CN112446430A - Fault identification method for direct-current power transmission system - Google Patents

Fault identification method for direct-current power transmission system Download PDF

Info

Publication number
CN112446430A
CN112446430A CN202011364505.8A CN202011364505A CN112446430A CN 112446430 A CN112446430 A CN 112446430A CN 202011364505 A CN202011364505 A CN 202011364505A CN 112446430 A CN112446430 A CN 112446430A
Authority
CN
China
Prior art keywords
transmission system
fault
training
neural network
imf
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
CN202011364505.8A
Other languages
Chinese (zh)
Inventor
邢超
高敬业
奚鑫泽
李胜男
刘明群
何鑫
徐志
卢佳
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.)
Electric Power Research Institute of Yunnan Power Grid Co Ltd
Original Assignee
Electric Power Research Institute of Yunnan Power Grid 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 Electric Power Research Institute of Yunnan Power Grid Co Ltd filed Critical Electric Power Research Institute of Yunnan Power Grid Co Ltd
Priority to CN202011364505.8A priority Critical patent/CN112446430A/en
Publication of CN112446430A publication Critical patent/CN112446430A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Physiology (AREA)
  • Supply And Distribution Of Alternating Current (AREA)

Abstract

The application provides a fault identification method for a direct current power transmission system, which is used for identifying faults of the direct current power transmission system based on a genetic neural network algorithm. On one hand, the problems of low recognition rate and low calculation speed in the fault recognition process of the direct current transmission system can be solved. On the other hand, the repeatability of the computer is fully utilized, and the fault identification rate and the operation speed are improved. The method comprises the steps of establishing a high-voltage direct-current power transmission system model by utilizing PSCAD/EMTDC simulation software, simulating a large number of different types of faults, obtaining enough test sets and training sets, training and testing a genetic neural network model on the basis, and verifying effectiveness, feasibility and reliability of an FEEMD algorithm in fault identification application of a direct-current power transmission system.

Description

Fault identification method for direct-current power transmission system
Technical Field
The application relates to the technical field of relay protection research of direct current transmission systems, in particular to a fault identification method of a direct current transmission system.
Background
The direct current transmission system has the advantages of large transmission capacity, long transmission distance and the like, so that the direct current transmission system has obvious advantages in the aspect of long-distance electric energy transmission. However, the direct current overhead line is generally long, the terrain along the line is complex, the damping of the direct current transmission system is small, and when the line has a short-circuit fault, the fault current can rise to a high level in a short time, so that the internal equipment of the current exchange station is greatly influenced. Therefore, the method has important significance for rapidly and effectively distinguishing the direct current transmission line faults and other faults such as lightning stroke and the like.
The direct current transmission line is used as an element with the highest fault rate in the high-voltage direct current transmission system, and the direct current transmission line needs to be quickly diagnosed firstly. Machine learning algorithms such as neural networks and support vector machines are often applied to fault identification and classification of the direct-current power transmission system at present, but the fault identification rate in the direct-current power transmission system is low, the speed is low, and sometimes more manual intervention is needed.
Disclosure of Invention
The application provides a fault identification method for a direct current transmission system, which aims to solve the problem of low fault identification rate.
The application provides a fault identification method for a direct current transmission system, which comprises the following steps:
s1: acquiring a fault current signal;
s2: decomposing the fault current signal by adopting a FEEMD algorithm to obtain a plurality of IMF components;
s3: selecting IMF1、IMF2And IMF3The components form a plurality of genetic neural network input characteristic quantities;
s4: randomly selecting a plurality of input characteristic quantities to form a training set;
s5: training a genetic neural network model by using the training set;
s6: randomly selecting a plurality of input characteristic quantities to form a test set;
s7: testing the trained genetic neural network model by using the test set to obtain a test result;
s8: and comparing and analyzing the test result and the actual result to obtain a fault identification result.
Optionally, a large number of simulation is performed on different fault types of the dc power transmission system according to the PSCAD/EMTDC electromagnetic transient simulation software, so as to obtain the fault transient current signal.
Optionally, the training set includes a plurality of training samples, the test set includes a plurality of test samples, and the number of the plurality of training samples is greater than the number of the plurality of test samples.
Optionally, the training set and the test set are avoided to be identical.
Optionally, the step of training the genetic neural network model by using the training set further includes training the genetic neural network model until the convergence curve meets the precision requirement, and then the training is completed.
According to the technical scheme, the method for identifying the fault of the direct current power transmission system comprises the steps of obtaining a fault current signal; decomposing the fault current signal by adopting a FEEMD algorithm to obtain a plurality of IMF components; selecting IMF1、IMF2And IMF3The components form a plurality of genetic neural network input characteristic quantities; randomly selecting a plurality of input characteristic quantities to form a training set; training a genetic neural network model by using the training set; randomly selecting a plurality of input characteristic quantities to form a test set; using the test set to train the completed postTesting the genetic neural network model to obtain a test result; and comparing and analyzing the test result and the actual result to obtain a fault identification result. On one hand, the problems of low recognition rate and low calculation speed in the fault recognition process of the direct current transmission system can be solved. On the other hand, the repeatability of the computer is fully utilized, and the fault identification rate and the operation speed are improved. The method comprises the steps of establishing a high-voltage direct-current power transmission system model by utilizing PSCAD/EMTDC simulation software, simulating a large number of different types of faults, obtaining enough test sets and training sets, training and testing a genetic neural network model on the basis, and verifying effectiveness, feasibility and reliability of an FEEMD algorithm in fault identification application of a direct-current power transmission system.
Drawings
In order to more clearly explain the technical solution of the present application, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious to those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flow chart of a method for identifying a fault in a dc power transmission system.
Detailed Description
Reference will now be made in detail to embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following examples do not represent all embodiments consistent with the present application. But merely as exemplifications of systems and methods consistent with certain aspects of the application, as recited in the claims.
Referring to fig. 1, fig. 1 is a flow chart of a method for identifying a fault of a dc power transmission system. The application provides a fault identification method for a direct current transmission system, which comprises the following steps:
s1: acquiring a fault current signal;
s2: decomposing the fault current signal by adopting a FEEMD algorithm to obtain a plurality of IMF components;
s3: selecting IMF1、IMF2And IMF3The components form a plurality of genetic neural network input characteristic quantities;
s4: randomly selecting a plurality of input characteristic quantities to form a training set;
s5: training a genetic neural network model by using the training set;
s6: randomly selecting a plurality of input characteristic quantities to form a test set;
s7: testing the trained genetic neural network model by using the test set to obtain a test result;
s8: and comparing and analyzing the test result and the actual result to obtain a fault identification result.
Furthermore, the rapid ensemble empirical mode decomposition (FEEMD) is used as a time-frequency analysis method, and has good effect on processing nonlinear and non-stationary signals; when different types of faults occur in the direct current transmission system, fault transient current signals are extracted by using the rectification side detection device of the high-voltage direct current transmission system, wherein the transient current signals are composed of different component signals. The method comprises the steps of inputting a fault transient current signal, decomposing the fault transient current signal by adopting a FEEMD algorithm to obtain a plurality of Intrinsic Mode Functions (IMFs) including the IMFs1、IMF2、IMF3The n IMF components are equal, the generalization capability of the neural network is considered, and the IMF is selected1、IMF2、IMF3The three signal components are used as input characteristic quantities of the genetic neural network model. Specifically, because the first three IMF components contain abundant fault information and are more responsive to different fault types, the IMF is selected1、IMF2、IMF3The three components constitute the input characteristic quantity of the genetic neural network.
Further, IMF1、IMF2、IMF3The three signal components constitute a vector. When different types of faults occur in the direct current transmission system, for example, the direct current transmission line is in earth fault, lightning fault and the inverter is in commutation failure, the generated fault transient current signals are different, namely the obtained IMF1、IMF2、IMF3Three signalsThe vectors of component components are also different. The formed vector can be used as an input sample of the genetic neural network algorithm, the sample is input into a genetic neural network algorithm program, and a value representing the fault type of the input sample can be output through program calculation. Further, step S4 includes performing a large number of simulations on different fault types occurring at different fault locations of the dc power transmission system; and randomly selecting a plurality of input characteristic quantities as a training set, and training the genetic neural network model until the convergence curve meets the precision requirement and then finishing the training. In order to improve the prediction precision and generalization capability, a plurality of input characteristic quantities are randomly selected as a test set, the trained genetic neural network model is tested by using the test set different from the training set to obtain a test result, and the test result is compared with the real fault type for analysis. The analysis includes classifying the states, such as normal states, line faults, and other faults. Specifically, the training set includes a plurality of training samples, the test set includes a plurality of test samples, and the number of the plurality of training samples is greater than the number of the plurality of test samples. The training set is to reflect the different fault types as comprehensively as possible. And judging whether the fault recognition genetic neural network model has practical value or not, wherein the test set is required to avoid the training set so as to comprehensively test and evaluate the generalization capability of the fault recognition genetic neural network model.
The application provides a fault identification method for a direct current power transmission system, which is used for identifying faults of the direct current power transmission system based on a genetic neural network algorithm to obtain a test result and compare and analyze the test result with a real fault type. The method comprises acquiring a fault current signal; decomposing the fault current signal by adopting a FEEMD algorithm to obtain a plurality of IMF components; selecting IMF1、IMF2And IMF3The components form a plurality of genetic neural network input characteristic quantities; randomly selecting a plurality of input characteristic quantities to form a training set; training a genetic neural network model by using the training set; randomly selecting a plurality of input characteristic quantities to form a test set; using the test set to train the trained genetic neural networkTesting the model to obtain a test result; and comparing and analyzing the test result and the actual result to obtain a fault identification result. On one hand, the problems of low recognition rate and low calculation speed in the fault recognition process of the direct current transmission system can be solved. On the other hand, the repeatability of the computer is fully utilized, and the fault identification rate and the operation speed are improved. The method comprises the steps of establishing a high-voltage direct-current power transmission system model by utilizing PSCAD/EMTDC simulation software, simulating a large number of different types of faults, obtaining enough test sets and training sets, training and testing a genetic neural network model on the basis, and verifying effectiveness, feasibility and reliability of an FEEMD algorithm in fault identification application of a direct-current power transmission system. Compared with the existing method, the method has the characteristics of high fault recognition rate, high operation speed, easiness in obtaining the optimal solution, high convergence speed and the like.
The embodiments provided in the present application are only a few examples of the general concept of the present application, and do not limit the scope of the present application. Any other embodiments extended according to the scheme of the present application without inventive efforts will be within the scope of protection of the present application for a person skilled in the art.

Claims (5)

1. A fault identification method for a direct current transmission system is characterized by comprising the following steps:
s1: acquiring a fault current signal;
s2: decomposing the fault current signal by adopting a FEEMD algorithm to obtain a plurality of IMF components;
s3: selecting IMF1、IMF2And IMF3The components form a plurality of genetic neural network input characteristic quantities;
s4: randomly selecting a plurality of input characteristic quantities to form a training set;
s5: training a genetic neural network model by using the training set;
s6: randomly selecting a plurality of input characteristic quantities to form a test set;
s7: testing the trained genetic neural network model by using the test set to obtain a test result;
s8: and comparing and analyzing the test result and the actual result to obtain a fault identification result.
2. The method according to claim 1, wherein the fault transient current signal is obtained by performing a plurality of simulations on different fault types of the dc power transmission system according to PSCAD/EMTDC electromagnetic transient simulation software.
3. The method according to claim 1, wherein the training set comprises a plurality of training samples, the test set comprises a plurality of test samples, and the number of the training samples is greater than the number of the test samples.
4. A method according to claim 1, characterized by avoiding that said training set and said test set are identical.
5. The method according to claim 1, wherein the step of training the genetic neural network model using the training set further comprises training the genetic neural network model until the convergence curve meets the accuracy requirement.
CN202011364505.8A 2020-11-27 2020-11-27 Fault identification method for direct-current power transmission system Pending CN112446430A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011364505.8A CN112446430A (en) 2020-11-27 2020-11-27 Fault identification method for direct-current power transmission system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011364505.8A CN112446430A (en) 2020-11-27 2020-11-27 Fault identification method for direct-current power transmission system

Publications (1)

Publication Number Publication Date
CN112446430A true CN112446430A (en) 2021-03-05

Family

ID=74738955

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011364505.8A Pending CN112446430A (en) 2020-11-27 2020-11-27 Fault identification method for direct-current power transmission system

Country Status (1)

Country Link
CN (1) CN112446430A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113392589A (en) * 2021-06-30 2021-09-14 云南电网有限责任公司电力科学研究院 High-voltage direct-current converter station fault analysis method and system based on convolutional neural network

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2015158198A1 (en) * 2014-04-17 2015-10-22 北京泰乐德信息技术有限公司 Fault recognition method and system based on neural network self-learning
CN106443310A (en) * 2016-11-22 2017-02-22 国网四川省电力公司广安供电公司 Transformer fault detection method based on SOM (Self Organizing Map) neural network
CN110470937A (en) * 2019-07-15 2019-11-19 昆明理工大学 Based on FEEMD Sample Entropy+neural network HVDC transmission system line fault and commutation failure method for diagnosing faults
CN110501603A (en) * 2019-07-24 2019-11-26 昆明理工大学 Utilize the forever rich direct-current commutation failure method for diagnosing faults of EMD and neural network
CN110598170A (en) * 2019-08-06 2019-12-20 天津大学 Data prediction method based on FEEMD decomposition time sequence
CN110849625A (en) * 2019-10-10 2020-02-28 淮阴工学院 Bearing fault diagnosis method under variable working condition based on mixed entropy and joint distribution adaptation

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2015158198A1 (en) * 2014-04-17 2015-10-22 北京泰乐德信息技术有限公司 Fault recognition method and system based on neural network self-learning
CN106443310A (en) * 2016-11-22 2017-02-22 国网四川省电力公司广安供电公司 Transformer fault detection method based on SOM (Self Organizing Map) neural network
CN110470937A (en) * 2019-07-15 2019-11-19 昆明理工大学 Based on FEEMD Sample Entropy+neural network HVDC transmission system line fault and commutation failure method for diagnosing faults
CN110501603A (en) * 2019-07-24 2019-11-26 昆明理工大学 Utilize the forever rich direct-current commutation failure method for diagnosing faults of EMD and neural network
CN110598170A (en) * 2019-08-06 2019-12-20 天津大学 Data prediction method based on FEEMD decomposition time sequence
CN110849625A (en) * 2019-10-10 2020-02-28 淮阴工学院 Bearing fault diagnosis method under variable working condition based on mixed entropy and joint distribution adaptation

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113392589A (en) * 2021-06-30 2021-09-14 云南电网有限责任公司电力科学研究院 High-voltage direct-current converter station fault analysis method and system based on convolutional neural network
CN113392589B (en) * 2021-06-30 2022-09-27 云南电网有限责任公司电力科学研究院 High-voltage direct-current converter station fault analysis method and system based on convolutional neural network

Similar Documents

Publication Publication Date Title
Mohammadi et al. A fast fault detection and identification approach in power distribution systems
CN110829417B (en) Electric power system transient stability prediction method based on LSTM double-structure model
CN105203876A (en) Transformer on-line monitoring state assessment method utilizing support vector machine and correlation analysis
CN108304567A (en) High-tension transformer regime mode identifies and data classification method and system
CN110726898B (en) Power distribution network fault type identification method
CN109444667A (en) Power distribution network initial failure classification method and device based on convolutional neural networks
CN105467971A (en) Electric power secondary equipment monitoring system and method
CN114298175A (en) Power equipment state monitoring and fault early warning method and system based on edge calculation
CN107798283A (en) A kind of neural network failure multi classifier based on the acyclic figure of decision-directed
CN113358993B (en) Online fault diagnosis method and system for multi-level converter IGBT
CN114091549A (en) Equipment fault diagnosis method based on deep residual error network
CN112446430A (en) Fault identification method for direct-current power transmission system
CN117668751B (en) High-low voltage power system fault diagnosis method and device
CN110361609A (en) Extra-high voltage equipment monitors system and method
Gao et al. Accurate identification partial discharge of cable termination for high-speed trains based on wavelet transform and convolutional neural network
CN113610119A (en) Method for identifying power transmission line developmental fault based on convolutional neural network
CN111898446A (en) Single-phase earth fault studying and judging method based on multi-algorithm normalization analysis
CN117420385A (en) High-voltage direct-current transmission line fault identification method based on convolution
CN116502149A (en) Low-voltage power distribution network user-transformation relation identification method and system based on current characteristic conduction
CN113392589B (en) High-voltage direct-current converter station fault analysis method and system based on convolutional neural network
CN115712865A (en) Power grid fault identification method and system based on neural network model and computer readable storage medium
CN115130505A (en) FOCS fault diagnosis method based on improved residual shrinkage network
CN114252725A (en) HHT and ResNet 18-based single-phase earth fault type comprehensive identification method
Lima et al. A modified negative selection algorithm applied in the diagnosis of voltage disturbances in distribution electrical systems
CN112598152A (en) High-voltage circuit breaker fault diagnosis method based on improved affine propagation clustering

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