A method for detecting quality of production line harness

By generating the morphological matrix and pixel correlation matrix, the problems of incomplete and low efficiency of traditional wire harness detection are solved, and timely identification and efficient detection of wire harness quality are realized to ensure the quality and safety of wire harness products.

CN118710639BActive Publication Date: 2024-11-15QINGDAO YUJIN ELECTRO CIRCUIT SYST
View PDF 9 Cites 0 Cited by

Patent Information

Application Number
CN202411181342.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-27
Publication Date
2024-11-15
Estimated Expiration
2044-08-27

AI Technical Summary

Technical Problem

Traditional wire harness quality detection methods have problems such as incomplete inspection, low efficiency and error-prone, and it is difficult to meet the needs of modern industry for high-quality products.

Method used

A production line harness quality detection method is adopted to generate a morphological matrix by collecting target images, and the first and second pixel correlation matrices are further generated, the quality detection threshold is determined, and whether there are defects in the line harness. This method generates a morphological matrix through diagonal morphological pixel point sets and closed morphological pixel point sets, and uses Hadamama product operation to obtain a quality detection threshold to ensure the comprehensiveness and accuracy of the detection.

Benefits of technology

It realizes timely discovery and identification of wire harness quality, improves product quality and reliability, reduces failure rate and safety hazards in the production process, and improves production efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118710639B_ABST
    Figure CN118710639B_ABST
Patent Text Reader

Abstract

The present invention discloses a production line harness quality detection method, which belongs to the field of image processing technology, and includes the following steps: S1, collecting the target image when the harness is produced, and generating a morphological matrix for the target image; S2, based on the morphological matrix, generating a first pixel association matrix and a second pixel association matrix, and determining the quality detection threshold corresponding to the target image; S3, based on the quality detection threshold, determining whether the target image has quality defects. The present invention checks the appearance of the harness, finds its surface defects in time, and ensures that the quality of the harness meets the standard requirements, which not only improves the quality and reliability of the harness product, but also reduces the failure rate and safety hazards in the production process, and improves production efficiency.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention belongs to the technical field of image processing, and in particular relates to a method for detecting the quality of a production line harness. Background Art

[0002] As an important part of electrical connection, wire harness is widely used in many fields such as automobile, aerospace and electronic equipment. The quality of wire harness directly affects the stability and safety of the whole system. However, the traditional wire harness quality inspection method usually adopts manual inspection, but there are problems such as incomplete inspection, low inspection efficiency and easy error, which makes it difficult to meet the demand of modern industrial production for high-quality products. Summary of the invention

[0003] In order to solve the above problems, the present invention proposes a production line harness quality detection method.

[0004] The technical solution of the present invention is: a production line quality detection method comprises the following steps:

[0005] S1, collecting the target image when the wire harness is produced, and generating a morphological matrix for the target image;

[0006] S2. Based on the morphological matrix, generate a first pixel association matrix and a second pixel association matrix, and determine a quality detection threshold corresponding to the target image;

[0007] S3. Determine whether the target image has quality defects based on the quality detection threshold.

[0008] In S3, if there are pixels in the target image whose pixel values ​​are lower than the quality detection threshold, it means that there are abnormal pixels on the wiring harness, that is, there are quality defects.

[0009] Furthermore, S1 includes the following sub-steps:

[0010] S11, collecting the target image when the wire harness production is completed;

[0011] S12, extracting the pixel points where the two diagonal lines of the target image are located as a diagonal morphological pixel point set;

[0012] S13, the target image Line Column pixels, Line Column pixels, Line Column pixels and Line The pixel points of the columns are connected in sequence to form a closed line segment, and the pixel points where the closed line segment is located are taken as the closed morphological pixel point set, where M represents the number of rows of the target image, and N represents the number of columns of the target image. Indicates rounding up;

[0013] S14, generating a morphological pixel constraint value according to the diagonal morphological pixel point set and the closed morphological pixel point set;

[0014] S15. Generate a morphological matrix for the target image according to the morphological pixel constraint values.

[0015] The beneficial effect of the above further scheme is: in the present invention, the pixel points contained in the diagonal lines and closed line segments of the target image can cover the pixel conditions of the pixel points in most areas of the target image, so the present invention selects the pixel points of these line segments to form a pixel point set, and then extracts the characteristic pixel points of the two pixel point sets to generate morphological pixel constraint values.

[0016] Furthermore, in S14, the calculation formula of the morphological pixel constraint value B is: ; In the formula, a1 represents the pixel value of the first pixel in the diagonal pixel set, a I represents the pixel value of the first pixel in the diagonal pixel set, max(·) represents the maximum value operation, b1 represents the pixel value of the first pixel in the closed pixel set, and b J It represents the pixel value of the Jth pixel in the closed morphological pixel set, M represents the number of rows of the target image, and N represents the number of columns of the target image.

[0017] Furthermore, in S15, the morphology matrix X form The expression is: Where c 1,1 Represents the pixel value of the pixel in the first row and first column of the target image, c 1,N Represents the pixel value of the pixel in the 1st row and the Nth column in the target image, c M,1 Represents the pixel value of the pixel in the Mth row and the first column of the target image, c M,N represents the pixel value of the pixel at the Mth row and Nth column in the target image, and B represents the morphological pixel constraint value.

[0018] Furthermore, S2 includes the following sub-steps:

[0019] S21, generating a first pixel correlation matrix for the target image;

[0020] S22, performing a Hadamard product operation on the first pixel correlation matrix and the morphology matrix to obtain a second pixel correlation matrix;

[0021] S24. Determine a quality detection threshold corresponding to the target image according to the first pixel association matrix and the second pixel association matrix.

[0022] The beneficial effect of the above further scheme is that: in the present invention, the pixel points of each pixel point of the target image are reconstructed according to the characteristic parameters (i.e., the spectral radius) of the morphological matrix to obtain a first pixel quality matrix, and the second pixel association matrix is ​​obtained by element-by-element multiplication of the first pixel quality matrix and the morphological matrix. The first pixel association matrix and the second pixel association matrix have the same size, and the quality detection threshold can be obtained after the operation.

[0023] Furthermore, S21 includes the following sub-steps:

[0024] S211, extracting the spectrum radius of the morphological matrix;

[0025] S212: Determine the element value of each pixel in the first pixel association matrix according to the spectral radius of the morphological matrix and the pixel values ​​of the pixel points in the target image, and generate a first pixel association matrix.

[0026] The number of rows and columns of the first pixel association matrix is ​​the same as that of the target image, and the element values ​​corresponding to each pixel point can be filled in.

[0027] Further, in S212, the element value y of the pixel point in the mth row and nth column in the first pixel association matrix is mn The calculation formula is: Where c m,n represents the pixel value of the pixel at the mth row and nth column in the target image, R represents the spectral radius of the morphological matrix, C max Represents the maximum pixel value of the target image, C min Represents the minimum pixel value of the target image,

[0028] Furthermore, in S24, the calculation formula of the quality detection threshold β corresponding to the target image is: ; Wherein, Y represents the first pixel association matrix, Z represents the second pixel association matrix, T represents the matrix transpose, and η represents the maximum singular value of the morphological matrix.

[0029] The beneficial effects of the present invention are as follows: the present invention discloses a production harness quality detection method, which collects a target image when the harness is produced, extracts pixel points with more representative and universal positions in the target image, forms two pixel point sets, generates a morphological matrix using the characteristic pixel values ​​of the two pixel point sets; generates two association matrices using the morphological matrix, thereby determining the quality detection threshold and completing the defect identification of the harness. The present invention checks the appearance of the harness, promptly discovers its surface defects, and ensures that the quality of the harness meets the standard requirements, which not only improves the quality and reliability of the harness product, but also reduces the failure rate and safety hazards in the production process, and improves production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1The figure is a flow chart of the production harness quality detection method. DETAILED DESCRIPTION

[0031] The embodiments of the present invention will be further described below in conjunction with the accompanying drawings.

[0032] like Figure 1 As shown, the present invention provides a method for detecting the quality of a production line, comprising the following steps:

[0033] S1, collecting the target image when the wire harness is produced, and generating a morphological matrix for the target image;

[0034] S2. Based on the morphological matrix, generate a first pixel association matrix and a second pixel association matrix, and determine a quality detection threshold corresponding to the target image;

[0035] S3. Determine whether the target image has quality defects based on the quality detection threshold.

[0036] In S3, if there are pixels in the target image whose pixel values ​​are lower than the quality detection threshold, it means that there are abnormal pixels on the wiring harness, that is, there are quality defects.

[0037] In this embodiment of the present invention, S1 includes the following sub-steps:

[0038] S11, collecting the target image when the wire harness production is completed;

[0039] S12, extracting the pixel points where the two diagonal lines of the target image are located as a diagonal morphological pixel point set;

[0040] S13, the target image Line Column pixels, Line Column pixels, Line Column pixels and Line The pixel points of the columns are connected in sequence to form a closed line segment, and the pixel points where the closed line segment is located are taken as the closed morphological pixel point set, where M represents the number of rows of the target image, and N represents the number of columns of the target image. Indicates rounding up;

[0041] S14, generating a morphological pixel constraint value according to the diagonal morphological pixel point set and the closed morphological pixel point set;

[0042] S15. Generate a morphological matrix for the target image according to the morphological pixel constraint values.

[0043] In the present invention, the pixel points contained in the diagonal lines and closed line segments of the target image can cover the pixel conditions of the pixel points in most areas of the target image, so the present invention selects the pixel points of these line segments to form a pixel point set, and then extracts the characteristic pixel points of the two pixel point sets to generate morphological pixel constraint values.

[0044] In the embodiment of the present invention, in S14, the calculation formula of the morphological pixel constraint value B is: ; In the formula, a1 represents the pixel value of the first pixel in the diagonal pixel set, a I represents the pixel value of the first pixel in the diagonal pixel set, max(·) represents the maximum value operation, b1 represents the pixel value of the first pixel in the closed pixel set, and b J It represents the pixel value of the Jth pixel in the closed morphological pixel set, M represents the number of rows of the target image, and N represents the number of columns of the target image.

[0045] In the embodiment of the present invention, in S15, the morphology matrix X form The expression is: Where c 1,1 Represents the pixel value of the pixel in the first row and first column of the target image, c 1,N Represents the pixel value of the pixel in the 1st row and the Nth column in the target image, c M,1 Represents the pixel value of the pixel in the Mth row and the first column of the target image, c M,N represents the pixel value of the pixel at the Mth row and Nth column in the target image, and B represents the morphological pixel constraint value.

[0046] In this embodiment of the present invention, S2 includes the following sub-steps:

[0047] S21, generating a first pixel correlation matrix for the target image;

[0048] S22, performing a Hadamard product operation on the first pixel correlation matrix and the morphology matrix to obtain a second pixel correlation matrix;

[0049] S24. Determine a quality detection threshold corresponding to the target image according to the first pixel association matrix and the second pixel association matrix.

[0050] In the present invention, the pixel points of each pixel point of the target image are reconstructed according to the characteristic parameters (i.e., the spectral radius) of the morphological matrix to obtain a first pixel quality matrix, and the second pixel association matrix is ​​obtained by element-by-element multiplication of the first pixel quality matrix and the morphological matrix. The first pixel association matrix and the second pixel association matrix have the same size, and the quality detection threshold can be obtained after the operation.

[0051] In the embodiment of the present invention, S21 includes the following sub-steps:

[0052] S211, extracting the spectrum radius of the morphological matrix;

[0053] S212: Determine the element value of each pixel in the first pixel association matrix according to the spectral radius of the morphological matrix and the pixel values ​​of the pixel points in the target image, and generate a first pixel association matrix.

[0054] The number of rows and columns of the first pixel association matrix is ​​the same as that of the target image, and the element values ​​corresponding to each pixel point can be filled in.

[0055] In the embodiment of the present invention, in S212, the element value y of the pixel point in the mth row and the nth column in the first pixel association matrix is mn The calculation formula is: Where c m,n represents the pixel value of the pixel at the mth row and nth column in the target image, R represents the spectral radius of the morphological matrix, C max Represents the maximum pixel value of the target image, C min Represents the minimum pixel value of the target image,

[0056] In the embodiment of the present invention, in S24, the calculation formula of the quality detection threshold β corresponding to the target image is: ; Wherein, Y represents the first pixel association matrix, Z represents the second pixel association matrix, T represents the matrix transpose, and η represents the maximum singular value of the morphological matrix.

[0057] Those skilled in the art will appreciate that the embodiments described herein are intended to help readers understand the principles of the present invention, and should be understood that the protection scope of the present invention is not limited to such specific statements and embodiments. Those skilled in the art can make various other specific variations and combinations that do not deviate from the essence of the present invention based on the technical revelations disclosed by the present invention, and these variations and combinations are still within the protection scope of the present invention.

Claims

1. A method for detecting the quality of a production line, characterized in that: The following steps are involved: S1, collecting the target image when the wire harness is produced, and generating a morphological matrix for the target image; S2. Based on the morphological matrix, generate a first pixel association matrix and a second pixel association matrix, and determine a quality detection threshold corresponding to the target image; S3, determining whether the target image has quality defects based on the quality detection threshold; The S1 comprises the following sub-steps: S11, collecting the target image when the wire harness production is completed; S12, extracting the pixel points where the two diagonal lines of the target image are located as a diagonal morphological pixel point set; S13, the target image Line Column pixels, Line Column pixels, Line Column pixels and Line The pixel points of the columns are connected in sequence to form a closed line segment, and the pixel points where the closed line segment is located are taken as the closed morphological pixel point set, where M represents the number of rows of the target image, and N represents the number of columns of the target image. Indicates rounding up; S14, generating a morphological pixel constraint value according to the diagonal morphological pixel point set and the closed morphological pixel point set; S15, generating a morphological matrix for the target image according to the morphological pixel constraint value; In S14, the calculation formula of the morphological pixel constraint value B is: ; In the formula, a1 represents the pixel value of the first pixel in the diagonal pixel set, a I represents the pixel value of the first pixel in the diagonal pixel set, max(·) represents the maximum value operation, b1 represents the pixel value of the first pixel in the closed pixel set, and b J represents the pixel value of the Jth pixel in the closed morphological pixel set, M represents the number of rows of the target image, and N represents the number of columns of the target image; In S15, the morphology matrix X form The expression is: Where c 1,1 Represents the pixel value of the pixel in the first row and first column of the target image, c 1,N Represents the pixel value of the pixel in the 1st row and the Nth column in the target image, c M,1 Represents the pixel value of the pixel in the Mth row and the first column of the target image, c M,N represents the pixel value of the pixel at the Mth row and Nth column in the target image, and B represents the morphological pixel constraint value; The S2 comprises the following sub-steps: S21, generating a first pixel correlation matrix for the target image; S22, performing a Hadamard product operation on the first pixel correlation matrix and the morphology matrix to obtain a second pixel correlation matrix; S24, determining a quality detection threshold corresponding to the target image according to the first pixel association matrix and the second pixel association matrix; The S21 comprises the following sub-steps: S211, extracting the spectrum radius of the morphological matrix; S212, determining the element value of each pixel in the first pixel association matrix according to the spectral radius of the morphological matrix and the pixel value of the pixel in the target image, and generating the first pixel association matrix; In S212, the element value y of the pixel point in the mth row and nth column in the first pixel association matrix mn The calculation formula is: ; In the formula, c m,n represents the pixel value of the pixel at the mth row and nth column in the target image, R represents the spectral radius of the morphological matrix, C max Represents the maximum pixel value of the target image, C min Represents the minimum pixel value of the target image, In S24, the calculation formula of the quality detection threshold β corresponding to the target image is: ; Wherein, Y represents the first pixel association matrix, Z represents the second pixel association matrix, T represents the matrix transpose, and η represents the maximum singular value of the morphological matrix.

Citation Information

Patent Citations

  • Motion target detection method based on improved minimum cross entropy

    CN102800107A

  • Automatic extraction method for road vector mark lines in vehicle-mounted laser scanning point cloud

    CN106067003A

  • Product surface defect detection method

    CN106683099A

  • Image registration quality detection method and device, apparatus and storage medium

    CN111145230A

  • Automatic quality control method for heat-preservation container

    CN112326664A