High resistance ground fault detection method of distribution network based on wavelet transform and neural network

A technology of high-resistance ground fault and neural network, which is applied in the direction of fault location, fault detection according to conductor type, and electrical measurement, can solve threats to the stable operation of the power system and personal safety, reduce the reliability of power grid power supply, and equipment protection leapfrog trips, etc. problem, to achieve the effect of increasing detection reliability and efficiency, good generalization ability, and avoiding catastrophic forgetting

Inactive Publication Date: 2020-11-27
FUZHOU UNIV
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the free air, the grounding impedance of arc grounding changes greatly, causing the existing protection to start and recover repeatedly, which may cause the protection of adjacent lines and equipment to trip over the level, and also cause the overvoltage of the whole system, and then damage the electrical equipment. Expand the accident and reduce the power supply reliability of the power grid
Long-term operation of the line with a fault may cause the temperature of the fault point to be too high, causing a fire and causing permanent damage to electrical equipment, and the step voltage around the grounding point can reach several thousand volts, seriously threatening the stable operation of the power system and personal safety

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
  • High resistance ground fault detection method of distribution network based on wavelet transform and neural network
  • High resistance ground fault detection method of distribution network based on wavelet transform and neural network
  • High resistance ground fault detection method of distribution network based on wavelet transform and neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0033] Please refer to figure 1 , the present invention provides a kind of distribution network high-impedance ground fault detection method based on wavelet transform and neural network, comprising the following steps:

[0034] Step S1: collecting the current signal of the distribution network line to be detected;

[0035] Step S2: adopt db4 wavelet as mother wavelet, carry out discrete wavelet transform to line current signal, and obtain reconstruction waveform;

[0036] Step S3: the neural network parameter of evolution is set;

[0037] Step S4: using the reconstructed waveform as the input of the evolved neural network, calculating the Manhattan distance between the input and the kth neuron of the evolution layer, the degree of activation of the kth neuron and the error between the output and the expected value;

[0038] Step S5: If the activatio...

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 high-resistance-ground fault detection method based on wavelet transform and neural network for power distribution network. When the high resistance grounding fault occurs on the power distribution network, failure current is small, arcs are often accompanied, and ordinary zero sequence current protection is difficult to be detected; according to the high-resistance-ground fault detection method based on the wavelet transform and the neural network for the power distribution network, evolutionary neural network is used for improving a traditional detection method; and the evolutionary neural network is an intelligent system based on a dynamic connection structure, and topology structure can be adjusted to incorporate new information through incremental learning.According to the high-resistance-ground fault detection method based on the wavelet transform and the neural network for the power distribution network, trouble signals are processed by discrete wavelet transform and inputted into the evolutionary neural network to detect the high-resistance-ground fault of the power distribution network.

Description

technical field [0001] The invention relates to detection of grounding faults in distribution networks, in particular to a detection method for high-resistance grounding faults in distribution networks based on wavelet transform and neural network. Background technique [0002] High-impedance ground fault (HIF) refers to the ground fault that occurs when power lines pass through conductive media such as roads, soil, branches or cement buildings. It may occur at various voltage levels and affect the normal operation of the distribution network. Due to the high-impedance characteristics of non-metallic conductive media, when a high-resistance ground fault occurs in the distribution network, the fault current is very small and often accompanied by arcing, which is difficult to detect with ordinary zero-sequence current protection. Among the high-resistance ground faults in low-current grounding systems, especially resonant grounding systems, arcing ground faults account for a l...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G01R31/08
CPCG01R31/086G01R31/088Y04S10/52
Inventor 苏文聪朱星宇金涛
Owner FUZHOU UNIV
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