A method for detecting the quality of insulation layer of new energy high-voltage and high-current energy storage wiring harness

Abstract

The present invention relates to the field of graphic recognition technology, and specifically to a method for detecting the quality of the insulation layer of a new energy high-voltage and high-current energy storage harness, including obtaining a surface image of the energy storage harness; preprocessing the surface image of the energy storage harness to obtain a crack connection domain; calculating the crack extension coefficient based on the crack state in the crack connection domain; performing damage analysis based on the internal edge of the crack connection domain to obtain the conductor coefficient; analyzing the bending property of the energy storage harness to obtain the bending coefficient; and calculating the crack hazard coefficient of the energy storage harness based on the crack extension coefficient, the conductor coefficient and the bending coefficient. The present invention uses the crack morphological features, the internal edge characteristics of the crack, and the bending state of the harness where the crack is located confirmed by the image of the crack, and uses this as the basis for calculating the crack hazard coefficient. The calculation result can accurately quantify the type and severity of the crack, and has the effect of measuring the quality of the insulation layer in a digital way, which is conducive to classifying the cracks and ensuring the stability of the harness quality.

Description

Technical Field

[0001] The present invention relates to the field of pattern recognition technology, and in particular to a method for detecting the quality of an insulation layer of a new energy high-voltage and high-current energy storage wiring harness. Background Art

[0002] New energy high-voltage and high-current energy storage wiring harness is an electrical component specially used in electric vehicles. It is usually composed of multiple wires and insulating materials, and is used to transmit high-voltage electrical energy from energy storage devices (such as battery packs) to motors, inverters or other electronic control units. In order to prevent electrical short circuits and leakage, the insulation material of the wiring harness must be able to maintain good insulation performance under high voltage, so it is particularly important to detect the surface insulation layer of the wiring harness.

[0003] However, when inspecting the insulation layer of energy storage harnesses, although surface defects can usually be found relatively easily, the types and degrees of these defects may vary, involving the physical and chemical properties of the insulation material. This complexity makes it difficult to accurately assess the true impact of these defects on the overall quality and performance of the insulation layer. Therefore, it is crucial to determine the overall quality of the insulation layer based on the defects on the surface of the harness. Summary of the invention

[0004] In order to solve the above technical problems, the purpose of the present invention is to provide a method for detecting the quality of the insulation layer of a new energy high-voltage and high-current energy storage wiring harness to improve the above problems. In order to achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0005] The present invention provides a method for detecting the quality of an insulation layer of a new energy high-voltage and high-current energy storage harness, the method comprising: acquiring a surface image of the energy storage harness; preprocessing the surface image of the energy storage harness to obtain a crack connection domain in the surface of the energy storage harness; calculating a crack extension coefficient based on crack morphological characteristics in the crack connection domain; performing a damage analysis based on the internal edge of the crack connection domain to obtain a conductor coefficient; performing a bending analysis of the energy storage harness based on the surface image of the energy storage harness and the crack connection domain to obtain a bending coefficient; and calculating a crack hazard coefficient of the energy storage harness based on the crack extension coefficient, the conductor coefficient and the bending coefficient.

[0006] In one possible implementation, the energy storage harness surface image is preprocessed to obtain a crack connected domain in the energy storage harness surface, including: graying the energy storage harness surface image to obtain a grayscale image; performing edge detection on the grayscale image using a preset edge detection mathematical model to obtain crack edges; and segmenting the grayscale image based on the crack edges to obtain a crack connected domain.

[0007] In a possible implementation, the preset edge detection mathematical model is a canny operator edge detection mathematical model.

[0008] In a possible implementation, the crack extension coefficient is calculated based on the crack morphological characteristics in the crack connected domain, including: confirming two endpoints on the edge of the crack connected domain, the two endpoints are the two points with the largest distance between them in the crack connected domain; calculating the cracking angle corresponding to each endpoint based on the angle pixel points around the endpoints, the angle pixel points are the pixel points located on both sides of the endpoint and constituting the edge of the crack; counting the number of pixel points of each line segment in the extended line segment set corresponding to each endpoint, the extended line segment set includes five line segments that are parallel to each other and adjacent in sequence, one of the line segments in the extended line segment set is adjacent to the endpoint, and each line segment in the extended line segment set is perpendicular to the direction line, which is the line connecting the two end points; the crack extension coefficient is calculated based on the cracking angle corresponding to each endpoint and the number of pixel points of each line segment in the extended line segment set.

[0009] In a possible implementation, a conductor coefficient is obtained by performing a damage calculation based on the internal edge of the gap connected domain, including: calculating a centroid area according to the grayscale value in the gap connected domain; screening candidate edges located inside the gap connected domain to obtain a damaged edge set, the damaged edge set including at least one damaged edge; connecting the midpoints of each damaged edge according to the centroid area to obtain a centerline set, and recording the angle between each line segment in the centerline set and the horizontal line as an angle set; counting the distance from the damaged edge to the gap edge to obtain a distance set; and calculating the conductor coefficient based on the angle set, the distance set, the gap connected domain, and the grayscale value corresponding to the centroid area.

[0010] In a possible implementation, candidate edges located inside the gap connected domain are screened to obtain a broken edge set, wherein the broken edge set includes at least one broken edge, including: projecting all candidate edges inside the gap connected domain to the gap edge from the centroid area to obtain a plurality of projected edges; using the DTW algorithm to calculate the DTW value of each candidate edge and the corresponding projected edge respectively; and screening to obtain the broken edge set according to the relationship between a preset screening threshold and the DTW value corresponding to each candidate edge.

[0011] In a possible implementation, the preset screening threshold is 0.8.

[0012] In a possible implementation, the bending coefficient of the energy storage harness is obtained by calculating the bendability of the energy storage harness based on the surface image of the energy storage harness and the connected domain of the crack, including: extracting the harness in the surface image of the energy storage harness based on the connected domain of the crack to obtain a harness segment image, wherein the harness segment image contains a crack, and the harness segment image contains a preset number of pixels from the end of the harness to the end point of the crack; fitting straight lines are performed on the edges on both sides of the harness in the harness segment image to obtain two loss values; and calculating the average of the two loss values, and using the calculated result as the bending coefficient.

[0013] In a possible implementation, the straight line fitting process is a least squares straight line fitting process.

[0014] In a possible implementation, the crack hazard coefficient of the energy storage harness is calculated based on the crack extension coefficient, the conductor coefficient and the bending coefficient, and then includes: when the crack hazard coefficient is less than a first safety threshold, a first display command is sent to the display screen, and the first display command is used to trigger the display screen to display content that can be repaired by adhesive; when the crack hazard coefficient is greater than the first safety threshold and less than the second safety threshold, a second display command is sent to the display screen, and the second display command is used to trigger the display screen to display content that can be repaired by repair materials; when the crack hazard coefficient is greater than a third safety threshold, a third display command is sent to the display screen, and the third display command is used to trigger the display screen to display danger warning content, the first safety threshold is less than the second safety threshold, and the second safety threshold is less than the third safety threshold.

[0015] The present invention has the following beneficial effects:

[0016] In order to confirm the quality of the insulation layer of the energy storage harness in the present invention, the surface image of the energy storage harness is collected and preprocessed to obtain the connected domain of cracks on the harness surface; and the crack extension coefficient, conductor coefficient and bending coefficient are confirmed according to the crack morphological characteristics of the crack connection domain, the internal edge characteristics of the crack, and the bending state of the harness where the crack is located. The above-mentioned crack extension coefficient, conductor coefficient and bending coefficient are combined as the basis for calculating the crack hazard coefficient. The crack hazard coefficient finally obtained can better reflect whether the crack itself will continue to crack under the bending of the energy storage harness, and can also reflect the current crack cracking degree and whether the crack is prone to continuous cracking and development under stress. The method of calculating the crack hazard coefficient of the insulation layer of the energy storage harness by the present invention can better guide production personnel to carry out targeted treatment of the cracks. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 A schematic flow chart of a method for detecting the quality of an insulation layer of a new energy high-voltage and high-current energy storage wiring harness provided in Embodiment 1 of the present invention;

[0019] Figure 2 A schematic flow chart of step S2 provided in Example 1 of the present invention;

[0020] Figure 3 A schematic flow chart of step S3 provided in Example 1 of the present invention;

[0021] Figure 4 A schematic flow chart of step S4 provided in Example 1 of the present invention;

[0022] Figure 5 This is a schematic flow chart of step S5 provided in Embodiment 1 of the present invention. DETAILED DESCRIPTION

[0023] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the insulation layer quality detection method of a new energy high-voltage and high-current energy storage harness proposed by the present invention, its specific implementation method, structure, characteristics and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0024] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0025] Embodiment 1:

[0026] The specific scheme of the insulation layer quality detection method of the new energy high-voltage and high-current energy storage wiring harness provided by the present invention is described in detail below in conjunction with the accompanying drawings.

[0027] See also Figure 1, which shows a flow chart of a method for detecting the quality of an insulation layer of a new energy high-voltage and high-current energy storage wiring harness provided by an embodiment of the present invention, which includes step S1, step S2, step S3, step S4, step S5, step S6, step S7, step S8 and step S9.

[0028] S1. Obtaining a surface image of the energy storage harness.

[0029] It should be noted that in this embodiment, it is preferred to perform surface insulation layer inspection on the new energy high-voltage and high-current energy storage harness that needs to be inspected after production. The process of acquiring the surface image of the energy storage harness in this step includes: first straightening the energy storage harness and placing it on a horizontal acquisition surface, and then using an industrial high-resolution camera to acquire the surface image of the energy storage harness.

[0030] S2. Preprocessing the energy storage wire harness surface image to obtain a crack connected domain in the energy storage wire harness surface.

[0031] Since it is not necessary to analyze the surface state of the energy storage harness from the color space in this embodiment, see Figure 2 , this step includes step S21, step S22 and step S23.

[0032] S21, graying the surface image of the energy storage harness to obtain a grayscale image.

[0033] Therefore, in this embodiment, by graying the acquired energy storage harness surface image to obtain the energy storage harness surface grayscale image, the calculation efficiency can be effectively improved.

[0034] S22, using a preset edge detection mathematical model to perform edge detection on the grayscale image to obtain the crack edge.

[0035] It should be noted that, since the cracked portion on the surface of the energy storage harness will cause a depression on the surface of the energy storage harness, the grayscale value of the cracked portion will be lower than the grayscale value of the surrounding area. Therefore, the preset edge detection mathematical model mentioned in this step is the canny operator edge detection mathematical model. Among them, the construction and use of the canny operator edge detection mathematical model are prior art and will not be repeated in the present invention.

[0036] S23. Segment the grayscale image based on the crack edge to obtain a crack connected domain.

[0037] Among them, since the gray value of the crack part of the energy storage harness is lower than that of the surrounding area, the crack edge can be obtained by edge detection, and the connected domain of the crack part can be segmented by combining the gray value difference on both sides of the crack edge.

[0038] Since the quality inspection of the surface insulation layer of the energy storage harness can not fully obtain its internal damage only by obtaining its surface cracks. Therefore, in the present invention, it is also necessary to conduct a risk assessment on the connected domain of the crack part obtained above. In this embodiment, it is taken into account that the surface insulation layer of the energy storage harness needs to have good insulation performance. Therefore, for the crack part in the energy storage harness image, it is necessary to first determine its risk factor, and then process the crack part in the subsequent steps. Therefore, in this embodiment, first determine whether it has the possibility of cracking again based on the shape of the crack; and combined with the energy storage harness being a multi-layer structure, it is necessary to make a combined judgment based on the number of damaged layers. See step S3-step S4 for details.

[0039] S3. Calculate the crack extension coefficient based on the crack morphological characteristics in the crack connected domain.

[0040] In this step, the occurrence of the crack is considered, which will lead to differences in the shape of the crack, and the crack shape may cause the crack to continue to extend. Therefore, in this step, the extension coefficient is obtained by analyzing the crack shape.

[0041] Specifically, since the crack is strip-shaped, the shape of both sides of the strip-shaped crack needs to be analyzed. If the edges of both sides of the crack are pointed and the width of the tip gradually increases and the increasing speed gradually increases, it indicates that there is a trend of continued cracking. This embodiment uses this as a theoretical basis to obtain the elongation coefficient of the crack. Specifically, see Figure 3 This step includes step S31, step S32, step S33 and step S34.

[0042] S31. Confirm the edge of the gap connected domain to obtain two points with the largest distance on the edge of the gap connected domain, and record them as endpoints.

[0043] S32, calculating the cracking angle corresponding to each endpoint according to the angle pixel points around the endpoint, wherein the angle pixel points are pixel points respectively located on both sides of the endpoint and constituting the edge of the crack.

[0044] It should be noted that there is a limit on the number of angle pixel points in this step, such as ten pixels or five pixels. At the same time, in this step, if the crack continues to crack, it is considered that the crack will continue to spread outward from the two endpoints. Therefore, five angle pixel points on both sides of the two endpoints are linearly fitted, and the angle between the two fitting lines corresponding to each endpoint is recorded as the cracking angle. For those skilled in the art, other numbers of angle pixel points can also be selected, and no specific limitation is made in the present invention.

[0045] S33. Count the number of pixel points of each line segment in the extended line segment set corresponding to each endpoint, the extended line segment set includes five line segments that are parallel to each other and adjacent in sequence, one of the line segments in the extended line segment set is adjacent to the endpoint, and each line segment in the extended line segment set is perpendicular to a direction line, which is a line connecting the two end points.

[0046] In this step, the length of each line segment in each extended line segment set represents the width change of the accompanying direction line of the crack at the endpoint.

[0047] S34. Calculate the crack extension coefficient based on the crack angle corresponding to each endpoint and the number of pixels of each line segment in the extended line segment set.

[0048] It should be noted that the calculation formula of the crack extension coefficient in this step is as follows:

[0049]

[0050] in, represents the crack extension coefficient; represents the extension coefficient of the jth endpoint; represents a hyperbolic function; represents the cracking angle corresponding to the jth endpoint; Indicates that the jth endpoint corresponds to the The number of pixels in the line segment; Indicates that the jth endpoint corresponds to the The number of pixels in a line segment.

[0051] In the above calculation formula of the crack extension coefficient: the angle between the crack endpoints The smaller the value, the smaller the angle of the endpoint part. Therefore, there is a region with a smaller angle at the endpoint part of the crack. Under the action of subsequent cracking stress, it is easier to cause the endpoint part to continue to crack. Therefore, the higher the elongation coefficient, the smaller the angle of the endpoint part. Negatively correlated; at the same time, the mean difference in the number of pixels between two adjacent line segments on the direction line of the crack endpoint The larger the value, the wider the crack becomes along the direction of the endpoint, so the crack is more likely to continue to extend, so it is positively correlated with the extension coefficient. Calculating the crack shape through the above calculation formula can better meet the actual change state of the subsequent crack.

[0052] S4. Perform damage calculation based on the inner edge of the crack connected domain to obtain a conductor coefficient.

[0053] It should be noted that the energy storage harness is composed of conductors, shielding layers, sheaths, insulating layers, connectors, etc. Therefore, in this step, it is considered that the energy storage harness is composed of several uniform layered structures. For the cracked part of the energy storage harness, multiple layers may be damaged due to deep damage, and the wires may even be exposed due to excessive damage; and the more damaged layers and the deeper the wires, the more dangerous they are; if multiple layers of cracking occur, multiple layers of trap-like structures will appear inside the cracks. Therefore, in this embodiment, it is necessary to obtain the wire coefficient of the cracked part according to the number of damaged layers in the cracked part and whether the wires are exposed. For details, please refer to Figure 4 , step S4 includes step S41, step S42, step S43, step S44 and step S45.

[0054] S41, calculating the centroid region according to the gray value in the gap connected domain.

[0055] It should be noted that the method for calculating the centroid is a prior art and will not be described in detail in the present invention.

[0056] S42. Screening candidate edges located inside the gap connected domain to obtain a broken edge set, wherein the broken edge set includes at least one broken edge.

[0057] It should be noted that the candidate edges mentioned in this step are edges in the crack area, which may be formed by cracks in a layer in the energy storage harness. Step S4 is to screen these edges. Specifically, step S42 also includes step S421, step S422 and step S423.

[0058] S421 , projecting all candidate edges inside the gap connected domain to the gap edge from the centroid region to obtain a plurality of projected edges.

[0059] S422: Calculate the DTW value of each candidate edge and the corresponding projected edge using the DTW algorithm and perform normalization processing to obtain a normalized DTW value corresponding to each candidate edge.

[0060] S423: Screening to obtain a damaged edge set according to the relationship between a preset screening threshold and the normalized DTW value corresponding to each candidate edge.

[0061] If the internal cracking of the crack is considered in this step, a trap-shaped edge will be formed at the crack. Therefore, for each edge inside the crack, the DTW value of the edge and its projected edge is calculated, wherein the smaller the DTW value, the similarity between the internal edge of the crack and the edge of the crack portion. In this embodiment, the normalized DTW value is compared with a preset screening threshold, and the edge greater than the screening threshold is recorded as a damaged edge inside the crack. The screening threshold in the present invention is 0.8, and those skilled in the art may also select other data values, and specific restrictions are made in the present invention.

[0062] S43. Connect the midpoints of each damaged edge according to the centroid region to obtain a centerline set, and record the angle between each line segment in the centerline set and the horizontal line as an angle set.

[0063] S44, respectively counting the distances from the damaged edge to the crack edge to obtain a distance set.

[0064] S45. Calculate the wire coefficient based on the angle set, the distance set, the gap connected domain, and the grayscale value corresponding to the centroid area.

[0065] It should be noted that the calculation formula of the conductor coefficient in this step is as follows:

[0066]

[0067] in, The conductor coefficient representing the gap; The information entropy representing the distances from multiple damaged edges inside the crack to the crack edge; represents a distance set; The information entropy representing the angles between the multiple damaged edges inside the crack and the horizontal line; Represents a collection of angles; Represents the mean gray value of the centroid area; Represents the mean gray value of the connected domain of the gap; represents a hyperbolic function; +0.01 is to prevent the denominator from being zero.

[0068] In the above calculation formula, the information entropy of the angles between the multiple damaged edges inside the crack and the horizontal line is , the larger the value, the more angles of the damaged edges, so it means that the damaged edges are arranged in a circle inside the crack, which means that there are multiple layers of damage inside the crack; and the information entropy of the angles between the multiple damaged edges inside the crack and the horizontal line The larger the value, the more types of distance data there are at the damaged edge, which indicates that there are multiple layers of damage inside the crack. The larger the value, the more layers of damage there are, so the higher the conductor coefficient is. There is a positive correlation; and the ratio of the mean gray value of the pixel points in the centroid area to the mean gray value of the entire gap connected domain The larger the value, the higher the gray value of the centroid is compared to the overall gray value, which indicates that there is a bare wire inside the crack. Therefore, the higher the wire coefficient is, the higher the gray value is. Therefore, the above calculation formula can better describe the situation of internal leakage in the crack.

[0069] S5. Calculate the bending property of the energy storage harness based on the surface image of the energy storage harness and the connected domain of the crack to obtain a bending coefficient.

[0070] In this embodiment, if the crack is located at the bending part of the wire harness, it is more likely to continue to break due to the bending effect. Although the wire harness will be straightened for acquisition, the energy storage wire harness will not be completely straightened due to the bending stress, and a small bend will still be formed at the bending part. Figure 5 , this step also includes step S51, step S52 and step S53.

[0071] S51, performing harness extraction in the surface image of the energy storage harness based on the crack connected domain to obtain a harness segment image, wherein the harness segment image contains the crack, and the harness segment image contains a preset number of pixel points from the end of the harness to the end point of the crack.

[0072] It should be noted that this step is to obtain a section of the wire bundle where the crack is located according to the size of the crack. Specifically, the length of the wire bundle obtained is equal to three times the length of the crack. Therefore, the preset number of pixels is equal to the number of horizontal pixels between the two ends of the crack.

[0073] S52, performing straight line fitting processing on the edges on both sides of the wire bundle in the wire bundle segment image respectively to obtain two loss values.

[0074] It should be noted that in this step, the least square method is used to fit the straight lines to the edges on both sides of the harness, and the loss value when fitting by the least square method is recorded as the basis for calculating the bending coefficient.

[0075] S53, calculating the average of the two loss values, and using the calculated result as the bending coefficient.

[0076] S6. Calculate the crack hazard coefficient of the energy storage harness based on the crack extension coefficient, the conductor coefficient and the bending coefficient.

[0077] It should be noted that in this step, the calculation formula for the crack risk factor is as follows:

[0078]

[0079] in, Indicates the crack risk factor; represents the crack extension coefficient; It represents the conductor coefficient; Represents the bending coefficient.

[0080] Because it is impossible to discard all energy storage harnesses with cracks in practice. Figure 1 In this embodiment, the method further includes the step of performing subsequent processing according to the calculated crack risk coefficient, specifically including step S7, step S8 and step S9.

[0081] S7. When the crack risk factor is less than a first safety threshold, a first display command is sent to the display screen, where the first display command is used to trigger the display screen to display content that can be repaired with an adhesive.

[0082] S8. When the crack risk factor is greater than the first safety threshold and less than the second safety threshold, a second display command is sent to the display screen, wherein the second display command is used to trigger the display screen to display content that can be repaired by repair materials.

[0083] S9. When the crack risk factor is greater than a third safety threshold, a third display command is sent to the display screen, and the third display command is used to trigger the display screen to display danger warning content, the first safety threshold is less than the second safety threshold, and the second safety threshold is less than the third safety threshold.

[0084] Specifically, in the application, the first safety threshold can be set to 6, the second safety threshold can be set to 15, and the third safety threshold can be set to 20. At the same time, technical personnel in this field can also set them to other values ​​according to actual conditions. No specific limitations are made in the present invention.

[0085] Moreover, in this embodiment, considering that for cracks with a crack risk factor less than or equal to the first safety threshold, some text or agreed images can be displayed through the first display command to prompt the inspector that the crack can be repaired with a suitable adhesive. And during the repair process, it is only necessary to ensure that the adhesive suitable for the material and stress environment is selected. Similarly, for cracks with a crack risk factor greater than the first safety threshold and less than the second safety threshold, some text or agreed images can be displayed through the second display command to prompt that the surface can be repaired using a patch or applying appropriate touch-up paint, and during the repair process, it is necessary to ensure that the repair material is compatible with the harness material and can withstand the normal stress and environmental conditions of the harness; however, for cracks with a crack risk factor greater than the third safety threshold, some text or agreed images can be displayed through the third display command to warn that the crack in the harness is dangerous and that it is necessary to consider replacing a new energy storage harness.

[0086] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0087] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for detecting the quality of the insulation layer of a new energy high-voltage and high-current energy storage harness, characterized in that: The method comprises: Acquire the surface image of the energy storage harness; Preprocessing the energy storage wire harness surface image to obtain a crack connected domain in the energy storage wire harness surface; The crack extension coefficient is calculated based on the crack morphological characteristics in the crack connected domain; Perform damage analysis based on the internal edge of the crack connected domain to obtain a conductor coefficient; Based on the surface image of the energy storage harness and the crack connected domain, the bending property of the energy storage harness is analyzed to obtain a bending coefficient; The crack hazard coefficient of the energy storage harness is calculated based on the crack extension coefficient, the conductor coefficient and the bending coefficient.

2. The insulation layer quality detection method of the new energy high-voltage and high-current energy storage wiring harness according to claim 1 is characterized in that: The energy storage wire harness surface image is preprocessed to obtain a crack connected domain in the energy storage wire harness surface, including: grayscale the surface image of the energy storage harness to obtain a grayscale image; Using a preset edge detection mathematical model to perform edge detection on the grayscale image, the edge of the crack is obtained; The grayscale image is segmented based on the crack edge to obtain a crack connected region.

3. The insulation layer quality detection method of the new energy high-voltage and high-current energy storage wiring harness according to claim 2 is characterized in that: The preset edge detection mathematical model is the canny operator edge detection mathematical model.

4. The insulation layer quality detection method of the new energy high-voltage and high-current energy storage wiring harness according to claim 1 is characterized in that: The crack extension coefficient is calculated based on the crack morphological characteristics in the crack connected domain, including: Confirming two endpoints on the edge of the gap connected domain, the two endpoints being two points with the largest distance between them in the gap connected domain; The cracking angle corresponding to each endpoint is calculated according to the angle pixel points around the endpoint, wherein the angle pixel points are pixel points located on both sides of the endpoint and forming the edge of the crack; Counting the number of pixels of each line segment in the extended line segment set corresponding to each endpoint, the extended line segment set includes five line segments that are parallel to each other and adjacent in sequence, one of the line segments in the extended line segment set is adjacent to the endpoint, and each line segment in the extended line segment set is perpendicular to a direction line, which is a line connecting the two end points; The crack extension coefficient is calculated based on the cracking angle corresponding to each endpoint and the number of pixels of each line segment in the extended line segment set.

5. The insulation layer quality detection method of the new energy high-voltage and high-current energy storage wiring harness according to claim 1 is characterized in that: The conductor coefficient is obtained by performing damage calculation based on the internal edge of the crack connected domain, including: The centroid region is calculated according to the gray value in the connected domain of the crack; Screening candidate edges located inside the gap connected domain to obtain a broken edge set, wherein the broken edge set includes at least one broken edge; Connecting the midpoints of each damaged edge according to the centroid region to obtain a midline set, and recording the angle between each line segment in the midline set and the horizontal line as an angle set; The distances from the damaged edge to the crack edge are counted respectively to obtain a distance set; The conductor coefficient is calculated based on the angle set, the distance set, the grayscale value corresponding to the gap connected domain, and the grayscale value corresponding to the centroid area.

6. The insulation layer quality detection method of the new energy high-voltage and high-current energy storage wiring harness according to claim 5 is characterized in that: The candidate edges located inside the gap connected domain are screened to obtain a broken edge set, wherein the broken edge set includes at least one broken edge, including: Projecting all candidate edges inside the gap connected domain to the gap edge from the centroid region to obtain a plurality of projected edges; Use the DTW algorithm to calculate the DTW value of each candidate edge and the corresponding projected edge; According to the relationship between the preset screening threshold and the DTW value corresponding to each candidate edge, the damaged edge set is screened out.

7. The insulation layer quality detection method of the new energy high-voltage and high-current energy storage wiring harness according to claim 6 is characterized in that: The preset screening threshold is 0.

8.

8. The insulation layer quality detection method of the new energy high-voltage and high-current energy storage wiring harness according to claim 1 is characterized in that: The bending coefficient of the energy storage harness is obtained by calculating the bending property of the energy storage harness based on the surface image of the energy storage harness and the crack connected domain, including: Based on the crack connected domain, a wire harness is extracted in the surface image of the energy storage wire harness to obtain a wire harness segment image, wherein the wire harness segment image contains a crack, and the wire harness segment image contains a preset number of pixel points from the end of the wire harness to the end point of the crack; Performing straight line fitting processing on the edges of both sides of the wire bundle in the wire bundle segment image respectively to obtain two loss values; The average of the two loss values ​​is calculated, and the result is used as the bending coefficient.

9. The insulation layer quality detection method of the new energy high-voltage and high-current energy storage wiring harness according to claim 8 is characterized in that: The straight line fitting process is a least squares straight line fitting process.

10. The insulation layer quality detection method of the new energy high-voltage and high-current energy storage wiring harness according to claim 1 is characterized in that: The crack hazard coefficient of the energy storage harness is calculated based on the crack extension coefficient, the conductor coefficient and the bending coefficient, and then the method further includes: When the crack risk factor is less than a first safety threshold, a first display command is sent to the display screen, wherein the first display command is used to trigger the display screen to display content that can be repaired by adhesive; When the crack risk factor is greater than the first safety threshold and less than the second safety threshold, a second display command is sent to the display screen, wherein the second display command is used to trigger the display screen to display content that can be repaired by repair materials; When the crack risk factor is greater than the third safety threshold, a third display command is sent to the display screen, and the third display command is used to trigger the display screen to display the danger warning content, the first safety threshold is less than the second safety threshold, and the second safety threshold is less than the third safety threshold.

Images