Artificial neural network-based fault positioning method of ultrahigh-voltage DC power transmission line

An artificial neural network and ultra-high voltage direct current technology, applied in the direction of fault location, measurement of electricity, measurement of electrical variables, etc., can solve problems such as poor positioning accuracy and influence of line parameter accuracy, and achieve strong ability to withstand transition resistance and high precision Effect

Pending Publication Date: 2019-01-18
ELECTRIC POWER RESEARCH INSTITUTE OF STATE GRID SHANDONG ELECTRIC POWER COMPANY +1
View PDF9 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It has low requirements on sampling rate and high reliability, but is affected by the accuracy of

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
  • Artificial neural network-based fault positioning method of ultrahigh-voltage DC power transmission line
  • Artificial neural network-based fault positioning method of ultrahigh-voltage DC power transmission line
  • Artificial neural network-based fault positioning method of ultrahigh-voltage DC power transmission line

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The present invention mainly adopts the head amplitude ratio of voltage traveling wave and current traveling wave line mode components in different scales, takes the UHV DC transmission line fault location method based on artificial neural network as the core, supplemented by the global geometric mean optimal method Carry out fault distance measurement, the content of the invention is described further now, the fault location process of the present invention is as follows figure 2 shown.

[0032] 1. When the transmission line fails, the current signal and voltage signal of the line are respectively obtained from the measurement points at both ends of the transmission line. When the transmission line fails, the current signal and voltage of the line are respectively obtained from the measurement points at both ends of the transmission line Signal, the simulation sampling frequency is 100kHz.

[0033] 2. At present, UHV DC transmission lines mostly operate in bipolar mo...

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 discloses an artificial neural network-based fault positioning method of an ultrahigh-voltage DC power transmission line. The artificial neural network-based fault positioning method comprises the following steps of acquiring a fault voltage signal and a current signal of measurement points at two sides of a DC line; decoupling to obtain linear mode components; performing wavelet transformation on the linear mode components to obtain different scale signals, and solving amplitude ratio of an initial wave head; training a neural network by taking the amplitude ratio of the initialwave heads of the linear mode components of the obtained voltage signal and the obtained current signal as an input sample of the neural network and fault distance as an output sample set to form a fault distance-measurement neural network, inputting a test sample of the amplitude ratio of the initial wave heads of the linear mode components of the voltage signal and the current signal into the trained neural network to obtain fault distance; and performing result optimization by a global geometric mean optimal method. By the artificial neural network-based fault positioning method, the faultdistance measurement of the power transmission line can be achieved, and the artificial neural network-based fault positioning method has the advantages of relatively high accuracy and high transition resistance endurability.

Description

technical field [0001] The invention relates to a fault location method of an extra-high voltage direct current transmission line based on an artificial neural network, and belongs to the technical field of power system line protection. Background technique [0002] UHV DC transmission has the advantages of large transmission capacity, long power transmission distance, and narrow line corridor, so it has obvious advantages in long-distance power transmission. my country's vast territory and the reverse distribution of energy and load determine that UHV DC transmission technology has broad application prospects in my country. The DC transmission line is the component with the highest failure rate in the DC system. Since the DC transmission line is generally long, the terrain along the line is complex, and the environment is harsh, it is extremely difficult to accurately find the fault point through line inspection, which seriously affects the recovery of permanent faults. ti...

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
CPCG01R31/088Y04S10/52
Inventor 李宽苏欣施雨刘萌李玉敦张健磊尹欢欢赵斌超王宏黄秉青张婉婕杨超王昕张国辉麻常辉
Owner ELECTRIC POWER RESEARCH INSTITUTE OF STATE GRID SHANDONG ELECTRIC POWER COMPANY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products