Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Fault branch identification method of three-terminal direct-current power-transmission-line discrete wavelet transformation and support vector machine

A DC transmission line, discrete wavelet transform technology, applied in the direction of measuring electrical variables, fault location, fault detection according to conductor type, etc., can solve problems such as the failure of traveling wave distance measurement, large communication interference, dead zone at the beginning and end of the line, etc.

Active Publication Date: 2017-01-04
KUNMING UNIV OF SCI & TECH
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Conventional ranging is greatly affected by the operation mode and the accuracy of line parameters. The accuracy of traveling wave ranging is high, but it depends on the accurate time synchronization at both ends of the line, which is greatly affected by communication interference, and there will be dead zones at the beginning and end of the line.
When the fault occurs at the beginning and end of the line, due to the fast transmission speed of the traveling wave, the traveling wave detection and acquisition module in the traveling wave ranging Sometimes or when the communication at both ends of the line fails, the traveling wave distance measuring device cannot measure distance normally; when the traveling wave distance measuring device itself fails, the traveling wave distance measuring device will also lose its function

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Fault branch identification method of three-terminal direct-current power-transmission-line discrete wavelet transformation and support vector machine
  • Fault branch identification method of three-terminal direct-current power-transmission-line discrete wavelet transformation and support vector machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] Embodiment 1: Three-terminal direct current transmission line such as figure 1 shown. Its line parameters are as follows: the length l of the three overhead DC lines 1 , l 2 and l 3 The order is 100km, 30km and 50km. Now assume that the MT branch is 45km away from the M terminal and a positive line fault occurs, and the transition resistance is 50Ω.

[0028] According to the first step, in the three-terminal DC transmission line, use the simulation data to form historical samples: set the fault location in the MT branch, the NT branch and the QT branch respectively, the step size is 1km, and the transition resistance is set to 0Ω and 10Ω respectively and 100Ω, the time window length is 1ms, and the fault current data is obtained; according to the second step, the db4 wavelet decomposition is performed on the traveling wave of the measured terminal current, and the wavelet transform coefficient under the second scale is selected as the input attribute of SVM1, and th...

Embodiment 2

[0029] Embodiment 2: Three-terminal direct current transmission line such as figure 1 shown. Its line parameters are as follows: the length l of the three overhead DC lines 1 , l 2 and l 3 The order is 100km, 30km and 50km. Now suppose that the NT branch is 126km away from the M terminal and a positive line fault occurs, and the transition resistance is 10Ω.

[0030] According to the first step, in the three-terminal DC transmission line, use the simulation data to form historical samples: set the fault location in the MT branch, the NT branch and the QT branch respectively, the step size is 1km, and the transition resistance is set to 0Ω and 10Ω respectively and 100Ω, the time window length is 1ms, and the fault current data is obtained; according to the second step, the db4 wavelet decomposition is performed on the traveling wave of the measured terminal current, and the wavelet transform coefficient under the second scale is selected as the input attribute of SVM1, and ...

Embodiment 3

[0031] Embodiment 3: Three-terminal direct current transmission line such as figure 1 shown. Its line parameters are as follows: the length l of the three overhead DC lines 1 , l 2 and l 3 The order is 100km, 30km and 50km. Assume now that the positive line fault occurs 134km away from the M terminal of the QT branch, and the transition resistance is 50Ω.

[0032]According to the first step, in the three-terminal DC transmission line, use the simulation data to form historical samples: set the fault location in the MT branch, the NT branch and the QT branch respectively, the step size is 1km, and the transition resistance is set to 0Ω and 10Ω respectively and 100Ω, the time window length is 1ms, and the fault current data is obtained; according to the second step, the db4 wavelet decomposition is performed on the traveling wave of the measured terminal current, and the wavelet transform coefficient under the second scale is selected as the input attribute of SVM1, and the ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a fault branch identification method of three-terminal direct-current power-transmission-line discrete wavelet transformation and a support vector machine and belongs to the electric power system fault range finding technology field. The method is characterized by setting fault positions in a three-terminal direct-current MT branch, an NT branch and a QT branch, setting a step length to be 1km and transition resistors to be 0omega, 10omega and 100omega respectively; secondly, defining a time window length to be 1ms, carrying out db4 wavelet decomposition on a measurement terminal current traveling wave, selecting a wavelet transformation coefficient under a second scale as an input attribute of the support vector machine SVM, establishing a SVM fault branch discrimination model, training the model, and defining that SVM output 1 is a QT branch fault, output 0 is a MT branch fault and output -1 is an NT branch fault; and finally, when a three-terminal direct-current line is generated, carrying out db4 wavelet decomposition on the current traveling wave and inputting the SVM, and according to an output result of the SVM, realizing determination of the fault branch.

Description

technical field [0001] The invention relates to a three-terminal direct current transmission line discrete wavelet transform and a fault branch identification method of a support vector machine, which belongs to the technical field of power system fault distance measurement. Background technique [0002] Multi-terminal flexible DC transmission is composed of three or more converter stations and the DC lines connecting them. In terms of economy, more DC transmission systems at both ends can save transmission corridors, reduce the number of high-cost converter stations, and effectively reduce investment costs and operating costs; in terms of flexibility, one or some converter stations can be made The flow station can be operated as a rectifier or as an inverter, and the power flow distribution can be adjusted through power reversal. Researching the fault location technology applicable to faulty branch identification of three-terminal DC transmission lines can effectively impr...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G01R31/08
CPCG01R31/085G01R31/088
Inventor 束洪春姚艳萍田鑫萃
Owner KUNMING UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products