Method and device for automatically identifying thickness of cable insulation layer

Abstract

The invention discloses a cable insulation layer thickness automatic identification method and device, and belongs to the technical field of cable sheath detection. The method comprises the following steps: acquiring an image file by using an imread function, extracting a predetermined channel of an image as a grey-scale map, carrying out binarization processing on the predetermined channel through an imbinarize function to obtain a black and white binarized graph, calling hole filling of the binarized graph of which the imfill function is greater than the black and white binarized graph, and establishing a filling circular graph of which the contour is continuous and smooth and the internal hole is filled; measuring a circle center and a cross section in the filling circular ring graph by utilizing a circular Hough transform principle, and calculating the thickness of a circular ring in the filling circular ring graph; and extracting the diameter and thickness of the ring, introducing an ellipse fitting algorithm, calculating the shortest and longest outer diameters of the ring, obtaining an ellipse fitting result, and adjusting the measurement angle to measure the ring thickness of the corresponding angle. According to the method, the standard circular ring detection model is established, the ellipse fitting equation is fitted, irregular shapes occurring in actual production are processed, the detection accuracy is improved, and the adaptability to variation is enhanced.

Description

Technical Field

[0001] The invention belongs to the technical field of cable sheath detection, and in particular relates to a method and a device for automatically identifying the thickness of a cable insulation layer. Background Art

[0002] The outer sheath of wires and cables plays an insulating and protective role, ensuring the safety of power transmission. If the outer sheath thickness does not meet the standard, the wires may be exposed, causing safety accidents such as short circuits and electric shocks. The correct outer sheath thickness can effectively prevent the wires from being corroded by external physical and chemical factors, such as friction, moisture, chemical corrosion, etc., to ensure the long-term stable operation of wires and cables. The manufacture and use of wires and cables must comply with national or international standards, and the outer sheath size is one of the key indicators. Qualified dimensions ensure that the product meets relevant specifications and certification requirements, avoiding legal and commercial disputes caused by quality issues. In certain specific application scenarios, the outer sheath size of wires and cables will affect their electrical and mechanical properties. The correct size can ensure that the cable works normally under specific conditions and meets the design and use requirements. By testing the outer sheath size of wires and cables, its reliability in actual use can be evaluated, its service life can be predicted, and a reasonable maintenance and replacement plan can be formulated to avoid significant losses caused by cable failures. Summary of the invention

[0003] Purpose of the invention: To provide a method and device for automatically identifying the thickness of a cable insulation layer, which solves the above-mentioned problems existing in the prior art.

[0004] Technical solution: A method for automatically identifying the thickness of a cable insulation layer, comprising the following steps:

[0005] Use the imread function to obtain the image file, extract the image of the predetermined channel as a grayscale image, use the imbinarize function to binarize the grayscale image to obtain a black and white binary image, call the imfill function to fill the holes of the black and white binary image, create a filled donut chart with a continuous and smooth outline and filled internal holes, obtain the filled donut chart, and repair the internal defects of the filled donut chart;

[0006] Using the circular Hough transform principle, the center and cross section of the filled donut diagram are measured, and the thickness of the donut in the filled donut diagram is calculated;

[0007] Extract the diameter and thickness of the ring, introduce an ellipse fitting algorithm, calculate the shortest and longest outer diameters of the ring, obtain the ellipse fitting result, adjust the measurement angle to measure the thickness of the ring at the corresponding angle, at least calculate the average thickness of the ring, the minimum thickness of the ring and the average outer diameter of the ring, and at least graphically output the center position, length measurement results and ellipse fitting auxiliary lines.

[0008] Preferably, the process of measuring the center and cross section of the filled donut diagram is as follows:

[0009] The imfindcircles function is based on the principle of circular Hough transform. It obtains the point in the image space of the filled donut chart, maps the point to the parameter space to obtain the donut, obtains the mapping parameters corresponding to the donut to form a mapping parameter set, builds a standard donut detection model, and generates several cones for each edge point in the image space through the standard donut detection model. The intersection of the cones is the center of the circle. Circles and the center of the circle are drawn on the filled donut chart based on the detected edge points and the center of the circle, and the average diameter is marked.

[0010] Preferably, the imfindcircles function call statement is as follows:

[0011] [centers,radii]=imfindcircles((I1),[R1R2],"Sensitivity",Sensit);

[0012] Where: I1 represents the input image matrix, where when the edge is obvious and the contrast is strong, the filled donut image is used as the image matrix, and when the grayscale gradient information is obtained, the grayscale image is used as the image matrix; R1 represents the search range of the maximum radius; R2 represents the search range of the minimum radius; Sensit represents the sensitivity of detection; centers represents the coordinates of the center of the detected circle [x, y]; radii represents the radius value of the detected circle; Sensitivity represents the sensitivity parameter of circle detection, and its value range is 0 to 1.

[0013] Preferably, the process of calculating the shortest and longest outer diameters of the ring by an ellipse fitting algorithm is as follows:

[0014] The ellipse fitting equation is as follows:

[0015] ax 2 +bxy+cy 2 +dx+ey+f=0(1)

[0016] Where: x represents the horizontal coordinate of the point on the ellipse; y represents the vertical coordinate of the point on the ellipse; a represents x 2 The coefficient of the term is a real number and a≠0; b represents the coefficient of the xy term, describing the rotation angle of the ellipse; c represents the y 2 The coefficient of the term is a real number and c≠0; d represents the coefficient of the x-order term, which is related to the x-coordinate of the center point of the ellipse; e represents the coefficient of the y-order term, which is related to the y-coordinate of the center point of the ellipse; f represents the constant term, which determines the size of the ellipse;

[0017] The parameters obtained through the ellipse fitting equation are used in conjunction with the ring detection model to obtain the adapted ellipse, providing a mathematical basis for the least squares method.

[0018] Cost function: Cost(A) = (XA + B c ) T (XA+B Z ) (2)

[0019] Where A represents the design matrix, where the dimension of the design matrix is ​​N×6, containing the coordinate information of N sampling points, and each row is in the form of [x 2 ,xy,y 2 , x, y, 1]; X represents the parameter vector to be solved [a, b, c, d, e, f] T , contains six coefficients of the elliptic equation, Z represents the constraint vector, B represents the regularization term, which is used to add additional constraints; the parameter vector [a, b, c, d, e, f] T In the above example, a represents x. 2 The coefficient of the term, a is a real number and a≠0; b represents the coefficient of the xy term, describing the rotation angle of the ellipse; c represents the y 2 The coefficient of the term, c is a real number and c≠0; d represents the coefficient of the first-order term x, which is related to the x-coordinate of the center point of the ellipse; e represents the coefficient of the first-order term y, which is related to the y-coordinate of the center point of the ellipse; f represents the constant term, which adjusts the size of the ellipse; T represents the target vector;

[0020] The least squares formula is:

[0021] Where: T represents the target vector, which contains the coordinate information of the sampling points.

[0022] Preferably, the center coordinates of the ellipse are obtained by converting the general form into the standard form using formulas (4) and (5), and the formulas (4) and (5) are as follows:

[0023]

[0024] Where: X 0 Indicates the X coordinate of the center point of the ellipse; Y 0 Indicates the Y coordinate of the center point of the ellipse.

[0025] Preferably, the angle between the main axis of the ellipse and the coordinate axis is calculated by formula (6), and formula (6) is as follows:

[0026]

[0027] Preferably, the major axis and the minor axis are calculated by formula (7), which involves the properties of quadratic equations and the geometric characteristics of ellipses:

[0028]

[0029] Where: a椭 represents the length of the major semi-axis of the ellipse, b 椭 F is the length of the minor axis of the ellipse. 椭 Denotes the discriminant of the elliptic equation, A 椭 In the equation of the ellipse Term coefficient, C 椭 In the equation of the ellipse Item coefficient.

[0030] Preferably, the process of calculating the thickness of the ring is as follows:

[0031] Get 6 points radially, with the radial interval angle of each point being 60°. For each angle, generate a straight line from the center of the circle to the outside:

[0032] x=floor(a 椭 +r 参 ×cos(theta)) (9);

[0033] y=floor(b 椭 +r 参 × sin(theta)) (10);

[0034] Where: x 直 Indicates the horizontal coordinate of the point on the generated line, y 直 Indicates the ordinate of the point on the generated straight line, r 参 represents the distance parameter from the center of the circle to the measurement point, theta represents the angle of the sampling point, and the angle increases by 60°;

[0035] The binary image difference method is used to detect the inner and outer edges. The calculation formula is as follows:

[0036] RP=(Q(F1-I2)-Q(F1-I1)) (11);

[0037] Where: RP represents the edge response value, Q represents the absolute value function, F1 represents the gray value of the current pixel, I2 represents the gray value of the adjacent point on the right side of the current pixel, and I1 represents the gray value of the adjacent point on the left side of the current pixel.

[0038] A device for automatically identifying the thickness of a cable insulation layer comprises a shell, a light source adjuster is installed in the shell, a height adjustment component is installed on the opposite side of the light source adjuster, a clamping component is installed on the height adjustment component, the clamping component is used to clamp a camera, and a detection port is provided at the end of the clamping component close to the light source adjuster for irradiating the light source.

[0039] Beneficial effects: The present invention relates to a method and device for automatically identifying the thickness of a cable insulation layer. According to the use scenario of the cable, a predetermined channel is selected as a grayscale image, and the grayscale image is binarized to shorten the operation time. Selective extraction can maximize the use of effective information while maintaining the calculation efficiency. The measurement is performed at a preset angle to fully capture the geometric characteristics of the cable insulation layer.

[0040] By building a standard circular ring detection model and fitting the ellipse fitting equation, the irregular shapes that appear in actual production can be processed to improve the accuracy of detection and enhance the adaptability to variations. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 is a system block diagram of the present invention;

[0042] Figure 2 It is a structural schematic diagram of the present invention;

[0043] Figure 3 It is a schematic diagram of measuring the thickness of the cable insulation layer of the present invention.

[0044] Figure 2 The figures are marked as follows: 1. housing; 2. light source adjuster; 3. height adjustment assembly; 4. clamping assembly; 5. detection port. DETAILED DESCRIPTION

[0045] like Figures 1 to 3 As shown, the present invention provides a technical solution: a method for automatically identifying the thickness of a cable insulation layer, comprising the following steps:

[0046] The imread function is used to obtain the image file, and the image of the predetermined channel of the image is extracted as a grayscale image. The grayscale image is binarized by the imbinarize function to obtain a black and white binary image. The imfindcircles function call statement is as follows:

[0047] [centers,radii]=imfindcircles((I1),[R1R2],"Sensitivity",Sensit);

[0048] Where: I1 represents the input image matrix, where when the edge is obvious and the contrast is strong, the filled donut image is used as the image matrix, and when the grayscale gradient information is obtained, the grayscale image is used as the image matrix; R1 represents the search range of the maximum radius; R2 represents the search range of the minimum radius; Sensit represents the sensitivity of detection; centers represents the coordinates of the center of the detected circle [x, y]; radii represents the radius value of the detected circle; Sensitivity represents the sensitivity parameter of circle detection, and its value range is 0 to 1; call the imfill function to fill the holes of the black and white binary graphics, establish a filled donut image with a continuous and smooth outline and filled internal holes, obtain the filled donut image, and repair the internal defects of the filled donut image;

[0049] The circle center and cross section of the filled doughnut diagram are measured by using the circular Hough transform principle, and the thickness of the ring in the filled doughnut diagram is calculated. The process of measuring the circle center and cross section of the filled doughnut diagram is as follows:

[0050] The imfindcircles function is based on the circular Hough transform principle. In this embodiment, the Hough transform in the imfindcircles function is used to obtain a point in the image space of the filled doughnut diagram, and the point is mapped to the parameter space to obtain a doughnut, and the mapping parameters corresponding to the doughnut are obtained to form a mapping parameter set, and a standard doughnut detection model is built. The standard doughnut detection model is used to generate a number of cones for each edge point in the image space, and the intersection of the cones is the center of the circle. Circles and centers are drawn on the filled doughnut diagram according to the detected edge points and centers of the circles, and the average diameter is marked. The diameter and thickness of the doughnut are extracted, and an ellipse fitting algorithm is introduced to calculate the shortest and longest outer diameters of the doughnut, and the ellipse fitting result is obtained. The measurement angle is adjusted to measure the thickness of the doughnut at the corresponding angle, and at least the average thickness of the doughnut, the minimum thickness of the doughnut and the average outer diameter of the doughnut are calculated. At least the center position, length measurement results and ellipse fitting auxiliary lines are graphically output. The standard doughnut detection model is built in conjunction with the ellipse fitting equation to handle irregular shapes that appear in actual production, improve the accuracy of detection, and enhance the adaptability to variation.

[0051] In a further embodiment, the process of calculating the shortest and longest outer diameters of a ring by an ellipse fitting algorithm is as follows:

[0052] The ellipse fitting equation is as follows:

[0053] ax 2 +bxy+cy 2 +dx+ey+f=0(1)

[0054] Where: x represents the horizontal coordinate of the point on the ellipse; y represents the vertical coordinate of the point on the ellipse; a represents x 2The coefficient of the term is a real number, and a≠0; b represents the coefficient of the xy term, describing the rotation angle of the ellipse; c represents the y 2 The coefficient of the term is a real number, and c≠0; d represents the coefficient of the x-order term, which is related to the x-coordinate of the center point of the ellipse; e represents the coefficient of the y-order term, which is related to the y-coordinate of the center point of the ellipse; f represents the constant term, which determines the size of the ellipse;

[0055] The parameters obtained through the ellipse fitting equation are used in conjunction with the ring detection model to obtain the adapted ellipse, providing a mathematical basis for the least squares method.

[0056] Cost function: Cost(A) = (XA + B c ) T (XA+B Z ) (2)

[0057] Where A represents the design matrix, where the dimension of the design matrix is ​​N×6, containing the coordinate information of N sampling points, and each row is in the form of [x 2 ,xy,y 2 , x, y, 1]; X represents the parameter vector to be solved [a, b, c, d, e, f] T , contains six coefficients of the elliptic equation, Z represents the constraint vector, B represents the regularization term, which is used to add additional constraints; the parameter vector [a, b, c, d, e, f] T In the above example, a represents x. 2 The coefficient of the term, a is a real number and a≠0; b represents the coefficient of the xy term, describing the rotation angle of the ellipse; c represents the y 2 The coefficient of the term, c is a real number and c≠0; d represents the coefficient of the first-order term x, which is related to the x-coordinate of the center point of the ellipse; e represents the coefficient of the first-order term y, which is related to the y-coordinate of the center point of the ellipse; f represents the constant term, which adjusts the size of the ellipse; T represents the target vector;

[0058] The least squares formula is:

[0059] Where: T represents the target vector, which contains the coordinate information of the sampling points.

[0060] In a further embodiment, the center coordinates of the ellipse are obtained by converting the general form into the standard form using formulas (4) and (5), and the formulas (4) and (5) are as follows:

[0061]

[0062] Where: X 0 Indicates the X coordinate of the center point of the ellipse; Y 0 Indicates the Y coordinate of the center point of the ellipse.

[0063] In a further embodiment, the angle between the main axis of the ellipse and the coordinate axis is calculated by formula (6), and formula (6) is as follows:

[0064]

[0065] In a further embodiment, the major axis and the minor axis are calculated by formulas (7) and (8), which involve the properties of quadratic equations and the geometric characteristics of ellipses:

[0066]

[0067] Where: a 椭 represents the length of the major semi-axis of the ellipse, b 椭 F is the length of the minor axis of the ellipse. 椭 Denotes the discriminant of the elliptic equation, A 椭 In the equation of the ellipse Term coefficient, C 椭 In the equation of the ellipse Item coefficient.

[0068] In a further embodiment, the thickness of the ring is calculated as follows:

[0069] Get 6 points radially, with the radial interval angle of each point being 60°. For each angle, generate a straight line from the center of the circle to the outside:

[0070] x=floor(a 椭 +r 参 ×cos(theta)) (9);

[0071] y=floor(b 椭 +r 参 × sin(theta)) (10);

[0072] Where: x 直 Indicates the horizontal coordinate of the point on the generated line, y 直 Indicates the ordinate of the point on the generated straight line, r 参 represents the distance parameter from the center of the circle to the measurement point, theta represents the angle of the sampling point, and the angle increases by 60°;

[0073] The Matlab code snippet is as follows:

[0074] theta1=[pi / 32*pi / 34*pi / 35*pi / 3];

[0075] theta1 = [0pi];

[0076] These two sets of angles together make up the measurements every 60°:

[0077] pi / 3 = 60°

[0078] 2*pi / 3=120°

[0079] pi=180°

[0080] 4*pi / 3=240°

[0081] 5*pi / 3=300°

[0082] 0=0°

[0083] That is, the angle is equivalent to 360°;

[0084] The width corresponding to the thickness of the ring is calculated using the following formula:

[0085]

[0086] Where: x r Represents the x-coordinate set of edge points; y r Represents the y coordinate set of edge points; max(x r ) represents the maximum value on the x-axis; min(x r ) represents the minimum value on the x-axis; max(y r ) represents the maximum value on the y-axis; min(y r ) represents the maximum value on the y-axis; P 2 M represents the conversion ratio from pixels to actual size;

[0087] In the Matlab code, we expose some input parameters for modification at any time to suit various situations and improve the detection speed:

[0088] res1, res2=cc.Final_dec(z, t, 0.99, 38.082, 120, 180, nargout=2)

[0089] in

[0090] z indicates the file save path

[0091] t represents the image loading path

[0092] 0.99 indicates the similarity of circle detection, 0-1, the larger the value, the more circles are detected.

[0093] 38.082 means P 2 M is the conversion factor from pixels to actual measurement units. Convert the number of px to the length unit mm. This needs to be debugged and calibrated with standard parts.

[0094] 120 / 180 represents the search radius range of the circle. Here, 120-180 represents the search radius of an approximate circle with a px number from 120 to 180.

[0095] nargout indicates that the program is expected to output two return results res1 and res2

[0096] Output:

[0097] Average diameter:

[0098] Long axis diameter:

[0099] Minor axis diameter:

[0100] Average thickness: mean([D2(:,1),D(:,1:2),D2(:,2),D(:,3:4)] T )

[0101] Minimum thickness: min([D2(:,1),D(:,1:2),D2(:,2),D(:,3:4)] T ) to complete the layer thickness of the cable insulation layer being tested.

[0102] In a further embodiment, a binary image difference method is used to detect inner and outer edges, and its calculation formula is as shown in formula (11):

[0103] RP=(Q(F1-I2)-Q(F1-I1)) (11);

[0104] Where: RP represents the edge response value, Q represents the absolute value function, F1 represents the gray value of the current pixel, I2 represents the gray value of the adjacent point on the right side of the current pixel, and I1 represents the gray value of the adjacent point on the left side of the current pixel.

[0105] Through the above technical solution, the following working process can be realized by the automatic identification device of the cable insulation thickness:

[0106] The automatic identification device for the thickness of the cable insulation layer includes a shell 1, in which a light source regulator 2 is installed, and a height adjustment component 3 is installed on the opposite side of the light source regulator 2. A clamping component 4 is installed on the height adjustment component 3, and the height of the clamping component 4 is adjusted by the height adjustment component 3. The clamping component 4 is used to clamp a camera, and a detection port 5 is provided at the end of the clamping component 4 close to the light source regulator 2 to enable the clamped camera to move away from or close to the detection port 5. The detection port 5 is used to place a cable, and the cable is illuminated by a light source. With the cooperation of the camera and the light source regulator 2, the cable thickness is detected.

[0107] The preferred embodiments of the present invention are described in detail above; however, the present invention is not limited to the specific details in the above embodiments. Within the technical concept of the present invention, various equivalent transformations can be made to the technical solutions of the present invention, and these equivalent transformations all belong to the protection scope of the present invention.

Claims

1. A method for automatically identifying the thickness of a cable insulation layer, characterized in that: The following steps are involved: Use the imread function to obtain the image file, extract the image of the predetermined channel as a grayscale image, use the imbinarize function to binarize the grayscale image to obtain a black and white binary image, call the imfill function to fill the holes of the black and white binary image, create a filled donut chart with a continuous and smooth outline and filled internal holes, obtain the filled donut chart, and repair the internal defects of the filled donut chart; Using the circular Hough transform principle, the center and cross section of the filled donut diagram are measured, and the thickness of the donut in the filled donut diagram is calculated; Extract the diameter and thickness of the ring, introduce an ellipse fitting algorithm, calculate the shortest and longest outer diameters of the ring, obtain the ellipse fitting result, adjust the measurement angle to measure the thickness of the ring at the corresponding angle, at least calculate the average thickness of the ring, the minimum thickness of the ring and the average outer diameter of the ring, and at least graphically output the center position, length measurement results and ellipse fitting auxiliary lines.

2. The method for automatically identifying the thickness of a cable insulation layer according to claim 1, characterized in that: The process for determining the center and cross section of a filled donut chart is as follows: The imfindcircles function is based on the principle of circular Hough transform. It obtains the point in the image space of the filled donut chart, maps the point to the parameter space to obtain the donut, obtains the mapping parameters corresponding to the donut to form a mapping parameter set, builds a standard donut detection model, and generates several cones for each edge point in the image space through the standard donut detection model. The intersection of the cones is the center of the circle. Circles and the center of the circle are drawn on the filled donut chart based on the detected edge points and the center of the circle, and the average diameter is marked.

3. The method for automatically identifying the thickness of a cable insulation layer according to claim 2, characterized in that: The imfindcircles function call statement is as follows: [centers,radii]=imfindcircles((I1),[R1R2],"Sensitivity",Sensit); Where: I1 represents the input image matrix, where when the edge is obvious and the contrast is strong, the filled donut image is used as the image matrix, and when the grayscale gradient information is obtained, the grayscale image is used as the image matrix; R1 represents the search range of the maximum radius; R2 represents the search range of the minimum radius; Sensit represents the sensitivity of detection; centers represents the coordinates of the center of the detected circle [x, y]; radii represents the radius value of the detected circle; Sensitivity represents the sensitivity parameter of circle detection, and its value range is 0 to 1.

4. The method for automatically identifying the thickness of a cable insulation layer according to claim 2, characterized in that: The process of calculating the shortest and longest outer diameters of a ring using the ellipse fitting algorithm is as follows: The ellipse fitting equation is as follows: ax 2 +bxy+cy 2 +dx+ey+f=0(1) Where: x represents the horizontal coordinate of the point on the ellipse; y represents the vertical coordinate of the point on the ellipse; a represents x 2 The coefficient of the term is a real number and a≠0; b represents the coefficient of the xy term, describing the rotation angle of the ellipse; c represents the y 2 The coefficient of the term is a real number and c≠0; d represents the coefficient of the x-order term, which is related to the x-coordinate of the center point of the ellipse; e represents the coefficient of the y-order term, which is related to the y-coordinate of the center point of the ellipse; f represents the constant term, which determines the size of the ellipse; The parameters obtained through the ellipse fitting equation are used in conjunction with the ring detection model to obtain the adapted ellipse, providing a mathematical basis for the least squares method. Cost function: Cost(A) = (XA + B c ) T (XA+B Z ) (2) Where A represents the design matrix, where the dimension of the design matrix is ​​N×6, containing the coordinate information of N sampling points, and each row is in the form of [x 2 ,xy,y 2 , x, y, 1]; X represents the parameter vector to be solved [a, b, c, d, e, f] T , contains six coefficients of the elliptic equation, Z represents the constraint vector, B represents the regularization term, which is used to add additional constraints; the parameter vector [a, b, c, d, e, f] T In the above example, a represents x. 2 The coefficient of the term, a is a real number and a≠0; b represents the coefficient of the xy term, describing the rotation angle of the ellipse; c represents the y 2 The coefficient of the term, c is a real number and c≠0; d represents the coefficient of the first-order term x, which is related to the x-coordinate of the center point of the ellipse; e represents the coefficient of the first-order term y, which is related to the y-coordinate of the center point of the ellipse; f represents the constant term, which adjusts the size of the ellipse; T represents the target vector; The least squares formula is: Where: T represents the target vector, which contains the coordinate information of the sampling points.

5. A method for automatically identifying the thickness of a cable insulation layer according to claim 4, characterized in that: The center coordinates of the ellipse are obtained by converting the general form into the standard form using formulas (4) and (5). Formulas (4) and (5) are as follows: Where: X0 represents the X coordinate of the center point of the ellipse; Y0 represents the Y coordinate of the center point of the ellipse.

6. A method for automatically identifying the thickness of a cable insulation layer according to claim 4, characterized in that: The angle between the main axis of the ellipse and the coordinate axis is calculated by formula (6), which is as follows:

7. A method for automatically identifying the thickness of a cable insulation layer according to claim 4, characterized in that: The calculation of the major axis and minor axis by formula (7) involves the properties of quadratic equations and the geometric characteristics of ellipses: Where: a 椭 represents the length of the major semi-axis of the ellipse, b 椭 F is the length of the minor axis of the ellipse. 椭 Denotes the discriminant of the elliptic equation, A 椭 In the equation of the ellipse Term coefficient, C 椭 In the equation of the ellipse Item coefficient.

8. The method for automatically identifying the thickness of a cable insulation layer according to claim 4, characterized in that: The process of calculating the thickness of the ring is as follows: Get 6 points radially, with the radial interval angle of each point being 60°. For each angle, generate a straight line from the center of the circle to the outside: x=floor(a 椭 +r 参 ×cos(theta)) (9); y=floor(b 椭 +r 参 ×sin(theta)) (10); Where: x 直 Indicates the horizontal coordinate of the point on the generated line, y 直 Indicates the ordinate of the point on the generated straight line, r 参 represents the distance parameter from the center of the circle to the measurement point, theta represents the angle of the sampling point, and the angle increases by 60°; The binary image difference method is used to detect the inner and outer edges. The calculation formula is as follows: RP=(Q(F1-I2)-Q(F1-I1)) (11); Where: RP represents the edge response value, Q represents the absolute value function, F1 represents the gray value of the current pixel, I2 represents the gray value of the adjacent point on the right side of the current pixel, and I1 represents the gray value of the adjacent point on the left side of the current pixel.

9. A device for automatically identifying the thickness of a cable insulation layer, wherein the device is used to implement a method for automatically identifying the thickness of a cable insulation layer as claimed in any one of claims 1 to 8, characterized in that: The invention comprises a shell (1), wherein a light source adjuster (2) is installed in the shell (1), a height adjustment component (3) is installed on the opposite side of the light source adjuster (2), a clamping component (4) is installed on the height adjustment component (3), the clamping component (4) is used to clamp a camera, and a detection port (5) is provided at the end of the clamping component (4) close to the light source adjuster (2) for irradiating the light source.

Images