Power cable insulation performance on-line monitoring method and device

Abstract

The invention provides an online monitoring method and device for the insulation performance of a power cable. The method comprises the steps that a multi-mode sensor network is constructed to synchronously collect multi-dimensional cable data, an electromagnetic-thermal-chemical multi-physics field coupling model is established, and the insulation state of the cable is analyzed in real time. And monitoring the insulation defect and predicting the residual service life by using the mixed deep learning model. And dynamically generating an early warning threshold value by adopting a digital twinning method based on spatio-temporal characteristics, and adaptively adjusting a monitoring strategy. According to the invention, multi-dimensional data are synchronously acquired through the multi-modal sensor network, and the limitation of single parameter monitoring is broken through. The insulation degradation characteristics of the cable are accurately captured through multi-dimensional data fusion, and quantitative description of energy transfer and material evolution is achieved through a constructed coupling model. And through a residual network and a cavity convolution space encoder, combining a bidirectional LSTM-GRU time encoder, and extracting spatial and temporal characteristics of the cable. The cross-modal attention mechanism fuses multi-source features, and improves the accuracy of defect identification and life prediction.

Description

Technical Field

[0001] The present invention relates to the technical field of cable insulation performance monitoring, and in particular to an online monitoring method and device for power cable insulation performance. Background Art

[0002] As the core component of the power transmission and distribution system of the power grid, the insulation performance of the power cable directly affects the safe operation of the power system. With the increase in power grid load density and the prominent problem of cable aging, the traditional offline detection mode can no longer meet the requirements of real-time, accuracy and full coverage.

[0003] Traditional monitoring methods mostly rely on a single type of sensor (such as temperature or partial discharge detection only), and cannot simultaneously obtain the multi-dimensional characteristics of the cable insulation state (electromagnetic, thermal, chemical, etc.). For example, there is a strong temporal and spatial correlation between partial discharge pulses and temperature field distribution, but the existing system lacks multimodal data fusion capabilities, resulting in insufficient accuracy in defect diagnosis. Existing cable status assessment models are mostly based on a single physical field (such as a heat conduction model), ignoring the electromagnetic-thermal-chemical multi-field coupling effect. Cable insulation degradation is essentially the result of the synergistic effect of electrical-thermal-chemical multi-physical fields. Traditional simplified models are difficult to accurately describe the defect evolution mechanism (such as the chain reaction of temperature gradient and chemical degradation caused by partial discharge). The warning thresholds of existing monitoring systems mostly use fixed standards (such as the temperature limit specified by IEC), without considering the dynamic characteristics of cable operating conditions (such as load fluctuations, sudden changes in ambient temperature) and the real-time impact of defect evolution rate on the threshold, resulting in a high false alarm / missing alarm rate. Traditional monitoring strategies use fixed sampling frequencies and sensor working modes, which cannot be adaptively adjusted according to the health status of the cable. For example, high-frequency monitoring is still used in the early development stage of defects, resulting in a waste of resources; while low-frequency sampling is still maintained in critical conditions, delaying the timing of fault handling. Summary of the invention

[0004] The present invention aims to at least solve the technical problem of insufficient defect diagnosis accuracy in the prior art, and in particular innovatively proposes a method and device for online monitoring of power cable insulation performance.

[0005] In order to achieve the above-mentioned object of the present invention, the present invention provides a method for online monitoring of insulation performance of a power cable, the method comprising: S1. Building a multimodal sensor network, and synchronously collecting multidimensional cable data based on the multimodal sensor network, wherein the multidimensional cable data includes partial discharge pulse data, distributed temperature field data, dielectric loss factor, and chemical characteristic gas data; S2. Establishing an electromagnetic-thermal-chemical multi-physics field coupling model, inputting the multi-dimensional cable data into the electromagnetic-thermal-chemical multi-physics field coupling model, and analyzing the multi-dimensional evolution law of the cable insulation state in real time; S3. Establish a hybrid deep learning model, use the hybrid deep learning model to extract the spatiotemporal features in the multi-dimensional evolution law, monitor the insulation defects of the cable based on the spatiotemporal features, and predict the remaining service life of the cable; S4. Based on the spatiotemporal characteristics, a digital twin method is used to dynamically generate a warning threshold, and the monitoring strategy is adaptively adjusted based on the warning threshold and operating condition parameters.

[0006] As an optional embodiment of the present invention, optionally, synchronously collecting multi-dimensional cable data based on the multimodal sensor network in step S1 includes: S101, using a partial discharge detection system combining a differential Rogowski coil array and a high-frequency current transformer to collect partial discharge pulse data; S102, a distributed optical fiber temperature measurement system based on the Raman scattering principle collects distributed temperature field data; S103, collecting dielectric loss factor using a dielectric loss factor monitoring module including a programmable frequency source and an orthogonal sampling phase-sensitive demodulation circuit; S104, collecting chemical characteristic gas data using a gas monitoring unit composed of a nanotube array gas sensor and an optical fiber evanescent wave sensor.

[0007] As an optional embodiment of the present invention, optionally, establishing the electromagnetic-thermal-chemical multi-physics field coupling model in step S2 includes: S201, establishing an electromagnetic field model using the partial discharge pulse data; S202, establishing a heat conduction model using the distributed temperature field data and dielectric loss factor; S203, using the chemical characteristic gas data to establish a chemical reaction field model; S204, coupling the electromagnetic field model with the heat conduction model, and coupling the heat conduction model with the chemical reaction field model to obtain an electromagnetic-thermal-chemical multi-physics field coupling model; S205, performing a confidence assessment on the electromagnetic-thermal-chemical multi-physics field coupling model, and optimizing the electromagnetic-thermal-chemical multi-physics field coupling model based on the assessment result.

[0008] As an optional embodiment of the present invention, optionally, establishing a hybrid deep learning model in step S3 includes: S301, performing spatiotemporal alignment and standardization processing on the multi-dimensional cable data to construct a tensor input including space-time dimensions; S302, constructing a spatial encoder based on a combination of a residual network and a dilated convolution, and using the spatial encoder to extract a spatial feature vector from the tensor input; S303, cascading a bidirectional long short-term memory network and a gated recurrent unit to obtain a time encoder, and using the time encoder to extract a time series feature vector of the insulation performance in the tensor input; S304, dynamically weighting and fusing the spatial feature vector and the temporal feature vector based on the cross-modal attention fusion module to obtain spatiotemporal features; S305, constructing a cable structure life prediction model using a graph convolutional network based on the spatiotemporal features; S306, constructing a cable insulation defect recognition model using a lightweight classifier based on the spatiotemporal features, and identifying the type of cable insulation defects based on the cable insulation defect recognition model; S307, respectively training and verifying the cable structure life prediction model and the cable insulation defect identification model; S308. Integrate the trained cable structure life prediction model and cable insulation defect recognition model to obtain a hybrid deep learning model.

[0009] As an optional embodiment of the present invention, optionally, in step S4, adaptively adjusting the monitoring strategy based on the warning threshold and the operating condition parameter includes: S401. Construct a digital twin model based on the multi-dimensional evolution law of cable insulation status; S402, the digital twin model dynamically generates a warning threshold of the cable insulation performance using a machine learning method based on the currently collected multi-dimensional cable data and the cable operating parameters; S403, when the insulation defect of the monitored cable approaches the warning threshold of the cable insulation performance, triggering the warning mechanism; S404, if the insulation defect of the monitoring cable is far away from the warning threshold, reduce the monitoring frequency; S405. If the insulation defect of the monitoring cable approaches or exceeds the warning threshold, increase the monitoring frequency; S406: Evaluate the effect of the adjusted monitoring strategy. If the evaluation result shows that the adjusted monitoring strategy fails to effectively improve the monitoring accuracy, re-execute steps S401 to S405.

[0010] On the other hand, the present invention further provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the method for online monitoring of power cable insulation performance.

[0011] Beneficial effects of the present invention: The present invention realizes the synchronous acquisition of partial discharge pulses, temperature fields, dielectric loss and chemical gases through a multimodal sensor network, breaking through the limitations of traditional single parameter monitoring. Multi-dimensional data fusion can accurately capture the multi-physical characteristics of cable insulation degradation (such as the spatiotemporal correlation between temperature gradients caused by partial discharge and chemical degradation), and the constructed electromagnetic-thermal-chemical coupling model can realize the quantitative description of energy transfer and material evolution in the process of cable insulation degradation by associating electromagnetic energy consumption, heat conduction and chemical reaction kinetics through Hamiltonian operators. Complex degradation mechanisms such as water tree aging and local carbonization can be accurately analyzed. By adopting a spatial encoder composed of a residual network and a hole convolution, combined with a bidirectional LSTM-GRU cascade time encoder, the spatiotemporal correlation characteristics of the cable state tensor can be effectively extracted. The cross-modal attention mechanism dynamically weights and fuses multi-source features, improving the probability of insulation defect recognition and the accuracy of remaining life prediction. The dynamic warning threshold generated in real time based on the digital twin model can adapt to changes in operating parameters (load rate, ambient temperature, etc.) and reduce the false alarm rate. The closed-loop optimization mechanism of the monitoring strategy (the sampling frequency is increased by 3-5 times when the defect is close to the threshold, and the frequency is automatically reduced during the stable period) reduces the monitoring energy consumption and significantly improves the economic efficiency of operation and maintenance.

[0012] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which: Figure 1 This is a flow chart of a method for online monitoring of insulation performance of a power cable according to Embodiment 1 of the present invention; Figure 2 It is a schematic diagram of the structure of an electronic device according to Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0014] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0015] Example 1 like Figure 1 As shown, a method for online monitoring of insulation performance of a power cable, the method comprising: S1. Building a multimodal sensor network, and synchronously collecting multidimensional cable data based on the multimodal sensor network, wherein the multidimensional cable data includes partial discharge pulse data, distributed temperature field data, dielectric loss factor, and chemical characteristic gas data; It should be noted that in step S1, the multimodal sensor network is a multimodal sensor network composed of differential Rogowski coils, distributed optical fiber temperature measurement, dielectric loss monitoring and nanotube gas sensors. Specifically, the differential Rogowski coil array is combined with a high-frequency current transformer to achieve high-sensitivity capture of local discharge pulses and ensure accurate acquisition of local discharge signals. The distributed optical fiber temperature measurement system is based on the principle of Raman scattering, distributed along the length of the cable, and monitors the temperature field distribution in real time to provide detailed temperature data. The dielectric loss factor monitoring module integrates a programmable frequency source and an orthogonal sampling phase-sensitive demodulation circuit to accurately measure the dielectric loss of the cable and reflect the loss characteristics of the cable insulation material. The gas monitoring unit composed of a nanotube array gas sensor and an optical fiber evanescent wave sensor can sensitively detect chemical characteristic gases released inside the cable, such as carbon monoxide. These gases are products of thermal decomposition or chemical degradation of cable insulation materials and are of great value for evaluating the insulation status of the cable.

[0016] S2. Establishing an electromagnetic-thermal-chemical multi-physics field coupling model, inputting the multi-dimensional cable data into the electromagnetic-thermal-chemical multi-physics field coupling model, and analyzing the multi-dimensional evolution law of the cable insulation state in real time; It should be noted that in this embodiment, an electromagnetic-thermal-chemical multi-physics field coupling model is established, and the local discharge pulse data is mapped into an electromagnetic field model, a temperature field and dielectric loss driven heat conduction model, and a chemical gas concentration triggering a chemical reaction field model, and the bidirectional coupling relationship between the three fields is described by partial differential equations (such as Joule heat driving the temperature field, and the chemical reaction rate is affected by temperature). The model combines the control equations of electromagnetic, thermal, and chemical fields through the Hamiltonian operator, introduces a confidence assessment mechanism (such as residual analysis) to dynamically optimize the model parameters, and improves the analytical accuracy of the insulation degradation chain reaction.

[0017] S3. Establish a hybrid deep learning model, use the hybrid deep learning model to extract the spatiotemporal features in the multi-dimensional evolution law, monitor the insulation defects of the cable based on the spatiotemporal features, and predict the remaining service life of the cable; It should be noted that the hybrid deep learning model adopts a dual encoder architecture: Spatial encoder: Combines residual network with dilated convolution to extract spatial distribution features of insulation defects (such as partial discharge cluster morphology); Temporal encoder: Cascade bidirectional LSTM and GRU to capture the temporal law of insulation performance degradation (such as the growth trend of dielectric loss).

[0018] The cross-modal attention mechanism dynamically fuses spatiotemporal features, the graph convolutional network (GCN) combines the cable topology to predict the remaining life, and the lightweight classifier (such as MobileNet) identifies the defect type (such as water branches and electrical corrosion holes) in real time.

[0019] S4. Based on the spatiotemporal characteristics, a digital twin method is used to dynamically generate a warning threshold, and the monitoring strategy is adaptively adjusted based on the warning threshold and operating condition parameters.

[0020] It should be noted that the physical state of the cable is mapped in real time based on the digital twin model, and the condition-sensitive warning threshold is dynamically generated using historical data and online learning (such as incremental SVM), and the monitoring strategy is adjusted according to the defect development rate (derived from spatiotemporal characteristics): Away from the threshold: reduce the sampling frequency (e.g. from 1kHz to 100Hz); Approaching the threshold: Increase monitoring density and trigger local enhanced scanning (such as focusing on suspected defect areas).

[0021] Through closed-loop effect evaluation (such as comprehensive optimization of F1-score and computing resource consumption), the digital twin model and monitoring strategy are iteratively updated to achieve a balance between resource efficiency and diagnostic accuracy.

[0022] In summary, the online monitoring method for the insulation performance of power cables in this embodiment realizes the synchronous acquisition of multi-dimensional characteristics of cable insulation status by constructing a multimodal sensor network, effectively solving the problem of single data and insufficient accuracy of defect diagnosis in the prior art. This method not only breaks through the limitations of traditional monitoring technology, but also realizes the quantitative description of energy transfer and material evolution during cable insulation degradation through the establishment of an electromagnetic-thermal-chemical multi-physical field coupling model, thereby being able to accurately analyze complex degradation mechanisms.

[0023] In addition, the use of hybrid deep learning models further improves the probability of insulation defect identification and the accuracy of remaining life prediction. The model effectively extracts the spatiotemporal correlation features of the cable state tensor through a dual encoder architecture, and realizes dynamic weighted fusion of multi-source features through a cross-modal attention mechanism. This not only improves the accuracy of monitoring.

[0024] Finally, the early warning threshold dynamically generated based on the digital twin method enables the monitoring strategy to be adaptively adjusted according to the operating parameters of the cable and the defect development rate. This not only reduces the false alarm rate, but also continuously optimizes the digital twin model and monitoring strategy through a closed-loop effect evaluation mechanism, achieving a balance between resource efficiency and diagnostic accuracy.

[0025] As an optional embodiment of the present invention, optionally, synchronously collecting multi-dimensional cable data based on the multimodal sensor network in step S1 includes: S101, using a partial discharge detection system combining a differential Rogowski coil array and a high-frequency current transformer to collect partial discharge pulse data; It should be noted that in step S101, the differential Rogowski coil array is combined with the high-frequency current transformer to achieve high-precision capture of the cable partial discharge signal. The differential Rogowski coil array has the characteristics of high sensitivity and fast response speed, and can accurately capture the weak pulse signal generated by partial discharge. The high-frequency current transformer can amplify and convert these pulse signals, which is convenient for subsequent data processing and analysis.

[0026] S102, a distributed optical fiber temperature measurement system based on the Raman scattering principle collects distributed temperature field data; It should be noted that the distributed optical fiber temperature measurement system based on the Raman scattering principle in step S102 can continuously measure temperature along the length of the cable and provide high-precision temperature distribution data. The system uses optical fiber as a sensing element and measures temperature by detecting the intensity change of Raman scattered light. It has the advantages of wide measurement range, high accuracy, and no electromagnetic interference. The collected distributed temperature field data can reflect the temperature state of the cable at different positions.

[0027] S103, collecting dielectric loss factor using a dielectric loss factor monitoring module including a programmable frequency source and an orthogonal sampling phase-sensitive demodulation circuit; It should be noted that the design of the dielectric loss factor monitoring module in step S103 adopts advanced electronic measurement technology to ensure the accurate measurement of the dielectric loss factor. The programmable frequency source can output signals of different frequencies as needed to meet the dielectric loss measurement requirements of different cables. The orthogonal sampling phase-sensitive demodulation circuit can efficiently extract the dielectric loss signal, eliminate interference, and improve measurement accuracy. The dielectric loss factor data collected by this module can reflect the degree of loss of the cable insulation material.

[0028] S104, collecting chemical characteristic gas data using a gas monitoring unit composed of a nanotube array gas sensor and an optical fiber evanescent wave sensor.

[0029] It should be noted that in step S104, the nanotube array gas sensor has the characteristics of high sensitivity and rapid response, and can accurately detect trace chemical characteristic gases released inside the cable. The optical fiber evanescent wave sensor uses the evanescent wave effect of light to measure the gas concentration with high precision. The combined use of these two sensors improves the accuracy and reliability of chemical characteristic gas detection. The collected chemical characteristic gas data can reflect the degree of thermal decomposition or chemical degradation of the cable insulation material.

[0030] As an optional embodiment of the present invention, optionally, establishing the electromagnetic-thermal-chemical multi-physics field coupling model in step S2 includes: S201, establishing an electromagnetic field model using the partial discharge pulse data; S202, establishing a heat conduction model using the distributed temperature field data and dielectric loss factor; S203, using the chemical characteristic gas data to establish a chemical reaction field model; S204, coupling the electromagnetic field model with the heat conduction model, and coupling the heat conduction model with the chemical reaction field model to obtain an electromagnetic-thermal-chemical multi-physics field coupling model; S205, performing a confidence assessment on the electromagnetic-thermal-chemical multi-physics field coupling model, and optimizing the electromagnetic-thermal-chemical multi-physics field coupling model based on the assessment result.

[0031] It should be noted that in step S205, the confidence assessment mechanism is carried out by comparing the consistency of the model prediction results with the experimental data or historical data. Specifically, residual analysis, correlation coefficient calculation or cross-validation methods can be used to evaluate the confidence of the model. If the evaluation results show that there is a large deviation between the model prediction results and the actual situation, it is necessary to adjust the model parameters or optimize the model structure to improve the accuracy and reliability of the model. Through continuous iteration and optimization, an electromagnetic-thermal-chemical multi-physics field coupling model that can accurately reflect the multi-dimensional evolution law of the cable insulation state is finally obtained.

[0032] As an optional embodiment of the present invention, optionally, the expression of the electromagnetic-thermal-chemical multi-physics field coupling model is: Electromagnetic field model: ; The electromagnetic field model is used to describe the electromagnetic field distribution generated by partial discharge in cable insulation and its influence on the material. The electromagnetic field model is established through the magnetic vector potential equation and the current continuity equation. Specifically, the partial discharge pulse is collected by the high-frequency current transformer and the differential Rogowski coil array, and then input into the model as the excitation source ( ); the equation is solved by solving the magnetic vector potential The distribution of the electric field strength can be calculated indirectly ( ) and magnetic field strength ( );Electromagnetic field energy through Joule heat term ( ) is coupled to the heat conduction model. When constructing the electromagnetic field model, the finite element method (FEM) or finite difference time domain (FDTD) method is used to discretize the solution region, and the boundary conditions (such as perfect conductor boundary) are set in combination with the cable geometry (such as insulation layer and shielding layer).

[0033] Heat conduction model: ; The purpose of constructing the heat conduction model is to describe the temperature field distribution of the cable and the influence of thermal stress on the insulation material; the heat conduction model is established based on Fourier's law and energy conservation equation; the distributed optical fiber temperature measurement system provides initial temperature field data ( ), the dielectric loss factor is collected by the orthogonal sampling phase-sensitive demodulation circuit to calculate the heat generated by dielectric loss; the Joule heat term ( ) is input in real time by the electromagnetic field model to form an electrical-thermal coupling; the temperature gradient drives the heat conduction process, and the high temperature area accelerates the aging of the insulation material. The heat conduction model is established using the finite volume method (FVM) or finite element method to solve the transient temperature field; nonlinear thermal conductivity ( ) to reflect the temperature dependence of the material.

[0034] Chemical reaction field model: ; The chemical reaction field model is established to describe the diffusion and reaction kinetics of chemical gases generated by the aging of insulating materials. The chemical reaction field model is established by combining Fick's diffusion law and Arrhenius reaction equation; the nanotube array gas sensor and the optical fiber evanescent wave sensor collect the chemical gas concentration in real time ( ), as the model input; the temperature field ( ) The reaction rate is controlled by the Arrhenius equation ( ), high temperature accelerates chemical degradation; diffusion term ( ) describes the concentration gradient driven diffusion of gas in the insulating layer. The chemical reaction field model is established by using the finite difference method (FDM) to solve the reaction-diffusion equation; the temperature output of the coupled heat conduction model is used to dynamically update the reaction rate constant.

[0035] in, represents the Hamiltonian operator, represents the magnetic permeability of the material, represents the magnetic vector potential, represents the conductivity, represents the partial derivative of the magnetic vector potential with respect to time, represents the source current density, represents the material density, represents the specific heat capacity, Indicates temperature, represents thermal conductivity, represents the Joule heat term, represents the concentration of chemical products, represents the diffusion coefficient, represents the frequency factor, represents the activation energy, is the gas constant, Represents the reaction kinetics function.

[0036] Electromagnetic-thermal coupling: Joule heating term of electromagnetic field model ( ) as heat source input into the heat conduction model; Thermal-chemical coupling: Temperature field of the heat conduction model ( ) regulates the rate of chemical reactions ( ); Bidirectional feedback: chemical degradation changes the conductivity of the material ( ) and thermal conductivity ( ), which in turn affects the distribution of electromagnetic field and temperature field, forming a closed-loop coupling.

[0037] As an optional embodiment of the present invention, optionally, establishing a hybrid deep learning model in step S3 includes: S301, performing spatiotemporal alignment and standardization processing on the multi-dimensional cable data to construct a tensor input including space-time dimensions; It should be noted that in step S301, the spatiotemporal alignment is to ensure that the data from different sensors can be aligned in the same time frame and spatial position for subsequent feature extraction and pattern recognition. The standardization process is to eliminate the dimensional differences between different data dimensions and improve the training efficiency and accuracy of the model. By constructing a tensor input containing space-time dimensions, the hybrid deep learning model can more effectively capture the multi-dimensional evolution of the cable insulation state.

[0038] S302, constructing a spatial encoder based on a combination of a residual network and a dilated convolution, and using the spatial encoder to extract a spatial feature vector from the tensor input; It should be noted that in step S302, the spatial encoder uses the residual network (ResNet) as the basic architecture, and introduces skip connections to alleviate the gradient vanishing problem in the deep network, thereby improving the training stability and feature extraction ability of the model. The introduction of dilated convolution can increase the receptive field of the convolution kernel, allowing the model to consider a wider range of contextual information when capturing spatial features. Through the action of the spatial encoder, the key spatial features in the tensor input are effectively extracted and encoded into spatial feature vectors.

[0039] S303, cascading a bidirectional long short-term memory network and a gated recurrent unit to obtain a time encoder, and using the time encoder to extract a time series feature vector of the insulation performance in the tensor input; It should be noted that in step S303, the time encoder combines the advantages of the bidirectional long short-term memory network (Bi-LSTM) and the gated recurrent unit (GRU). Bi-LSTM can process sequence data from two directions (forward and reverse) simultaneously, capture contextual information, and enhance the modeling ability of temporal dependencies. GRU simplifies the structure of LSTM by introducing update gates and reset gates, improves computational efficiency, and maintains good feature extraction performance. The cascaded use of Bi-LSTM and GRU not only retains detailed temporal information, but also improves the operating efficiency of the model. The time encoder analyzes the time series in the tensor input, extracts the characteristics of the insulation performance changing over time, and encodes them into a time series feature vector.

[0040] S304, dynamically weighting and fusing the spatial feature vector and the temporal feature vector based on the cross-modal attention fusion module to obtain spatiotemporal features; It should be noted that in step S304, the cross-modal attention fusion module first calculates the attention weights between the spatial feature vector and the temporal feature vector. These weights reflect the relative importance of different features in describing the cable insulation state. Then, the spatial feature vector and the temporal feature vector are dynamically weighted and fused according to these weights to generate a spatiotemporal feature vector that integrates spatial and temporal information. This process not only enhances the model's ability to capture the multi-dimensional evolution of the cable insulation state, but also improves the model's recognition accuracy for different working conditions and defect types.

[0041] S305, constructing a cable structure life prediction model using a graph convolutional network based on the spatiotemporal features; It should be noted that in step S305, a graph convolutional network (GCN) is used to construct a cable structure life prediction model because GCN can efficiently process graph structure data and capture complex relationships between nodes. In a graph convolutional network, various parts of a cable (such as an insulation layer, a conductor, etc.) are represented as nodes in a graph, and the connection relationships between them (such as physical connections, heat conduction paths, etc.) are represented as edges in a graph. Through graph convolution operations, the model can learn the structural information contained in these nodes and edges, and then accurately predict the life of the cable. Specifically, the spatiotemporal feature vector is used as the input of the graph convolutional network, and after multiple layers of graph convolution operations, the feature representation of each node is obtained. Then, using these feature representations and prior knowledge of the cable structure, a cable structure life prediction model is constructed. The model can comprehensively consider the electromagnetic, thermal, chemical and other aspects of the cable, as well as the interaction between them, to achieve accurate prediction of the cable life.

[0042] S306, constructing a cable insulation defect recognition model using a lightweight classifier based on the spatiotemporal features, and identifying the type of cable insulation defects based on the cable insulation defect recognition model; It should be noted that in step S306, the lightweight classifier uses algorithms such as convolutional neural network (CNN) or support vector machine (SVM), which have low computational complexity and memory usage while maintaining high recognition accuracy. The spatiotemporal feature vector is used as the input of the lightweight classifier, and after feature extraction and classification decision, the type of cable insulation defect is output. In order to further improve the generalization ability and robustness of the model, data enhancement technology (such as random noise addition, image rotation, etc.) can be used to pre-process the training data to increase the diversity of the model's training samples.

[0043] S307, respectively training and verifying the cable structure life prediction model and the cable insulation defect identification model; It should be noted that in step S307, the training process is carried out using synthetic data sets and experimental data sets with labels, and the labels include the actual life of the cable and the known types of insulation defects. The synthetic data set is generated by simulating the operating conditions of the cable under different working conditions, including the changes in various electromagnetic, thermal and chemical parameters, and their effects on the insulation state of the cable. The experimental data set comes from the actual cable insulation performance monitoring experiment, which contains a variety of defect types and different degrees of aging. During the training process, a cross-validation strategy is used to evaluate the performance of the model to ensure that the model can show good generalization ability on different data sets. The verification process is carried out by comparing the consistency of the model prediction results with the experimental verification data to verify the accuracy and reliability of the model. Through training and verification, a hybrid deep learning model that can accurately predict the cable life and identify the insulation defect type is finally obtained.

[0044] S308. Integrate the trained cable structure life prediction model and cable insulation defect recognition model to obtain a hybrid deep learning model.

[0045] It should be noted that in step S308, the cable structure life prediction model and the cable insulation defect recognition model are integrated by building a unified model framework. This framework can simultaneously receive the spatiotemporal feature vector as input and call two sub-models for prediction. Specifically, for the cable structure life prediction, the framework passes the spatiotemporal feature vector to the graph convolution network part, and after multi-layer graph convolution operations, the predicted life of the cable is output. For the identification of cable insulation defects, the framework passes the spatiotemporal feature vector to the lightweight classifier part, and after feature extraction and classification decisions, the type of insulation defect is output.

[0046] As an optional embodiment of the present invention, optionally, in step S302, the time encoder extracts the time series feature vector of the insulation performance in the tensor input as follows: , ; in, represents the initial layer spatial feature map, Represents the spatial distribution data output by the electromagnetic-thermal-chemical multi-physics field coupling model, Indicates Layer spatial feature map, represents the activation function, Indicates The dilated convolution kernel of the layer, represents the dilated convolution operation, Indicates Layer spatial feature map, Indicates Bias of the layer; In step S303, the expression for extracting the time series feature vector of the insulation performance in the tensor input by using the time encoder is: , , , ; in, Represents the time step The hidden state vector of the forward LSTM, represents the long short-term memory network, Represents the time step The input vector is the time series output of the electromagnetic-thermal-chemical multi-physics field coupling model. Represents the time step The hidden state vector of the forward LSTM, Represents the time step The hidden state vector of the LSTM before and after, Represents the time step The hidden state vector of the LSTM before and after, represents the bidirectional long short-term memory network at time step The spliced ​​hidden state of Represents a splicing operation, represents the gated recurrent unit at time step The hidden state of represents the gated recurrent unit operation, represents the gated recurrent unit at time step The hidden state of .

[0047] As an optional embodiment of the present invention, optionally, in step S304, the expression for dynamically weighting and fusing the spatial feature vector and the temporal feature vector by the cross-modal attention fusion module is: , , , ; in, represents the spatial eigenvector after projection, represents the learned projection matrix, which is used to map the spatial feature vector and the temporal feature vector to a common dimension, Indicates global average pooling of the spatial feature map. represents the bias term of the projection layer, represents the time series feature vector after projection, The learned projection matrix is ​​used to map the temporal and spatial feature vectors to a common dimension, Indicates the time dimension pooling of the time series feature vector. represents the bias term of the projection layer, represents the dynamically generated attention weight vector, represents the activation function, represents the transpose of the projected spatial eigenvector, represents the learnable attention matrix, represents the scaling factor, Represents the spatiotemporal characteristics, Represents element-wise multiplication.

[0048] As an optional embodiment of the present invention, optionally, in step S3, the expression for monitoring the insulation defects of the cable based on the spatiotemporal characteristics is: ; in, represents the predicted probability vector, represents the activation function, represents the classification layer parameters, Represents the spatiotemporal characteristics, Represents the bias vector of the classification layer; Monitoring the cable based on the spatiotemporal characteristics to predict the remaining service life of the cable in step S3 includes: , , , , ; in, represents the encoded hidden state sequence, Indicates encoding the input feature matrix, Represents the time step The normalized weight of represents the transpose of the feature transformation matrix, represents the feature transformation matrix, Represents the time step The hidden state sequence of represents the bias term of attention calculation, Represents the time step The hidden state sequence of represents the context vector, represents the predicted original life value, represents the decoding weight matrix, represents the decoding bias term, represents the life expectancy prediction value, represents the physical attenuation factor, Indicates the insulation aging rate coefficient, Represents the current time step.

[0049] As an optional embodiment of the present invention, optionally, in step S4, adaptively adjusting the monitoring strategy based on the warning threshold and the operating condition parameter includes: S401. Construct a digital twin model based on the multi-dimensional evolution law of cable insulation status; It should be noted that in step S401, the digital twin model realizes high-precision simulation of the insulation state of the cable by integrating multi-dimensional information such as the physical structure, material properties, and operating environment of the cable. The model can reflect the evolution of the insulation state of the cable under different working conditions in real time. The establishment of the digital twin model is specifically as follows: First, collect the physical structure parameters of the cable, such as conductor size, insulation layer thickness, etc., and material property data, such as dielectric constant and thermal conductivity of the insulating material. Then, according to the actual operating environment of the cable, including factors such as temperature, humidity, and electromagnetic field strength, set the corresponding simulation conditions. Then, using advanced simulation software, the above information is input into the model to perform multi-physical field coupling simulation to simulate the insulation state changes of the cable under different working conditions. By continuously iterating and optimizing the model parameters, the output results of the digital twin model are highly consistent with the actual situation, thereby realizing high-precision simulation and real-time reflection of the insulation state of the cable.

[0050] S402, the digital twin model dynamically generates a warning threshold of the cable insulation performance using a machine learning method based on the currently collected multi-dimensional cable data and the cable operating parameters; It should be noted that in step S402, the digital twin model not only considers the physical structure and material properties of the cable, but also combines real-time operating data, such as current, voltage, temperature, etc., as well as historical fault records, and uses machine learning algorithms to deeply mine and analyze these data, thereby dynamically adjusting the warning threshold. This dynamic adjustment mechanism can more accurately reflect the current insulation state of the cable, avoid false alarms or missed alarms, and improve the accuracy and reliability of monitoring. The generation of the warning threshold is specifically as follows: First, the insulation performance data of the cable, including key indicators such as insulation resistance and leakage current, are extracted from the historical database. Then, these data are trained using machine learning algorithms, such as support vector machines, random forests, etc., to establish a mapping relationship between insulation performance and warning thresholds. Next, according to the currently collected multi-dimensional cable data and operating parameters, the input of the model is updated in real time, and a new warning threshold is dynamically generated. Finally, the generated warning threshold is compared with the insulation performance data monitored in real time. If the threshold is exceeded, the warning mechanism is triggered and the operation and maintenance personnel are notified in time for processing.

[0051] S403, when the insulation defect of the monitored cable approaches the warning threshold of the cable insulation performance, triggering the warning mechanism; S404, if the insulation defect of the monitoring cable is far away from the warning threshold, reduce the monitoring frequency; S405. If the insulation defect of the monitoring cable approaches or exceeds the warning threshold, increase the monitoring frequency; It should be noted that in steps S404 and S405, by dynamically adjusting the monitoring strategy, refined management and efficient monitoring of the cable insulation state can be achieved. Specifically, when it is monitored that the insulation defects of the cable are gradually approaching the early warning threshold, it indicates that the insulation performance of the cable may be gradually deteriorating. At this time, the early warning mechanism is triggered, which can remind the operation and maintenance personnel to take timely measures to intervene and prevent the occurrence of insulation failures. When the insulation defects of the cable are monitored to be far away from the early warning threshold, it indicates that the insulation state of the cable is relatively stable. At this time, the monitoring frequency can be appropriately reduced to reduce unnecessary monitoring costs. On the contrary, when the insulation defects of the cable are monitored to be close to or exceed the early warning threshold, it indicates that the insulation performance of the cable may have serious problems. At this time, the monitoring frequency needs to be increased to pay closer attention to the insulation state of the cable and ensure the safe operation of the cable. In this way, refined management and efficient monitoring of the cable insulation state can be achieved, and the operation safety and reliability of the cable can be improved.

[0052] S406: Evaluate the effect of the adjusted monitoring strategy. If the evaluation result shows that the adjusted monitoring strategy fails to effectively improve the monitoring accuracy, re-execute steps S401 to S405.

[0053] It should be noted that in step S406, the effect evaluation is mainly carried out by comparing the monitoring data before and after the adjustment, analyzing the triggering frequency, false alarm rate and missed alarm rate of the early warning mechanism and other indicators. If the evaluation results show that the adjusted monitoring strategy fails to effectively improve the monitoring accuracy, the possible reasons include the insufficient accuracy of the digital twin model, the weak adaptability of the machine learning algorithm, or the unreasonable selection of the operating parameters. To address these problems, data can be collected again, model parameters can be optimized, machine learning algorithms can be improved, or the selection range of operating parameters can be adjusted to improve the accuracy and reliability of the monitoring strategy. Through continuous iteration and optimization, this embodiment can achieve accurate monitoring and early warning of cable insulation performance, providing a strong guarantee for the safe operation of the cable.

[0054] Example 2 This embodiment also provides an electronic device, referring to Figure 2 , including a memory 404 and a processor 402, wherein the memory 404 stores a computer program, and the processor 402 is configured to run the computer program to execute the steps in any of the above-mentioned embodiments of the method for online monitoring of the insulation performance of a power cable.

[0055] Specifically, the processor 402 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0056] Among them, the memory 404 may include a large capacity memory 404 for data or instructions. By way of example and not limitation, the memory 404 may include a hard disk drive (HDD), a floppy disk drive, a solid state drive (SSD), a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 404 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 404 may be inside or outside the data processing device. In a specific embodiment, the memory 404 is a non-volatile memory. In a specific embodiment, the memory 404 includes a read-only memory (ROM) and a random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (Programmable Read-Only Memory, PROM for short), an erasable PROM (Erasable Programmable Read-Only Memory, EPROM for short), an electrically erasable PROM (Electrically Erasable Programmable Read-Only Memory, EEPROM for short), an electrically alterable ROM (Electrically Alterable Read-Only Memory, EAROM for short) or a flash memory (FLASH) or a combination of two or more of these. Under appropriate circumstances, the RAM can be a static random access memory (Static Random-Access Memory, abbreviated as SRAM) or a dynamic random access memory (Dynamic Random Access Memory, abbreviated as DRAM), wherein the DRAM can be a fast page mode dynamic random access memory 404 (Fast Page Mode Dynamic Random Access Memory, abbreviated as FPMDRAM), an extended data output dynamic random access memory (Extended Date Out Dynamic Random Access Memory, abbreviated as EDODRAM), a synchronous dynamic random access memory (Synchronous Dynamic Random-Access Memory, abbreviated as SDRAM), etc.

[0057] The memory 404 may be used to store or cache various data files required for processing and / or communication, as well as possible computer program instructions executed by the processor 402 .

[0058] The processor 402 reads and executes the computer program instructions stored in the memory 404 to implement any one of the distribution methods for distributing data based on rule engine encapsulation in the above embodiments.

[0059] Optionally, the electronic device may further include a transmission device 406 and an input / output device 408 , wherein the transmission device 406 is connected to the processor 402 , and the input / output device 408 is connected to the processor 402 .

[0060] The transmission device 406 can be used to receive or send data via a network. The specific examples of the above-mentioned network may include a wired or wireless network provided by a communication provider of the electronic device. In one example, the transmission device includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 406 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0061] The input / output device 408 is used to input or output information. In this embodiment, the input information may be various configuration information of the package component, and the output information may be data to be distributed.

[0062] Optionally, in this embodiment, the processor 402 may be configured to perform the following steps through a computer program: Create an engineering service on the spring system, introduce a package component into the engineering service, and the package component depends on the dependency library as a dependency file, and the package component at least includes a rule input configuration table for configuring rules, a condition configuration table for configuring rule conditions, and a sending configuration table for configuring the http protocol; After starting the distribution service of the engineering service, the packaged component is added to the IOC container; The engineering service loads the rule configuration of the current data rule into the memory based on the encapsulation component, generates the current data rule based on the rule, adds the current data rule to the rule group and registers the rule group to the bean of the IOC container; An externally exposed access trigger interface is created on the engineering service and an execution method of a rule engine is defined. After being triggered, the rule engine executes the data distribution task from the memory according to the rule configuration.

[0063] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0064] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the claims and their equivalents.

Claims

1. A method for online monitoring of insulation performance of power cables, characterized in that: The method comprises: S1. Building a multimodal sensor network, and synchronously collecting multidimensional cable data based on the multimodal sensor network, wherein the multidimensional cable data includes partial discharge pulse data, distributed temperature field data, dielectric loss factor, and chemical characteristic gas data; S2. Establishing an electromagnetic-thermal-chemical multi-physics field coupling model, inputting the multi-dimensional cable data into the electromagnetic-thermal-chemical multi-physics field coupling model, and analyzing the multi-dimensional evolution law of the cable insulation state in real time; S3. Establish a hybrid deep learning model, use the hybrid deep learning model to extract the spatiotemporal features in the multi-dimensional evolution law, monitor the insulation defects of the cable based on the spatiotemporal features, and predict the remaining service life of the cable; S4. Based on the spatiotemporal characteristics, the digital twin method is used to dynamically generate warning thresholds, and the monitoring strategy is adaptively adjusted based on the warning thresholds and operating condition parameters.

2. The method for online monitoring of insulation performance of power cables according to claim 1, characterized in that: In step S1, synchronously collecting multi-dimensional cable data based on the multimodal sensor network includes: S101, using a partial discharge detection system combining a differential Rogowski coil array and a high-frequency current transformer to collect partial discharge pulse data; S102, a distributed optical fiber temperature measurement system based on Raman scattering principle collects distributed temperature field data; S103, collecting dielectric loss factor using a dielectric loss factor monitoring module including a programmable frequency source and an orthogonal sampling phase-sensitive demodulation circuit; S104. Collect chemical characteristic gas data using a gas monitoring unit composed of a nanotube array gas sensor and an optical fiber evanescent wave sensor.

3. The method for online monitoring of insulation performance of power cables according to claim 1, characterized in that: The establishment of the electromagnetic-thermal-chemical multi-physics field coupling model in step S2 includes: S201, establishing an electromagnetic field model using the partial discharge pulse data; S202, establishing a heat conduction model using the distributed temperature field data and dielectric loss factor; S203, using the chemical characteristic gas data to establish a chemical reaction field model; S204, coupling the electromagnetic field model with the heat conduction model, and coupling the heat conduction model with the chemical reaction field model to obtain an electromagnetic-thermal-chemical multi-physics field coupling model; S205, performing a confidence assessment on the electromagnetic-thermal-chemical multi-physics field coupling model, and optimizing the electromagnetic-thermal-chemical multi-physics field coupling model based on the assessment result.

4. The method for online monitoring of insulation performance of power cables according to claim 3, characterized in that: The expression of the electromagnetic-thermal-chemical multi-physics field coupling model is: ， ， ； in, represents the Hamiltonian operator, represents the magnetic permeability of the material, represents the magnetic vector potential, represents the conductivity, represents the partial derivative of the magnetic vector potential with respect to time, represents the source current density, represents the material density, represents the specific heat capacity, Indicates temperature, represents thermal conductivity, represents the Joule heat term, represents the concentration of chemical products, represents the diffusion coefficient, represents the frequency factor, represents the activation energy, is the gas constant, Represents the reaction kinetics function.

5. The method for online monitoring of insulation performance of power cables according to claim 1, characterized in that: Establishing the hybrid deep learning model in step S3 includes: S301, performing spatiotemporal alignment and standardization processing on the multi-dimensional cable data to construct a tensor input including space-time dimensions; S302, constructing a spatial encoder based on a combination of a residual network and a dilated convolution, and using the spatial encoder to extract a spatial feature vector from the tensor input; S303, cascading a bidirectional long short-term memory network and a gated recurrent unit to obtain a time encoder, and using the time encoder to extract a time series feature vector of the insulation performance in the tensor input; S304, dynamically weighting and fusing the spatial feature vector and the temporal feature vector based on the cross-modal attention fusion module to obtain spatiotemporal features; S305, constructing a cable structure life prediction model using a graph convolutional network based on the spatiotemporal features; S306, constructing a cable insulation defect recognition model using a lightweight classifier based on the spatiotemporal features, and identifying the type of cable insulation defects based on the cable insulation defect recognition model; S307, respectively training and verifying the cable structure life prediction model and the cable insulation defect identification model; S308. Integrate the trained cable structure life prediction model and cable insulation defect recognition model to obtain a hybrid deep learning model.

6. The method for online monitoring of insulation performance of power cables according to claim 5, characterized in that: In step S302, the time encoder extracts the time series feature vector of the insulation performance in the tensor input as follows: ， ； in, represents the initial layer spatial feature map, Represents the spatial distribution data output by the electromagnetic-thermal-chemical multi-physics field coupling model, Indicates Layer spatial feature map, represents the activation function, Indicates The dilated convolution kernel of the layer, represents the dilated convolution operation, Indicates Layer spatial feature map, Indicates Bias of the layer; In step S303, the expression for extracting the time series feature vector of the insulation performance in the tensor input by using the time encoder is: ， ， ， ； in, Represents the time step The hidden state vector of the forward LSTM, represents the long short-term memory network, Represents the time step The input vector is the time series output of the electromagnetic-thermal-chemical multi-physics field coupling model. Represents the time step The hidden state vector of the forward LSTM, Represents the time step The hidden state vector of the LSTM before and after, Represents the time step The hidden state vector of the LSTM before and after, represents the bidirectional long short-term memory network at time step The spliced ​​hidden state of Represents a splicing operation, represents the gated recurrent unit at time step The hidden state of represents the gated recurrent unit operation, represents the gated recurrent unit at time step The hidden state of .

7. The method for online monitoring of insulation performance of power cables according to claim 5, characterized in that: In step S304, the expression of the cross-modal attention fusion module dynamically weighted fusion of spatial feature vectors and temporal feature vectors is: ， ， ， ； in, represents the spatial eigenvector after projection, represents the learned projection matrix, which is used to map the spatial feature vector and the temporal feature vector to a common dimension, Indicates global average pooling of the spatial feature map. represents the bias term of the projection layer, represents the time series feature vector after projection, The learned projection matrix is ​​used to map the temporal and spatial feature vectors to a common dimension, Indicates the time dimension pooling of the time series feature vector. represents the bias term of the projection layer, represents the dynamically generated attention weight vector, represents the activation function, represents the transpose of the projected spatial eigenvector, represents the learnable attention matrix, represents the scaling factor, Represents the spatiotemporal characteristics, Represents element-wise multiplication.

8. The method for online monitoring of insulation performance of power cables according to claim 5, characterized in that: In step S3, the expression for monitoring the insulation defects of the cable based on the spatiotemporal characteristics is: ； in, represents the predicted probability vector, represents the activation function, represents the classification layer parameters, Represents the spatiotemporal characteristics, Represents the bias vector of the classification layer; Monitoring the cable based on the spatiotemporal characteristics to predict the remaining service life of the cable in step S3 includes: ， ， ， ， ； in, represents the encoded hidden state sequence, Indicates encoding the input feature matrix, Represents the time step The normalized weight of represents the transpose of the feature transformation matrix, represents the feature transformation matrix, Represents the time step The hidden state sequence of represents the bias term of attention calculation, Represents the time step The hidden state sequence of represents the context vector, represents the predicted original life value, represents the decoding weight matrix, represents the decoding bias term, represents the life expectancy prediction value, represents the physical attenuation factor, Indicates the insulation aging rate coefficient, Represents the current time step.

9. The method for online monitoring of insulation performance of power cables according to claim 1, characterized in that: In step S4, the monitoring strategy is adaptively adjusted based on the warning threshold and the operating condition parameters, including: S401. Construct a digital twin model based on the multi-dimensional evolution law of cable insulation status; S402, the digital twin model dynamically generates a warning threshold of the cable insulation performance using a machine learning method based on the currently collected multi-dimensional cable data and the cable operating parameters; S403, when the insulation defect of the monitored cable approaches the warning threshold of the cable insulation performance, triggering the warning mechanism; S404, if the insulation defect of the monitoring cable is far away from the warning threshold, reduce the monitoring frequency; S405. If the insulation defect of the monitoring cable approaches or exceeds the warning threshold, increase the monitoring frequency; S406: Evaluate the effect of the adjusted monitoring strategy. If the evaluation result shows that the adjusted monitoring strategy fails to effectively improve the monitoring accuracy, re-execute steps S401 to S405.

10. An electronic device comprising a memory and a processor, characterized in that: The memory stores a computer program, and the processor is configured to run the computer program to execute the method for online monitoring of insulation performance of a power cable as claimed in any one of claims 1 to 9.

Images