reflective area where the pixel is located is small, that is, the edge is irregular, the possibility of the pixel having defects in the texture angle is greater, that is, the greater the degree of texture defects.

[0084] S33: Determine the degree of defects in each non-reflective area.

[0085] In each non-reflective area, first determine the comprehensive defect degree of each pixel according to the gray-scale defect degree and texture defect degree of each pixel, and then determine the defect degree of the non-reflective area according to the comprehensive defect degrees of all pixels.

[0086] In one embodiment, the comprehensive defect degree of each pixel in each non-reflective area is determined based on the following method: taking the mean value of the gray-scale defect degree and texture defect degree of each pixel in the non-reflective area as the comprehensive defect degree of each pixel. Among them, the calculation formula for the comprehensive defect degree of each pixel is:

[0087]

[0088] In this formula, is the comprehensive defect degree of the th pixel in the th non-reflective area, is the gray-scale defect degree of the th pixel in the th non-reflective area, is the texture defect degree of the th pixel in the th non-reflective area.

[0089] In one embodiment, the defect degree of each non-reflective area is determined based on the following method: taking the mean value of the comprehensive defect degrees of all pixels in each non-reflective area as the defect degree of this non-reflective area.

[0090] S4: Determine the defect degree of each reflective area according to the area ratio of the scratched area in each reflective area.

[0091] Due to its own physical structure and light reflection characteristics, the surface of the liquid cooling plate has a curved shape in the reflective area. For the scratched area in the reflective area, due to physical damage, it presents a short and irregular white scratched form, and in the previous step S2, the scratched area has been classified as the reflective area category.

[0092] In one embodiment, the scratched area in each reflective area is extracted according to the following method:

[0093] From an optical perspective, the scratched area will damage the flatness of the object surface. When light shines on the scratched area, diffuse reflection will occur, making the scratched area appear brighter in the image, and the corresponding gray value is larger. Although the gray value of the normal (without scratches) reflective area surface is also relatively high, due to its relatively flat surface, the light reflection is relatively regular, and the light entering the camera is relatively small, so the gray value is lower than that of the scratched area.

[0094] Therefore, the image of the reflective area is binarized, and the part with a smaller gray value (representing the normal area) is marked as 0, while the part with a larger gray value (most likely the scratched area, because the scratched area has a larger gray value in the gray-scale image) is marked as 1. This step simplifies the image information and facilitates subsequent focusing on the scratched area.

[0095] In the binarized image, the parts marked as 1 (i.e., the suspected scratched areas) are subjected to connected component labeling, and then the edge detection algorithm is used for these labeled connected components to determine the edges of these connected components. Finally, the closed area enclosed by the edges of each connected component is used as each scratched area.

[0096] In one embodiment, the method for obtaining the defect degree of each reflective area is as follows:

[0097] Within each reflective area, all the scratched areas it contains are obtained. The number of pixel points in each scratched area is counted. The area of each scratched area is equal to the total number of pixel points it contains. The total area of the scratched areas is obtained by accumulating the areas of all scratched areas. The ratio of the total area of the scratched areas to the total area of the entire reflective area is used as the defect degree of the reflective area.

[0098] Since the size of the scratched area is directly related to the performance and service life of the liquid cooling plate. This calculation method can intuitively reflect the actual coverage degree of the scratch on the reflective area, and thus indirectly reflect the influence degree of the scratch on the overall physical performance of the liquid cooling plate.

[0099] S5: Comprehensively determine the total defect degree of the liquid cooling plate, and determine the defect detection result according to the size of the total defect degree.

[0100] In one embodiment, the total defect degree of the liquid cooling plate is determined based on the following formula:

[0101]

[0102] In the formula, is the total defect degree of the liquid cooling plate, is the weight of , is the weight of , , , is the mean value of the normalized defect degrees of all non-reflective areas (first perform the normalization operation on the defect degrees of all non-reflective areas, and then calculate the mean value), is the mean value of the normalized defect degrees of all reflective areas (first perform the normalization operation on the defect degrees of all reflective areas, and then calculate the mean value).

[0103] The weights are set in this way to reflect that the defect degree of the non-reflective area has a greater impact on the total defect degree. Since the non-reflective area usually represents the normal surface structure of the liquid cooling plate, its defects (such as scratches, pits, corrosion, etc.) directly affect the mechanical strength and heat conduction performance of the liquid cooling plate. Therefore, the defect degree of the non-reflective area has a more direct impact on the overall performance of the liquid cooling plate.

[0104] The total defect degree calculated by this formula can more truly reflect the overall performance status of the liquid cooling plate. In actual production and quality inspection, it can provide a more accurate quantitative basis for determining whether the liquid cooling plate is qualified and meets the usage requirements. For example, in the heat dissipation system of electronic devices, it can be determined whether the liquid cooling plate can be adopted based on this total defect degree, avoiding problems such as poor heat dissipation of the device caused by ignoring local defects.

[0105] In one embodiment, the method for determining the defect detection result according to the size of the total defect degree is as follows:

[0106] The first threshold of the preset total defect degree is 0.3, the second threshold is 0.5, and the third threshold is 0.7; when the total defect degree is less than or equal to 0.3, there are no defects on the surface of the liquid cooling plate; when the total defect degree is greater than 0.3 and less than or equal to 0.5, there are slight defects on the surface of the liquid cooling plate; when the total defect degree of the liquid cooling plate is greater than 0.5 and less than or equal to 0.7, there are moderate defects on the surface of the liquid cooling plate; when the total defect degree of the liquid cooling plate is greater than 0.7, there are severe defects on the surface of the liquid cooling plate.

[0107] Through this defect detection method, in the production inspection link, the liquid cooling plates can be quickly classified and screened according to the total defect degree. For a large number of products to be detected, different quality grades can be quickly distinguished, improving the detection efficiency, reducing labor costs and time costs, and ensuring that only products meeting specific quality requirements enter the next link or the market.

[0108] The present invention also provides a surface defect detection system for a liquid cooling plate. The surface defect detection system includes a memory and a processor. A computer program is stored on the memory, and the processor executes the computer program to implement the steps of any of the above-mentioned surface defect detection methods to complete the surface defect detection of the liquid cooling plate.

[0109] Although this specification has shown and described multiple embodiments of the present invention, it is obvious to those skilled in the art that such embodiments are provided only by way of example. Those skilled in the art will think of many changes, alterations, and alternative ways without departing from the spirit and concept of the present invention. It should be understood that various alternative solutions to the embodiments of the present invention described herein can be adopted in the process of practicing the present invention.

Claims

1. A method for detecting surface defects of a liquid cooling plate, characterized in that: include: Collect the surface image of the liquid cooling plate for preprocessing and divide it into reflective area and non-reflective area; For each non-reflective area: The grayscale defect degree of each pixel is determined based on the local grayscale fluctuation degree of each pixel and the contrast of each non-reflective area, satisfying the following formula: ； In the formula, For the The non-reflective area The grayscale defect degree of each pixel, is the normalization function, and They are and The weight of For the The contrast of the non-reflective area For the The non-reflective area The local grayscale fluctuation degree of each pixel point; according to the gradient consistency of each pixel point and the edge regularity of each non-reflective area, the texture defect degree of each pixel point is determined to satisfy the following formula: ； In the formula, For the The non-reflective area The degree of texture defect of each pixel, is the normalization function, and are weights, It is The non-reflective area The gradient value of a pixel, To obtain the maximum value function, It is The absolute value of the maximum gradient value corresponding to all pixels in the non-reflective area, It is The edge regularity of the non-reflective area, is the absolute value symbol; the edge regularity of each non-reflective area is the normalized mean of the curvature change values ​​of all edge pixels of each non-reflective area; The average of the grayscale defect degree and the texture defect degree of each pixel is taken as the comprehensive defect degree of each pixel, and the average of the comprehensive defect degrees of all pixels is taken as the defect degree of each non-reflective area; For each reflective area: extract all scratched areas in each reflective area, and take the ratio of the total area of ​​all scratched areas to the total area of ​​each reflective area as the defect degree of each reflective area; The total defect degree of the liquid cooling plate is determined by comprehensively considering the defect degree of each non-reflective area and the defect degree of each reflective area, and the defect detection result of the surface of the liquid cooling plate is determined according to the total defect degree.

2. The surface defect detection method of a liquid cooling plate according to claim 1, characterized in that: The total defect level of the liquid cooling plate is determined based on the following relationship: ； In the formula, is the total defect level of the liquid cooling plate, for The weight of for The weight of is the normalized mean of the defect levels of all non-reflective areas, It is the normalized mean of the defect degree of all reflective areas.

3. The surface defect detection method of the liquid cooling plate according to claim 1, characterized in that: The method of dividing the reflective area and the non-reflective area is: Performing region growing on the surface image to obtain multiple initial regions, if the average grayscale value of all pixels in a certain initial region is greater than or equal to a preset grayscale threshold, the initial region is used as a reflective region; if the average grayscale value of all pixels in a certain initial region is less than the preset grayscale threshold, the initial region is used as a non-reflective region; If the edge regularity of a certain reflective area is less than or equal to a preset edge regularity threshold, the reflective area is also divided into a non-reflective area.

4. The surface defect detection method of the liquid cooling plate according to claim 1, characterized in that: The degree of local grayscale fluctuation of each pixel is determined based on the variance of the grayscale values ​​of the eight neighboring pixels of each pixel.

5. The surface defect detection method of the liquid cooling plate according to claim 1, characterized in that: The contrast of each non-reflective area is obtained as follows: Obtain the gray level co-occurrence matrix of each non-reflective area in the directions of 0 degrees, 45 degrees, 90 degrees, 135 degrees and 180 degrees, and obtain the average gray level co-occurrence matrix; calculate the contrast of the non-reflective area based on the average gray level co-occurrence matrix: ； In the formula, For the The contrast of the non-reflective area is the total number of gray levels in the mean gray-level co-occurrence matrix, and All are grayscale. is the mean gray-level co-occurrence matrix The element at the position, the value of the element is the gray value and The gray value combination of The probability of appearing in a non-reflective area.

6. The surface defect detection method of a liquid cooling plate according to claim 1, characterized in that: The method to extract all scratched areas in each reflective area is: Each reflective area is binarized to obtain a binary image of each reflective area, pixels with a gray value of 1 in the binary image are marked as connected domains, edge detection is performed on each marked connected domain, and the closed area enclosed by the edge of each connected domain is used as the scratch area.

7. The surface defect detection method of a liquid cooling plate according to claim 1, characterized in that: The method for determining the defect detection results of the liquid cooling plate surface according to the total defect degree is: A first threshold, a second threshold, and a third threshold of the total defect degree are preset, and the first threshold is smaller than the second threshold, and the second threshold is smaller than the third threshold; When the total defect degree is less than or equal to the first threshold, the surface of the liquid cooling plate is free of defects; When the total defect degree is greater than the first threshold and less than or equal to the second threshold, there are slight defects on the surface of the liquid cooling plate; when the total defect degree of the liquid cooling plate is greater than the second threshold and less than or equal to the third threshold, there are moderate defects on the surface of the liquid cooling plate; when the total defect degree of the liquid cooling plate is greater than the third threshold, there are severe defects on the surface of the liquid cooling plate.

8. A surface defect detection system for a liquid cooling plate, characterized in that: The defect detection system comprises a memory and a processor, wherein a computer program is stored in the memory, and the processor executes the computer program to implement the steps of the defect detection method according to any one of claims 1 to 7.

Images