[go: up one dir, main page]

CN119293608A - A medium voltage grounding fault intelligent diagnosis system and control method thereof - Google Patents

A medium voltage grounding fault intelligent diagnosis system and control method thereof Download PDF

Info

Publication number
CN119293608A
CN119293608A CN202411403222.8A CN202411403222A CN119293608A CN 119293608 A CN119293608 A CN 119293608A CN 202411403222 A CN202411403222 A CN 202411403222A CN 119293608 A CN119293608 A CN 119293608A
Authority
CN
China
Prior art keywords
fault
module
signal
diagnosis
alarm
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202411403222.8A
Other languages
Chinese (zh)
Inventor
胡海燕
曹纯青
陈莳
刘浩
周鹏
贾鹏
顾朦朦
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangsu Tianyan Information Industry Co ltd
Original Assignee
Jiangsu Tianyan Information Industry Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jiangsu Tianyan Information Industry Co ltd filed Critical Jiangsu Tianyan Information Industry Co ltd
Priority to CN202411403222.8A priority Critical patent/CN119293608A/en
Publication of CN119293608A publication Critical patent/CN119293608A/en
Pending legal-status Critical Current

Links

Classifications

    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R19/00—Arrangements for measuring currents or voltages or for indicating presence or sign thereof
    • G01R19/0092—Arrangements for measuring currents or voltages or for indicating presence or sign thereof measuring current only
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/08—Locating faults in cables, transmission lines, or networks
    • G01R31/081—Locating faults in cables, transmission lines, or networks according to type of conductors
    • G01R31/086—Locating faults in cables, transmission lines, or networks according to type of conductors in power transmission or distribution networks, i.e. with interconnected conductors
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/08—Locating faults in cables, transmission lines, or networks
    • G01R31/088—Aspects of digital computing
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/50—Testing of electric apparatus, lines, cables or components for short-circuits, continuity, leakage current or incorrect line connections
    • G01R31/52—Testing for short-circuits, leakage current or ground faults
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G06F18/2131—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on a transform domain processing, e.g. wavelet transform
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/243—Classification techniques relating to the number of classes
    • G06F18/24317—Piecewise classification, i.e. whereby each classification requires several discriminant rules
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/08—Feature extraction
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/12—Classification; Matching
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
    • Y04S10/52—Outage or fault management, e.g. fault detection or location

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Computing Systems (AREA)
  • Medical Informatics (AREA)
  • Power Engineering (AREA)
  • Testing Of Short-Circuits, Discontinuities, Leakage, Or Incorrect Line Connections (AREA)

Abstract

本发明涉及中压接地故障智能诊断技术领域，尤其为一种中压接地故障智能诊断系统及其控制方法，包括：数据采集模块、信号处理模块、特征提取模块、故障诊断模块、显示与报警模块；数据采集模块用于采集中压配电线路中的暂态电流信号，数据采集模块采用罗柯夫斯基线圈，配备温度补偿功能；信号处理模块用于通过多分辨率小波变换对采集的暂态电流信号进行分解，且信号处理模块用于提取信号的时频特征；特征提取模块用于计算各分解尺度下的能量矩Qj，以表征故障信号在不同频带中的能量分布；本发明中，通过小波变换提取暂态信号的时频特征，结合最小二乘多级支持向量机，能够有效识别复杂环境下的高阻接地故障，提高了诊断的精度和可靠性。

The present invention relates to the technical field of intelligent diagnosis of medium-voltage grounding faults, and in particular to an intelligent diagnosis system for medium-voltage grounding faults and a control method thereof, comprising: a data acquisition module, a signal processing module, a feature extraction module, a fault diagnosis module, and a display and alarm module; the data acquisition module is used to acquire transient current signals in a medium-voltage distribution line, and the data acquisition module adopts a Rogowski coil and is equipped with a temperature compensation function; the signal processing module is used to decompose the acquired transient current signals through multi-resolution wavelet transform, and the signal processing module is used to extract the time-frequency characteristics of the signals; the feature extraction module is used to calculate the energy moment Q j under each decomposition scale to characterize the energy distribution of the fault signal in different frequency bands; in the present invention, the time-frequency characteristics of the transient signal are extracted through wavelet transform, and combined with a least squares multi-level support vector machine, the high-resistance grounding fault in a complex environment can be effectively identified, and the accuracy and reliability of the diagnosis are improved.

Description

Intelligent medium-voltage grounding fault diagnosis system and control method thereof
Technical Field
The invention relates to the technical field of medium-voltage grounding fault intelligent diagnosis, in particular to a medium-voltage grounding fault intelligent diagnosis system and a control method thereof.
Background
The intelligent medium-voltage ground fault diagnosis system is an advanced monitoring and analysis system specially designed for detecting, positioning and diagnosing the ground fault in a medium-voltage power distribution network, and the system is generally integrated with various sensors, signal processing technologies, data processing algorithms and intelligent diagnosis tools so as to improve the accuracy and response speed of fault detection;
The medium-voltage direct-current power distribution network is widely applied to the scenes such as photovoltaic energy access, however, in actual operation, a medium-voltage circuit may be affected by environmental factors, such as increase of transition resistance, so that high-resistance ground faults occur, the detection precision of the traditional fault diagnosis method for the high-resistance ground faults is not high, and particularly, fine fault identification is difficult to realize under various complex environmental conditions, so that the intelligent diagnosis system for the medium-voltage ground faults and the control method thereof are provided for the problems.
Disclosure of Invention
The invention aims to provide a medium-voltage grounding fault intelligent diagnosis system and a control method thereof, which aim to solve the problems that a medium-voltage circuit is possibly influenced by environmental factors, such as increase of transition resistance, so that high-resistance grounding faults occur, the detection precision of the traditional fault diagnosis method for the high-resistance grounding faults is not high, and particularly, the precise fault identification is difficult to realize under various complex environmental conditions.
In order to achieve the above purpose, the present invention provides the following technical solutions:
the intelligent medium-voltage grounding fault diagnosis system comprises a data acquisition module, a signal processing module, a characteristic extraction module, a fault diagnosis module and a display and alarm module;
The data acquisition module is used for acquiring transient current signals in the medium-voltage distribution line, adopts a rogowski coil and is provided with a temperature compensation function;
The signal processing module is used for decomposing the acquired transient current signals through multi-resolution wavelet transformation, and extracting time-frequency characteristics of the signals;
the feature extraction module is used for calculating energy moment Q j under each decomposition scale so as to represent the energy distribution of fault signals in different frequency bands;
the fault diagnosis module adopts a least square multistage support vector machine, takes the extracted time-frequency characteristics as input, performs classification diagnosis of high-resistance ground faults and outputs fault diagnosis results;
the display and alarm module is used for displaying fault diagnosis results in real time and triggering alarm when detecting high-resistance ground faults, and the alarm module comprises a plurality of alarm modes of sound, light, short messages or APP pushing.
The invention is further optimized, wherein the signal processing module uses orthogonal wavelet transformation to carry out multi-scale decomposition on the transient current signal, the decomposition layer number is J, and the signal obtained under each decomposition scale comprises a detail signal and a discrete smooth approximation value.
As a further optimization of the invention, the feature extraction module calculates the energy moment Q j at each decomposition scale by:
Wherein M is the number of sampling points, D j [ n ] is the discrete detail signal under j decomposition scale, gamma j is the corresponding weight factor, and Deltat is the sampling time interval.
The invention further optimizes the content, wherein a least square multistage support vector machine in the fault diagnosis module adopts a kernel function K (x i,xj) and performs parameter optimization on the kernel function K by a Lagrange optimization method, and the optimization targets are as follows:
where w is the weight vector, C is the penalty parameter, and ζ i is the relaxation factor.
The invention further optimizes the content, wherein the fault diagnosis module trains the least square multistage support vector machine by utilizing historical fault data, and updates model parameters thereof through real-time signals so as to realize online learning and dynamic fault diagnosis.
The display and alarm module comprises an alarm threshold setting unit, and when the predicted fault occurrence probability exceeds a preset threshold, the system automatically triggers an alarm signal.
As a further optimization of the invention, the method comprises the following steps:
s1, signal acquisition, namely acquiring transient current signals in a medium-voltage distribution line in real time through a data acquisition module;
S2, signal processing, namely performing multi-scale decomposition on the acquired transient current signal by utilizing orthogonal wavelet transformation to acquire a detail signal and a discrete smooth approximation value under each decomposition scale;
s3, extracting the time-frequency characteristics of fault signals by calculating energy moment under each decomposition scale;
s4, fault diagnosis, namely inputting the extracted time-frequency characteristics into a least square multistage support vector machine to perform fault classification diagnosis, and obtaining probability or classification result of fault occurrence;
And S5, displaying and alarming results, namely displaying and triggering an alarm in real time according to the fault diagnosis results.
As a further optimization of the invention, in the feature extraction step, the calculated energy moment Q j characterizes the energy distribution of the signal in each frequency band and is used for identifying high-resistance ground faults in combination with the nonlinear features of the signal.
The invention further optimizes the content, wherein the fault diagnosis step adjusts parameters of the support vector machine through a Lagrange optimization method to realize the fine classification diagnosis of different fault types.
As the content of further optimization of the invention, the system utilizes the data acquired in real time to perform online learning and model updating, thereby ensuring the timeliness and accuracy of fault diagnosis.
Compared with the prior art, the invention has the beneficial effects that:
1. According to the invention, the time-frequency characteristics of transient signals are extracted through wavelet transformation, and a least square multistage support vector machine is combined, so that high-resistance ground faults in a complex environment can be effectively identified, the accuracy and reliability of diagnosis are improved, and the parameters of the support vector machine are optimized by adopting a least square method and a Lagrange optimization technology, so that a diagnosis system can maintain high-efficiency fault identification capability under various environmental conditions, and a real-time signal processing and online learning mechanism can rapidly respond and process new fault signals, thereby ensuring that the power distribution network can timely and accurately diagnose and alarm when faults occur, and ensuring the safe operation of the system;
2. According to the invention, through integrating the multi-resolution wavelet transformation and the least square multi-stage support vector machine, the high-resistance grounding fault signal in the medium-voltage direct-current power distribution network is effectively extracted and analyzed, and the time-frequency characteristics of the fault signal can be captured by the system by utilizing the multi-scale analysis capability of the wavelet transformation, so that the accurate diagnosis of complex nonlinear faults is realized;
3. According to the invention, the system can adjust the diagnosis model in real time, dynamically adapt to the continuously-changing fault mode and operation condition, ensure that the high-efficiency fault identification capability can be maintained under different environments, reduce the downtime of the power system, reduce the operation and maintenance cost and prolong the service life of equipment.
Drawings
Fig. 1 is a flowchart of an intelligent diagnosis system for medium voltage ground fault and a control method thereof.
Detailed Description
Referring to fig. 1, the present invention provides a technical solution:
the intelligent medium-voltage grounding fault diagnosis system comprises a data acquisition module, a signal processing module, a characteristic extraction module, a fault diagnosis module and a display and alarm module;
The data acquisition module is used for acquiring transient current signals in the medium-voltage distribution line, adopts a rogowski coil and is provided with a temperature compensation function;
The signal processing module is used for decomposing the acquired transient current signals through multi-resolution wavelet transformation, and extracting time-frequency characteristics of the signals;
the feature extraction module is used for calculating energy moment Q j under each decomposition scale so as to represent the energy distribution of fault signals in different frequency bands;
the fault diagnosis module adopts a least square multistage support vector machine, takes the extracted time-frequency characteristics as input, performs classification diagnosis of high-resistance ground faults and outputs fault diagnosis results;
The display and alarm module is used for displaying fault diagnosis results in real time and triggering alarm when high-resistance ground faults are detected, the alarm module comprises a plurality of alarm modes of sound, light, short messages or APP pushing, and through the cooperative work of the modules, the system can realize rapid and accurate diagnosis of the medium-voltage ground faults and ensure safe operation of an electric power system.
According to the technical scheme further implemented by the scheme, the signal processing module carries out multi-scale decomposition on the transient current signal by using orthogonal wavelet transformation, the decomposition layer number is J, the signals obtained under each decomposition scale comprise detail signals and discrete smooth approximation values, the orthogonal wavelet transformation provides multi-scale analysis on fault signals, fault characteristics in different frequency bands can be effectively captured, and the accuracy and reliability of diagnosis are enhanced;
As a further implementation of the solution, the feature extraction module calculates the energy moment Q j under each decomposition scale according to the following formula:
Wherein M is the number of sampling points, D j n is the discrete detail signal under j decomposition scale, gamma j is the corresponding weight factor, deltat is the sampling time interval, and the calculation of energy moment can quantify the energy distribution of the signal in each frequency band, thereby providing refined fault feature extraction and supporting more accurate fault diagnosis;
As a further implementation technical scheme of the scheme, a least square multistage support vector machine in the fault diagnosis module adopts a kernel function K (x i,xj), and performs parameter optimization on the kernel function K by a Lagrange optimization method, wherein the optimization targets are as follows:
Wherein w is a weight vector, C is a punishment parameter, xi i is a relaxation factor, and the system can optimize the decision boundary of a support vector machine through a Lagrangian optimization method, so that the accuracy and the robustness of fault classification are ensured;
According to the technical scheme further implemented by the scheme, the fault diagnosis module trains the least square multistage support vector machine by utilizing historical fault data, model parameters of the least square multistage support vector machine are updated through real-time signals, online learning and dynamic fault diagnosis are achieved, and the system can adapt to continuously-changing operation environments and improves the instantaneity and accuracy of fault diagnosis through online learning and model updating;
According to the technical scheme further implemented by the scheme, the display and alarm module comprises an alarm threshold setting unit, when the predicted fault occurrence probability exceeds a preset threshold, the system automatically triggers an alarm signal, and the set alarm threshold can ensure that an alarm is sent out in time when a high-probability fault occurs, so that the system downtime is reduced and the accident risk is reduced;
example 1
The method is characterized in that a medium-voltage direct-current power distribution network is subjected to high-resistance grounding fault risks due to photovoltaic energy access, and particularly when environmental conditions change, the traditional fault detection method is difficult to accurately identify the faults, so that the intelligent medium-voltage grounding fault diagnosis system based on the method is implemented for improving the accuracy and timeliness of fault detection;
The implementation steps are as follows:
The method comprises the following steps of S1, signal acquisition, namely installing a high-precision current sensor at a key node of the power distribution network, wherein the high-precision current sensor is used for acquiring transient current signals in real time, and a data acquisition module transmits the signals to a signal processing module;
S2, performing multi-scale decomposition on the acquired transient current signal by using orthogonal wavelet transformation, and obtaining a detail signal and a discrete smooth approximation value under each decomposition scale by assuming that the signal is decomposed into 4 scales, wherein high-frequency and low-frequency characteristics in the signal are effectively separated through the process;
S3, extracting features, namely calculating energy moments Q j for each decomposition scale, wherein the energy moments Q j reflect the energy distribution of signals in each frequency band, and the extracted features show that significant energy concentration exists at the 3 rd decomposition scale, so that high-resistance ground faults possibly exist;
S4, fault diagnosis, namely inputting the extracted time-frequency characteristics into a least square multistage support vector machine for classification diagnosis, accurately identifying high-resistance ground faults by a system through an optimized kernel function and weight, and giving out a fault probability of 85%;
s5, displaying and alarming results, namely immediately triggering an alarm signal by a display and alarm module and displaying a fault position and possible fault types on a monitoring interface to inform operation and maintenance personnel to process because the fault probability exceeds a 70% alarm threshold preset by the system;
as a result, through the implementation, the system successfully detects and diagnoses the high-resistance ground fault in the medium-voltage distribution network, ensures that the fault is identified and processed in an early stage, and avoids more serious power accidents, thereby proving the high efficiency and accuracy of the invention in the detection of the high-resistance ground fault.
Example two
In another project, a medium-voltage direct current power distribution network is adopted in one industrial park to provide power support for a plurality of production workshops, transient current fluctuation often occurs in the power distribution network due to high-frequency start-stop operation of production equipment, and the risk of high-resistance ground faults is increased.
The implementation steps are as follows:
S1, signal acquisition, wherein an installed sensor network covers key power nodes of the whole industrial park, transient current signals of all the nodes are acquired in real time, and the signals are collected to a central processing unit by a data acquisition module;
s2, signal processing, namely carrying out 6-layer decomposition on the acquired signals by adopting orthogonal wavelet transformation, successfully extracting signal details containing high-frequency and low-frequency characteristics by a system through decomposition, and particularly focusing on abnormal signals appearing in decomposing the 5 th layer and the 6 th layer;
S3, extracting characteristics, namely calculating an energy moment Q j for each signal of the decomposition scale, wherein in the analysis process, the energy moment Q j of the 5 th layer is found to be obviously higher than that of other layers, which implies that the possibility of high-resistance ground faults exists in the frequency band;
s4, fault diagnosis, namely inputting the extracted characteristic of the energy moment Q j into a least square multistage support vector machine to perform fault diagnosis, wherein the system has the capability of classifying complex fault types after online learning, and a diagnosis result shows that a high-resistance ground fault exists on an electric power line of a specific workshop, and the fault probability is 92%;
S5, result display and alarm, namely, according to the diagnosis result, the system gives an alarm in a control room, and highlights the specific position and type of the fault on a monitoring screen, so that maintenance personnel can rapidly position and solve the fault according to the system prompt, and the production continuity is ensured;
In practical application, the intelligent diagnosis system successfully identifies and diagnoses the high-resistance ground fault in the complex environment, ensures the stability of the power distribution network of the industrial park, and further proves the applicability and reliability of the intelligent diagnosis system in various environmental conditions.
The principles and embodiments of the present invention have been described herein with reference to specific examples, the description of which is intended only to facilitate an understanding of the method of the present invention and its core ideas. The foregoing is merely illustrative of the preferred embodiments of the invention, and it will be appreciated that numerous modifications, adaptations and variations of the invention can be made by those skilled in the art without departing from the principles of the invention, and that other features and advantages of the invention can be combined in any suitable manner, and that no improvement in the design or design of the invention is intended to be applied directly to other applications.

Claims (10)

1.一种中压接地故障智能诊断系统，其特征在于，包括：数据采集模块、信号处理模块、特征提取模块、故障诊断模块、显示与报警模块；1. A medium voltage ground fault intelligent diagnosis system, characterized by comprising: a data acquisition module, a signal processing module, a feature extraction module, a fault diagnosis module, a display and alarm module; 所述数据采集模块用于采集中压配电线路中的暂态电流信号，所述数据采集模块采用罗柯夫斯基线圈，所述配备温度补偿功能；The data acquisition module is used to collect transient current signals in the medium voltage distribution line. The data acquisition module adopts a Rogowski coil and is equipped with a temperature compensation function. 所述信号处理模块用于通过多分辨率小波变换对采集的暂态电流信号进行分解，且信号处理模块用于提取信号的时频特征；The signal processing module is used to decompose the collected transient current signal through multi-resolution wavelet transform, and the signal processing module is used to extract the time-frequency characteristics of the signal; 所述特征提取模块用于计算各分解尺度下的能量矩Qj，以表征故障信号在不同频带中的能量分布；The feature extraction module is used to calculate the energy moment Q j at each decomposition scale to characterize the energy distribution of the fault signal in different frequency bands; 所述故障诊断模块，采用最小二乘多级支持向量机，将提取的时频特征作为输入，进行高阻接地故障的分类诊断，输出故障诊断结果；The fault diagnosis module adopts the least squares multi-level support vector machine, takes the extracted time-frequency features as input, performs classification diagnosis of high-resistance grounding faults, and outputs fault diagnosis results; 所述显示与报警模块，用于实时显示故障诊断结果，并在检测到高阻接地故障时触发报警，所述报警模块包括声音、光线、短信或APP推送多种报警方式。The display and alarm module is used to display the fault diagnosis results in real time and trigger an alarm when a high-resistance grounding fault is detected. The alarm module includes multiple alarm modes such as sound, light, text message or APP push. 2.根据权利要求1所述的一种中压接地故障智能诊断系统，其特征在于：所述信号处理模块使用正交小波变换对暂态电流信号进行多尺度分解，分解层数为J，各分解尺度下获得的信号包括细节信号和离散平滑逼近值。2. According to claim 1, a medium-voltage grounding fault intelligent diagnosis system is characterized in that: the signal processing module uses orthogonal wavelet transform to perform multi-scale decomposition on the transient current signal, the decomposition level is J, and the signal obtained at each decomposition scale includes a detail signal and a discrete smooth approximation value. 3.根据权利要求1所述的一种中压接地故障智能诊断系统，其特征在于：所述特征提取模块通过下式计算每个分解尺度下的能量矩Qj：3. A medium voltage ground fault intelligent diagnosis system according to claim 1, characterized in that: the feature extraction module calculates the energy moment Q j at each decomposition scale by the following formula: 式中，M为采样点数量，Dj[n]为第j个分解尺度下的离散细节信号，γj为对应的权重因子，△t为采样时间间隔。Where M is the number of sampling points, Dj [n] is the discrete detail signal at the jth decomposition scale, γj is the corresponding weight factor, and △t is the sampling time interval. 4.根据权利要求1所述的一种中压接地故障智能诊断系统，其特征在于：所述故障诊断模块中的最小二乘多级支持向量机采用核函数K(xi,xj)，并通过拉格朗日优化方法对其进行参数优化，优化目标为：4. A medium voltage ground fault intelligent diagnosis system according to claim 1, characterized in that: the least squares multi-level support vector machine in the fault diagnosis module adopts a kernel function K( xi , xj ), and optimizes its parameters by Lagrangian optimization method, and the optimization target is: 式中，w为权重向量，C为惩罚参数，ξi为松弛因子。Where w is the weight vector, C is the penalty parameter, and ξ i is the relaxation factor. 5.根据权利要求1所述的一种中压接地故障智能诊断系统，其特征在于：所述故障诊断模块利用历史故障数据对最小二乘多级支持向量机进行训练，并通过实时信号更新其模型参数，实现在线学习和动态故障诊断。5. A medium voltage grounding fault intelligent diagnosis system according to claim 1, characterized in that: the fault diagnosis module uses historical fault data to train the least squares multi-level support vector machine, and updates its model parameters through real-time signals to achieve online learning and dynamic fault diagnosis. 6.根据权利要求1所述的一种中压接地故障智能诊断系统，其特征在于：所述显示与报警模块包括一个报警阈值设定单元，当预测的故障发生概率超过预设阈值时，系统自动触发报警信号。6. A medium voltage ground fault intelligent diagnosis system according to claim 1, characterized in that: the display and alarm module includes an alarm threshold setting unit, and when the predicted probability of fault occurrence exceeds a preset threshold, the system automatically triggers an alarm signal. 7.基于权利要求1-6任一项所述的一种中压接地故障智能诊断系统的控制方法，其特征在于：包括以下步骤：7. A control method for a medium voltage ground fault intelligent diagnosis system according to any one of claims 1 to 6, characterized in that it comprises the following steps: S1：信号采集：通过数据采集模块实时采集中压配电线路中的暂态电流信号；S1: Signal acquisition: The data acquisition module is used to collect transient current signals in the medium voltage distribution line in real time; S2：信号处理：利用正交小波变换对采集的暂态电流信号进行多尺度分解，获取各分解尺度下的细节信号和离散平滑逼近值；S2: Signal processing: Use orthogonal wavelet transform to perform multi-scale decomposition on the collected transient current signal to obtain the detail signal and discrete smooth approximation value at each decomposition scale; S3：特征提取：通过计算各分解尺度下的能量矩，提取故障信号的时频特征；S3: Feature extraction: extract the time-frequency characteristics of the fault signal by calculating the energy moment at each decomposition scale; S4：故障诊断：将提取的时频特征输入最小二乘多级支持向量机进行故障分类诊断，得到故障发生的概率或分类结果；S4: Fault diagnosis: The extracted time-frequency features are input into the least squares multi-level support vector machine for fault classification diagnosis to obtain the probability of fault occurrence or classification results; S5：结果显示与报警：根据故障诊断结果实时显示并触发报警。S5: Result display and alarm: Real-time display and alarm triggering according to the fault diagnosis results. 8.根据权利要求7所述的一种中压接地故障智能诊断系统的控制方法，其特征在于：所述特征提取步骤中，计算的能量矩Qj表征了信号在各频带中的能量分布，并结合信号的非线性特征用于高阻接地故障的识别。8. The control method of a medium voltage ground fault intelligent diagnosis system according to claim 7 is characterized in that: in the feature extraction step, the calculated energy moment Qj characterizes the energy distribution of the signal in each frequency band, and is combined with the nonlinear characteristics of the signal for identifying high resistance ground faults. 9.根据权利要求7所述的一种中压接地故障智能诊断系统的控制方法，其特征在于：所述故障诊断步骤通过拉格朗日优化方法调整支持向量机的参数，实现对不同故障类型的精细化分类诊断。9. The control method of a medium voltage ground fault intelligent diagnosis system according to claim 7 is characterized in that: the fault diagnosis step adjusts the parameters of the support vector machine through the Lagrangian optimization method to achieve refined classification diagnosis of different fault types. 10.根据权利要求7所述的一种中压接地故障智能诊断系统的控制方法，其特征在于：系统利用实时采集的数据进行在线学习和模型更新，确保故障诊断的及时性和准确性。10. The control method of a medium voltage ground fault intelligent diagnosis system according to claim 7, characterized in that the system uses real-time collected data to perform online learning and model updating to ensure the timeliness and accuracy of fault diagnosis.
CN202411403222.8A 2024-10-09 2024-10-09 A medium voltage grounding fault intelligent diagnosis system and control method thereof Pending CN119293608A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202411403222.8A CN119293608A (en) 2024-10-09 2024-10-09 A medium voltage grounding fault intelligent diagnosis system and control method thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202411403222.8A CN119293608A (en) 2024-10-09 2024-10-09 A medium voltage grounding fault intelligent diagnosis system and control method thereof

Publications (1)

Publication Number Publication Date
CN119293608A true CN119293608A (en) 2025-01-10

Family

ID=94152356

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202411403222.8A Pending CN119293608A (en) 2024-10-09 2024-10-09 A medium voltage grounding fault intelligent diagnosis system and control method thereof

Country Status (1)

Country Link
CN (1) CN119293608A (en)

Similar Documents

Publication Publication Date Title
CN109396954B (en) Embedded axis system abnormality intelligent measurement and information push-delivery apparatus
CN109977916A (en) A kind of Gases Dissolved in Transformer Oil on-line monitoring system based on embedded platform
CN119150189B (en) A method and system for detecting and analyzing power data anomaly based on big data
CN114371353A (en) Power equipment abnormity monitoring method and system based on voiceprint recognition
CN119224489B (en) Power distribution network fault detection system based on photovoltaic new energy
CN119165297B (en) Fault judgment method of oilfield distribution network based on line voltage amplitude variation
CN118861662A (en) A fault detection method for oil-immersed transformer based on gas above oil surface
CN118228126A (en) Water and electricity unit fault early warning method and system based on WSVD and SVDD
CN118155660A (en) Hydropower unit audio signal abnormality detection method based on generation countermeasure network
CN119293713A (en) A method for anomaly detection and automatic positioning based on data curve
CN105722129A (en) Wireless sensing network event detection method and system based on FSAX-MARKOV model
CN119199358A (en) Substation power equipment monitoring system and method based on Dianhong IoT operating system
CN118677113A (en) Power cabinet monitoring system and method based on AI model
CN119044634A (en) Capacitor state detection and analysis method and system
CN119293608A (en) A medium voltage grounding fault intelligent diagnosis system and control method thereof
CN118011115A (en) Online lightning arrester monitoring system and method based on hardware capture mechanism
CN117367589A (en) All-weather auxiliary temperature measurement system for substation main equipment based on AI technology
CN116796261A (en) Closed switch equipment mechanical characteristic prediction method based on artificial intelligence
CN111224468B (en) Photovoltaic equipment safe operation and maintenance platform based on cloud computing
CN118972235B (en) Power communication network fault diagnosis method, system and device based on deep learning
CN120316692B (en) A fault diagnosis method and system based on electrical box parameter prediction
CN112051493A (en) Hidden danger type identification method and device for power distribution network equipment
CN119322302B (en) A method for online monitoring of voltage transformer
CN119669836B (en) Permanent magnet generator air gap eccentricity fault identification method and system
CN115343569B (en) A high voltage cable fault diagnosis method and system based on leakage current monitoring

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination