FPC flexible flat cable appearance defect detection method and device, medium and product

Abstract

The invention relates to the technical field of FPC detection, in particular to an FPC flexible flat cable appearance defect detection method and device, a medium and a product. The method comprises the following steps: acquiring an original image, a circuit layer wiring diagram and a laminated structure diagram of the FPC flexible flat cable; respectively comparing the original image with the circuit layer wiring diagram and the laminated structure diagram, and determining the appearance defect of the FPC flexible flat cable; based on the appearance defect of the FPC flexible flat cable, whether the FPC flexible flat cable can be reworked is judged, and if it is judged that the FPC flexible flat cable can be reworked, the reworking cost is calculated; and determining a processing strategy of the FPC flexible flat cable based on the rework cost and the new product cost of the FPC flexible flat cable. According to the invention, the detection accuracy of the appearance defects of the FPC flexible flat cable can be improved.

Description

Technical Field

[0001] The present application relates to the field of FPC detection technology, and in particular to a method, equipment, medium and product for detecting appearance defects of FPC flexible cables. Background Art

[0002] Flexible printed circuit (FPC) cables are widely used in consumer electronics, automotive electronics, medical devices, and other fields due to their lightweight, flexible, and high-density wiring. However, FPCs are prone to various cosmetic defects during the manufacturing process, directly impacting product reliability and service life. The related technology relies on experienced inspectors performing visual inspections using microscopes, which can easily lead to missed inspections due to fatigue. Summary of the Invention

[0003] In order to solve the problem of low accuracy in detecting appearance defects of FPC flexible cables in the prior art, the present application provides a method, device, medium and product for detecting appearance defects of FPC flexible cables.

[0004] In the first aspect, the present application provides a method for detecting appearance defects of FPC flexible cables, which adopts the following technical solutions: A method for detecting appearance defects of an FPC flexible cable, comprising: Obtain the original image, circuit layer routing diagram and stacking structure diagram of the FPC flexible cable; Comparing the original image with the circuit layer routing diagram and the stacking structure diagram respectively to determine the appearance defects of the FPC flexible cable; Determining whether the FPC cable can be reworked based on the appearance defects of the FPC cable, and if it is determined that the FPC cable can be reworked, calculating the rework cost; A processing strategy for the FPC flexible cable is determined based on the rework cost and the new product cost of the FPC flexible cable.

[0005] By adopting the above technical solution, the original image is compared with the circuit layer routing diagram and the stacking structure diagram respectively, which can accurately identify various appearance defects, including circuit defects, surface blemishes and cover film defects, etc., greatly improving the accuracy of defect identification. Based on the identified appearance defects, it is judged whether the FPC soft cable can be reworked, which can avoid ineffective rework of unrepairable products, saving time and cost. When it is determined that rework is possible, the rework cost is calculated to make the cost accounting clear and transparent. By comparing the rework cost and the new product cost to determine the processing strategy, it can help producers reduce production losses and improve production efficiency and resource utilization based on the cost-effectiveness principle.

[0006] In a preferred example, the present application may be further configured as follows: comparing the original image with the circuit layer routing diagram and the stacking structure diagram to determine the appearance defects of the FPC flexible cable, including: Comparing the original image with the circuit layer trace, identifying a first defective region having a circuit defect and a second defective region having a surface flaw on the original image, and determining the degree of defects in the first defective region and the second defective region; The original image and the stacked structure diagram are compared to identify a third defective area having a cover film defect on the original image, and determine the degree of the defect in the third defective area.

[0007] By adopting the above technical solution and comparing the original image with the circuit layer routing diagram, not only can the first defect area of the circuit defect be identified through parameters such as circuit shape and line width, but the second defect area of the surface defect can also be determined based on surface texture and color information. Moreover, by quantitatively analyzing relevant features, the defect degree of these two types of defect areas can be accurately determined. By comparing the original image with the stacking structure diagram, the third defect area of the covering film defect can be identified with reference to the designed covering film position, thickness and other information. The defect degree of the area can be determined by comparing the actual with the standard. For example, the offset of the covering film can be accurately detected through the covering film boundary information in the stacking structure diagram, thereby improving the accuracy and reliability of FPC soft cable appearance defect identification.

[0008] In a preferred example, the present application may be further configured as follows: comparing the original image with the circuit layer trace to identify a first defective area having a circuit defect on the original image, including: Extracting a standard line width from the wiring diagram of the circuit layer; Extracting a center line of each circuit in the original image, and identifying a disconnection area in the original image based on the standard line width and the center line of each circuit; Identifying an area of a non-designed connection region in the original image, and identifying a short circuit region in the original image based on the standard line width and the area; The local edge curvature of each circuit in the original image is calculated, and the burr area in the original image is identified based on the local edge curvature and a preset standard curvature; the open circuit area, the short circuit area and the burr area constitute the first defect area.

[0009] By adopting the above technical solution, the center lines of each line in the original image are extracted, and the broken circuit areas are identified in combination with the standard line width. This can accurately locate the connection anomalies caused by disconnection in the line without missing the line break points, greatly improving the accuracy of broken circuit detection, identifying the area of non-designed connection areas, and identifying short-circuit areas based on the standard line width, effectively filtering out misjudgments caused by the line's own characteristics, and accurately locking short-circuit problems in complex line structures. The local curvature of each line edge in the original image is calculated and compared with the preset standard curvature to identify burr areas. It can not only keenly capture subtle anomalies on the line edge, but also reduce the subjectivity of human judgment through quantified curvature comparison, thereby improving the accuracy of line defect detection.

[0010] In a preferred example, the present application may be further configured as follows: comparing the original image with the circuit layer trace to identify a second defective area having a surface defect on the original image, including: Extracting linear features from the original image, determining initial scratches based on the linear features, and filtering the initial scratches based on the circuit layer alignment diagram to obtain a scratch area; The color features of the original image and the standard color features of the circuit layer trace are extracted, and the color features are compared with the standard color features to obtain a color difference area; the scratch area and the color difference area constitute the second defect area.

[0011] By adopting the above technical solution, linear features are extracted from the original image and the initial scratches are determined. This can keenly capture linear information similar to scratches in the image, providing basic data for scratch detection. The initial scratches are filtered with the help of the circuit layer routing diagram, effectively eliminating the interference caused by the circuit itself, greatly improving the accuracy of scratch detection. The color features of the original image and the circuit layer routing diagram are extracted and compared, and the color difference areas caused by oxidation can be accurately identified.

[0012] In a preferred example, the present application may be further configured as follows: the original image includes a plane image and a surface height map of the FPC flexible cable; The comparing the original image with the stacked structure diagram to identify a third defective area having a cover film defect on the original image includes: Extracting an actual cover film boundary from the planar image and extracting a designed cover film boundary from the stacked structure diagram, comparing the actual cover film boundary with the designed cover film boundary to obtain an offset area of the actual cover film boundary compared to the designed cover film boundary; The surface height map and the stacked structure map are compared to determine the bubble area of the cover film of the FPC cable; the offset area and the bubble area constitute the third defect area.

[0013] By adopting the above technical solution, the actual covering film boundary is extracted from the plane image in the original image, and the designed covering film boundary is extracted from the laminate structure diagram. By comparing the two, the offset area of the covering film can be determined intuitively and accurately. The bubble area is determined by comparing the surface height map and the laminate structure map. The surface height map provides three-dimensional information of the covering film surface, which makes up for the lack of height information in the plane image, so that the detection system can keenly capture the surface bulges or depressions of the covering film caused by bubbles, effectively identify bubbles hidden inside the covering film, and greatly improve the sensitivity of bubble detection.

[0014] In a preferred example, the present application may be further configured as follows: judging whether the FPC flexible cable can be reworked based on the appearance defect of the FPC flexible cable includes: Determine whether there is an irreparable defect type among the appearance defects of the FPC flexible cable; If the unrepairable defect type does not exist in the appearance defects, determine whether the defect degree of each defect type exceeds the corresponding repairable threshold; if the defect degree of each defect type of the FPC flexible cable does not exceed the corresponding repairable threshold, determine that the FPC flexible cable can be reworked.

[0015] By adopting the above technical solution, it is possible to determine whether there are unrepairable defect types in the appearance defects of FPC flexible cables, and quickly screen out products that cannot be repaired due to serious defects, avoiding the waste of manpower, material resources and time on such products, and effectively improving the utilization efficiency of production resources. When there are no unrepairable defect types, the defect degree of each defect type is compared with the corresponding repairable threshold, providing a quantitative and scientific evaluation standard for whether rework is possible, which not only avoids misjudgment due to subjective judgment, but also ensures the accuracy and consistency of the judgment results.

[0016] In a preferred example, the present application may be further configured as follows: the calculation of the rework cost includes: For each defect type in the appearance defects, calculating a sub-rework cost of the defect type based on the defect area and defect degree corresponding to the defect type; The sum of the sub-rework costs of each defect type in the appearance defect is calculated as the rework cost.

[0017] By adopting the above technical solution, for each defect type in the appearance defects, the sub-rework cost is calculated based on its corresponding defect area and defect degree, which can accurately refine the cost accounting to each specific defect type, fully considering the differences in repair difficulty and resource consumption of different defects, making the cost calculation more accurate and reasonable.

[0018] In a second aspect, the present application provides an electronic device, which adopts the following technical solution: one or more processors; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the FPC flexible cable appearance defect detection method as described in any one of the first aspects.

[0019] In a third aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium stores a computer program thereon. When the computer program is executed in a computer, the computer is caused to execute the FPC flexible cable appearance defect detection method as described in any one of the first aspects.

[0020] In a fourth aspect, the present application provides a computer program product that adopts the following technical solution: A computer program product includes a computer program. When the computer program is executed by a processor, it implements the FPC flexible cable appearance defect detection method as described in any one of the first aspects.

[0021] In summary, this application has the following beneficial technical effects: This application compares the original image with the circuit layer routing diagram and the stacking structure diagram respectively, and can accurately identify various types of appearance defects, including circuit defects, surface blemishes and covering film defects, etc., greatly improving the accuracy of defect identification. It determines whether the FPC soft cable can be reworked based on the identified appearance defects, which can avoid ineffective rework of unrepairable products, saving time and costs. When it is determined that rework is possible, the rework cost is calculated to make the cost accounting clear and transparent. The processing strategy is determined by comparing the rework cost and the new product cost. Based on the cost-effectiveness principle, it can help producers reduce production losses and improve production efficiency and resource utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 This is a flow chart of a method for detecting appearance defects of an FPC flexible cable provided in an embodiment of the present application; Figure 2 This is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] The following is combined with Figure 1 -Attached Figure 2 This application is described in further detail.

[0024] This specific embodiment is merely an explanation of the present application and is not a limitation of the present application. After reading this specification, those skilled in the art may make non-creative modifications to the present embodiment as needed, but as long as they are within the scope of the claims of the present application, they are protected by the patent law.

[0025] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0026] In this document, the term "and / or" simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document, unless otherwise specified, generally indicates an "or" relationship between the related objects.

[0027] It should be noted that in the optional embodiments of the present application, the object information and other related data involved, when the embodiments in the present application are applied to specific products or technologies, need to obtain the permission or consent of the object, and the collection, use and processing of the relevant data need to comply with the relevant laws, regulations and standards of the relevant countries and regions. In other words, if the embodiments of the present application involve data related to the object, it needs to be obtained through the authorization and consent of the object, the authorization and consent of the relevant departments, and in compliance with the relevant laws, regulations and standards of the country and region. If personal information is involved in the embodiments, the acquisition of all personal information requires the consent of the individual. If sensitive information is involved, the separate consent of the information subject needs to be obtained. The embodiments also need to be implemented with the authorization and consent of the object.

[0028] The present invention provides a method for detecting appearance defects of FPC flexible cables. Figure 1As shown, the method provided in the embodiment of the present application is performed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected via wired or wireless communication. The embodiment of the present application is not limited here. This embodiment uses any model of FPC flexible cable as an example to illustrate the appearance defect detection method. The method includes steps S101 to S104, wherein: S101, obtaining an original image of the FPC flexible cable, a circuit layer routing diagram, and a stacking structure diagram.

[0029] Specifically, the original image includes a planar image and a surface height map. A high-resolution industrial camera is used to capture the planar image of the FPC flexible cable, while a 3D structured light camera is used to capture the surface height map of the FPC flexible cable. Furthermore, the original image can be preprocessed, including image enhancement and image noise reduction, to improve image quality.

[0030] The circuit layer routing diagram and stacking structure diagram can be extracted from the CAD design file of the FPC soft cable, which contains detailed design information of the soft cable, such as circuit layout, line width, spacing, and stacking structure of each layer.

[0031] S102: Compare the original image with the circuit layer routing diagram and the stacking structure diagram to determine appearance defects of the FPC flexible cable.

[0032] Specifically, a feature matching algorithm is used to register the original image, the circuit layer trace, and the stackup structure diagram to ensure spatial alignment. Appearance defects fall into three categories: circuit defects, surface defects, and cover film defects. Circuit defects include short circuits, open circuits, and burrs; surface defects include scratches and oxidation; and cover film defects include film offset and bubbles.

[0033] Compare the planar image with the circuit layer trace to identify any circuit defects and surface flaws on the FPC cable, as well as the defect area and severity. Compare the planar image with the stackup structure diagram to identify any cover film offset on the FPC cable, and compare the surface height map with the stackup structure diagram to identify any cover film bubbles on the FPC cable.

[0034] S103 . Determine whether the FPC flexible cable can be reworked based on the appearance defects of the FPC flexible cable. If it is determined that the FPC flexible cable can be reworked, calculate the rework cost.

[0035] Specifically, for each defect type in the FPC flexible cable's appearance defects, a sub-rework cost for that defect type is calculated based on the defect area and defect severity corresponding to that defect type. The sub-rework cost includes the equipment cost, material cost, and labor cost required to repair that defect type. The rework cost is calculated as the sum of the sub-rework costs for each defect type in the FPC flexible cable's appearance defects.

[0036] S104: Determine a processing strategy for the FPC flexible cable based on the rework cost and the new product cost of the FPC flexible cable.

[0037] Specifically, the historical processing data of the FPC flexible flat cable is obtained, and the new product cost of the tested FPC flexible flat cable model is calculated based on the historical processing data. The rework cost and the new product cost are compared. If the rework cost is higher than the new product cost, the processing strategy for the FPC flexible flat cable is to process a new product. If the rework cost is not higher than the new product cost, the processing strategy for the FPC flexible flat cable is to rework and repair.

[0038] This embodiment can accurately identify various appearance defects, including circuit defects, surface flaws, and cover film defects, by comparing the original image with the circuit layer routing diagram and the stacking structure diagram, greatly improving the accuracy of defect identification. It can determine whether the FPC flexible cable can be reworked based on the identified appearance defects, thereby avoiding ineffective rework of unrepairable products and saving time and costs. When it is determined that rework is possible, the rework cost is calculated to make cost accounting clear and transparent. The processing strategy is determined by comparing the rework cost with the new product cost. Based on the cost-effectiveness principle, it can help manufacturers reduce production losses and improve production efficiency and resource utilization.

[0039] A possible implementation of the embodiment of the present application is to compare the original image with the circuit layer routing diagram and the stacking structure diagram to determine the appearance defects of the FPC flexible cable, including: Comparing the original image with the circuit layer trace, identifying a first defective area having a circuit defect and a second defective area having a surface defect on the original image, and determining the degree of defects in the first defective area and the second defective area; The original image and the stacked structure image are compared to identify a third defect area where a cover film defect exists on the original image, and determine the degree of the defect in the third defect area.

[0040] In this embodiment, the planar image is compared with the circuit layer alignment diagram to sequentially identify whether the planar image contains short circuit areas, open circuit areas, and burr areas. The identified defective areas constitute the first defect area of the circuit defect. The planar image is compared with the circuit layer alignment diagram to sequentially identify whether the planar image contains scratch areas and color difference areas (i.e., oxidized areas). The identified scratch areas and / or color difference areas constitute the second defect area of the surface defect. The planar image is compared with the stacking structure diagram to identify the offset area of the cover film in the planar image. The surface height map is compared with the stacking structure diagram to identify the bubble area in the surface height map where bubbles are present. The offset area and bubble area constitute the third defect area of the cover film defect.

[0041] By comparing the original image with the circuit layer routing diagram, this embodiment can not only identify the first defect area of the circuit defect through parameters such as circuit shape and line width, but also determine the second defect area of the surface defect based on surface texture and color information. By quantitatively analyzing related features, the defect degrees of these two types of defect areas can be accurately determined. By comparing the original image with the stacking structure diagram, the third defect area of the covering film defect can be identified with reference to the designed covering film position, thickness and other information. The defect degree of this area can be determined by comparing the actual and standard differences. For example, the offset of the covering film can be accurately detected through the covering film boundary information in the stacking structure diagram, thereby improving the accuracy and reliability of FPC soft cable appearance defect identification.

[0042] A possible implementation of the embodiment of the present application is to compare the original image with the circuit layer trace to identify a first defective area having a circuit defect in the original image, including: Extract standard line width from the circuit layer trace diagram; Extract the center line of each line in the original image, and identify the disconnection area in the original image based on the standard line width and the center line of each line; Identify the area of non-designed connection areas in the original image, and identify short-circuit areas in the original image based on standard line width and area; The local edge curvature of each circuit in the original image is calculated, and the burr area in the original image is identified based on the local edge curvature and a preset standard curvature; the open circuit area, the short circuit area and the burr area constitute the first defect area.

[0043] In this embodiment, the standard line width can be directly extracted from the parameters of the line layer routing diagram, where the line width represents the size of the line in a direction perpendicular to the current flow.

[0044] The process of extracting the centerline of each line in the original image involves grayscaling, noise reduction, and binarization. Grayscaling converts the image into a grayscale image, reducing color interference and retaining only brightness information. Noise reduction can improve image quality. Binarization can be performed by presetting an appropriate threshold using a global thresholding method. Regions in the image with pixel values greater than the threshold are set to white (representing the line), and regions with pixel values less than the threshold are set to black (representing the background). Next, an edge detection algorithm is used to extract the edges of each line in the image to obtain its outline. Skeletonization is then performed on each detected line to convert it into a single-pixel centerline.

[0045] For any line, the continuity is checked point by point along its centerline. The distance between each pair of adjacent pixels is calculated as the break distance. If the break distance between any two pixels exceeds the preset break threshold, a break is determined. If the break distance between any two adjacent pixels on the centerline does not exceed the preset break threshold, the line is deemed to be free of breaks and further identification of break areas is unnecessary. The preset break threshold is calculated as standard line width multiplied by a preset ratio, which can be set by technical personnel based on practical experience and industry standards.

[0046] For each centerline, define the two pixels where the break distance exceeds the standard as points A and B, respectively. Connect AB, and draw two perpendicular lines to AB through A and B, respectively. From the perpendicular line through A, start at A and extend to the ends of the perpendicular line, cutting line segments with a length of 1 / 2 the standard line width to obtain endpoints C and D. From the perpendicular line through B, start at B and extend to the ends of the perpendicular line, cutting line segments with a length of 1 / 2 the standard line width to obtain endpoints E and F. Connect CD, F, and EC sequentially to obtain a closed region as the break area. The resulting break area is a rectangle, and the area of the break area can be calculated based on the lengths of CD and AB. If there are multiple break locations in the planar image, multiple break areas will be determined.

[0047] For the disconnection region, the area of each disconnection region can be used as the corresponding defect degree.

[0048] After registering the planar image and the circuit layer trace, a connected domain analysis is performed on each of the planar image and the trace, demarcating each connected domain in the planar image and the trace. Each connected domain in the trace is uniquely numbered, and mapping and image difference operations are performed on the planar image and the trace. Areas in the planar image that are inconsistent with the trace are identified as initial non-designed connected areas. Each independent non-designed connected area is marked, and the trace number of the trace is mapped to the corresponding connected domain in the planar image.

[0049] Furthermore, for each non-designed connection area on the plane image, the number of numbers mapped on the connected domain where the non-designed connection area is located is identified. If the number exceeds 1, it is determined that the non-designed connection area has caused a short circuit, and the non-designed connection area is treated as a short-circuit area, and the area of the short-circuit area is calculated.

[0050] For the short-circuit region, the area of each short-circuit region may be used as the corresponding defect degree.

[0051] For the detection of burr areas, edge detection can be performed on the plane image to obtain the edge information of the line. The line edge can be discretized into a series of points. For each discrete point, the local curvature is calculated by calculating the geometric relationship of the points in the neighborhood. For example, the three-point method can be used to select the point and the two adjacent points before and after it, and the curvature of the arc formed by these three points can be calculated to approximate the local curvature of the point. According to the curvature characteristics of the normal line edge, a standard area threshold, namely the preset standard curvature, is preset. The calculated local curvature of each point is compared with the preset standard curvature. If the local curvature of a point (or more than a preset number of points) exceeds the preset standard curvature, the edge area is determined to be a burr area. The average local curvature of the points in the burr area that exceeds the preset standard area is used as the defect degree of the burr area.

[0052] This embodiment extracts the centerline of each line in the original image and uses the standard line width to identify the broken circuit area. This can accurately locate connection anomalies caused by disconnection in the line without missing any line break points, significantly improving the accuracy of broken circuit detection. It also identifies the area of non-designed connection areas and identifies short-circuit areas based on the standard line width, effectively filtering out misjudgments caused by the line's inherent characteristics. It can accurately identify short-circuit problems in complex line structures. It calculates the local curvature of each line edge in the original image and compares it with a preset standard curvature to identify burr areas. This not only can it keenly capture subtle anomalies at the line edge, but also reduces the subjectivity of human judgment through quantified curvature comparison, thereby improving the accuracy of line defect detection.

[0053] A possible implementation of the embodiment of the present application is to compare the original image with the circuit layer trace to identify a second defective area having a surface defect in the original image, including: Extract linear features from the original image, determine the initial scratch based on the linear features, and filter the initial scratch based on the circuit layer trace to obtain the scratch area; The color features of the original image and the standard color features of the circuit layer trace are extracted, and the color features and the standard color features are compared to obtain a color difference area; the scratch area and the color difference area constitute a second defect area.

[0054] In this embodiment, the plane image and the circuit layer routing diagram can be converted into grayscale images respectively, and then the edge information of the plane image and the circuit layer routing diagram can be extracted respectively using the edge detection algorithm. Then, the edge points obtained by the edge detection are converted into the parameter space using the Hough transform, and straight lines and curves are detected as linear features in the plane image and the circuit layer routing diagram respectively, to obtain the potential scratch positions preliminarily determined in the plane image.

[0055] For the extracted linear features, reasonable thresholds for length and direction are set to filter out lines that match the scratch characteristics from the plane image as the initial scratches. For example, a minimum length threshold can be set to exclude lines that are too short, and a reasonable direction range can be manually set based on experience or experiments to filter out lines that match the direction of common scratches.

[0056] Compare the initial scratch in the planar image with the linear features of the circuit layer trace. Exclude lines that overlap with the trace. For the remaining lines, determine their position in the planar image. Dilate each line, using the result as the scratch area. Furthermore, the length or area of each scratch can be used as the defect severity.

[0057] Color features are extracted from the planar image. For the circuit layer trace diagram, its standard color features can be set by technicians based on the color features of the actual FPC soft cable. Methods such as Euclidean distance and Mahalanobis distance can be used to calculate the difference between the color features of the planar image and the standard color features of the circuit layer trace diagram. The calculated color difference is compared with a preset color difference threshold, and areas where the color difference exceeds the preset color difference threshold are divided as color difference areas. The preset color difference threshold can be set based on actual oxidation conditions or oxidation experiments. Color differences exceeding the preset color difference threshold indicate excessive oxidation. The area of the color difference area is used as the corresponding defect level.

[0058] This embodiment extracts linear features from the original image and determines the initial scratches. It can keenly capture linear information similar to scratches in the image, providing basic data for scratch detection. It uses the circuit layer routing diagram to filter the initial scratches, effectively eliminating interference caused by the circuit itself, greatly improving the accuracy of scratch detection. The color features of the original image and the circuit layer routing diagram are extracted and compared, and the color difference areas caused by oxidation can be accurately identified.

[0059] In a possible implementation of the embodiment of the present application, the original image includes a plane image and a surface height map of the FPC flexible cable; Compare the original image with the stacked structure diagram to identify the third defect area where the cover film defect exists on the original image, including: Extracting the actual cover film boundary from the plane image and extracting the designed cover film boundary from the stacked structure diagram, comparing the actual cover film boundary with the designed cover film boundary to obtain an offset area of the actual cover film boundary compared to the designed cover film boundary; The surface height map and the stacking structure map are compared to determine the bubble area of the cover film of the FPC flexible cable; the offset area and the bubble area constitute the third defect area.

[0060] In this embodiment, edge detection and contour extraction are performed on a planar image to obtain all contours within the planar image. Predefined area and shape conditions are then selected from all contours to determine the actual cover film boundary. The area can be defined as the area of the actual cover film boundary being no less than a preset threshold, thereby eliminating interference from small areas. The shape is determined based on the actual shape of the cover film. Cover film boundary information is directly extracted from the stacked structure diagram based on the design data, serving as the designed cover film boundary.

[0061] The actual covering film boundary and the designed covering film boundary are matched with each other, and the offset between the corresponding points is calculated. The offset threshold is pre-set according to the production specifications. When the offset of a point exceeds the preset offset threshold, the area where the point is located is marked as an offset area.

[0062] By analyzing the surface height map, we can obtain height values at different locations. We extract the standard height information of the cover film from the stack structure diagram to clarify the height range of the cover film at different locations under normal conditions. We align the surface height map with the stack structure diagram, and calculate the height difference between the height value at each location on the surface height map and the required height at the corresponding location on the stack structure diagram. We pre-set a height difference threshold based on production specifications, compare each height difference value with the height difference threshold, and demarcate areas where the height difference exceeds the threshold as bubble areas. The area of the bubble area can be used as the degree of defect.

[0063] This embodiment uses the plane image in the original image to extract the actual covering film boundary, and at the same time extracts the designed covering film boundary from the laminate structure diagram. By comparing the two, the offset area of the covering film can be determined intuitively and accurately, and the bubble area is determined by comparing the surface height map and the laminate structure map. The surface height map provides three-dimensional information of the covering film surface, which makes up for the lack of height information in the plane image, allowing the detection system to keenly capture the surface protrusions or depressions of the covering film caused by bubbles, effectively identify bubbles hidden inside the covering film, and greatly improve the sensitivity of bubble detection.

[0064] A possible implementation of the embodiment of the present application is to determine whether an FPC flexible cable can be reworked based on appearance defects of the FPC flexible cable, including: Determine whether there are irreparable defects in the appearance of the FPC cable; If there is no unrepairable defect type among the appearance defects, determine whether the defect degree of each defect type exceeds the corresponding repairable threshold. If the defect degree of each defect type of the FPC flexible cable does not exceed the corresponding repairable threshold, it is determined that the FPC flexible cable can be reworked.

[0065] In this embodiment, defect types include: circuit short circuit, circuit break, circuit burr, scratch, oxidation, cover film offset, and cover film bubble. In addition to the defect types given in this embodiment, the defect type can also be flexibly set according to actual conditions, and this embodiment does not limit it. Technicians can pre-set the unrepairable defect type based on production conditions. Optionally, oxidation can be set as an unrepairable defect type. When an unrepairable defect type exists among the appearance defects of the FPC flexible cable, it is determined that the FPC flexible cable cannot be reworked.

[0066] For each defect type, a corresponding repairability threshold is pre-set based on actual production experience. Optionally, for line short circuits, a threshold for the number of shorted areas and a threshold for the area (single area area threshold and / or sum of area area threshold) can be set separately. The repairability threshold is exceeded if any of the following conditions exist: the number of shorted areas exceeds the number threshold, the area of a single area exceeds the single area threshold, or the sum of the areas of all shorted areas exceeds the sum of area threshold.

[0067] For line breaks, you can set the number threshold and area threshold of the broken areas (single area area threshold and / or area sum threshold) separately. When any of the following situations occurs, it is determined that the repairable threshold is exceeded: the number of broken areas exceeds the number threshold, the area of a certain area exceeds the single area threshold, and the sum of the areas of all broken areas exceeds the area sum threshold.

[0068] For line glitches, the burr area quantity threshold and curvature threshold can be set separately. When any of the following conditions exists, it is determined that the repairable threshold is exceeded: the number of burr areas exceeds the quantity threshold, or the curvature of a burr area exceeds the curvature threshold.

[0069] For scratches, you can set a scratch quantity threshold and a scratch length threshold respectively. When any of the following conditions exists, it is determined that the repairable threshold is exceeded: the number of scratches exceeds the quantity threshold, or the length of a certain scratch exceeds the length threshold.

[0070] For the offset of the cover film, an offset threshold can be pre-set. When any offset area exceeds the offset threshold, it is determined to have exceeded the repairable threshold.

[0071] For bubbles in the covering film, the bubble number and area thresholds can be pre-set. When any of the following conditions exists, it is determined that the repairable threshold is exceeded: the bubble number exceeds the number threshold, and the area of a certain bubble exceeds the area threshold.

[0072] If the degree of any defect type of the FPC cable exceeds the corresponding repairable threshold, the FPC cable is determined to be unreworkable.

[0073] This embodiment can quickly screen out products that cannot be repaired due to serious defects by determining whether there are unrepairable defect types among the appearance defects of the FPC flexible cable, avoiding wasting manpower, material resources and time on such products, and effectively improving the utilization efficiency of production resources. When there are no unrepairable defect types, the defect degree of each defect type is compared with the corresponding repairable threshold, providing a quantitative and scientific evaluation standard for whether rework is necessary, avoiding misjudgment due to subjective judgment, and ensuring the accuracy and consistency of the judgment results.

[0074] A possible implementation of the embodiment of the present application is to calculate the rework cost, including: For each defect type in the appearance defects, the sub-rework cost of the defect type is calculated based on the defect area and defect degree corresponding to the defect type. The sub-rework cost includes equipment cost, material cost and labor cost. The sum of the sub-rework costs of each defect type in the appearance defect is calculated as the rework cost.

[0075] In this embodiment, for defects such as short circuits, disconnects, burrs, scratches, and cover film bubbles, a repair cost per unit area (for scratches, a repair cost per unit length) can be pre-set for each defect type based on the actual repair situation. After the appearance defects of the FPC cable are determined, the sum of the defect area for each appearance defect type is calculated (for scratches, the sum of the lengths of each scratch is calculated). The product of the calculated sum of area / sum of length for each defect type and the corresponding unit repair cost (repair cost per unit area / repair cost per unit length) is used as the sub-rework cost for the defect type.

[0076] The unit repair cost for each defect type can be calculated by combining the sum of equipment and material costs. Specifically, based on historical experience, the repair time and material cost (material price) per unit area / length are determined. The ratio of the equipment's total production benefit (the sum of the economic benefits of all products) over its entire lifecycle to its lifecycle duration is used as the unit-time equipment production benefit. The product of the repair time and the unit-time equipment production benefit is then used as the equipment cost in the unit repair cost.

[0077] The new product cost of FPC flexible cables includes new product equipment cost and new product material cost. The new product material cost and new product production time are determined based on historical production experience. The product cost of new product equipment is the product of the equipment production efficiency per unit time and the new product production time. The sum of the new product equipment cost and the new product material cost is the new product cost.

[0078] This embodiment calculates the sub-rework cost for each defect type in the appearance defects based on its corresponding defect area and defect degree, and can accurately refine the cost accounting to each specific defect type, fully considering the differences in repair difficulty and resource consumption of different defects, making the cost calculation more accurate and reasonable.

[0079] An electronic device is provided in an embodiment of the present application, such as Figure 2 As shown, Figure 2 The electronic device 200 shown includes a processor 201 and a memory 203. The processor 201 and the memory 203 are connected, for example, via a bus 202. Optionally, the electronic device 200 may further include a transceiver 204. It should be noted that in actual applications, the number of transceivers 204 is not limited to one, and the structure of the electronic device 200 does not constitute a limitation on the embodiments of the present application.

[0080] Processor 201 can be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 201 can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0081] The bus 202 may include a path for transmitting information between the above components. The bus 202 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 202 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2 Only one thick line is used in the diagram, but it does not mean that there is only one bus or one type of bus.

[0082] The memory 203 may be a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0083] The memory 203 is used to store application code for executing the solution of the present application, and is controlled by the processor 201. The processor 201 is used to execute the application code stored in the memory 203 to implement the content shown in the embodiment of the FPC flexible cable appearance defect detection method.

[0084] Figure 2 The electronic device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0085] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer-readable storage medium is run on a computer, the computer can execute the contents shown in the aforementioned embodiment of the FPC flexible cable appearance defect detection method.

[0086] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the flowcharts of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0087] An embodiment of the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, the contents shown in the aforementioned FPC flexible cable appearance defect detection method embodiment are implemented.

[0088] The above are only some of the implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for detecting appearance defects of FPC flexible cables, characterized in that: include: Obtain the original image, circuit layer routing diagram and stacking structure diagram of the FPC flexible cable; Comparing the original image with the circuit layer routing diagram and the stacking structure diagram respectively to determine the appearance defects of the FPC flexible cable; Determining whether the FPC cable can be reworked based on the appearance defects of the FPC cable, and if it is determined that the FPC cable can be reworked, calculating the rework cost; A processing strategy for the FPC flexible cable is determined based on the rework cost and the new product cost of the FPC flexible cable.

2. The method for detecting appearance defects of FPC flexible cables according to claim 1, wherein: The comparing the original image with the circuit layer routing diagram and the stacking structure diagram to determine the appearance defects of the FPC flexible cable includes: Comparing the original image with the circuit layer trace, identifying a first defective region having a circuit defect and a second defective region having a surface flaw on the original image, and determining the degree of defects in the first defective region and the second defective region; The original image and the stacked structure diagram are compared to identify a third defective area having a cover film defect on the original image, and determine the degree of the defect in the third defective area.

3. The method for detecting appearance defects of FPC flexible cables according to claim 2, wherein: The comparing the original image with the circuit layer alignment diagram to identify a first defective area having a circuit defect on the original image includes: Extracting a standard line width from the wiring diagram of the circuit layer; Extracting a center line of each circuit in the original image, and identifying a disconnection area in the original image based on the standard line width and the center line of each circuit; Identifying an area of a non-designed connection region in the original image, and identifying a short circuit region in the original image based on the standard line width and the area; The local edge curvature of each circuit in the original image is calculated, and the burr area in the original image is identified based on the local edge curvature and a preset standard curvature; the open circuit area, the short circuit area and the burr area constitute the first defect area.

4. The method for detecting appearance defects of FPC flexible cables according to claim 2, wherein: The comparing the original image with the circuit layer alignment diagram to identify a second defective area having a surface defect on the original image includes: Extracting linear features from the original image, determining initial scratches based on the linear features, and filtering the initial scratches based on the circuit layer alignment diagram to obtain a scratch area; The color features of the original image and the standard color features of the circuit layer trace are extracted, and the color features are compared with the standard color features to obtain a color difference area; the scratch area and the color difference area constitute the second defect area.

5. The method for detecting appearance defects of FPC flexible cables according to claim 2, wherein: The original image includes a plane image and a surface height map of the FPC flexible cable; The comparing the original image with the stacked structure diagram to identify a third defective area having a cover film defect on the original image includes: Extracting an actual cover film boundary from the planar image and extracting a designed cover film boundary from the stacked structure diagram, comparing the actual cover film boundary with the designed cover film boundary to obtain an offset area of the actual cover film boundary compared to the designed cover film boundary; The surface height map and the stacked structure map are compared to determine the bubble area of the cover film of the FPC cable; the offset area and the bubble area constitute the third defect area.

6. The method for detecting appearance defects of FPC flexible cables according to claim 1, wherein: The determining whether the FPC flexible cable can be reworked based on the appearance defect of the FPC flexible cable includes: Determine whether there is an irreparable defect type among the appearance defects of the FPC flexible cable; If the unrepairable defect type does not exist in the appearance defects, determine whether the defect degree of each defect type exceeds the corresponding repairable threshold; if the defect degree of each defect type of the FPC flexible cable does not exceed the corresponding repairable threshold, determine that the FPC flexible cable can be reworked.

7. The method for detecting appearance defects of FPC flexible cables according to claim 1, wherein: The calculation of rework costs includes: For each defect type in the appearance defects, calculating a sub-rework cost of the defect type based on the defect area and defect degree corresponding to the defect type; The sum of the sub-rework costs of each defect type in the appearance defect is calculated as the rework cost.

8. An electronic device, characterized in that: include: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the FPC flexible cable appearance defect detection method according to any one of claims 1-7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed in a computer, the computer is caused to execute the FPC flexible cable appearance defect detection method according to any one of claims 1 to 7.

10. A computer program product, characterized in that The method comprises a computer program, which, when executed by a processor, implements the steps of the FPC flexible cable appearance defect detection method according to any one of claims 1 to 7.

Images