Underground cable working condition identification and safety monitoring method and system

Through integrated sensors to obtain multiple signals of underground cables and perform data processing, the problem of low detection efficiency of cable environmental status and mining damage behavior in the prior art is solved, real-time monitoring of cable operating conditions and timely detection of damage behavior is realized. Improves fault detection efficiency and reduces maintenance costs.

CN118914746AInactive Publication Date: 2024-11-08SHANGHAI JIYAN POWER TECH CO LTD
View PDF 16 Cites 0 Cited by

Patent Information

Application Number
CN202410974224.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-19
Publication Date
2024-11-08
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The prior art is difficult to monitor the environmental status and excavation damage behavior of underground cables in real time, resulting in low fault detection efficiency, high maintenance cost, and inability to stop damage behavior in time.

Method used

The cable's sheath current signal, connector temperature, discharge signal and well vibration signal are obtained through integrated sensors, and the data processor is used to perform timing data processing and signal decomposition and reconstruction, combining mutation signal detection, local discharge signal denoising and vibration signal denoising The model calculates the results of the cable damage assessment, insulation aging and vibration type assessment, and store them in the database and display them in the human-computer interactive interface.

Benefits of technology

Real-time monitoring of cable operating conditions and timely detection of mining and damage behaviors is realized, fault detection efficiency is improved, and maintenance costs are reduced.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118914746A_ABST
    Figure CN118914746A_ABST
Patent Text Reader

Abstract

The invention relates to an underground cable working condition identification and safety monitoring method and system, and belongs to the technical field of underground cable working condition identification and data analysis. The method comprises the following steps: acquiring sheath current signal data, cable joint temperature data, discharge signal data and cable well vibration signal data of a cable through an integrated sensor; the data processor adds timestamps to the data and preprocesses the data to obtain frequency band signals, de-noising discharge signals and de-noising vibration signals; comparing the cable joint temperature data with a preset temperature threshold value to obtain a temperature abnormity grade result, obtaining a cable insulation aging evaluation result, a vibration type evaluation result and a cable sheath damage evaluation result through different evaluation models, and storing the evaluation results in a database list; and the intelligent terminal calls a corresponding list according to the serial number of the integrated sensor and displays the list on a human-computer interaction interface. The cable operation state and the external environment state are reflected in real time, and the working condition identification and safety monitoring of the underground cable are realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of underground cable working condition identification and data analysis, and in particular relates to an underground cable working condition identification and safety monitoring method and system. Background Art

[0002] In the current power system, underground cables are important transmission and distribution facilities, and their safe operation is crucial to ensuring the stability and reliability of power supply. With the acceleration of urbanization, underground cables are used more and more widely, but they also face many challenges, such as difficulty in fault detection, high maintenance costs, and insufficient environmental monitoring. Therefore, it is particularly important to develop an efficient and accurate method and system for identifying and safely detecting underground cable conditions.

[0003] At the same time, with the popularization of cable lines, problems such as hidden cable faults have become increasingly prominent. At present, the main problems of urban cables include the following aspects. First, the cables are damaged by external forces such as violent excavation, resulting in disconnection and other power outages. Second, problems such as the cable head manufacturing process cause insulation damage to the cable head, further causing insulation breakdown discharge, fire, etc.

[0004] In the past, underground cables were mainly supervised by manual inspections to check, record and analyze cable trenches at different locations. However, this method not only cannot reflect the environmental status of the cable trench in real time, but also consumes a lot of human resources and is inefficient. The traditional supervision method only monitors the operating status of the cable itself and cannot monitor whether the cable has been damaged by excavation. In addition, the feedback cycle of cable excavation is long, and it is impossible to stop the damage in time and carry out follow-up work. Summary of the invention

[0005] In order to solve the above problems existing in the prior art, the present invention provides a method and system for identifying the working condition and safety monitoring of underground cables.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] S1: acquiring the sheath current signal data, the cable joint temperature data, the discharge signal data and the cable well vibration signal data of the cable through an integrated sensor, and transmitting the sheath current signal data, the cable joint temperature data, the discharge signal data and the cable well vibration signal data to a data processor;

[0008] S2: The data processor obtains time-series sheath current signal data, time-series discharge signal data and time-series vibration signal data by adding timestamps according to the sheath current signal data, the discharge signal data and the cable well vibration signal data, obtains the current mutation signal by intercepting the mutation signal detection model according to the time-series sheath current data, and decomposes and reconstructs the current mutation signal by decomposing and reconstructing the model to obtain the frequency band signal; obtains the denoised discharge signal data by calculating the partial discharge signal denoising model according to the time-series discharge signal data; obtains the denoised vibration signal by calculating the vibration signal denoising model according to the time-series vibration signal data;

[0009] S3: Compare the cable joint temperature data with the preset temperature threshold to obtain the temperature anomaly grade result; calculate the denoised discharge signal data through the partial discharge signal recognition model to obtain the cable insulation aging assessment result; calculate the denoised vibration signal data through the vibration assessment model to obtain the vibration type assessment result; use the frequency band signal as the input data of the sheath current assessment model to obtain the cable sheath damage assessment result;

[0010] S4: The processor stores the temperature anomaly level result, the cable insulation aging assessment result, the vibration type assessment result and the cable sheath damage assessment result into a corresponding list in a database according to the number of the integrated sensor, and the smart terminal calls the list according to the number of the integrated sensor and displays it on the human-computer interaction interface.

[0011] As a preferred technical solution of the present invention, the mutation signal detection model obtains a first test value and a second test value through a cumulative sum algorithm according to the sequential sheath current data, determines a fault phase identification index according to the first test value and the second test value, and determines a time window value according to the identification index, and finally intercepts the current mutation signal according to the time window value, wherein the calculation formula of the first test value, the second test value and the identification index is:

[0012] Q1(k)=max(Q1(k-1)+I(k)-p),

[0013] Q2(k)=max(Q2(k-1)-I(k)-p),

[0014] Q i (k) = Q1(k) + Q2(k),

[0015] Where Q1(k) is the first test value at time k, Q2(k) is the second test value at time k, Q i (k) is the identification index, I(k) is the sheath current signal data value at time k, and p is the reference coefficient.

[0016] Specifically, the decomposition and reconstruction model is to decompose the current mutation signal by a wavelet transform algorithm to obtain a decomposition signal, and obtain a frequency band signal by a reconstruction algorithm according to the decomposition signal, wherein the wavelet exchange algorithm performs low-pass filtering and high-pass filtering on the current mutation signal to obtain a low-pass output signal and a high-pass output signal, and downsamples the low-pass output signal and the high-pass output signal to obtain an average signal and a detail signal of the current mutation signal, and the calculation formulas of the average signal and the detail signal are:

[0017]

[0018]

[0019] Wherein H0 is the low-pass filter coefficient, H1 is the high-pass filter coefficient, C(Z) is the average signal, d(Z) is the detail signal, j and m are non-zero real number parameters, and Z is the length of the current mutation signal;

[0020] The reconstruction algorithm is to insert zero values ​​between two samples of the average signal for stretching, and then pass it through a low-pass filter to obtain a reconstructed low-pass output signal, and then pass the detail signal through a high-pass filter after upsampling to obtain a reconstructed high-pass output signal, and add the reconstructed low-pass output signal and the reconstructed high-pass output signal to obtain the frequency band signal, wherein the frequency band signal calculation formula is:

[0021]

[0022] Wherein X(Z) is the frequency band signal, Z is the length of the current mutation signal, j and m are non-zero real number parameters, H0 is the low-pass filter coefficient, H1 is the high-pass filter coefficient, C(Z) is the average signal, and d(Z) is the detail signal.

[0023] Specifically, the partial discharge signal denoising model initializes the pole symmetric modal decomposition parameters, performs pole symmetric modal decomposition on the time series discharge signal data to obtain a series of intrinsic modal components, calculates the correlation coefficient and peak value of each intrinsic modal component, selects the effective intrinsic modal component according to the correlation coefficient and the peak value, and reconstructs to obtain the denoised discharge signal;

[0024] The vibration signal denoising model decomposes the time series vibration signal into a series of intrinsic mode components according to the time series vibration signal data through the empirical mode decomposition method, determines the noisy mode components through autocorrelation analysis according to the intrinsic mode components, and calculates the initial threshold of each noisy mode component, obtains the optimal stratification threshold through the least mean square algorithm according to the initial threshold, and thresholds the noisy mode components according to the optimal stratification threshold to obtain the denoised vibration signal.

[0025] Specifically, the partial discharge signal recognition model includes the feature extraction unit, the feature selection unit and the classifier. The feature extraction unit first obtains the partial discharge signal vector according to the denoised partial discharge signal data through two-dimensional convolution, and then performs position encoding on the partial discharge signal vector to obtain a coded partial discharge signal vector. The coded partial discharge signal vector is input into a stacked three-layer deep network architecture for multi-head self-attention calculation to obtain a feature vector and the feature vector is transmitted to the feature selection unit. The feature selection unit obtains a vector similarity matrix by calculating the divergence between the feature vectors, adds the divergence between each vector and other vectors according to the similarity matrix to obtain a feature score, and then selects a feature vector subset according to the feature score. Finally, the feature vector subset is fused to obtain a fused feature and the fused feature is transmitted to the classifier. The classifier compares the fused feature with a preset feature classification to obtain the cable insulation aging assessment result.

[0026] Specifically, the sheath current assessment model extracts features from the frequency band signal to obtain waveform features and energy features, constructs a feature vector based on the waveform features and the energy features, normalizes the feature vector to obtain a normalized result, and uses the normalized result as input data of a seven-layer deep convolutional neural network to obtain a status diagnosis result through adaptive learning. The classifier compares the status diagnosis result with a preset result classification to obtain the cable sheath damage assessment result.

[0027] Specifically, the vibration assessment model obtains normalized signal data based on the denoised vibration signal data through normalization processing, performs primary feature extraction based on the normalized signal data to obtain vibration duration data, performs secondary feature extraction based on the normalized signal data to obtain time domain feature data, frequency domain feature data and space feature data, uses the vibration duration data as input data of the primary classifier to obtain the initial classification of the denoised vibration signal through calculation, and uses the time domain feature data, the frequency domain feature data and the space feature data as input data of the secondary classifier through calculation according to the initial classification to obtain the vibration type assessment result; wherein, the time domain feature data includes the peak value, average value, effective value, peak factor and kurtosis factor of the signal, the frequency domain feature data includes the center of gravity frequency, mean square frequency and frequency variance, and the spatial feature data is the vibration conduction distance.

[0028] A system for identifying and safely monitoring the working conditions of underground cables, characterized by comprising: a data acquisition module, a data preprocessing module, a data comparison module and a data visualization module;

[0029] The data acquisition module is used to obtain the sheath current signal data, cable joint temperature data, discharge signal data and cable well vibration signal data of the cable through an integrated sensor, and transmit the sheath current signal data, the cable joint temperature data, the discharge signal data and the cable well vibration signal data to a data processor;

[0030] The data preprocessing module is used for the data processor to obtain time-series sheath current signal data, time-series discharge signal data and time-series vibration signal data by adding timestamps according to the sheath current signal data, the discharge signal data and the cable well vibration signal data, intercept and obtain current mutation signals through mutation signal detection model according to the time-series sheath current data, and decompose and reconstruct the current mutation signals through decomposition and reconstruction model to obtain frequency band signals; calculate denoised discharge signal data through partial discharge signal denoising model according to the time-series discharge signal data; calculate denoised vibration signal through vibration signal denoising model according to the time-series vibration signal data;

[0031] The data comparison module is used to compare the cable joint temperature data with a preset temperature threshold to obtain a temperature anomaly grade result; calculate the denoised discharge signal data through a partial discharge signal recognition model to obtain a cable insulation aging assessment result; calculate the denoised vibration signal data through a vibration assessment model to obtain a vibration type assessment result; and use the frequency band signal as input data of a sheath current assessment model to obtain a cable sheath damage assessment result through calculation;

[0032] The data display module is used for the processor to store the temperature anomaly level results, the cable insulation aging assessment results, the vibration type assessment results and the cable sheath damage assessment results into a corresponding list in the database according to the number of the integrated sensor, and the smart terminal calls the list according to the number of the integrated sensor and displays it on the human-computer interaction interface.

[0033] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, a method for identifying and safely monitoring the working conditions of underground cables is implemented.

[0034] A storage medium stores a computer program, characterized in that when the program is executed by a processor, a method for identifying and safely monitoring the working conditions of underground cables is implemented.

[0035] The beneficial effects of the present invention are:

[0036] (1) The temperature data of the cable joint, the cable sheath current signal data, and the cable discharge signal data are obtained by setting an integrated sensor. The data processor adds timestamps to the cable sheath current signal data and the discharge signal data. The current mutation signal of the time series sheath current signal data is intercepted by the mutation signal detection model, and the frequency band signal is obtained by the decomposition and reconstruction model. The frequency band signal is used as the input data of the sheath current assessment model to obtain the cable sheath damage assessment result through calculation; the time series discharge signal data is used as the input data of the partial discharge signal denoising model to obtain the denoised discharge signal data, and the cable insulation aging assessment result is calculated by the partial discharge signal recognition model; the temperature data of the cable joint is compared with the preset temperature threshold to obtain the temperature anomaly level result, and the cable sheath damage assessment result, the cable insulation aging assessment result and the temperature anomaly level result are stored in the database. The database is called by the intelligent terminal and displayed on the human-computer interaction interface to realize real-time monitoring of the cable operating conditions.

[0037] (2) An integrated sensor is provided to obtain the vibration signal data of the cable well. The data processor adds a timestamp to the vibration signal data of the cable well to obtain the time series vibration signal data. The denoised vibration signal is calculated by a vibration signal denoising model according to the time series vibration signal data. The denoised vibration signal data is used as the input data of the vibration assessment model to obtain the vibration type assessment result through calculation. The vibration type assessment result is stored in a database. The database is called by an intelligent terminal and displayed on a human-computer interaction interface. This realizes the monitoring of whether the cable is damaged by excavation, and timely stops the damage and carries out follow-up work. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0039] Figure 1 The present invention is a flowchart of a method and system for identifying and safely monitoring underground cable working conditions. DETAILED DESCRIPTION

[0040] The example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in a variety of forms and should not be construed as being limited to the examples set forth herein: on the contrary, these embodiments are provided so that the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art. In addition, the described features, structures, or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, well-known methods, devices, implementations, or operations are not shown or described in detail to avoid blurring the various aspects of the present disclosure. The blocks shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices. The flowcharts shown in the accompanying drawings are only exemplary illustrations and do not necessarily include all the content and operations / steps, nor do they necessarily have to be executed in the order described. For example, some operations / steps may be decomposed, while some operations / steps may be combined or partially combined, so the actual execution order may change according to actual circumstances.

[0041] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0042] See also Figure 1 , a method and system based on underground cable working condition identification and safety monitoring:

[0043] S1: acquiring the sheath current signal data, the cable joint temperature data, the discharge signal data and the cable well vibration signal data of the cable through an integrated sensor, and transmitting the sheath current signal data, the cable joint temperature data, the discharge signal data and the cable well vibration signal data to a data processor;

[0044] S2: The data processor obtains time-series sheath current signal data, time-series discharge signal data and time-series vibration signal data by adding timestamps according to the sheath current signal data, the discharge signal data and the cable well vibration signal data, obtains the current mutation signal by intercepting the mutation signal detection model according to the time-series sheath current data, and decomposes and reconstructs the current mutation signal by decomposing and reconstructing the model to obtain the frequency band signal; obtains the denoised discharge signal data by calculating the partial discharge signal denoising model according to the time-series discharge signal data; obtains the denoised vibration signal by calculating the vibration signal denoising model according to the time-series vibration signal data;

[0045] S3: Compare the cable joint temperature data with the preset temperature threshold to obtain the temperature anomaly grade result; calculate the denoised discharge signal data through the partial discharge signal recognition model to obtain the cable insulation aging assessment result; calculate the denoised vibration signal data through the vibration assessment model to obtain the vibration type assessment result; use the frequency band signal as the input data of the sheath current assessment model to obtain the cable sheath damage assessment result;

[0046] S4: The processor stores the temperature anomaly level result, the cable insulation aging assessment result, the vibration type assessment result and the cable sheath damage assessment result into a corresponding list in a database according to the number of the integrated sensor, and the smart terminal calls the list according to the number of the integrated sensor and displays it on the human-computer interaction interface.

[0047] In this embodiment, the integrated sensor is composed of multiple measuring units, including an infrared temperature measurement unit, a sheath current measurement unit, a discharge signal acquisition unit, and a vibration signal acquisition unit. The infrared temperature measurement unit obtains the temperature data of the cable joint, the sheath current measurement unit obtains the sheath current data of the cable, the discharge signal of the cable is obtained by the discharge signal acquisition unit, and the vibration signal data of the cable well is obtained by the vibration signal acquisition unit.

[0048] As a preferred technical solution of the present invention, the mutation signal detection model obtains a first test value and a second test value through a cumulative sum algorithm according to the sequential sheath current data, determines a fault phase identification index according to the first test value and the second test value, and determines a time window value according to the identification index, and finally intercepts the current mutation signal according to the time window value, wherein the calculation formula of the first test value, the second test value and the identification index is:

[0049] Q1(k)=max(Q1(k-1)+I(k)-p),

[0050] Q2(k)=max(Q2(k-1)-I(k)-p),

[0051] Qi (k) = Q1(k) + Q2(k),

[0052] Where Q1(k) is the first test value at time k, Q2(k) is the second test value at time k, Q i (k) is the identification index, I(k) is the sheath current signal data value at time k, and p is the reference coefficient.

[0053] Specifically, the decomposition and reconstruction model is to decompose the current mutation signal by a wavelet transform algorithm to obtain a decomposition signal, and obtain a frequency band signal by a reconstruction algorithm according to the decomposition signal, wherein the wavelet exchange algorithm performs low-pass filtering and high-pass filtering on the current mutation signal to obtain a low-pass output signal and a high-pass output signal, and downsamples the low-pass output signal and the high-pass output signal to obtain an average signal and a detail signal of the current mutation signal, and the calculation formulas of the average signal and the detail signal are:

[0054]

[0055]

[0056] Wherein H0 is the low-pass filter coefficient, H1 is the high-pass filter coefficient, C(Z) is the average signal, d(Z) is the detail signal, j and m are non-zero real number parameters, and Z is the length of the current mutation signal;

[0057] The reconstruction algorithm is to insert zero values ​​between two samples of the average signal for stretching, and then pass it through a low-pass filter to obtain a reconstructed low-pass output signal, and then pass the detail signal through a high-pass filter after upsampling to obtain a reconstructed high-pass output signal, and add the reconstructed low-pass output signal and the reconstructed high-pass output signal to obtain the frequency band signal, wherein the frequency band signal calculation formula is:

[0058]

[0059] Wherein X(Z) is the frequency band signal, Z is the length of the current mutation signal, j and m are non-zero real number parameters, H0 is the low-pass filter coefficient, H1 is the high-pass filter coefficient, C(Z) is the average signal, and d(Z) is the detail signal.

[0060] Specifically, the partial discharge signal denoising model initializes the pole symmetric modal decomposition parameters, performs pole symmetric modal decomposition on the time series discharge signal data to obtain a series of intrinsic modal components, calculates the correlation coefficient and peak value of each intrinsic modal component, selects the effective intrinsic modal component according to the correlation coefficient and the peak value, and reconstructs to obtain the denoised discharge signal;

[0061] The vibration signal denoising model decomposes the time series vibration signal into a series of intrinsic mode components according to the time series vibration signal data through the empirical mode decomposition method, determines the noisy mode components through autocorrelation analysis according to the intrinsic mode components, and calculates the initial threshold of each noisy mode component, obtains the optimal stratification threshold through the least mean square algorithm according to the initial threshold, and thresholds the noisy mode components according to the optimal stratification threshold to obtain the denoised vibration signal.

[0062] Specifically, the partial discharge signal recognition model includes the feature extraction unit, the feature selection unit and the classifier. The feature extraction unit first obtains the partial discharge signal vector according to the denoised partial discharge signal data through two-dimensional convolution, and then performs position encoding on the partial discharge signal vector to obtain a coded partial discharge signal vector. The coded partial discharge signal vector is input into a stacked three-layer deep network architecture for multi-head self-attention calculation to obtain a feature vector and the feature vector is transmitted to the feature selection unit. The feature selection unit obtains a vector similarity matrix by calculating the divergence between the feature vectors, adds the divergence between each vector and other vectors according to the similarity matrix to obtain a feature score, and then selects a feature vector subset according to the feature score. Finally, the feature vector subset is fused to obtain a fused feature and the fused feature is transmitted to the classifier. The classifier compares the fused feature with a preset feature classification to obtain the cable insulation aging assessment result.

[0063] Specifically, the sheath current assessment model extracts features from the frequency band signal to obtain waveform features and energy features, constructs a feature vector based on the waveform features and the energy features, normalizes the feature vector to obtain a normalized result, and uses the normalized result as input data of a seven-layer deep convolutional neural network to obtain a status diagnosis result through adaptive learning. The classifier compares the status diagnosis result with a preset result classification to obtain the cable sheath damage assessment result.

[0064] In this embodiment, an integrated sensor is provided to obtain the temperature data of the cable joint, the cable sheath current signal data, and the discharge signal data of the cable. The data processor adds timestamps to the cable sheath current signal data and the discharge signal data, intercepts the current mutation signal of the time-series sheath current signal data through the mutation signal detection model, and obtains the frequency band signal through the decomposition and reconstruction model. The frequency band signal is used as the input data of the sheath current assessment model to obtain the cable sheath damage assessment result through calculation; the time-series discharge signal data is used as the input data of the partial discharge signal denoising model to obtain the denoised discharge signal data, and the cable insulation aging assessment result is calculated through the partial discharge signal recognition model; the temperature data of the cable joint is compared with the preset temperature threshold to obtain the temperature anomaly level result, the cable sheath damage assessment result, the cable insulation aging assessment result and the temperature anomaly level result are stored in the database, and the database is called by the intelligent terminal and displayed on the human-computer interaction interface to realize real-time monitoring of the cable operating conditions.

[0065] Specifically, the vibration assessment model obtains normalized signal data based on the denoised vibration signal data through normalization processing, performs primary feature extraction based on the normalized signal data to obtain vibration duration data, performs secondary feature extraction based on the normalized signal data to obtain time domain feature data, frequency domain feature data and space feature data, uses the vibration duration data as input data of the primary classifier to obtain the initial classification of the denoised vibration signal through calculation, and uses the time domain feature data, the frequency domain feature data and the space feature data as input data of the secondary classifier through calculation according to the initial classification to obtain the vibration type assessment result; wherein, the time domain feature data includes the peak value, average value, effective value, peak factor and kurtosis factor of the signal, the frequency domain feature data includes the center of gravity frequency, mean square frequency and frequency variance, and the spatial feature data is the vibration conduction distance.

[0066] In this embodiment, an integrated sensor is provided to obtain cable well vibration signal data, a data processor adds a timestamp to the cable well vibration signal data to obtain time series vibration signal data, a denoised vibration signal is calculated based on the time series vibration signal data through a vibration signal denoising model, and the denoised vibration signal data is used as input data of a vibration assessment model to obtain a vibration type assessment result through calculation, and the vibration type assessment result is stored in a database, and the database is called by an intelligent terminal and displayed on a human-computer interaction interface, thereby realizing monitoring of whether the cable is damaged by excavation, and timely stopping the destructive behavior and carrying out follow-up work.

[0067] A system for identifying and safely monitoring the working conditions of underground cables, characterized by comprising: a data acquisition module, a data preprocessing module, a data comparison module and a data visualization module;

[0068] The data acquisition module is used to obtain the sheath current signal data, cable joint temperature data, discharge signal data and cable well vibration signal data of the cable through an integrated sensor, and transmit the sheath current signal data, the cable joint temperature data, the discharge signal data and the cable well vibration signal data to a data processor;

[0069] The data preprocessing module is used for the data processor to obtain time-series sheath current signal data, time-series discharge signal data and time-series vibration signal data by adding timestamps according to the sheath current signal data, the discharge signal data and the cable well vibration signal data, intercept and obtain current mutation signals through mutation signal detection model according to the time-series sheath current data, and decompose and reconstruct the current mutation signals through decomposition and reconstruction model to obtain frequency band signals; calculate denoised discharge signal data through partial discharge signal denoising model according to the time-series discharge signal data; calculate denoised vibration signal through vibration signal denoising model according to the time-series vibration signal data;

[0070] The data comparison module is used to compare the cable joint temperature data with a preset temperature threshold to obtain a temperature anomaly grade result; calculate the denoised discharge signal data through a partial discharge signal recognition model to obtain a cable insulation aging assessment result; calculate the denoised vibration signal data through a vibration assessment model to obtain a vibration type assessment result; and use the frequency band signal as input data of a sheath current assessment model to obtain a cable sheath damage assessment result through calculation;

[0071] The data display module is used for the processor to store the temperature anomaly level results, the cable insulation aging assessment results, the vibration type assessment results and the cable sheath damage assessment results into a corresponding list in the database according to the number of the integrated sensor, and the smart terminal calls the list according to the number of the integrated sensor and displays it on the human-computer interaction interface.

[0072] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, a method for identifying and safely monitoring the working conditions of underground cables is implemented.

[0073] A storage medium stores a computer program, characterized in that when the program is executed by a processor, a method for identifying and safely monitoring the working conditions of underground cables is implemented.

[0074] The program code included in the method in the embodiment of the present invention can be transmitted with any appropriate medium, including but not limited to wireless, electric wire, optical cable, etc., or any suitable combination mentioned above. The computer program code for performing the operation of the present invention can be written with one or more programming languages ​​or their combination, and the programming language includes object-oriented programming languages--such as Java, Smalltalk, C++, and also includes conventional procedural programming languages--such as "C" language or similar programming languages. The program code can be executed completely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on the remote computer, or executed completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0075] The above is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still belong to the specification of the technical solution of the present invention.

Claims

1. A method for identifying and safely monitoring underground cable conditions, characterized in that: include: S1: acquiring the sheath current signal data, the cable joint temperature data, the discharge signal data and the cable well vibration signal data of the cable through an integrated sensor, and transmitting the sheath current signal data, the cable joint temperature data, the discharge signal data and the cable well vibration signal data to a data processor; S2: The data processor obtains time-series sheath current signal data, time-series discharge signal data and time-series vibration signal data by adding timestamps according to the sheath current signal data, the discharge signal data and the cable well vibration signal data, obtains the current mutation signal by intercepting the mutation signal detection model according to the time-series sheath current data, and decomposes and reconstructs the current mutation signal by decomposing and reconstructing the model to obtain the frequency band signal; obtains the denoised discharge signal data by calculating the partial discharge signal denoising model according to the time-series discharge signal data; obtains the denoised vibration signal by calculating the vibration signal denoising model according to the time-series vibration signal data; S3: Compare the cable joint temperature data with the preset temperature threshold to obtain the temperature anomaly grade result; calculate the denoised discharge signal data through the partial discharge signal recognition model to obtain the cable insulation aging assessment result; calculate the denoised vibration signal data through the vibration assessment model to obtain the vibration type assessment result; use the frequency band signal as the input data of the sheath current assessment model to obtain the cable sheath damage assessment result; S4: The processor stores the temperature anomaly level result, the cable insulation aging assessment result, the vibration type assessment result and the cable sheath damage assessment result into a corresponding list in a database according to the number of the integrated sensor, and the smart terminal calls the list according to the number of the integrated sensor and displays it on the human-computer interaction interface.

2. The underground cable working condition identification and safety monitoring method according to claim 1 is characterized in that: The mutation signal detection model obtains a first test value and a second test value through a cumulative sum algorithm according to the sequential sheath current data, determines a fault phase identification index according to the first test value and the second test value, determines a time window value according to the identification index, and finally intercepts a current mutation signal according to the time window value, wherein the calculation formulas of the first test value, the second test value and the identification index are: Q1(k)=max(Q1(k-1)+I(k)-p), Q2(k)=max(Q2(k-1)-I(k)-p), Q i (k)=Q1(k)+Q2(k), Where Q1(k) is the first test value at time k, Q2(k) is the second test value at time k, Q i (k) is the identification index, I(k) is the sheath current signal data value at time k, and p is the reference coefficient.

3. The underground cable working condition identification and safety monitoring method according to claim 1 is characterized in that: The decomposition and reconstruction model is to decompose the current mutation signal by wavelet transform algorithm to obtain a decomposition signal, and obtain a frequency band signal by reconstruction algorithm according to the decomposition signal, wherein the wavelet exchange algorithm performs low-pass filtering and high-pass filtering on the current mutation signal to obtain a low-pass output signal and a high-pass output signal, and downsamples the low-pass output signal and the high-pass output signal to obtain an average signal and a detail signal of the current mutation signal, and the calculation formula of the average signal and the detail signal is: Wherein H0 is the low-pass filter coefficient, H1 is the high-pass filter coefficient, C(Z) is the average signal, d(Z) is the detail signal, j and m are non-zero real number parameters, and Z is the length of the current mutation signal; The reconstruction algorithm is to insert zero values ​​between two samples of the average signal for stretching, and then pass it through a low-pass filter to obtain a reconstructed low-pass output signal, and then pass the detail signal through a high-pass filter after upsampling to obtain a reconstructed high-pass output signal, and add the reconstructed low-pass output signal and the reconstructed high-pass output signal to obtain the frequency band signal, wherein the frequency band signal calculation formula is: Wherein X(Z) is the frequency band signal, Z is the length of the current mutation signal, j and m are non-zero real number parameters, H0 is the low-pass filter coefficient, H1 is the high-pass filter coefficient, C(Z) is the average signal, and d(Z) is the detail signal.

4. The underground cable working condition identification and safety monitoring method according to claim 1 is characterized in that: The partial discharge signal denoising model initializes the pole symmetric modal decomposition parameters, performs pole symmetric modal decomposition on the time series discharge signal data to obtain a series of intrinsic modal components, calculates the correlation coefficient and peak value of each intrinsic modal component, selects effective intrinsic modal components according to the correlation coefficient and the peak value, and reconstructs them to obtain the denoised discharge signal; The vibration signal denoising model decomposes the time series vibration signal into a series of intrinsic mode components according to the time series vibration signal data through the empirical mode decomposition method, determines the noisy mode components through autocorrelation analysis according to the intrinsic mode components, and calculates the initial threshold of each noisy mode component, obtains the optimal stratification threshold through the least mean square algorithm according to the initial threshold, and thresholds the noisy mode components according to the optimal stratification threshold to obtain the denoised vibration signal.

5. The underground cable working condition identification and safety monitoring method according to claim 1 is characterized in that: The partial discharge signal recognition model includes the feature extraction unit, the feature selection unit and the classifier. The feature extraction unit first obtains the partial discharge signal vector through two-dimensional convolution according to the denoised partial discharge signal data, and then performs position encoding on the partial discharge signal vector to obtain the encoded partial discharge signal vector. The encoded partial discharge signal vector is input into a stacked three-layer deep network architecture for multi-head self-attention calculation to obtain the feature vector and the feature vector is transmitted to the feature selection unit. The feature selection unit obtains the vector similarity matrix by calculating the divergence between the feature vectors, adds the divergence between each vector and other vectors according to the similarity matrix to obtain the feature score, and then selects the feature vector subset according to the feature score. Finally, the feature vector subset is fused to obtain the fused feature and the fused feature is transmitted to the classifier. The classifier compares the fused feature with the preset feature classification to obtain the cable insulation aging assessment result.

6. The underground cable working condition identification and safety monitoring method according to claim 1 is characterized in that: The sheath current assessment model extracts features from the frequency band signal to obtain waveform features and energy features, constructs a feature vector based on the waveform features and the energy features, normalizes the feature vector to obtain a normalized result, uses the normalized result as input data for a seven-layer deep convolutional neural network, and obtains a state diagnosis result through adaptive learning. The classifier compares the state diagnosis result with a preset result classification to obtain the cable sheath damage assessment result.

7. The underground cable working condition identification and safety monitoring method according to claim 1 is characterized in that: The vibration assessment model obtains normalized signal data based on the denoised vibration signal data through normalization processing, performs primary feature extraction based on the normalized signal data to obtain vibration duration data, performs secondary feature extraction based on the normalized signal data to obtain time domain feature data, frequency domain feature data and space feature data, uses the vibration duration data as input data of the primary classifier to obtain the initial classification of the denoised vibration signal through calculation, and uses the time domain feature data, the frequency domain feature data and the space feature data as input data of the secondary classifier through calculation according to the initial classification to obtain the vibration type assessment result; wherein the time domain feature data includes the peak value, average value, effective value, peak factor and kurtosis factor of the signal, the frequency domain feature data includes the center of gravity frequency, mean square frequency and frequency variance, and the space feature data is the vibration conduction distance.

8. A system for identifying and safely monitoring the working condition of underground cables, used to execute the method for identifying and safely monitoring the working condition of underground cables as claimed in any one of claims 1 to 7, characterized in that: include: Data acquisition module, data preprocessing module, data comparison module and data visualization module; The data acquisition module is used to obtain the sheath current signal data, cable joint temperature data, discharge signal data and cable well vibration signal data of the cable through an integrated sensor, and transmit the sheath current signal data, the cable joint temperature data, the discharge signal data and the cable well vibration signal data to a data processor; The data preprocessing module is used for the data processor to obtain time-series sheath current signal data, time-series discharge signal data and time-series vibration signal data by adding timestamps according to the sheath current signal data, the discharge signal data and the cable well vibration signal data, intercept and obtain current mutation signals through mutation signal detection model according to the time-series sheath current data, and decompose and reconstruct the current mutation signals through decomposition and reconstruction model to obtain frequency band signals; calculate denoised discharge signal data through partial discharge signal denoising model according to the time-series discharge signal data; calculate denoised vibration signal through vibration signal denoising model according to the time-series vibration signal data; The data comparison module is used to compare the cable joint temperature data with a preset temperature threshold to obtain a temperature anomaly grade result; calculate the denoised discharge signal data through a partial discharge signal recognition model to obtain a cable insulation aging assessment result; calculate the denoised vibration signal data through a vibration assessment model to obtain a vibration type assessment result; and use the frequency band signal as input data of a sheath current assessment model to obtain a cable sheath damage assessment result through calculation; The data display module is used for the processor to store the temperature anomaly level results, the cable insulation aging assessment results, the vibration type assessment results and the cable sheath damage assessment results into a corresponding list in the database according to the number of the integrated sensor, and the smart terminal calls the list according to the number of the integrated sensor and displays it on the human-computer interaction interface.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the underground cable working condition identification and safety monitoring method as described in any one of claims 1-8 is implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the underground cable working condition identification and safety monitoring method as described in any one of claims 1 to 8 is implemented.

Citation Information

Patent Citations

  • Nonlinear fault detection method based on semi-supervised manifold learning

    CN103234767A

  • GIS mechanical fault diagnosis method based on mechanical state signal analysis

    CN109635428A

  • 10kV single core cable early state identification method based on deep convolutional neural network

    CN110068748A

  • Cable external force damage early warning and diagnosing device based on vibration signal monitoring

    CN110443968A

  • Data noise reduction method and system for bridge structure monitoring

    CN110598615A