Fault section binary positioning method based on self-checking learning

Abstract

The invention belongs to the technical field of automation of a power system, and particularly discloses a fault section binary positioning method based on self-checking learning, which comprises the following steps: after a fault occurs, an acquisition terminal uploads an actual measurement signal to a master station, firstly, wavelet transform is utilized to complete time sequence synchronization of a waveform and polarity checking of a detection device; and a twin neural network is introduced to complete similarity judgment of upstream and downstream transient zero-sequence currents of a fault point, fault section positioning is realized, and finally, on the basis of a system network topology, a binary search method is used to quickly determine a minimum fault section. The method can effectively eliminate interference caused by operation errors of transmission time delay of communication equipment and reverse connection of a current transformer, adaptive learning of the twin neural network can reveal potential relations of data, the fault detection capability under the conditions of different grounding positions, grounding moments, transition resistances and the like is improved, a fast search algorithm is combined, and the fault detection efficiency is improved. The generalization of the neural network can be fully reflected, the calculation amount of the master station can be reduced, and the positioning efficiency is improved.

Description

technical field [0001] The present application belongs to the technical field of power system automation, and relates to a method for segment location of single-phase grounding faults in medium-voltage distribution networks. And quickly locate the faulty section. Background technique [0002] Electricity has always been the energy that people rely on for survival. In order to ensure the normal life of people, it is necessary to strengthen the construction of power grid projects and provide more reliable power guarantees. Therefore, when a fault occurs in the distribution network, rapid and accurate troubleshooting is still an important task that needs to be completed. Among them, the medium-voltage distribution network is widely used in urban and rural power distribution in my country. It is a bridge connecting terminal power users and large power grids, and is directly related to the power quality and power supply reliability of users. Among all the faults, the single-pha...

AI Technical Summary

Problems solved by technology

[0005] In view of this, the purpose of the present invention is to propose a method based on current transformers in the case of complex networks, that is, there are a large number of nodes to be detected with unknown operating states in the distribution network, and there are blind spots for fault location caused by various factors. (CT) The twin neural network (SNN) of power frequency polarity verification realizes the identification of abnormal points or pseudo similar points, and at the same time combines the binary search method (BS) to overcome the search efficiency brought about by the sequential polling judgment of the centralized management of the main station low problem

Images