An intelligent evaluation method for the assembly quality of router housing

An intelligent evaluation method for router shells accurately identifies heat dissipation hole areas and crack impacts, enhancing the assessment of assembly quality by analyzing edge images and morphological changes, thereby improving detection and evaluation accuracy.

CN118735923BActive Publication Date: 2025-01-03DONGGUAN CITY JIANG LIN HARDWARE IND CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202411230794.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-04
Publication Date
2025-01-03
Estimated Expiration
2044-09-04

AI Technical Summary

Technical Problem

Existing methods for evaluating the assembly quality of router shells are inaccurate due to the similarity in grayscale performance between cracks and heat dissipation holes, making it difficult to detect and assess the impact of cracks on the heat dissipation functionality.

Method used

An intelligent evaluation method that analyzes edge images to identify heat dissipation hole regions, screens for cracks within these regions, and assesses the potential impact of cracks on heat dissipation areas, using morphological changes, distance, and area differences to determine assembly quality.

Benefits of technology

Improves the accuracy of crack detection and evaluation of assembly quality by precisely identifying heat dissipation hole areas and the potential influence of cracks, leading to a more reliable assessment of router shell quality.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118735923B_ABST
    Figure CN118735923B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of image analysis technology, and in particular to an intelligent evaluation method for the assembly quality of a router shell, comprising: obtaining an edge image of the router shell; obtaining a heat dissipation hole area in the edge image; obtaining cracks in the heat dissipation hole sub-area according to the grayscale value of pixels in the heat dissipation hole sub-area and the position of the heat dissipation hole area; obtaining the potential influence of each end of each crack in the heat dissipation hole sub-area on the heat dissipation hole area according to the proximity of the crack in the heat dissipation hole sub-area to the adjacent heat dissipation hole area after extension; obtaining the quality index of the heat dissipation hole sub-area; and evaluating the assembly quality of the router shell according to the quality index of the heat dissipation hole sub-area, the area of ​​the heat dissipation hole area in the edge image, and the area of ​​the crack in the edge image. The present invention improves the accuracy of the evaluation of the assembly quality of the router shell.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of image analysis, and in particular to an intelligent evaluation method for the assembly quality of a router shell. Background Art

[0002] The quality of router shell assembly directly affects the overall quality and performance stability of router products. Through intelligent evaluation, crack defects in the router shell can be discovered in time to ensure the quality of router products.

[0003] When evaluating the assembly quality of a router shell, the existing method only analyzes the crack defect area on the surface of the router shell through edge detection to evaluate the assembly quality of the router shell. Since the router shell itself has heat dissipation holes, and the cracks on the surface of the router shell may be connected to the heat dissipation holes, and the grayscale performance of the cracks and the heat dissipation holes is similar, it is difficult to detect the crack defects. At the same time, the cracks will also have a potential impact on the heat dissipation hole area. For example, over time, the cracks may extend to the heat dissipation holes. If the assembly quality of the router shell is evaluated only by analyzing the crack defect area on the surface of the router shell, the assembly quality evaluation of the router shell will be inaccurate. Summary of the invention

[0004] In order to solve the above problems, the present invention provides an intelligent evaluation method for the assembly quality of a router housing.

[0005] The intelligent evaluation method for the assembly quality of a router housing of the present invention adopts the following technical scheme:

[0006] An embodiment of the present invention provides an intelligent evaluation method for the assembly quality of a router housing, the method comprising the following steps:

[0007] Get an edge image of the router housing;

[0008] According to the shape change of the edge in the edge image, several initial heat dissipation hole regions in the edge image are obtained; according to the distance change and area change between the initial heat dissipation hole regions, several heat dissipation hole regions in the edge image are obtained;

[0009] The edge image is divided according to the heat dissipation hole area to obtain several heat dissipation hole sub-areas of the edge image; several cracks in each heat dissipation hole sub-area are obtained according to the gray value of the pixel point in the heat dissipation hole sub-area and the position of the heat dissipation hole area; the potential influence of each end of each crack in each heat dissipation hole sub-area on the heat dissipation hole area is obtained according to the proximity of the crack in the heat dissipation hole sub-area to the adjacent heat dissipation hole area after extension;

[0010] According to the number and area of ​​cracks in the heat dissipation hole sub-region and the potential influence of each end of each crack on the heat dissipation hole region, the quality index of each heat dissipation hole sub-region is obtained; according to the quality index of the heat dissipation hole sub-region, the area of ​​the heat dissipation hole region in the edge image and the area of ​​the crack in the edge image, the assembly quality parameters of the router shell are obtained; according to the size of the assembly quality parameters, the assembly quality of the router shell is evaluated.

[0011] Furthermore, the step of obtaining a plurality of initial heat dissipation hole regions in the edge image according to the morphological changes of the edge in the edge image includes the following specific steps:

[0012] For any edge in the edge image of the router shell, obtain the original chain code of the edge, take the absolute value of the difference between each direction symbol in the original chain code and the next direction symbol as the change value of each direction symbol in the original chain code, and assign the change value of the direction symbol to The corresponding pixel points are used as the edge pixel points of the heat dissipation hole; the edges formed by the continuous heat dissipation hole edge pixel points are obtained, and they are all recorded as the initial heat dissipation hole edges; if any initial heat dissipation hole edge forms a closed area, the closed area is used as an initial heat dissipation hole area; if any initial heat dissipation hole edge does not form a closed area, the pixel points on the initial heat dissipation hole edge are fitted to obtain a closed circular area as an initial heat dissipation hole area.

[0013] Furthermore, the step of obtaining a plurality of heat dissipation hole regions in the edge image according to the distance change and area change between the initial heat dissipation hole regions includes the following specific steps:

[0014] For any initial heat dissipation hole area in the edge image of the router shell, obtain the shortest distance between the initial heat dissipation hole area and other initial heat dissipation hole areas; obtain the difference between the shortest distance and the average shortest distance, where the average shortest distance is the average of the shortest distances between all initial heat dissipation hole areas and other initial heat dissipation hole areas; obtain the difference between the area of ​​the initial heat dissipation hole area and the average area of ​​all initial heat dissipation hole areas; multiply the reciprocal of the difference between the shortest distance and the average shortest distance and the reciprocal of the difference between the area of ​​the initial heat dissipation hole area and the average area of ​​all initial heat dissipation hole areas, and normalize them to obtain the probability that the initial heat dissipation hole area in the edge image of the router shell belongs to the heat dissipation hole area;

[0015] According to the probability that the initial heat dissipation hole area belongs to the heat dissipation hole area, several heat dissipation hole areas are screened out.

[0016] Furthermore, the method of screening out a plurality of heat dissipation hole regions according to the probability that the initial heat dissipation hole region belongs to the heat dissipation hole region includes the following specific steps:

[0017] An initial heat dissipation hole region whose probability of belonging to the heat dissipation hole region is greater than a preset first threshold is used as the heat dissipation hole region in the edge image of the router housing, where the first threshold is 0.7.

[0018] Furthermore, the step of dividing the edge image according to the heat dissipation hole regions to obtain a plurality of heat dissipation hole sub-regions of the edge image includes the following specific steps:

[0019] Starting from the upper left corner of the edge image of the router shell, in order from left to right and from top to bottom, the minimum circumscribed rectangle determined by every four adjacent heat dissipation hole areas is used as the heat dissipation hole sub-area of ​​the edge image of the router shell.

[0020] Furthermore, the method of obtaining a number of cracks in each heat dissipation hole sub-region according to the grayscale value of the pixel point in the heat dissipation hole sub-region and the position of the heat dissipation hole region includes the following specific steps:

[0021] For any heat dissipation hole sub-region, obtain the pixel point with a grayscale value of 0 in the heat dissipation hole sub-region. If the pixel point with a grayscale value of 0 does not belong to the heat dissipation hole region in the heat dissipation hole sub-region, take the pixel point as the crack pixel point of the heat dissipation hole sub-region, obtain all the crack pixel points of the heat dissipation hole sub-region, and obtain several cracks in the heat dissipation hole sub-region according to the continuous crack pixel points in the heat dissipation hole sub-region.

[0022] Furthermore, the step of obtaining the potential influence of each end of each crack in each heat dissipation hole sub-region on the heat dissipation hole region according to the proximity of the crack in the heat dissipation hole sub-region to the adjacent heat dissipation hole region after the crack extends includes the following specific steps:

[0023] For any heat dissipation hole sub-region with a crack and any end of any crack in the heat dissipation hole sub-region, the shortest distance from the crack to the nearest heat dissipation hole region in the extension direction of the end is obtained, which is recorded as the first shortest distance; the angle value between the extension direction of the crack at the end and the horizontal right direction is obtained, and the angle value is the angle value obtained with the horizontal right direction as 0° and the counterclockwise direction as the positive direction; the first angle value between the extension direction of the crack at the end and the nearest heat dissipation hole region is obtained, and the specific method for obtaining the first angle value is as follows: the distance between the last pixel point of the crack at the end and the tangent of the nearest heat dissipation hole region in the extension direction of the end is obtained, and the minimum angle value between the extension direction of the crack at the end and the tangent is taken as the first angle value; the reciprocal of the first shortest distance, the reciprocal of the angle value and the difference value of the first angle value are multiplied and normalized to obtain the potential impact of the crack at the end of the heat dissipation hole sub-region on the heat dissipation hole region.

[0024] Furthermore, the quality index of each heat dissipation hole sub-region is obtained according to the number and area of ​​cracks in the heat dissipation hole sub-region and the potential influence of each end of each crack on the heat dissipation hole region, and the specific steps include the following:

[0025] For any heat dissipation hole sub-region, the average potential influence degree of both ends of each crack in the heat dissipation hole sub-region on the heat dissipation hole region is obtained, and the product of the reciprocal of the average potential influence degree and the reciprocal of the corresponding crack area is used as the weighted potential influence degree of the crack on the heat dissipation hole region; the product of the accumulated value of the weighted potential influence degree of all cracks in the heat dissipation hole sub-region on the heat dissipation hole region and the reciprocal of the number of cracks in the heat dissipation hole sub-region is used as the quality index of the heat dissipation hole sub-region.

[0026] Furthermore, the assembly quality parameter of the router housing is obtained according to the quality index of the heat dissipation hole sub-region, the area of ​​the heat dissipation hole region in the edge image, and the area of ​​the crack in the edge image, and the specific steps include the following:

[0027] The average value of the quality index of all heat dissipation hole sub-areas, the ratio of the area of ​​all heat dissipation hole areas to the area of ​​the edge image, and the inverse of all crack areas in the edge image are multiplied and normalized to obtain the assembly quality parameters of the router housing.

[0028] Furthermore, the step of evaluating the assembly quality of the router housing according to the size of the assembly quality parameter includes the following specific steps:

[0029] If the assembly quality parameter of the router shell is less than the preset second threshold, the assembly quality of the router shell is unqualified; if the assembly quality parameter of the router shell is greater than or equal to the preset second threshold, the assembly quality of the router shell is qualified; the second threshold is 0.8.

[0030] The beneficial effects of the technical solution of the present invention are as follows: after acquiring the edge image of the router shell, the present invention obtains a more accurate heat dissipation hole area by analyzing the morphological changes of the edge in the edge image and the distance changes and area changes between the heat dissipation hole areas, reduces the difficulty in determining the accurate heat dissipation hole area due to the connection between the crack and the heat dissipation hole, and then more accurately obtains the cracks in the heat dissipation hole sub-area, thereby improving the accuracy of crack detection; at the same time, by analyzing the proximity of the crack to the adjacent heat dissipation hole area after extension, the potential influence of each end of each crack in each heat dissipation hole sub-area on the heat dissipation hole area is obtained, and the assembly quality of the router shell is more reasonably evaluated. Finally, the assembly quality parameters of the router shell are obtained through the quality index of the heat dissipation hole sub-area, the area of ​​the heat dissipation hole area in the edge image and the area of ​​the crack in the edge image, the assembly quality of the router shell is evaluated, and the accuracy of the assembly quality evaluation of the router shell is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 creative work.

[0032] Figure 1 A flowchart of a method for intelligently evaluating the assembly quality of a router housing provided by one embodiment of the present invention;

[0033] Figure 2 A flowchart of obtaining assembly quality parameters of a router housing provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0034] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the intelligent evaluation method for the assembly quality of a router housing proposed by the present invention, its specific implementation, structure, features and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0035] 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.

[0036] The specific scheme of the intelligent evaluation method for the assembly quality of a router housing provided by the present invention is described in detail below with reference to the accompanying drawings.

[0037] See also Figure 1 and Figure 2 , which shows a flowchart of a method for intelligently evaluating the assembly quality of a router housing provided by an embodiment of the present invention and a flowchart of obtaining assembly quality parameters of the router housing, the method comprising the following steps:

[0038] Step S001: Acquire an edge image of a router housing.

[0039] It should be noted that the main purpose of this embodiment is to obtain the quality index of the heat dissipation hole sub-area by analyzing the potential impact of the cracks on the router shell on the heat dissipation hole area, and to obtain the assembly quality parameters of the router shell in combination with the performance of the cracks on the router shell. Before starting the analysis, first collect the required images.

[0040] Specifically, obtain the edge image of the router housing as follows:

[0041] The surface of the assembled router shell is photographed from above by a camera to obtain an RGB image of the router shell surface. The RGB image is grayscaled and histogram equalized to obtain a grayscale image of the router shell. The Canny operator is used to perform edge detection on the grayscale image of the router shell to obtain an edge image of the router shell.

[0042] It should be noted that since the surface of the router casing is white, the shooting background needs to be set to white when shooting to facilitate subsequent quality assessment.

[0043] At this point, the edge image of the router casing is obtained.

[0044] Step S002: obtaining a plurality of initial heat dissipation hole regions in the edge image according to the shape change of the edge in the edge image; obtaining a plurality of heat dissipation hole regions in the edge image according to the distance change and area change between the initial heat dissipation hole regions.

[0045] It should be noted that in order to better analyze the potential impact of cracks on the router shell on the heat dissipation hole area, it is necessary to first determine the heat dissipation hole area. The edge image of the router shell is obtained above. Since the heat dissipation holes on the router shell are mainly circular, their edges will present a circular shape. Therefore, several initial heat dissipation hole areas are obtained through the morphological changes of the edges in the edge image.

[0046] Specifically, according to the morphological changes of the edge in the edge image, several initial heat dissipation hole regions in the edge image are obtained, as follows:

[0047] For any edge in the edge image of the router shell, obtain the original chain code of the edge, take the absolute value of the difference between each direction symbol in the original chain code and the next direction symbol as the change value of each direction symbol in the original chain code, and assign the change value of the direction symbol to The corresponding pixel points are used as the edge pixel points of the heat dissipation hole; the edges formed by the continuous heat dissipation hole edge pixel points are obtained and recorded as the initial heat dissipation hole edges; if any of the initial heat dissipation hole edges forms a closed area, the closed area is used as an initial heat dissipation hole area; if any of the initial heat dissipation hole edges does not form a closed area, the pixel points on the initial heat dissipation hole edge are fitted to obtain a closed circular area as an initial heat dissipation hole area. It should be noted that in this embodiment, the least squares method is used to perform circular fitting on the pixel points on the initial heat dissipation hole edge that does not form a closed area. The specific fitting is an existing method and will not be repeated in this embodiment.

[0048] It should be noted that since the heat dissipation holes are mainly circular, their edges will present a circular shape, which is reflected in the original chain code of the edge as a moderate change in the direction symbol. Therefore, the initial heat dissipation hole edge is screened by analyzing the change value of the direction symbol in the original chain code of the edge. At the same time, considering that the cracks may be connected to the heat dissipation holes, making it difficult to determine the edges of the heat dissipation holes, the pixels that show a shape close to a circle are fitted to obtain the initial heat dissipation hole area. Since the morphology of some cracks may be close to that of the heat dissipation holes, the initial heat dissipation hole area is obtained here, and further analysis is needed later.

[0049] It should be noted that the initial heat dissipation hole area is obtained above. Since the morphology of some cracks may be similar to that of heat dissipation holes, it will interfere with the determination of the true heat dissipation hole area. Therefore, it is necessary to combine the distance change and area change between the initial heat dissipation hole areas to obtain the true heat dissipation hole area. Since the distances between the heat dissipation hole areas are approximately equal and the areas are also relatively close, several heat dissipation hole areas in the edge image are obtained through distance change and area change.

[0050] Specifically, according to the distance change and area change between the initial heat dissipation hole regions, a plurality of heat dissipation hole regions in the edge image are obtained, which includes the following steps:

[0051] First, according to the distance change and area change between the initial heat dissipation hole areas, the probability that each initial heat dissipation hole area in the edge image of the router shell belongs to the heat dissipation hole area is obtained.

[0052] Secondly, according to the probability that the initial heat dissipation hole area belongs to the heat dissipation hole area, several heat dissipation hole areas are screened out.

[0053] Preferably, in one embodiment of the present invention, the probability that each initial heat dissipation hole area in the edge image of the router housing belongs to the heat dissipation hole area is obtained according to the distance change and area change between the initial heat dissipation hole areas, as follows:

[0054] For any initial heat dissipation hole area in the edge image of the router shell, the shortest distance between the initial heat dissipation hole area and other initial heat dissipation hole areas is obtained; the difference value between the shortest distance and the average shortest distance is obtained, and the average shortest distance is the average value of the shortest distances between all initial heat dissipation hole areas and other initial heat dissipation hole areas; the difference value between the area of ​​the initial heat dissipation hole area and the average area of ​​all initial heat dissipation hole areas is obtained; the reciprocal of the difference value between the shortest distance and the average shortest distance and the reciprocal of the difference value between the area of ​​the initial heat dissipation hole area and the average area of ​​all initial heat dissipation hole areas are multiplied and normalized to obtain the probability that the initial heat dissipation hole area in the edge image of the router shell belongs to the heat dissipation hole area.

[0055] As a specific example, a specific method for obtaining the probability that the initial heat dissipation hole area belongs to the heat dissipation hole area is as follows:

[0056]

[0057] In the formula, The edge image of the router housing The shortest distance between an initial heat dissipation hole area and other initial heat dissipation hole areas; is the average of the shortest distances between all initial heat dissipation hole areas and other initial heat dissipation hole areas in the edge image of the router shell; To take the absolute value; The edge image of the router housing The number of pixels in the initial heat dissipation hole area; is the mean number of pixels in all initial heat dissipation hole areas in the edge image of the router shell; is a linear normalization function; The edge image of the router housing The probability that an initial heat dissipation hole area belongs to the heat dissipation hole area.

[0058] It should be noted that, since the distances between the heat dissipation hole areas are approximately equal and the areas are relatively similar, the above formula obtains the probability that each initial heat dissipation hole area in the edge image of the router housing belongs to the heat dissipation hole area by analyzing the distance change and area change between the initial heat dissipation hole areas. The smaller the The shortest distance between the initial heat dissipation hole area and other initial heat dissipation hole areas changes less than the overall average distance. The more regular the distance between the initial heat dissipation hole areas, the shorter the distance between the initial heat dissipation hole areas. The higher the probability that the initial heat dissipation hole area belongs to the heat dissipation hole area; The smaller the The area of ​​the first initial heat dissipation hole area changes less than the overall area. The more regular the area of ​​the first initial heat dissipation hole area, the The higher the probability that the initial heat dissipation hole area belongs to the heat dissipation hole area, the purpose of adding 1 to the denominator is to prevent the denominator from being 0, which would cause an incalculable situation.

[0059] It should be noted that the above-obtained probability that each initial heat dissipation hole region in the edge image of the router housing belongs to the heat dissipation hole region is obtained, and a number of heat dissipation hole regions are screened out by setting a suitable threshold.

[0060] Specifically, according to the probability that the initial heat dissipation hole area belongs to the heat dissipation hole area, several heat dissipation hole areas are screened out, as follows:

[0061] An initial heat dissipation hole region whose probability of belonging to the heat dissipation hole region is greater than a preset first threshold is used as the heat dissipation hole region in the edge image of the router housing, where the first threshold is 0.7.

[0062] At this point, several heat dissipation hole areas in the edge image are obtained.

[0063] Step S003, dividing the edge image according to the heat dissipation hole area to obtain a number of heat dissipation hole sub-areas of the edge image; obtaining a number of cracks in each heat dissipation hole sub-area according to the grayscale value of the pixel point in the heat dissipation hole sub-area and the position of the heat dissipation hole area; and obtaining the potential influence of each end of each crack in each heat dissipation hole sub-area on the heat dissipation hole area according to the proximity of the crack in the heat dissipation hole sub-area to the adjacent heat dissipation hole area after extension.

[0064] It should be noted that since the cracks on the router casing are mainly distributed between the heat dissipation hole areas, for better subsequent analysis, it is necessary to divide the edge image according to the heat dissipation hole areas to obtain the heat dissipation hole sub-areas.

[0065] Specifically, the edge image is divided according to the heat dissipation hole area to obtain several heat dissipation hole sub-areas of the edge image, as follows:

[0066] Starting from the upper left corner of the edge image of the router shell, in order from left to right and from top to bottom, the minimum circumscribed rectangle determined by every four adjacent heat dissipation hole areas is used as the heat dissipation hole sub-area of ​​the edge image of the router shell. It should be noted that if the remaining heat dissipation hole areas are not enough to form four adjacent heat dissipation hole areas at the end of the division, no analysis will be performed.

[0067] It should be noted that in the above-mentioned heat dissipation hole sub-area, the cracks are mainly distributed between the heat dissipation hole areas in the heat dissipation hole sub-area. In order to better determine the potential impact of the cracks on the heat dissipation hole area, it is necessary to first determine the cracks in the heat dissipation hole sub-area. Since the grayscale expression of the cracks is similar to that of the heat dissipation hole area, both are pixels with a grayscale value of 0, the cracks in the heat dissipation hole sub-area can be determined by the grayscale value of the pixel points in the heat dissipation hole sub-area and the position of the heat dissipation hole area.

[0068] Specifically, according to the grayscale value of the pixel point in the heat dissipation hole sub-region and the position of the heat dissipation hole region, several cracks in each heat dissipation hole sub-region are obtained, as follows:

[0069] For any heat dissipation hole sub-region, obtain the pixel point with a grayscale value of 0 in the heat dissipation hole sub-region. If the pixel point with a grayscale value of 0 does not belong to the heat dissipation hole region in the heat dissipation hole sub-region, take the pixel point as the crack pixel point of the heat dissipation hole sub-region, obtain all the crack pixel points of the heat dissipation hole sub-region, and obtain several cracks in the heat dissipation hole sub-region according to the continuous crack pixel points in the heat dissipation hole sub-region.

[0070] It should be noted that since there are multiple heat dissipation hole sub-areas, some of the heat dissipation hole sub-areas may not have cracks. This embodiment mainly analyzes the heat dissipation hole sub-areas with cracks, while normal heat dissipation hole sub-areas do not have problems and are not analyzed.

[0071] It should be noted that the main purpose of this embodiment is to obtain the quality index of the heat dissipation hole sub-area by analyzing the potential impact of the cracks on the router shell on the heat dissipation hole area, and to obtain the assembly quality parameters of the router shell in combination with the performance of the cracks on the router shell. The cracks in the heat dissipation hole sub-area have been obtained above, and the potential impact of each end of the crack on the heat dissipation hole area is analyzed next. The closer the crack in the heat dissipation hole sub-area is to the adjacent heat dissipation hole area after extension, the more likely the crack will extend to the heat dissipation hole area after a period of time, and the greater the potential impact on the heat dissipation hole area. Therefore, by analyzing the proximity of the crack to the adjacent heat dissipation hole area after extension, the potential impact of each end of the crack on the heat dissipation hole area is obtained.

[0072] Preferably, in one embodiment of the present invention, the potential influence of each end of each crack in each heat dissipation hole sub-region on the heat dissipation hole region is obtained according to the proximity of the crack in the heat dissipation hole sub-region to the adjacent heat dissipation hole region after the crack extends, as follows:

[0073] For any heat dissipation hole sub-region with a crack and any end of any crack in the heat dissipation hole sub-region, the shortest distance from the crack to the nearest heat dissipation hole region in the extension direction of the end is obtained, which is recorded as the first shortest distance; the angle value between the extension direction of the crack at the end and the horizontal right direction is obtained, and the angle value is the angle value obtained with the horizontal right direction as 0° and the counterclockwise direction as the positive direction; the first angle value between the extension direction of the crack at the end and the nearest heat dissipation hole region is obtained, and the specific method for obtaining the first angle value is as follows: the distance between the last pixel point of the crack at the end and the tangent of the nearest heat dissipation hole region in the extension direction of the end is obtained, and the minimum angle value between the extension direction of the crack at the end and the tangent is taken as the first angle value; the reciprocal of the first shortest distance, the reciprocal of the angle value and the difference value of the first angle value are multiplied and normalized to obtain the potential impact of the crack at the end of the heat dissipation hole sub-region on the heat dissipation hole region.

[0074] As a specific example, the specific method for obtaining the potential impact degree is as follows:

[0075] Any heat dissipation hole sub-region with cracks is recorded as a target heat dissipation hole sub-region.

[0076] The extension direction of each crack at each end in the target heat dissipation hole sub-region is obtained. The specific method for obtaining the extension direction is as follows: for the last two pixels at any end of any crack in the target heat dissipation hole sub-region, the direction in which the second-last pixel of the last two pixels points to the last pixel is used as the extension direction of the crack at this end.

[0077]

[0078] In the formula, The target heat dissipation hole area The first shortest distance between the crack at the first end and the nearest heat dissipation hole area in the extension direction; The target heat dissipation hole area The angle between the extension direction of the crack at the first end and the horizontal rightward direction, wherein the angle is obtained with the horizontal rightward direction as 0° and the counterclockwise direction as the positive direction; The target heat dissipation hole area The first angle value between the extension direction of the crack at the first end and the nearest heat dissipation hole area, the specific method for obtaining the first angle value is as follows: obtain the first angle value in the target heat dissipation hole sub-area The last pixel point of the crack at the first end is the tangent line of the nearest heat dissipation hole area in the extension direction of the first end, and the first pixel point in the target heat dissipation hole sub-area is The minimum angle between the extension direction of the crack at the first end and the tangent line is denoted as ; To take the absolute value; is a linear normalization function; The target heat dissipation hole area The potential impact of the first end of the crack on the heat dissipation hole area.

[0079] It should be noted that if the crack in the heat dissipation hole sub-region is closer to the nearby heat dissipation hole region after extension, the crack may extend to the heat dissipation hole region after a period of time, and the potential impact on the heat dissipation hole region will be greater. Therefore, the above formula obtains the potential impact of each end of the crack on the heat dissipation hole region by analyzing the proximity of the crack to the nearby heat dissipation hole region after extension. The smaller the The closer the crack is to the nearest heat dissipation hole area in the extension direction of the first end, the greater the potential impact on the nearest heat dissipation hole area; The smaller the The smaller the angle between the extension direction of the crack at the first end and the tangent line passing through the last pixel point at the first end, the more likely the crack extension trend is to approach the heat dissipation hole area, and the greater the potential impact on the nearest heat dissipation hole area; the potential impact of each end of the crack on the heat dissipation hole area is obtained by combining the distance and angle.

[0080] Thus, the potential influence degree of each end of each crack in each heat dissipation hole sub-region on the heat dissipation hole region is obtained.

[0081] Step S004: obtaining a quality index of each heat dissipation hole sub-region according to the number and area of ​​cracks in the heat dissipation hole sub-region and the potential influence of each end of each crack on the heat dissipation hole region; obtaining an assembly quality parameter of the router housing according to the quality index of the heat dissipation hole sub-region, the area of ​​the heat dissipation hole region in the edge image and the area of ​​the crack in the edge image; and evaluating the assembly quality of the router housing according to the size of the assembly quality parameter.

[0082] It should be noted that the above-mentioned potential influence of each end of each crack in each heat dissipation hole sub-area on the heat dissipation hole area is obtained. Next, the quality of each heat dissipation hole sub-area is analyzed to better evaluate the assembly quality of the router shell. Since the quality of the heat dissipation hole sub-area is related to the number and area of ​​cracks in the heat dissipation hole sub-area and the potential influence of the two ends of each crack in the heat dissipation hole sub-area on the heat dissipation hole area, the greater the number, area and potential influence of cracks in the heat dissipation hole sub-area, the worse the quality of the heat dissipation hole sub-area is. Therefore, the quality index of the heat dissipation hole sub-area is obtained by analyzing the number and area of ​​cracks in the heat dissipation hole sub-area and the potential influence of the two ends of each crack in the heat dissipation hole sub-area on the heat dissipation hole area.

[0083] Preferably, in one embodiment of the present invention, the quality index of each heat dissipation hole sub-region is obtained according to the number and area of ​​cracks in the heat dissipation hole sub-region and the potential influence of each end of each crack on the heat dissipation hole region, as follows:

[0084] For any heat dissipation hole sub-region, the average potential influence degree of both ends of each crack in the heat dissipation hole sub-region on the heat dissipation hole region is obtained, and the product of the reciprocal of the average potential influence degree and the reciprocal of the corresponding crack area is used as the weighted potential influence degree of the crack on the heat dissipation hole region; the product of the accumulated value of the weighted potential influence degree of all cracks in the heat dissipation hole sub-region on the heat dissipation hole region and the reciprocal of the number of cracks in the heat dissipation hole sub-region is used as the quality index of the heat dissipation hole sub-region.

[0085] As a specific example, the specific method for obtaining the quality index is as follows:

[0086]

[0087] In the formula, is the number of cracks in the target heat dissipation hole area; The target heat dissipation hole area The area of ​​the crack; The target heat dissipation hole area The potential impact of the first end of the crack on the heat dissipation hole area; The target heat dissipation hole area The potential impact of the second end of the crack on the heat dissipation hole area; is the quality index of the target heat dissipation hole sub-region.

[0088] It should be noted that since the quality of the heat dissipation hole sub-region is related to the number and area of ​​cracks in the heat dissipation hole sub-region and the potential influence of both ends of each crack in the heat dissipation hole sub-region on the heat dissipation hole region, the greater the number, area and potential influence of cracks in the heat dissipation hole sub-region, that is, , , The larger it is, the worse the quality of the heat dissipation hole sub-area is. Therefore, the quality index of the heat dissipation hole sub-area is obtained by performing an inverse analysis.

[0089] It should be noted that the quality index of each heat dissipation hole sub-region is obtained above. By combining the quality index of the heat dissipation hole sub-region, the area of ​​the heat dissipation hole region and the area of ​​the crack, the assembly quality parameters of the router shell can be more reasonably evaluated. When the quality index of the heat dissipation hole sub-region is larger, the area of ​​the heat dissipation hole region is larger and the area of ​​the crack is smaller, it means that the assembly quality of the router shell is higher, that is, the assembly quality parameter of the router shell is larger.

[0090] Preferably, in one embodiment of the present invention, the assembly quality parameters of the router housing are obtained according to the quality index of the heat dissipation hole sub-region, the area of ​​the heat dissipation hole region in the edge image, and the area of ​​the crack in the edge image, as follows:

[0091] The average value of the quality index of all heat dissipation hole sub-areas, the ratio of the area of ​​all heat dissipation hole areas to the area of ​​the edge image, and the inverse of all crack areas in the edge image are multiplied and normalized to obtain the assembly quality parameters of the router housing.

[0092] As a specific example, the specific method for obtaining the assembly quality parameters is as follows:

[0093]

[0094] In the formula, is the average quality index of all heat dissipation hole sub-areas; is the area of ​​all heat dissipation holes in the edge image; is the area of ​​the edge image; is the area of ​​all cracks in the edge image; is a linear normalization function; It is the assembly quality parameter of the router casing.

[0095] It should be noted that The larger it is, the higher the overall quality of the heat dissipation hole area is, and the higher the assembly quality of the corresponding router shell is. The larger the value, the larger the heat dissipation hole area is, and the higher the assembly quality of the router shell is; The smaller it is, the smaller the crack on the surface of the router shell is, and the higher the assembly quality of the router shell is.

[0096] It should be noted that the assembly quality parameters of the router housing are obtained above, and the assembly quality of the router housing is evaluated by setting a suitable threshold.

[0097] Specifically, the assembly quality of the router housing is evaluated according to the size of the assembly quality parameters, as follows:

[0098] If the assembly quality parameter of the router shell is less than the preset second threshold, the assembly quality of the router shell is unqualified; if the assembly quality parameter of the router shell is greater than or equal to the preset second threshold, the assembly quality of the router shell is qualified; this embodiment is described with the second threshold being 0.8.

[0099] Through the above steps, an intelligent evaluation method for the assembly quality of a router housing is completed.

[0100] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent evaluation method for the assembly quality of a router housing, characterized in that: The method comprises the following steps: Get an edge image of the router housing; According to the shape change of the edge in the edge image, several initial heat dissipation hole regions in the edge image are obtained; according to the distance change and area change between the initial heat dissipation hole regions, several heat dissipation hole regions in the edge image are obtained; The edge image is divided according to the heat dissipation hole area to obtain several heat dissipation hole sub-areas of the edge image; several cracks in each heat dissipation hole sub-area are obtained according to the gray value of the pixel point in the heat dissipation hole sub-area and the position of the heat dissipation hole area; the potential influence of each end of each crack in each heat dissipation hole sub-area on the heat dissipation hole area is obtained according to the proximity of the crack in the heat dissipation hole sub-area to the adjacent heat dissipation hole area after extension; According to the number and area of ​​cracks in the heat dissipation hole sub-region and the potential influence of each end of each crack on the heat dissipation hole region, the quality index of each heat dissipation hole sub-region is obtained; according to the quality index of the heat dissipation hole sub-region, the area of ​​the heat dissipation hole region in the edge image and the area of ​​the crack in the edge image, the assembly quality parameters of the router shell are obtained; according to the size of the assembly quality parameters, the assembly quality of the router shell is evaluated.

2. According to claim 1, a method for intelligently evaluating the assembly quality of a router housing is characterized in that: The method of obtaining a plurality of initial heat dissipation hole regions in the edge image according to the shape change of the edge in the edge image includes the following specific steps: For any edge in the edge image of the router shell, obtain the original chain code of the edge, take the absolute value of the difference between each direction symbol in the original chain code and the next direction symbol as the change value of each direction symbol in the original chain code, and assign the change value of the direction symbol to The corresponding pixel points are used as the edge pixel points of the heat dissipation hole; the edges formed by the continuous heat dissipation hole edge pixel points are obtained, and they are all recorded as the initial heat dissipation hole edges; if any initial heat dissipation hole edge forms a closed area, the closed area is used as an initial heat dissipation hole area; if any initial heat dissipation hole edge does not form a closed area, the pixel points on the initial heat dissipation hole edge are fitted to obtain a closed circular area as an initial heat dissipation hole area.

3. According to claim 1, a method for intelligently evaluating the assembly quality of a router housing is characterized in that: The specific steps of obtaining a plurality of heat dissipation hole regions in the edge image according to the distance change and area change between the initial heat dissipation hole regions are as follows: For any initial heat dissipation hole area in the edge image of the router shell, obtain the shortest distance between the initial heat dissipation hole area and other initial heat dissipation hole areas; obtain the difference between the shortest distance and the average shortest distance, where the average shortest distance is the average of the shortest distances between all initial heat dissipation hole areas and other initial heat dissipation hole areas; obtain the difference between the area of ​​the initial heat dissipation hole area and the average area of ​​all initial heat dissipation hole areas; multiply the reciprocal of the difference between the shortest distance and the average shortest distance and the reciprocal of the difference between the area of ​​the initial heat dissipation hole area and the average area of ​​all initial heat dissipation hole areas, and normalize them to obtain the probability that the initial heat dissipation hole area in the edge image of the router shell belongs to the heat dissipation hole area; According to the probability that the initial heat dissipation hole area belongs to the heat dissipation hole area, several heat dissipation hole areas are screened out.

4. According to claim 3, a method for intelligently evaluating the assembly quality of a router housing is characterized in that: The specific steps of screening out a number of heat dissipation hole areas according to the probability that the initial heat dissipation hole area belongs to the heat dissipation hole area are as follows: An initial heat dissipation hole region whose probability of belonging to the heat dissipation hole region is greater than a preset first threshold is used as the heat dissipation hole region in the edge image of the router housing, where the first threshold is 0.

7.

5. According to claim 1, a method for intelligently evaluating the assembly quality of a router housing, characterized in that: The step of dividing the edge image according to the heat dissipation hole area to obtain a plurality of heat dissipation hole sub-areas of the edge image includes the following specific steps: Starting from the upper left corner of the edge image of the router shell, in order from left to right and from top to bottom, the minimum circumscribed rectangle determined by every four adjacent heat dissipation hole areas is used as the heat dissipation hole sub-area of ​​the edge image of the router shell.

6. The intelligent evaluation method for the assembly quality of a router housing according to claim 1, characterized in that: The specific steps of obtaining a number of cracks in each heat dissipation hole sub-region according to the grayscale value of the pixel point in the heat dissipation hole sub-region and the position of the heat dissipation hole region are as follows: For any heat dissipation hole sub-region, obtain the pixel point with a grayscale value of 0 in the heat dissipation hole sub-region. If the pixel point with a grayscale value of 0 does not belong to the heat dissipation hole region in the heat dissipation hole sub-region, take the pixel point as the crack pixel point of the heat dissipation hole sub-region, obtain all the crack pixel points of the heat dissipation hole sub-region, and obtain several cracks in the heat dissipation hole sub-region according to the continuous crack pixel points in the heat dissipation hole sub-region.

7. The method for intelligently evaluating the assembly quality of a router housing according to claim 1, characterized in that: The step of obtaining the potential influence of each end of each crack in each heat dissipation hole sub-region on the heat dissipation hole region according to the proximity of the crack in the heat dissipation hole sub-region to the adjacent heat dissipation hole region after the crack in the heat dissipation hole sub-region extends includes the following specific steps: For any heat dissipation hole sub-region with a crack and any end of any crack in the heat dissipation hole sub-region, the shortest distance from the crack to the nearest heat dissipation hole region in the extension direction of the end is obtained, which is recorded as the first shortest distance; the angle value between the extension direction of the crack at the end and the horizontal right direction is obtained, and the angle value is the angle value obtained with the horizontal right direction as 0° and the counterclockwise direction as the positive direction; the first angle value between the extension direction of the crack at the end and the nearest heat dissipation hole region is obtained, and the specific method for obtaining the first angle value is as follows: the distance between the last pixel point of the crack at the end and the tangent of the nearest heat dissipation hole region in the extension direction of the end is obtained, and the minimum angle value between the extension direction of the crack at the end and the tangent is taken as the first angle value; the reciprocal of the first shortest distance, the reciprocal of the angle value and the difference value of the first angle value are multiplied and normalized to obtain the potential impact of the crack at the end of the heat dissipation hole sub-region on the heat dissipation hole region.

8. The intelligent evaluation method for the assembly quality of a router housing according to claim 1, characterized in that: The method of obtaining the quality index of each heat dissipation hole sub-region according to the number and area of ​​cracks in the heat dissipation hole sub-region and the potential influence of each end of each crack on the heat dissipation hole region includes the following specific steps: For any heat dissipation hole sub-region, the average potential influence degree of both ends of each crack in the heat dissipation hole sub-region on the heat dissipation hole region is obtained, and the product of the reciprocal of the average potential influence degree and the reciprocal of the corresponding crack area is used as the weighted potential influence degree of the crack on the heat dissipation hole region; the product of the accumulated value of the weighted potential influence degree of all cracks in the heat dissipation hole sub-region on the heat dissipation hole region and the reciprocal of the number of cracks in the heat dissipation hole sub-region is used as the quality index of the heat dissipation hole sub-region.

9. The method for intelligently evaluating the assembly quality of a router housing according to claim 1, characterized in that: The method of obtaining the assembly quality parameter of the router housing according to the quality index of the heat dissipation hole sub-region, the area of ​​the heat dissipation hole region in the edge image, and the area of ​​the crack in the edge image includes the following specific steps: The average value of the quality index of all heat dissipation hole sub-areas, the ratio of the area of ​​all heat dissipation hole areas to the area of ​​the edge image, and the inverse of all crack areas in the edge image are multiplied and normalized to obtain the assembly quality parameters of the router housing.

10. The method for intelligently evaluating the assembly quality of a router housing according to claim 1, characterized in that: The specific steps of evaluating the assembly quality of the router housing according to the size of the assembly quality parameter are as follows: If the assembly quality parameter of the router shell is less than the preset second threshold, the assembly quality of the router shell is unqualified; if the assembly quality parameter of the router shell is greater than or equal to the preset second threshold, the assembly quality of the router shell is qualified; The second threshold is 0.8.

Citation Information

Patent Citations

  • Computer host shell scratch detection method based on image features

    CN117197138A

  • Router shell production quality detection method based on artificial intelligence

    CN118014935A