Composite insulated cable detection method, device and equipment

Abstract

The invention discloses a composite insulated cable detection method, device and equipment, and relates to the related technical field of cable detection, and the method comprises the steps: connecting a composite design production drawing, obtaining a composite hierarchical structure and material parameters of a composite insulated cable, and constructing a multi-layer physical structure model; determining a detection parameter and a detection channel of each structural layer; respectively carrying out directional detection on the composite insulated cable to obtain multi-source detection data, and executing hierarchical and interlayer state identification and prediction analysis to obtain an identification result; and generating a cable detection state thermodynamic diagram, and carrying out visual presentation of a fault position and an aging degree. The technical problems that in the prior art, it is difficult to deeply analyze the structural layer and interlayer state change of the composite cable, the fault position of the composite insulated cable cannot be accurately positioned, and the aging trend of the cable cannot be effectively predicted are solved, and the purposes of accurate detection, layered positioning of the fault position of the cable and accurate prediction of the aging trend of the cable are achieved. And the aging trend of the cable is effectively predicted and visually presented.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of cable detection, and particularly relates to a composite insulation cable detection method, device and equipment. BACKGROUND

[0002] The composite insulation cable realizes insulation, shielding and protection by composite design of multiple functional materials, effectively improves the safety and stability of power transmission. However, with the increasing complexity of cable operation environment (such as high temperature, high humidity, strong electromagnetic interference, etc.) and the increase of service life, potential faults such as aging, damage and partial discharge are prone to occur in the internal structure layers of the cable, which leads to the decline of cable performance and affects the safe and stable operation of the power system. Traditional cable detection methods (such as dielectric loss, infrared thermal image, partial discharge test, etc.) are mostly based on overall cable electrical parameter analysis or external thermal field observation, which cannot identify potential hazards such as local aging, material interface debonding and functional layer failure in the multi-layer composite structure, and thus cannot accurately locate the fault position and cannot in-depth analyze the state changes between the structure layers. In the face of composite structure cable, the detection efficiency and accuracy cannot meet the actual demand.

[0003] Therefore, in the related art, there are technical problems that the state changes of the structure layers and between the layers of the composite cable cannot be in-depth analyzed, the fault position of the composite insulation cable cannot be accurately located, and the aging trend of the cable cannot be effectively predicted. SUMMARY

[0004] The present application provides a composite insulation cable detection method, device and equipment, which solves the technical problems that the state changes of the structure layers and between the layers of the composite cable cannot be in-depth analyzed, the fault position of the composite insulation cable cannot be accurately located, and the aging trend of the cable cannot be effectively predicted in the prior art, and achieves the technical effects of accurate detection, layered positioning of the cable fault position, effective prediction of the aging trend of the cable and intuitive presentation.

[0005] The present application provides a composite insulation cable detection method, which comprises the following steps: connecting a composite design production drawing, obtaining a composite layer structure and material parameters of a composite insulation cable, and constructing a multi-layer physical structure model; determining a detection parameter and a detection channel of each structure layer based on the multi-layer physical structure model, wherein the detection channel has an associated detection means label; performing directional detection on the composite insulation cable through the detection channel respectively, obtaining multi-source detection data, inputting the multi-source detection data into the multi-layer physical structure model according to the directional relationship between the detection channel and the multi-layer physical structure model, performing hierarchical and interlayer state recognition and prediction analysis, and obtaining a recognition result; performing layered visualization processing on the multi-layer physical structure model and the corresponding recognition result, generating a cable detection state thermal map, and performing visual presentation of the fault position and the aging degree through the cable detection state thermal map.

[0006] In a possible implementation, the composite insulation cable detection method further performs the following processing: extracting conductor diameter, insulation layer thickness, shielding layer thickness, sheath layer thickness, and material dielectric constant, thermal conductivity, and interface adhesion characteristics from the composite design production drawing; establishing a composite hierarchical structure model according to the conductor diameter, insulation layer thickness, shielding layer thickness, and sheath layer thickness; and embedding material parameters according to the hierarchical mapping relationship between the material dielectric constant, thermal conductivity, and interface adhesion characteristics and the composite hierarchical structure model to construct the multi-layer physical structure model.

[0007] In a possible implementation, the composite insulation cable detection method further performs the following processing: the multi-source detection data includes dielectric response, ultrasonic reflection signal, and temperature rise change.

[0008] In a possible implementation, the composite insulation cable detection method further performs the following processing: performing electric field-thermal field-mechanical stress relationship analysis between layers based on the multi-layer physical structure model to establish a multi-physical field coupling model; starting a detection channel simultaneously under a power-on working condition, and respectively performing dielectric spectrum scanning, ultrasonic emission and reception of reflection signals, and infrared thermal imager capture of temperature rise change; performing coupling analysis on the dielectric response, ultrasonic reflection signal, and temperature rise change according to the multi-physical field coupling model, and performing composite layer aging analysis and interlayer adhesion risk area positioning through a pre-trained residual network to output the identification result.

[0009] In a possible implementation, the composite insulation cable detection method further performs the following processing: processing dielectric spectrum scanning data to extract insulation layer dielectric constant real part and imaginary part, and calculate frequency response offset; identifying defect echo area according to ultrasonic emission and reception of reflection signals, and calculating adhesion integrity index; performing time series analysis on temperature rise change to identify peak temperature rise rate and thermal diffusion path change, and determine thermal barrier failure coefficient; establishing a theoretical performance response curve based on the multi-physical field coupling model; comparing the theoretical performance response curve with detection data to calculate physical residual values of each index, the detection data being frequency response offset, adhesion integrity index, and thermal barrier failure coefficient; inputting the physical residual values as state characteristics into the residual network to perform cable structure layer aging degree prediction and interlayer adhesion risk area positioning, and outputting the identification result, the identification result including risk level and spatial coordinates.

[0010] In a possible implementation, the composite insulation cable detection method further performs the following processing: performing aging prediction analysis on historical operation data and detection data to establish a cable multi-time period aging path; performing self-healing analysis according to the cable multi-time period aging path, wherein a self-healing current limiting strategy is obtained by analyzing the influence of an operation load parameter on the service life of the cable multi-time period aging path; and performing self-healing control on the composite insulation cable according to the self-healing current limiting strategy.

[0011] In a possible implementation, the composite insulation cable detection method further performs the following processing: analyzing the influence of different load parameters on the aging of a target structure layer, establishing a load-life mapping function based on the influence, performing load fitting on the cable multi-time period aging path according to the load-life mapping function, and performing interlayer physical coupling influence based on the multi-physical field coupling model to obtain a self-healing current limiting strategy that is constrained by a structure layer aging threshold, wherein the self-healing current limiting strategy limits the maximum working current and the periodic load interval to delay the aging evolution path.

[0012] In a possible implementation, the composite insulation cable detection method further performs the following processing: based on the composite layer structure, scanning the composite insulation cable to obtain a measured layer thickness; and using the measured layer thickness to calibrate and correct the layer thickness of the multi-layer physical structure model.

[0013] The application further provides a composite insulation cable detection device, which comprises: a physical structure model construction module configured to connect a composite design production drawing, acquire a composite layer structure and material parameters of a composite insulation cable, and construct a multi-layer physical structure model; a detection channel determination module configured to determine, based on the multi-layer physical structure model, a detection parameter and a detection channel of each structure layer, wherein the detection channel has an associated detection means label; an identification result acquisition module configured to perform directional detection on the composite insulation cable through the detection channel respectively, acquire multi-source detection data, input the multi-source detection data into the multi-layer physical structure model according to a directional relationship between the detection channel and the multi-layer physical structure model, and perform layer and interlayer state identification and prediction analysis to obtain an identification result; and a cable detection state thermal map generation module configured to perform layered visualization processing according to the multi-layer physical structure model and the corresponding identification result, generate a cable detection state thermal map, and visually present a fault position and an aging degree through the cable detection state thermal map.

[0014] The application further provides an electronic device, which comprises a memory configured to store executable instructions and a processor configured to execute the executable instructions stored in the memory to implement a composite insulation cable detection method.

[0015] The application provides a composite insulation cable detection method, device and equipment, composite design production drawing is connected, composite layer structure and material parameters of the composite insulation cable are acquired, and a multilayer physical structure model is constructed; detection parameters and a detection channel of each structure layer are determined; directional detection is respectively performed on the composite insulation cable, multi-source detection data are acquired, hierarchical and interlayer state recognition and prediction analysis are performed, and a recognition result is acquired; a cable detection state heat map is generated, and a visual presentation of a fault position and an aging degree is performed. The technical problems that the composite cable structure layer and interlayer state change cannot be deeply analyzed, the fault position of the composite insulation cable cannot be accurately positioned, and the cable aging trend cannot be effectively predicted in the prior art are solved, accurate detection, hierarchical positioning of the cable fault position, effective prediction of the cable aging trend and intuitive presentation are achieved. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings of the embodiments of the present application will be briefly introduced below. In the present application, a flowchart is used to illustrate the operations performed by the device according to the embodiments of the present application. It should be understood that the foregoing or the following operations are not necessarily performed in sequence. On the contrary, according to the needs, various steps can be processed in reverse order or at the same time. Meanwhile, other operations can be added to these processes, or one or more steps of operations can be removed from these processes.

[0017] Figure 1 A composite insulation cable detection method flowchart is provided for the embodiments of the present application.

[0018] Figure 2 A composite insulation cable detection device structure diagram is provided for the embodiments of the present application.

[0019] Figure 3 A structure diagram of an electronic device is provided for the embodiments of the present application Explanation of reference signs: physical structure model construction module 10, detection channel determination module 20, recognition result acquisition module 30, cable detection state heat map generation module 40, input device 401, processor 402, memory 403, output device 404. DETAILED DESCRIPTION

[0020] The above description is only a summary of the technical solutions of the present application. In order to more clearly understand the technical means of the present application, the following specific embodiments of the present application can be implemented according to the content of the description, and in order to make the above and other purposes, characteristics and advantages of the present application more obvious and easy to understand, the following specific embodiments of the present application are described.

[0021] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings, and the described embodiments should not be regarded as limitations to the present application. All other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0022] In the following description, "some embodiments" are referred to, which describe a subset of all possible embodiments, but it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict. The term "first\second" referred to only distinguishes similar objects, and does not represent a specific order of the objects. The terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, device, product or server including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or modules not clearly listed or inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as understood by those skilled in the art to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application.

[0023] The embodiments of the present application provide a composite insulation cable detection method, as shown in the method comprises: Figure 1 The method comprises the following steps: Step S100, connect the composite design production drawing, obtain the composite layer structure and material parameters of the composite insulation cable, and construct a multi-layer physical structure model.

[0024] Step S100 further comprises the following steps: Step S110, extracting the conductor diameter, insulation layer thickness, shielding layer thickness, sheath layer thickness, and material dielectric constant, thermal conductivity, and interface bonding characteristics from the composite design production drawing; Step S120, establishing a composite layer structure model according to the conductor diameter, insulation layer thickness, shielding layer thickness, and sheath layer thickness; Step S130, embedding material parameters according to the hierarchical mapping relationship of the material dielectric constant, thermal conductivity, and interface bonding characteristics and the composite layer structure model, and constructing the multi-layer physical structure model.

[0025] Preferably, the composite design production drawing is retrieved from the design database or engineering documents of the cable manufacturer, which contains detailed labeling information of each structural layer of the cable, such as size parameters, material specifications, etc. Then, the composite hierarchical structure (geometric parameters) of the composite insulated cable is extracted from the composite design production drawing, which is used to define the spatial position and mutual relationship of each structural layer, and the material parameters (physical properties) are used to simulate the behavior of each layer material under electrical, thermal, and mechanical stress. Specifically, the composite hierarchical structure includes the conductor diameter, insulation layer thickness, shielding layer thickness, and sheath layer thickness, and the material parameters include the material dielectric constant, thermal conductivity, and interfacial adhesion properties. The conductor diameter is the diameter of the core conductive part of the cable, which directly affects the current-carrying capacity and resistance loss. The insulation layer thickness is the thickness of the insulating material wrapped around the conductor, which determines the electrical insulation performance and breakdown voltage of the cable. The shielding layer thickness is the thickness of the metal shielding layer (such as copper tape or aluminum foil), which is used to suppress electromagnetic interference and uniform electric field distribution. The sheath layer thickness refers to the thickness of the outermost protective material, which provides mechanical protection, moisture resistance, corrosion resistance, etc. The material dielectric constant measures the ability of the material to store electrical energy in an electric field, which affects the capacitance and partial discharge characteristics of the cable. The thermal conductivity measures the ability of the material to conduct heat, which is related to the heat dissipation performance and temperature rise control during cable operation. The interfacial adhesion properties refer to the bonding strength and compatibility between layers of materials, which affect the stability of the cable structure and the risk of interlayer peeling during long-term operation.

[0026] Preferably, according to the extracted conductor diameter, insulation layer thickness, shielding layer thickness, and sheath layer thickness, the layers are stacked in proportion to the size, such as using a three-dimensional modeling software (AutoCAD, SolidWorks) to create a cylinder as the conductor part of the cable based on the extracted conductor diameter, and then add architectural layers one by one, including adding a concentric cylinder outside the conductor, which builds the insulation layer by adjusting the inner and outer diameter difference; adding a shielding layer in the same way as a concentric cylinder outside the insulation layer; adding a sheath layer outside the shielding layer; and then forming a multi-layer cylindrical geometric model of the cable, i.e. a composite hierarchical structure model, for example, the overall structure presents a concentric cylindrical layered structure of conductor → insulation layer → shielding layer → sheath layer. Then, the material dielectric constant, thermal conductivity, and interfacial adhesion properties are assigned to each structural layer according to the hierarchical correspondence, for example, the insulation layer corresponds to a certain dielectric constant and thermal conductivity, the shielding layer corresponds to the electrical conductivity and thermal conductivity of metal materials, and the sheath layer corresponds to the mechanical strength and aging resistance properties of polymer materials. Through hierarchical mapping relationship, the material properties of each physical layer are ensured to be accurate and correct, and finally a multi-layer physical structure model with geometric size and physical properties is generated, which reproduces the real structure and material properties of the cable for parameter determination, multi-source data analysis, and state identification.

[0027] Further, step S100 further comprises step S140 of scanning the composite insulation cable based on the composite hierarchy to obtain a measured level thickness; and step S150 of calibrating and correcting the level thickness of the multi-layer physical structure model by using the measured level thickness.

[0028] Preferably, the outer surface of the composite insulation cable is spirally scanned by a laser caliper, each layer's outer diameter profile is fitted, and each layer's level thickness is calculated in combination with the conductor diameter, or the time difference of echo of sound waves at different material interfaces is measured by using ultrasonic pulse reflection to calculate the layer thickness, and then the measured level thickness is obtained; then a corresponding relationship between the measured data and the model level is established to ensure that the measured level thickness can be correctly matched to each layer of the model, and then a polar coordinate system is established with the center of the conductor as the origin, the measured level thickness is distributed according to the circumferential angle (such as 0°, 90°, 180°, 270° direction), and is associated with the radial thickness uniformity parameter in the multi-layer physical structure model (such as detecting whether there is thickness eccentricity), and then it is judged whether the level thickness of the multi-layer physical structure model has deviation, if there is, the level thickness parameter in the model is automatically updated by using the measured level thickness, and a calibration log is recorded, so as to ensure the accuracy and reliability of the cable detection and analysis.

[0029] Step S200 comprises determining the detection parameters and detection channels of each structure layer based on the multi-layer physical structure model, and the detection channels have associated detection means labels.

[0030] Preferably, according to the multi-layer physical structure model, the cable is decomposed into conductor layer, insulation layer, shielding layer, sheath layer and other independent levels, the spatial position, thickness range and material properties of each layer are determined, and then the key performance parameters that need to be detected are determined according to the functions and design requirements of each layer, and a mapping relationship between structure layer and detection parameter is established, as shown in Table 1: Table 1: Mapping data table of cable structure layer and detection parameter

[0031] Preferably, appropriate detection means are matched for each structure layer's detection parameter, and a corresponding relationship of detection parameter-detection means-detection channel is generated, wherein the detection channel has an associated detection means label. Specifically, for the insulation layer, the thickness uniformity is detected by a laser scanning channel, and the "laser thickness measurement" label is associated; for the shielding layer, the coverage rate is measured by an ultrasonic detection channel, and the "ultrasonic flaw detection" label is associated; for the sheath layer, the tensile strength is tested by a tensile test channel, and the "mechanical property test" label is associated; and the data acquisition point, detection sequence and precision requirement are defined for each detection channel, and it is ensured that the detection channel corresponds to the model level one by one.

[0032] Step S300, respectively detecting the composite insulation cable through the detection channels to obtain multi-source detection data, inputting the multi-source detection data into the multi-layer physical structure model according to the directional relationship between the detection channels and the multi-layer physical structure model, performing hierarchical and interlayer state recognition and prediction analysis to obtain a recognition result.

[0033] Step S300 further includes that the multi-source detection data includes dielectric response, ultrasonic reflection signal and temperature rise change.

[0034] Preferably, each detection channel corresponds to a specific structural layer (such as an insulation layer, a shielding layer) of the cable and matches a dedicated detection means, such as dielectric response testing for the insulation layer, ultrasonic reflection for the shielding layer and conductor interface; then respectively detecting the composite insulation cable, including dielectric response detection (applying an alternating electric field to the insulation layer and collecting current / voltage phase difference data), ultrasonic detection (scanning along the cable axis using a probe and collecting reflection echo signals at different depths) and temperature rise detection (passing a rated current through the conductor and recording the temperature change curve of each layer over time), to obtain multi-source detection data including dielectric response, ultrasonic reflection signal and temperature rise change, wherein the dielectric response reflects the polarization characteristics of the insulation material and is used to evaluate the aging degree or defects of the insulation layer; the ultrasonic reflection signal detects the interlayer bonding state (such as debonding and air bubbles) through the reflection / refraction of sound waves at different medium interfaces; the temperature rise change is measured by thermal imaging or thermocouple and analyzes the heat conduction performance and loss of the conductor or insulation layer.

[0035] Preferably, a corresponding relationship among the detection channel-structural layer-data type is established to ensure that the data is accurately attributed to a specific hierarchical layer in the multi-layer physical structure model, for example, dielectric response data is input through the insulation layer detection channel and corresponds to the dielectric constant parameter of the insulation layer in the multi-layer physical structure model, ultrasonic reflection signal is input through the shielding layer-insulation layer interface channel and corresponds to the interface bonding characteristic parameter in the multi-layer physical structure model, specifically, dielectric response data is input into the insulation layer level of the multi-layer physical structure model and compared with the designed dielectric constant (such as 2.3), ultrasonic reflection signal is input into the shielding layer-insulation layer interface node and matched with the preset interface bonding strength (such as 0.5 MPa) of the multi-layer physical structure model, and then interlayer correlation analysis is performed, for example, whether the surface roughness of the insulation layer affects the interface bonding is inferred through the abnormal ultrasonic reflection signal of the shielding layer.

[0036] Preferably, the execution level and interlayer state recognition refers to single layer state evaluation and interlayer interface analysis. For the insulation layer, if the measured dielectric loss tangent value is higher than the multi-layer physical structure model value by 20%, it is marked as an aging risk. For the sheath layer, if the temperature rise data shows that the heat dissipation efficiency is lower than the expected value of the multi-layer physical structure model, it indicates that the material formula needs to be adjusted. When an abnormal peak value appears in the ultrasonic reflection signal, the interface gap size is calculated through the model, and if it is ≥0.1 mm, it is determined as a debonding defect. Combined with dielectric response and thermal conductivity data, the water tree growth trend of the insulation layer and the conductor interface is predicted. The multi-source detection data is input into the multi-layer physical structure model for simulation and prediction analysis, that is, the performance evolution of the cable under extreme working conditions (such as overload current and high temperature environment) is simulated, and finally the visual recognition results are obtained, including generating a hierarchical state thermal map (such as green for normal and red for defect), and outputting an interlayer interface health index (such as interface adhesion reliability score 0-100 points). Further, the hierarchical and intelligent monitoring of the composite cable is realized, and the precision and efficiency of cable manufacturing and operation are significantly improved.

[0037] Further, step S300 further includes step S310, based on the multi-layer physical structure model, analyzing the electric field-thermal field-mechanical stress relationship between each layer to establish a multi-physical field coupling model; step S320, under the power-on working condition, starting the detection channel synchronously, respectively through dielectric spectrum scanning, ultrasonic wave emission and reception reflection signal, and infrared thermal imager capturing temperature rise change; step S330, according to the multi-physical field coupling model, coupling analyzing the dielectric response, ultrasonic reflection signal and temperature rise change, and through pre-training residual network, performing each composite layer aging analysis and interlayer adhesion risk area positioning, and outputting the recognition result.

[0038] Preferably, the electric field of the composite insulation cable determines the electrical performance of the cable insulation layer, the thermal field affects the thermal stability of the material, and the mechanical stress is related to the integrity of the cable structure. Based on the multi-layer physical structure model, finite element analysis (FEA) or finite volume method (FVM) is used for calculation to establish the coupling equation of electric field-thermal field-mechanical stress between each layer, for example, electric field distribution causes dielectric loss, generates heat and thus affects thermal field distribution, thermal field change leads to material expansion or shrinkage, and mechanical stress is generated, thereby constructing a complete multi-physical field coupling model. According to the actual operation condition of the composite insulation cable, the boundary conditions of the multi-physical field coupling model are set, such as the conductor passing through the rated current as the electric field excitation, the environmental temperature as the thermal field boundary, and the external mechanical pressure as the mechanical stress field boundary. At the same time, the material parameters in the multi-layer physical structure model are accurately input into the multi-physical field coupling model to ensure the accuracy and reliability of the multi-physical field model.

[0039] Preferably, under the simulated energized working condition, which is consistent with the setting condition when establishing the multi-physical field coupling model, the synchronous start-up presets the detection channels for each structural layer of the cable, ensuring the matching of data and model, and then respectively through dielectric spectrum scanning, ultrasonic wave emission and reception of reflection signals, and infrared thermal imager capturing temperature rise changes. Specifically, the dielectric spectrum analyzer is used to scan the insulation layer, collect dielectric response data at different frequencies, obtain the polarization characteristics and loss of the insulation material, and analyze the aging degree and defects of the insulation layer; the ultrasonic wave emitter emits ultrasonic waves to the cable, and the receiver receives the reflection signals of the interfaces of different structural layers, and according to the strength, time and other characteristics of the reflection signals, it is judged whether there are debonding, bubbles and other defects between the layers; the infrared thermal imager captures the temperature rise changes on the surface of the cable, and through the thermal imaging technology, the temperature distribution of the whole or part of the cable is obtained, and the thermal field distribution and whether there is a local overheating phenomenon are analyzed; and the collected multi-source data such as dielectric response, ultrasonic reflection signal, temperature rise change are preprocessed, including removing noise, signal filtering, data normalization, etc., to ensure the quality and usability of the data.

[0040] Preferably, the preprocessed multi-source detection data is input into the multi-physical field coupling model, and the data is coupled analyzed according to the relationship between electric field, thermal field and mechanical stress, for example, the electric field distribution model is corrected through the dielectric response data, and then the changes of thermal field and mechanical stress field are analyzed; the influence of interlayer structure change on physical field distribution is judged by using ultrasonic reflection signal; then the pre-trained residual network is used for aging analysis of each composite layer and positioning of interlayer bonding risk area, that is, the pre-trained residual network is used to analyze the aging of each composite layer of the cable combined with the data features obtained by coupling analysis, the residual network can learn the complex patterns and features in the data, and through the trained model, the multi-dimensional data such as dielectric response, thermal field and mechanical stress are processed to identify the degree and trend of composite layer aging; at the same time, based on the relationship between interlayer structure change and ultrasonic reflection signal, the interlayer bonding risk area is located, and specific identification results such as aging degree score of each layer, risk area position coordinates, etc. are output.

[0041] Preferably, the historical detection data of the composite insulation cable is collected, including accumulated dielectric response, ultrasonic reflection signal, temperature rise change and other multi-source detection data, and the corresponding cable structure layer (such as inner shielding layer, insulation layer, outer shielding layer, etc.), aging degree (such as normal, mild, severe aging), interlayer adhesion state (such as normal, debonding, bubble) need to be marked, and at the same time, the detection data under different aging degrees and interlayer defects is simulated through a multi-physical field coupling model; then the dielectric response is converted into a frequency domain feature vector, the ultrasonic signal time domain waveform features (such as reflection peak intensity, echo time difference) are extracted, and the temperature rise data is converted into a thermal imaging matrix (such as temperature distribution two-dimensional array); then the numerical data (such as dielectric constant, temperature rise value) is normalized (scaled to [0, 1]) or standardized (mean value is 0, variance is 1), and the image is preprocessed (if the ultrasonic / thermal image data is converted into an image, such as grayscale, noise reduction, data enhancement), and finally the dielectric response, ultrasonic and temperature rise data are spliced into a multi-dimensional feature vector, and the training data set is finally obtained.

[0042] Preferably, a residual network is constructed using a ResNet variant, the network structure is set and the input dimension of the input layer is adjusted according to the data type, the standard residual block is configured to include convolution, batch normalization (BN) and ReLU activation, and the output layer is set to output units for classification tasks (such as aging degree classification, normal, aging, severe aging), regression tasks (such as interlayer adhesion risk score, 0-1 risk score) and positioning tasks (such as risk area coordinates, positioning coordinate values); a weighted loss function is used for aging classification, risk scoring and positioning, and the initial learning rate is set to , and the learning rate is dynamically adjusted using cosine annealing; the batch size is set to 16-64, which is adjusted according to the GPU memory, and when the memory is insufficient, the batch size is reduced and the gradient accumulation step is increased. Then the training set, the validation set and the test set are divided in the ratio of 8:1:1 to ensure that the aging degree and defect type distribution in each set is balanced, the convolution layer is initialized using the ImageNet pre-trained weight (transfer learning), and if the data and the image are significantly different (such as pure numerical features), it can be randomly initialized; the training set is extracted by the residual network, the output layer generates prediction results according to the task type, and the loss function gradient is calculated, and the network parameters are updated by the optimizer; the residual network is verified using the validation set, and the accuracy, precision and recall indicators are used to test and evaluate the residual network using the test set, and the final residual network is obtained, which can output aging analysis and risk positioning results according to real-time detection data. Finally, the recognition results obtained by the residual network analysis are sorted and output in an intuitive form, such as generating a cable detection state thermal map, using different colors to identify the aging degree and risk area of each layer; a detailed detection report is provided, including physical field analysis results, aging risk assessment conclusions and maintenance suggestions, etc.

[0043] Further, step S330 further comprises step S331, processing the dielectric spectrum scanning data, extracting the real part and imaginary part of the dielectric constant of the insulation layer, and calculating the frequency response offset; step S332, identifying the defect echo area according to the ultrasonic wave transmission and reception reflection signal, and calculating the bonding integrity index; step S333, performing time sequence analysis on the temperature rise change, identifying the peak temperature rise rate and thermal diffusion path change, and determining the thermal barrier failure coefficient; step S334, establishing a theoretical performance response curve based on the multi-physical field coupling model; step S335, comparing the theoretical performance response curve with the detection data, calculating the physical residual value of each index, and the detection data is the frequency response offset, the bonding integrity index, and the thermal barrier failure coefficient; step S336, inputting the physical residual value as a state feature into the residual network, predicting the aging degree of each layer of the cable structure and positioning the bonding risk area between layers, and outputting the identification result, wherein the identification result comprises a risk level and a spatial coordinate.

[0044] Preferably, the dielectric spectrum scanning data is processed to extract the key features of the insulation layer aging, that is, the real part and imaginary part of the dielectric constant of the insulation layer, and then the measured dielectric spectrum is compared with the theoretical reference curve under the healthy state to calculate the offset of each frequency point, and the average offset or the maximum offset is taken as the frequency response offset, which reflects the deterioration degree of the polarization characteristics of the insulation material; the abnormal area (non-interface normal reflection clutter signal) in the ultrasonic echo image is identified through threshold segmentation and edge detection (such as Canny operator), and the ratio of the defect area pixel number to the total detection area pixel number is taken as the defect echo area proportion, and the bonding integrity index = 1-defect echo area proportion (value range 0~1, the closer to 1, the better the bonding state); under the power-on working condition, the temperature change curve of the conductor or the insulation layer with time is monitored, the maximum temperature rise rate before reaching thermal stability is extracted, the thermal diffusion coefficient change is calculated through the time and space sequence analysis of the infrared thermal image, the thermal flow abnormal area is located, and if the measured thermal diffusion coefficient is lower than 80% of the theoretical value or the peak temperature rise rate exceeds the threshold value (such as 0.5K / min), it is determined that there is a thermal barrier failure risk, and the thermal barrier failure coefficient value range is 0~1 (the larger the value, the higher the risk).

[0045] Preferably, in the multi-physical field coupling model, ideal parameters (such as designed dielectric constant, interface bonding strength 100%, and initial thermal conductivity value) without defects and aging are inputted to simulate the dielectric response curve of the cable under the rated working condition, the ultrasonic reflection theoretical echo (defect echo area is 0), and the temperature rise theoretical curve (thermal diffusion is uniform), to establish a theoretical performance response curve as a comparison benchmark of the detection data, which is used to quantify the deviation between the actual performance and the ideal state.

[0046] Preferably, the theoretical performance response curve is compared with the detection data (frequency response offset, bonding integrity index, thermal barrier failure coefficient), the physical residual value of each index is calculated, the larger the absolute value of the physical residual value of the frequency response offset, the more serious the aging; the larger the physical residual value of the bonding integrity index, the more serious the defect; the larger the physical residual value of the thermal barrier failure coefficient, the higher the thermal resistance; and the three physical residual values are spliced into a feature vector, which is input into the residual network as a state feature, the aging degree of each layer of the cable structure is predicted, and the bonding risk area between layers is located, the output layer outputs three aging level probability (such as normal / mild / severe aging) identification results, outputs the aging index (0-100 points), and directly outputs the coordinate offset of the risk area through the full connection layer, the actual risk coordinate is calculated combined with the spatial resolution (such as the accuracy of the ultrasonic probe ±1cm) of the detection equipment, and finally the identification result is output, including the risk level (low, medium, high) and the spatial coordinate, including mapping the risk area coordinate to the cable three-dimensional model to label the specific position to obtain the spatial coordinate.

[0047] Further, step S300 further comprises step S340 of performing aging prediction analysis on the historical operation data and the detection data to establish a cable multi-time period aging path; step S350 of performing self-healing analysis according to the cable multi-time period aging path, wherein a self-healing current limiting strategy is obtained by analyzing the life influence relationship of the operation load parameter on the cable multi-time period aging path; and step S360 of performing self-healing control on the composite insulation cable according to the self-healing current limiting strategy.

[0048] Preferably, the historical operation data is collected, including long-term operation parameters such as load current, voltage fluctuation, operation duration, and environmental temperature of the cable, and historical fault records (such as the number of partial discharge times and temperature rise abnormal events), which are used to analyze the aging rate of the cable under different working conditions; the detection data includes dielectric spectrum scanning data, which reflects the real part (energy storage capacity) and imaginary part (energy loss) of the dielectric constant of the insulation material and the frequency response offset, and is used to evaluate the degradation degree of the insulation molecular chain; the ultrasonic detection data calculates the bonding integrity index through the defect echo area to judge whether there are air gaps and peeling defects between the bonding interfaces of each layer (such as the conductor-insulation layer and the insulation-shielding layer) of the cable; the infrared thermal image data is used to extract the peak temperature rise rate and the thermal diffusion path change, calculate the thermal barrier failure coefficient, and identify the abnormal heat conduction area (such as local heat accumulation caused by insulation layer carbonization) caused by aging; then the historical operation data and the detection data are used for aging prediction analysis, the life cycle of the cable is divided into initial stage (0-5 years after commissioning), middle stage (5-15 years), and later stage (more than 15 years), and the aging characteristic model of each stage is established, and then the change curve of each index with time is fitted through regression analysis to form the time-aging index mapping relationship, and finally the cable multi-time period aging path is established.

[0049] Preferably, self-healing analysis is performed according to the cable multi-time period aging path, i.e. analyzing the impact of operating load on aging, specifically, extracting life impact factors, load current amplitude (overload operation will cause the temperature of the insulation layer to exceed the design threshold, accelerating thermal oxidation reaction) and load fluctuation frequency (frequent load changes will cause thermal expansion and contraction of the cable, exacerbating interlayer mechanical stress fatigue), obtaining life loss curves under different load levels through accelerated aging tests, and establishing a load-life mapping function; then, according to the current detection data, determining which stage of the aging path the cable is in, predicting when the life will end if the current load is maintained based on the aging path model, and according to the remaining life target, back calculating the maximum allowable load current, and scheduling through the smart grid system to realize real-time control of the cable load, which is finally used as a self-healing current limiting strategy; and self-healing control is performed on the composite insulation cable, such as adjusting the transformer tap of the substation, switching the capacitor bank, optimizing the power flow distribution of the power grid, and reducing the load of the target cable; peak-shaving power management is implemented for high-energy-consuming users, or the load fluctuation is smoothed through the energy storage system; after the self-healing control is executed, the dielectric response, ultrasonic reflection, temperature rise and other indicators are continuously monitored to verify the effectiveness of the current limiting strategy (such as whether the thermal barrier failure coefficient has decreased to the safe interval), and at the same time, it is ensured that the cable always operates on the optimal aging path.

[0050] Further, step S460 further comprises step S461 of analyzing the influence relationship of different load parameters on the aging of the target structure layer, and establishing a load-life mapping function based on the influence relationship; step S462, load fitting is performed on the cable multi-time period aging path according to the load-life mapping function, and interlayer physical coupling influence is performed based on the multi-physical field coupling model, and a self-healing current limiting strategy is obtained by strategy constraint with each structure layer aging threshold, the self-healing current limiting strategy limits the maximum working current and periodic load interval to delay the aging evolution path.

[0051] Preferably, by analyzing the influence of load parameters (such as current size, load cycle, etc.) on the aging of each structural layer of the cable, a mathematical model is established to deduce the current limiting strategy, and by controlling the current and load intermittence, the aging speed of the cable is delayed, and the service life of the cable is prolonged. Specifically, historical operation data (such as long-term load current, temperature monitoring data) and detection data (such as dielectric constant, ultrasonic defect, temperature rise, etc.) are collected, the correlation between load parameters and aging indicators (such as increase of dielectric constant imaginary part, increase of adhesive layer defect area) is quantified, and how different load parameters accelerate or slow down the aging of each layer of the cable is clarified; the relationship between load parameters and the life (or aging degree) of each layer of the cable is converted into a mathematical function, i.e. a load-life mapping function, which is used to predict the aging speed under different loads; then the cable multi-time period aging path (based on historical data) is matched with the load-life function to verify the accuracy of the model, and the influence of the aging of each structural layer on the adjacent layer is analyzed by using the electric field-thermal field-mechanical stress coupling model; the aging threshold of each structural layer is set as a constraint condition, such as the maximum value of the dielectric constant imaginary part of the insulation layer and the critical value of the adhesive layer defect area, etc., and if the threshold is exceeded, the cable is considered to be failed or the risk is unacceptable. Finally, a self-healing current limiting strategy is generated, which limits the maximum working current and periodic load intermittence. For example, according to the load-life function, the critical current value when a certain layer reaches the threshold is calculated and set as the maximum allowed current; cooling intervals (such as 0.5 hours of downtime every 4 hours of operation) are inserted in the periodic load to reduce the cumulative heat and mechanical stress fatigue. Through the current limiting strategy, the damage intensity of each physical field (electric field, thermal field, mechanical field) on the cable is reduced, so that the actual aging path (such as dielectric constant growth rate, defect expansion speed) is lower than that under the uncontrolled state, thereby prolonging the overall life of the cable.

[0052] In step S400, hierarchical visualization processing is performed according to the multi-layer physical structure model and the corresponding identification result, and a cable detection state thermal map is generated. The cable detection state thermal map is used for visual presentation of the fault position and the aging degree.

[0053] Preferably, the multi-layer physical structure model of the cable and the detection and identification results (such as the aging degree of each layer and the fault location) are converted into an intuitive cable detection status heat map, and the internal status of the cable is presented through visual variables such as color and brightness to assist operation and maintenance personnel in quickly locating defects and assessing risks. Specifically, independent visualization layers are generated for the conductor layer, insulation layer, shielding layer, and sheath layer. For example, the insulation layer layer focuses on displaying abnormal areas of dielectric constant (reflecting aging) and interface defects detected by ultrasound, and the shielding layer layer highlights areas of decreased conductivity or abnormal circulation points (possibly caused by corrosion or fracture). Then, continuous status indicators (such as aging degree 0~100 points) are mapped to color gradients (such as cold colors represent normal and warm colors represent risks). Commonly used color mapping schemes are normal (green, 0~30 points), slightly aged (yellow, 30~70 points), and severely aged (red, 70~100 points).

[0054] Preferably, the recognition results are then subjected to layered visualization, including drawing concentric circles according to the thickness ratio of each layer, filling the circumferential detection data into the annular area of ​​the corresponding layer according to the angle, filling the color of the insulating layer annular area according to the dielectric constant offset (such as the red area indicates that the offset exceeds the threshold), and marking the location of the debonding defect detected by ultrasound with black spots in the shielding layer annular area; dividing the cable into several units along the axial direction (such as one section per 1 meter), each unit corresponding to a cross section, and constructing a multi-layer cylindrical surface in a three-dimensional coordinate system with the axial direction as the Z axis, the circumferential angle as the θ axis, and the radius as the R axis. Slide along the Z axis to view the cross-sectional status at different positions, and display the multi-layer information by superimposing it through transparency adjustment. The cable detection status heat map is used to visualize the fault location and aging degree, thereby significantly improving the efficiency and accuracy of the cable detection status assessment, as shown in Table 2: Table 2 Cable detection status visualization data table

[0055] In the above, refer to Figure 1 A composite insulated cable detection method according to an embodiment of the present invention is described in detail. Figure 2 A composite insulated cable detection device according to an embodiment of the present invention is described.

[0056] A composite insulated cable detection device according to an embodiment of the present invention is used to solve the technical problems existing in the prior art, such as difficulty in deeply analyzing the structural layers of composite cables and the changes in the state between layers, inability to accurately locate the fault location of composite insulated cables, and inability to effectively predict the aging trend of cables. It achieves the technical effects of accurate detection, layered location of cable fault locations, effective prediction of cable aging trends and intuitive presentation. Figure 2As shown, a composite insulation cable detection device includes: a physical structure model construction module 10, a detection channel determination module 20, an identification result obtaining module 30, and a cable detection state thermal map generation module 40.

[0057] The physical structure model construction module 10 is configured to connect a composite design production drawing, obtain a composite hierarchical structure and material parameters of a composite insulation cable, and construct a multi-layer physical structure model. The detection channel determination module 20 is configured to determine detection parameters and detection channels of each structure layer based on the multi-layer physical structure model, and the detection channels have associated detection means labels. The identification result obtaining module 30 is configured to perform directional detection on the composite insulation cable through the detection channels respectively, obtain multi-source detection data, input the multi-source detection data into the multi-layer physical structure model according to the directional relationship between the detection channels and the multi-layer physical structure model, perform hierarchical and interlayer state identification and prediction analysis, and obtain an identification result. The cable detection state thermal map generation module 40 is configured to perform layered visualization processing according to the multi-layer physical structure model and the corresponding identification result, generate a cable detection state thermal map, and perform visual presentation of a fault position and an aging degree through the cable detection state thermal map.

[0058] Next, the specific configuration of the physical structure model construction module 10 will be described in detail. The physical structure model construction module 10 further includes: extracting a conductor diameter, an insulation layer thickness, a shielding layer thickness, a sheath layer thickness, and material dielectric constants, thermal conductivities, and interface bonding characteristics from the composite design production drawing; establishing a composite hierarchical structure model according to the conductor diameter, the insulation layer thickness, the shielding layer thickness, and the sheath layer thickness; and embedding material parameters according to a hierarchical mapping relationship between the material dielectric constants, the thermal conductivities, and the interface bonding characteristics and the composite hierarchical structure model to construct the multi-layer physical structure model.

[0059] Next, the specific configuration of the identification result obtaining module 30 will be described in detail. The identification result obtaining module 30 further includes: the multi-source detection data including dielectric response, ultrasonic reflection signal, and temperature rise change.

[0060] Next, the specific configuration of the identification result obtaining module 30 will be described in detail. The identification result obtaining module 30 further includes: performing electric field-thermal field-mechanical stress relationship analysis between layers based on the multi-layer physical structure model to establish a multi-physical field coupling model; starting the detection channels simultaneously under a power-on working condition, respectively performing dielectric spectrum scanning, ultrasonic emission and reception of reflection signals, and infrared thermal imager capture of temperature rise change; performing coupling analysis on the dielectric response, the ultrasonic reflection signal, and the temperature rise change according to the multi-physical field coupling model, and outputting the identification result through pre-training residual network for each composite layer aging analysis and interlayer bonding risk area positioning.

[0061] Next, the specific configuration of the identification result obtaining module 30 will be described in detail. The identification result obtaining module 30 further comprises: processing the dielectric spectrum scanning data, extracting the real part and the imaginary part of the dielectric constant of the insulation layer, and calculating the frequency response offset; identifying the defect echo area according to the ultrasonic wave transmission and reception reflection signal, and calculating the bonding integrity index; performing time sequence analysis on the temperature rise change, identifying the peak temperature rise rate and the thermal diffusion path change, and determining the thermal barrier failure coefficient; based on the multi-physical field coupling model, establishing a theoretical performance response curve; comparing the theoretical performance response curve with the detection data to calculate the physical residual value of each index, the detection data being the frequency response offset, the bonding integrity index, and the thermal barrier failure coefficient; inputting the physical residual value as a state feature into the residual network to predict the aging degree of each layer of the cable structure and locate the bonding risk area between the layers, and outputting the identification result, the identification result including the risk level and the spatial coordinates.

[0062] Next, the specific configuration of the identification result obtaining module 30 will be described in detail. The identification result obtaining module 30 further comprises: performing aging prediction analysis on the historical operation data and the detection data to establish a cable multi-time period aging path; performing self-healing analysis according to the cable multi-time period aging path, wherein the self-healing current limiting strategy is obtained by analyzing the life influence relationship of the operation load parameter on the cable multi-time period aging path; and performing self-healing control on the composite insulation cable according to the self-healing current limiting strategy.

[0063] Next, the specific configuration of the identification result obtaining module 30 will be described in detail. The identification result obtaining module 30 further comprises: analyzing the influence relationship of different load parameters on the aging of the target structure layer, establishing a load-life mapping function based on the influence relationship; fitting the load to the cable multi-time period aging path according to the load-life mapping function, and performing interlayer physical coupling influence based on the multi-physical field coupling model, to obtain a self-healing current limiting strategy, the self-healing current limiting strategy limiting the maximum working current and the periodic load interval to delay the aging evolution path.

[0064] Next, the specific configuration of the physical structure model construction module 10 will be described in detail. The physical structure model construction module 10 further comprises: based on the composite hierarchical structure, scanning the composite insulation cable to obtain the measured hierarchical thickness; and using the measured hierarchical thickness to calibrate and correct the hierarchical thickness of the multi-layer physical structure model.

[0065] The composite insulation cable detection device provided in the embodiments of the present application can perform the composite insulation cable detection method provided in any of the embodiments of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0066] Figure 3 is a structural schematic diagram of an electronic device provided by an embodiment of the present application, and shows a block diagram of an exemplary electronic device suitable for implementing the embodiment of the present application. Figure 3 The electronic device shown is merely an example and should not impose any limitation on the functions and use range of the embodiment of the present application. The electronic device is in the form of a general computing device, and its components can include, but are not limited to, an input device 401, a processor 402, a memory 403, and an output device 404. The processor 402 can be one or more; the memory 403 can include a computer readable medium and at least one program product, which has a set of (at least one) program modules configured to perform the functions of the embodiments of the present application.

[0067] The memory 403 shown in the embodiment of the present application can adopt any combination of one or more computer readable media; the computer readable storage medium can be, but is not limited to, an infrared ray, a semiconductor device, a device or a component, or any combination of the above, for storing software programs, computer executable programs and modules, such as the program instructions / modules corresponding to the composite insulation cable detection method in the embodiment of the present application. The processor 402 performs various functional applications and data processing of the computer device by running the software programs, instructions and modules stored in the memory 403, i.e. implements the above-mentioned composite insulation cable detection method.

[0068] Although the present application makes various references to certain modules in the device according to the embodiment of the present application, however, any number of different modules can be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be implemented; in addition, the specific names of the functional units are only for easy mutual differentiation, and do not limit the protection scope of the present application.

[0069] The above specific embodiments do not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A composite insulated cable detection method, characterized in that: include: Connect the composite design and production drawings, obtain the composite hierarchical structure and material parameters of the composite insulated cable, and build a multi-layer physical structure model; Determining detection parameters and detection channels for each structural layer based on the multi-layer physical structure model, wherein the detection channels have associated detection means labels; Performing directional detection on the composite insulated cable through the detection channels to obtain multi-source detection data, inputting the multi-source detection data into the multi-layer physical structure model according to the directional relationship between the detection channels and the multi-layer physical structure model, performing layer and inter-layer state recognition and prediction analysis to obtain recognition results; A layered visualization process is performed based on the multi-layer physical structure model and the corresponding recognition results to generate a cable detection status thermogram, and the fault location and aging degree are visualized through the cable detection status thermogram.

2. The composite insulated cable detection method according to claim 1, characterized in that: Obtain the composite hierarchical structure and material parameters of the composite insulated cable and build a multi-layer physical structure model, including: Extracting conductor diameter, insulation layer thickness, shielding layer thickness, jacket layer thickness, and material dielectric constant, thermal conductivity, and interface bonding properties from the composite design production drawing; Establishing a composite hierarchical structure model according to the conductor diameter, insulation layer thickness, shielding layer thickness, and sheath layer thickness; The material parameters are embedded according to the hierarchical mapping relationship between the material dielectric constant, thermal conductivity, interface bonding characteristics and the composite hierarchical structure model to construct the multi-layer physical structure model.

3. The composite insulated cable detection method according to claim 1, characterized in that: The multi-source detection data includes: dielectric response, ultrasonic reflection signal, and temperature rise change.

4. The composite insulated cable detection method according to claim 2, characterized in that: Obtain recognition results, including: Analyze the relationship between the electric field, thermal field and mechanical stress between layers based on the multi-layer physical structure model and establish a multi-physics coupling model; Under power-on conditions, the detection channels are started synchronously to capture temperature rise changes through dielectric spectrum scanning, ultrasonic emission and reception of reflected signals, and infrared thermal imager. According to the multi-physics field coupling model, a coupling analysis is performed on the dielectric response, ultrasonic reflection signal, and temperature rise change, and the aging analysis of each composite layer and the location of the interlayer bonding risk area are performed through a pre-trained residual network to output the identification result.

5. The composite insulated cable detection method according to claim 4, characterized in that: Outputting the recognition result includes: Process the dielectric spectrum scanning data, extract the real and imaginary parts of the dielectric constant of the insulation layer, and calculate the frequency response offset; Identify the defect echo area based on the ultrasonic emission and reception reflection signals and calculate the bonding integrity index; Perform time series analysis on temperature rise changes to identify peak temperature rise rate and heat diffusion path changes, and determine thermal barrier failure coefficients; Establishing a theoretical performance response curve based on the multi-physics field coupling model; Calculate the physical residual value of each indicator by comparing the theoretical performance response curve with the test data, wherein the test data are frequency response offset, bonding integrity index, and thermal barrier failure coefficient; The physical residual value is input into the residual network as a state feature to predict the aging degree of each layer of the cable structure and locate the interlayer bonding risk area, and the identification result is output. The identification result includes the risk level and spatial coordinates.

6. The composite insulated cable detection method according to claim 5, characterized in that: Also includes: Use historical operation data and test data to conduct aging prediction analysis and establish cable aging paths over multiple time periods; Performing self-healing analysis based on the cable multi-time period aging path, wherein a self-healing current limiting strategy is obtained by analyzing the influence of operating load parameters on the life of the cable multi-time period aging path; The self-healing current limiting strategy is used to control the composite insulated cable's self-healing performance.

7. The composite insulated cable detection method according to claim 6, characterized in that: Obtain the self-healing current limiting policy, including: Analyze the influence of different load parameters on the aging of the target structural layer, and establish a load-life mapping function based on the influence relationship; According to the load-life mapping function, the cable aging path in multiple time periods is load fitted, and the inter-layer physical coupling influence is performed based on the multi-physical field coupling model. The aging threshold of each structural layer is used to perform strategy constraints to obtain a self-healing current limiting strategy. The self-healing current limiting strategy limits the maximum operating current and periodic load interval to delay the aging evolution path.

8. The composite insulated cable detection method according to claim 2, characterized in that: Build a multi-layer physical structure model, which will also include: Based on the composite layer structure, scanning the composite insulated cable to obtain the measured layer thickness; The measured layer thickness is used to calibrate and correct the layer thickness of the multi-layer physical structure model.

9. A composite insulated cable detection device, characterized in that: The device is used to implement a composite insulated cable detection method according to any one of claims 1 to 8, and the device comprises: The physical structure model building module is used to connect the composite design production drawings, obtain the composite hierarchical structure and material parameters of the composite insulated cable, and build a multi-layer physical structure model; a detection channel determination module, configured to determine detection parameters and detection channels for each structural layer based on the multi-layer physical structure model, wherein the detection channels have associated detection means labels; an identification result obtaining module, configured to perform directional detection on the composite insulated cable through the detection channels to obtain multi-source detection data, input the multi-source detection data into the multi-layer physical structure model according to the directional relationship between the detection channels and the multi-layer physical structure model, perform layer and inter-layer state recognition and prediction analysis, and obtain an identification result; The cable detection status heat map generation module is used to perform layered visualization processing based on the multi-layer physical structure model and the corresponding recognition results to generate a cable detection status heat map, and to visualize the fault location and aging degree through the cable detection status heat map.

10. An electronic device, characterized in that: The electronic device comprises: a memory for storing executable instructions; The processor is configured to implement the composite insulated cable detection method according to any one of claims 1 to 8 when executing the executable instructions stored in the memory.

Images