Defective cable availability evaluation method and system and method for manufacturing defective cable

Abstract

The invention relates to a defective cable availability evaluation method and system and a method for manufacturing a defective cable. The defective cable availability evaluation method comprises the following steps: manufacturing a cable sample with an aging defect; collecting a multi-angle X-ray image of each cable sample through an X-ray imaging device, and carrying out image preprocessing; feature extraction is carried out on the preprocessed X-ray images, risk tags of different levels are added to the preprocessed X-ray images based on the extracted image features, and the risk tags indicate the availability of the cable; establishing an image classification model, and inputting the image features of each preprocessed X-ray image and the corresponding risk label into the image classification model for training to obtain a trained risk assessment model; and acquiring an X-ray image of a to-be-detected cable through X imaging equipment, performing preprocessing and feature extraction, acquiring image features of the to-be-detected cable, inputting the image features into the risk assessment model, and outputting a risk assessment result of the to-be-detected cable.

Description

TECHNICAL FIELD

[0001] The present application relates to a defect cable usability evaluation method, system and a method for manufacturing a defect cable, and belongs to the technical field of cable nondestructive testing. BACKGROUND

[0002] How to accurately judge whether the aging cable still has service capability and its remaining life is a long-standing technical pain point. The traditional cable state evaluation method mainly relies on manual inspection, sampling test or experience determination, which is difficult to support scientific decision-making and has low efficiency and high misjudgment rate.

[0003] Although X-ray technology has been widely used in cable internal defect detection, the existing means generally has the following problems:

[0004] The sample collection efficiency is low, and it is difficult to form a comprehensive cable defect data set;

[0005] The image after detection needs to be manually interpreted by experts, and the process is complicated and subjective;

[0006] There is no systematic risk classification mechanism, it is difficult to quantify the severity of the defect, and it cannot be directly converted into an operable maintenance suggestion. SUMMARY

[0007] In order to solve the problems existing in the prior art, the present application provides a defect cable usability evaluation method, system and a method for manufacturing a defect cable, which aims to build a fast, automatic and quantifiable cable ablation defect risk classification solution to support operation and maintenance decision-making for whether to continue using old cables.

[0008] The technical scheme of the present application is as follows:

[0009] On the one hand, the present application provides a defect cable usability evaluation method, comprising the following steps:

[0010] Manufacture cable samples with aging defects;

[0011] Collect multi-angle X-ray images of each cable sample by an X-ray imaging device, and perform image preprocessing;

[0012] Extract features from the preprocessed X-ray images, add different levels of risk labels to each preprocessed X-ray image based on the extracted image features, and the risk labels indicate the usability of the cable;

[0013] Establish an image classification model, input the image features and corresponding risk labels of each preprocessed X-ray image into the image classification model for training, and obtain a trained risk assessment model;

[0014] An X-ray image of the cable to be detected is collected by an X-ray imaging device, preprocessed and feature extracted, and the image features of the cable to be detected are input into a risk assessment model to output a risk assessment result of the cable to be detected.

[0015] As a preferred embodiment, the step of preprocessing the image comprises:

[0016] The X-ray image is filtered to remove noise;

[0017] The filtered X-ray image is subjected to contrast-limited adaptive histogram equalization, and all X-ray images are scaled to a uniform resolution and normalized grayscale.

[0018] As a preferred embodiment, the step of feature extraction of the preprocessed X-ray image comprises:

[0019] A semantic segmentation model is used to perform semantic segmentation on the preprocessed X-ray image to generate a binary mask image containing defect regions;

[0020] The binary mask image is subjected to connected component analysis to identify each independent defect region;

[0021] According to the identified defect region result, the number of defects, the average defect area, the area standard deviation and the spatial information entropy in a set unit length in the binary mask image are calculated as image features.

[0022] As a preferred embodiment, the semantic segmentation model uses a U-Net model combined with a MobileNetV2 network.

[0023] As a preferred embodiment, the method further comprises:

[0024] According to different risk labels, corresponding cable processing measures are formulated;

[0025] When the risk assessment result of the cable to be detected is obtained, a report containing the risk assessment result and the current processing measure is generated according to the corresponding risk assessment result.

[0026] As a preferred embodiment, the aging defect is a cable buffer layer ablation defect.

[0027] In another aspect, the present application also provides a defect cable usability assessment system, comprising:

[0028] A sample making module for making cable samples with aging defects;

[0029] An image processing module for collecting multi-angle X-ray images of each cable sample by an X-ray imaging device and preprocessing the images;

[0030] An image labeling module is configured to extract features from the preprocessed X-ray image, and add risk labels of different levels to each preprocessed X-ray image based on the extracted image features, the risk labels indicating the availability of the cable.

[0031] A model training module is configured to establish an image classification model, input the image features and corresponding risk labels of each preprocessed X-ray image into the image classification model for training, and obtain a trained risk assessment model.

[0032] An evaluation module is configured to acquire an X-ray image of a to-be-detected cable by an X imaging device, preprocess and extract features from the X-ray image, input the image features of the to-be-detected cable into the risk assessment model, and output a risk assessment result of the to-be-detected cable.

[0033] In another aspect, the present application further provides an electronic device, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the defect cable availability evaluation method according to any one of the embodiments of the present application when executing the program.

[0034] In another aspect, the present application further provides a computer readable storage medium, which stores a computer program, and the program is executable on a processor to implement the defect cable availability evaluation method according to any one of the embodiments of the present application.

[0035] In another aspect, the present application further provides a method for manufacturing an aging defect cable, which is applied to the defect cable availability evaluation method according to any one of the embodiments of the present application, and comprises the following steps:

[0036] A standard cable is cut into multiple small cables, both ends of each small cable are sealed, and multiple small holes are reserved at one end; the small holes are located at the junction of the axial direction of the buffer layer and the end of the cable, and the diameter of the small holes is consistent with the difference between the inner diameter of the aluminum sheath and the outer diameter of the buffer layer;

[0037] After water is injected into the small holes of each small cable, the small holes are sealed;

[0038] The small cable after water injection is segmented and placed, after each placement for a set time, the small cable is rotated by 90 degrees in the axial direction and then placed for a set time, and the placement is completed four times;

[0039] After the segmented placement is completed, the sealing material at both ends of each small cable is removed, and the cable surface layer is cut and peeled off at both ends of the small cable, respectively, to expose the insulation shielding layer and the aluminum sheath;

[0040] Copper foil electrodes are respectively pasted in a ring shape at the ends where the insulation shielding layer and the aluminum sheath are exposed, and alternating current constant current is applied to the copper foil electrodes at both ends for a set time, to obtain multiple cable samples with aging defects.

[0041] The present application has the beneficial effects in that:

[0042] The defect cable usability evaluation method provided by the present application focuses on the establishment of an intelligent auxiliary decision mechanism for whether the cable can still be used, that is, by comprehensively evaluating the ablation defect point density, distribution and other quantitative image features in the X-ray image, a graded risk evaluation result is automatically output, thereby providing technical support for daily inspection, early warning and replacement decision.

[0043] Additional aspects and advantages of the present application will be set forth in the description below, and in part will be obvious from the description, or can be learned by practice of the present application. Moreover, the various aspects and advantages of the present application can be realized and obtained by means of the instrumentalities and combinations pointed out in the appended claims. BRIEF DESCRIPTION OF DRAWINGS

[0044] Figure 1 Equation flowchart of the present application embodiment one.

[0045] Figure 2 System structure diagram for manufacturing cable aging defects in the present application embodiment five. DETAILED DESCRIPTION

[0046] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0047] It should be understood that the step numbers used herein are only for the convenience of description, and are not limited to the execution sequence of the steps.

[0048] It should be understood that the terms used in the present application specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the present application specification and the appended claims, unless otherwise clearly indicated by the context, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0049] The terms "comprise" and "include" indicate the presence of the described features, whole, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, whole, steps, operations, elements, components and / or sets thereof.

[0050] The term "and / or" refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0051] Embodiment One:

[0052] Referring to Figure 1 The embodiment proposes a method for evaluating the usability of defective cables, comprising the following steps:

[0053] S100, a cable sample with aging defects is made; controllable and repeatable aging defects are generated for subsequent algorithm training and testing.

[0054] S200, high-quality, multi-angle X-ray images of each cable sample are collected by an X-ray imaging device. When each cable sample is photographed, after each photographing, a 20° rotation is performed and one photographing is performed. The rotation direction of the previous step is repeated to cycle this step until 18 photographings are performed. The collected X-ray images are preprocessed and enhanced to improve the defect contrast and suppress noise, laying a foundation for automatic analysis.

[0055] S300, feature extraction is performed on the preprocessed X-ray images, and different levels of risk labels are added to each preprocessed X-ray image based on the extracted image features, the risk labels indicating the usability of the cable.

[0056] S400, an image classification model is established, and the image features of each preprocessed X-ray image and the corresponding risk label are input into the image classification model for training to obtain a trained risk assessment model.

[0057] S500, the X-ray images of the cable to be detected are collected by the X imaging device and preprocessed and feature extracted, the image features of the cable to be detected are input into the risk assessment model, and the risk assessment result of the cable to be detected is output.

[0058] The embodiment produces a defect sample, constructs an X-ray image database, and is matched with an intelligent recognition and grading mechanism to establish an automatic evaluation system for cable defect risks. The method core is formed through image enhancement + defect feature extraction + risk assessment model; finally, structured and interpretable risk level information is output to assist the power grid operation and maintenance team to make quick decisions without the intervention of experts.

[0059] As a preferred embodiment of the embodiment, in step S200, the image preprocessing step comprises:

[0060] Median filtering or bilateral filtering is applied to the X-ray image to remove salt and pepper noise and preserve edges.

[0061] CLAHE (Contrast Limited Adaptive Histogram Equalization) is used for the X-ray image after filtering to improve the visibility of ablation points under low signal-to-noise ratio.

[0062] All X-ray images are scaled to a uniform resolution and normalized gray scale to eliminate device / angle differences.

[0063] As a preferred embodiment of the present embodiment, the step of performing feature extraction on the pre-processed X-ray image comprises:

[0064] A lightweight MobileNetV2 combined with U-Net is used as the base model to perform pixel-level semantic segmentation on the pre-processed image, with the goal of generating a binary mask image of the defect area. A pixel value of 1 represents a defect area, and 0 represents the background.

[0065] The binary mask image is subjected to connected component analysis to identify each independent defect area.

[0066] According to the identified defect area result, the number of defects n, the average defect area A, and the area standard deviation σ A and spatial information entropy H in a set unit length (set to 14 cm in the present embodiment) in the binary mask image are calculated as image features.

[0067] The average area A is calculated by the number of defect area pixels, combined with the actual size of each pixel for proportional enlargement or reduction.

[0068] The spatial distribution entropy represents the discrete degree of the spatial distribution of defects in the image. The image can be divided into several grids (such as 16x9), and the proportion p j of defect pixels in each grid is calculated, and then the information entropy H is calculated. The specific calculation formula is as follows:

[0069]

[0070] where ε is the introduced residual term.

[0071] The obtained image feature output is a feature vector: x = [n, A, σ A , H].

[0072] As a preferred embodiment, the semantic segmentation model uses a U-Net model combined with a MobileNetV2 network.

[0073] As a preferred embodiment of the present embodiment, the method further comprises:

[0074] According to different risk labels, corresponding cable treatment measures are formulated;

[0075] For example, three risk labels are set, namely mild ablation, moderate ablation, and severe ablation, and the defined standards are:

[0076] Mild ablation: the number of ablation points n in the X-ray image of each 14 cm cable sample is less than μ n -σn and A < 1.0 mm 2 .

[0077] Moderate ablation: number of ablation points per 14 cm cable sample X-ray image n n -σ n <n<μ n +σ n .

[0078] Severe ablation: number of ablation points per 14 cm cable sample X-ray image n > μ n +σ n or A > 2.0 mm 2 H < 0.5.

[0079] wherein μ n is the mean area of the defect region.

[0080] The set cable treatment measures are respectively:

[0081] Mild ablation: retest within 96 hours.

[0082] Moderate ablation: retest within 48 hours, and plan replacement if necessary.

[0083] Severe ablation: replace immediately.

[0084] When the risk assessment result of the cable to be detected is obtained, a report containing the risk assessment result and the current treatment measure is generated according to the corresponding risk assessment result.

[0085] For example, the obtained risk assessment result of the cable to be detected is moderate ablation, and the corresponding output structured report is:

[0086] Risk level: level 2 (moderate ablation);

[0087] Main features: n = 12, μ_A = 0.8 mm 2 , σ_A = 0.3 mm 2 , H = 1.2;

[0088] Suggested operation: retest within 48 hours, and plan replacement if necessary.

[0089] As a preferred embodiment, the aging defect is a cable buffer layer ablation defect.

[0090] Example two:

[0091] The embodiment proposes a defect cable usability evaluation system, comprising:

[0092] A sample making module for making a cable sample with an aging defect; the module is used to realize the function of step S100 in example one, and will not be described here.

[0093] an image processing module, configured to acquire multi-angle X-ray images of each cable sample by the X-ray imaging device and perform image preprocessing; the module is configured to implement the function of step S200 in Embodiment I, and details are not repeated here;

[0094] an image labeling module, configured to extract features from the preprocessed X-ray images, add different levels of risk labels to each preprocessed X-ray image based on the extracted image features, and the risk labels indicate the availability of the cable; the module is configured to implement the function of step S300 in Embodiment I, and details are not repeated here;

[0095] a model training module, configured to establish an image classification model, input the image features and corresponding risk labels of each preprocessed X-ray image into the image classification model for training, and obtain a trained risk assessment model; the module is configured to implement the function of step S400 in Embodiment I, and details are not repeated here;

[0096] an evaluation module, configured to acquire X-ray images of a to-be-detected cable by the X imaging device, perform preprocessing and feature extraction, input the image features of the to-be-detected cable into the risk assessment model, and output a risk assessment result of the to-be-detected cable; the module is configured to implement the function of step S500 in Embodiment I, and details are not repeated here.

[0097] Embodiment III:

[0098] The embodiment provides an electronic device, which comprises a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and the processor implements the defect cable availability evaluation method according to any one of the embodiments of the present application when executing the program.

[0099] Embodiment IV:

[0100] The embodiment provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the defect cable availability evaluation method according to any one of the embodiments of the present application.

[0101] Embodiment V:

[0102] Specifically, Figure 2 The embodiment provides a method for manufacturing an aging defect cable, which is applied to the defect cable availability evaluation method according to any one of the embodiments of the present application and comprises the following steps:

[0103] cut a standard cable into multiple small cables each with a length of 20 cm, seal both ends of each small cable, and reserve multiple small holes at one end of each small cable; the small holes are located at the junction of the axial direction of the buffer layer and the interface of the one end of the cable, and the diameter of the small holes is consistent with the difference between the inner diameter of the aluminum sheath of the cable and the outer diameter of the buffer layer.

[0104] Water is injected into the small hole of each section of the small cable, and the amount of water injected is V = 10π(r1 2 -r2 2 ).

[0105] Wherein, V is the volume of water injected into the buffer layer, r1 is the inner diameter of the cable aluminum sheath, and r2 is the outer diameter of the cable insulation shield layer;

[0106] After water injection, the small hole is sealed.

[0107] After each cable sample is placed for 30 minutes, it is rotated 90 degrees clockwise or counterclockwise and continues to be placed, and each rotation maintains the first rotation direction until the fourth placement is completed.

[0108] After the segmented placement is completed, the sealing material at both ends of each section of the small cable is removed, and the cable surface layer is cut and peeled off at one end of the cable to expose a ring-shaped insulation shield layer with a width of 3 cm. The cable surface layer is cut and peeled off at the other end of the cable to expose a ring-shaped aluminum sheath with a width of 3 cm.

[0109] A 3 cm wide copper foil electrode is pasted in a ring shape at one end of the cable exposed insulation shield layer and tightly pasted in a ring. A 3 cm wide copper foil electrode is pasted in a ring shape at one end of the cable exposed aluminum sheath and tightly pasted in a ring.

[0110] A 50-150 mA, 50 Hz AC constant current is applied to the two electrodes for 60 minutes to obtain a plurality of cable samples with aging defects.

[0111] The above method can manufacture buffer layer defects in the cable by equivalent radial current treatment of the cable after water injection, which can provide sufficient defect cable samples for studying the development mechanism of cable buffer layer defects, and has important significance for the study of cable buffer layer ablation problems.

[0112] In the embodiments of the present application, "at least one" means one or more, and "multiple" means two or more. The "and / or" describes the association relationship of the associated objects, which means that there can be three kinds of relationships, for example, A and / or B, which can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Wherein A, B can be singular or plural. The character " / " generally represents an "or" relationship between the front and rear associated objects. "At least one of the following" and the like means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b and c can represent: a, b, c, a and b, a and c, b and c, or a and b and c, wherein a, b, c can be single or multiple.

[0113] Those skilled in the art can clearly understand that the units and algorithm steps described in the embodiments disclosed herein can be realized by electronic hardware, computer software and a combination of electronic hardware and computer software. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solutions. Those skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0114] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0115] In several embodiments provided in the present application, any function realized in the form of a software function unit and sold or used as an independent product can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the parts of the technical solutions that make contributions to the prior art or the parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0116] The above is only the embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent flow transformation, or direct or indirect application in other related technical fields, is also included in the patent protection scope of the present application.

Claims

1. A method of defect cable usability assessment, characterized by, The method comprises the following steps: manufacturing cable samples with aging defects; collecting multi-angle X-ray images of each cable sample by an X-ray imaging device and performing image preprocessing; extracting features from the preprocessed X-ray images, adding different levels of risk labels to each preprocessed X-ray image based on the extracted image features, and the risk labels indicating the availability of the cable; establishing an image classification model, inputting the image features and corresponding risk labels of each preprocessed X-ray image into the image classification model for training, and obtaining a trained risk assessment model; collecting X-ray images of the cable to be detected by the X imaging device, performing preprocessing and feature extraction, inputting the image features of the cable to be detected into the risk assessment model, and outputting the risk assessment result of the cable to be detected.

2. The method of claim 1, wherein, The step of performing image preprocessing comprises: performing filtering processing on the X-ray images to remove noise; performing contrast-limited adaptive histogram equalization on the filtered X-ray images, and scaling all X-ray images to a unified resolution and normalized gray scale.

3. The method of claim 1, wherein, The step of extracting features from the preprocessed X-ray images comprises: using a semantic segmentation model to perform semantic segmentation on the preprocessed X-ray images to generate a binary mask image containing defect regions; performing connected component analysis on the binary mask image to identify each independent defect region; According to the identified defect region result, the number of defects in a set unit length, the average defect area, the area standard deviation and the spatial information entropy in the binary mask image are calculated as image features.

4. The defect cable availability evaluation method according to claim 3, wherein: The semantic segmentation model uses a U-Net model combined with a MobileNetV2 network.

5. The method of claim 1, wherein, The method further comprises: developing corresponding cable processing measures according to different levels of risk labels; when the risk assessment result of the cable to be detected is obtained, generating a report containing the risk assessment result and the current processing measure according to the corresponding risk assessment result.

6. The defect cable availability evaluation method according to claim 1, wherein: The aging defect is a cable buffer layer ablation defect.

7. A system for assessing the availability of a defective cable, characterized by comprises: a sample manufacturing module for manufacturing cable samples with aging defects; an image processing module for collecting multi-angle X-ray images of each cable sample by an X-ray imaging device and performing image preprocessing; an image labeling module for extracting features from the preprocessed X-ray images, adding different levels of risk labels to each preprocessed X-ray image based on the extracted image features, and the risk labels indicating the availability of the cable; a model training module for establishing an image classification model, inputting the image features and corresponding risk labels of each preprocessed X-ray image into the image classification model for training, and obtaining a trained risk assessment model; an evaluation module for collecting X-ray images of the cable to be detected by the X imaging device, performing preprocessing and feature extraction, inputting the image features of the cable to be detected into the risk assessment model, and outputting the risk assessment result of the cable to be detected.

8. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor implements the defect cable usability evaluation method of any one of claims 1 to 6 when executing the program.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the defect cable usability evaluation method of any one of claims 1 to 6.

10. A method of manufacturing an aged defective cable, applied to the defective cable usability evaluation method according to any one of claims 1 to 6, characterized by, The method comprises the following steps: The standard cable is cut into multiple small cables, the two ends of each small cable are sealed, and multiple small holes are reserved at one end; the small holes are located at the junction of the axial direction of the buffer layer and the end of the cable, and the diameter of the small holes is consistent with the difference between the inner diameter of the aluminum sheath and the outer diameter of the buffer layer; After water is injected into the small holes of each small cable, the small holes are sealed; The water-injected small cable is segmented and placed, each time the small cable is rotated 90 degrees along the axial direction after being placed for a set time, and then placed for a set time again, and the process is repeated four times; After the segmented placement is completed, the sealing material at the two ends of each small cable is removed, and the surface layer of the small cable is cut and peeled off at both ends to expose the insulating shielding layer and the aluminum sheath, respectively; Copper foil electrodes are annularly pasted to the ends of the exposed insulating shielding layer and aluminum sheath, respectively, and alternating current constant current is applied to the copper foil electrodes at both ends for a set time to obtain multiple cable samples with aging defects.

Images