Power distribution network fault classification method based on adaptive neuro-fuzzy inference system

Abstract

The invention relates to a power distribution network fault classification method based on the adaptive neuro-fuzzy inference system. The method is an improved method based on the adaptive neuro-fuzzy inference system. According to several frequently-occurring short circuit fault types of the power distribution network, a hierarchical based adaptive neuro-fuzzy inference system is constructed in the method, various short circuit faults are simulated based on a simulation software and the fault phase current is collected as the training sample data, and the blended learning algorithm is used for training the constructed hierarchical adaptive neuro-fuzzy inference system to determine the parameter in the system; the hierarchical adaptive neuro-fuzzy inference system with the determined parameter can be used for discriminating the fault types of the power distribution network. A lot of simulation data validations indicate that the classification method provided by the invention has a higher classification and identification accuracy, and has a better robustness on the variation of the fault points and a strong adaptability on the variation of the network topology.

Description

technical field [0001] The invention relates to the technical field of power systems, in particular to a distribution network fault classification method based on an adaptive neuro-fuzzy reasoning system. Background technique [0002] With the continuous improvement of modern power users' requirements for power supply continuity and reliability and the increasing emphasis of power grid enterprises on user satisfaction, how to analyze the cause of the fault, select the fault feeder, isolate the fault section and quickly recover after the power grid fails Power supply is becoming increasingly important. Therefore, the research on fault diagnosis for post-fault analysis and providing auxiliary decision-making for operators has become more and more a focus of research. The research on fault classification, as the basis of post-fault analysis of distribution network such as line selection, location, and protection action evaluation, plays a very important role for operators to a...

AI Technical Summary

Problems solved by technology

[0003] The Adaptive Neuro-Fuzzy Inference System (ANFIS) was proposed by Jangles Roger et al. in 1991. One of the biggest weaknesses of the fuzzy model in the prior art is that it does not have the ability of learning and self-adaptation. , specifically manifested in the difficulty of adjusting the rules and corresponding membership functions

The neural network can generate corresponding mapping rules through learning according to the training sample set, but these mapping rules are usually hidden in the network in the form of connection weights, and it is difficult to analyze the relationship between specific weights and such mapping rules.

Images