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

Fault line selection method for distribution network based on adaptive neural fuzzy inference system

A distribution network fault, neuro-fuzzy technology, applied in fault location, fault detection according to conductor type, measurement of electricity, etc. Problems such as poor generalization ability

Active Publication Date: 2019-11-22
STATE GRID HENAN ELECTRIC POWER ELECTRIC POWER SCI RES INST +2
View PDF7 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The accuracy rate of single line selection criterion is not high, the generalization ability is poor, and it is difficult to adapt to different neutral point grounding methods and network structure changes

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 line selection method for distribution network based on adaptive neural fuzzy inference system
  • Fault line selection method for distribution network based on adaptive neural fuzzy inference system
  • Fault line selection method for distribution network based on adaptive neural fuzzy inference system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0108] In the training set, constructs such as Figure 6 In the distribution network model shown, the overhead lines adopt the Beryllon model, the feeder lengths are 1km, 3km, 7km, 15km, 20km, 25km, 35km, 40km, 44km, and 50km, and the model parameters are r 1 = 0.17Ω / km, r 0 = 0.23Ω / km, L 1 =1.21mH / km, L 0 =5.48mH / km, C 1 =9.7pF / km, C 0 =6pF / km, a single-phase grounding fault occurs at an interval of 4.5° between the fault phase voltage 0°~90°, the transition resistance of the grounding point is respectively 5Ω, 20Ω, 100Ω, 500Ω, 1000Ω, 1400Ω, 2000Ω on each line Set up 6 fault points respectively. In the test set, change the line parameters and simulation conditions, and the overhead line model parameter is r 1 = 0.33Ω / km, r 0 =1.041Ω / km, L 1 =1.31mH / km, L 0 =3.96mH / km, C 1 =7pF / km, C 0 =4pF / km, the cable line model parameters are: r 1 = 0.0791Ω / km, r 0 = 0.2273Ω / km, L 1 =0.2642mH / km, L 0 =0.9263mH / km, C 1 =0.373uF / km, C 0 =0.166uF / km, a single-phase grounding ...

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 a fault line selection method for a distribution network based on an adaptive neural fuzzy inference system. According to the method, a waveform correlation quantity, an attenuated DC component, and an energy spectrum entropy quantity of a line after fault occurrence are extracted by using wavelet packet transformation and a fault feature matrix is generated; special normalization of the fault feature matrix is carried out to eliminate influences of criterion failures under different fault conditions; with an adaptive neural fuzzy inference system, a fuzzy logic rule and a membership function parameter in the fuzzy theory are learned, so that the subjectivity of manual selection of the membership function and weight coefficient is avoided; and according to the multi-criteria fusion result, the advantage complementation between multiple criteria is realized. The method is not affected by the changes in the network structure of the distribution network and the transition resistance of the ground point, so that the reliability and safety of the system operation are enhanced substantially.

Description

technical field [0001] The invention belongs to the application field of distribution network fault line selection, and in particular relates to a distribution network fault line selection method based on an adaptive neuro-fuzzy reasoning system. Background technique [0002] As a key link in the power system that directly connects users and power distribution, the distribution network's safety, stability and operational reliability are directly related to the stable production of enterprises and the harmony and stability of society. Field operation experience shows that the probability of single-phase ground faults in the distribution network is the highest, accounting for more than 80% of the total electrical faults in the system. When a single-phase ground fault occurs in the system, because the current at the fault point is small, it does not affect the normal power supply to the load, and it is generally allowed to continue running for 1 to 2 hours. But at this time, t...

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
CPCG01R31/086G01R31/088
Inventor 冯光袁嘉玮王磊吴桐马建伟王鹏徐铭铭陈明焦在滨
Owner STATE GRID HENAN ELECTRIC POWER ELECTRIC POWER SCI RES INST
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com