High-voltage circuit breaker fault diagnosis method based on adaptive grey correlation analysis

Abstract

The invention discloses a high-voltage circuit breaker fault diagnosis method based on adaptive grey correlation analysis, which comprises the following steps: step A, acquiring multiple groups of fault current signals of switching-on and switching-off coils of high-voltage circuit breakers of various fault types, and respectively performing Hilbert-Huang transform, extracting current and time characteristic values to form a fault characteristic sequence, and performing FCM clustering on all fault characteristic sequences to obtain a typical fault characteristic sequence of each fault type; B,acquiring an operation current signal of a closing and opening coil when the high-voltage circuit breaker operates, performing Hilbert-Huang transform on the operation current signal, and extractingcurrent and time characteristic values to form a to-be-diagnosed characteristic sequence; and C, performing gray correlation analysis on the to-be-diagnosed feature sequence and the typical fault feature sequence of each fault type so that the gray correlation degree of the to-be-diagnosed feature sequence and the typical fault feature sequence of each fault type is obtained, and thus the fault type of the to-be-diagnosed feature sequence is obtained.

Description

technical field [0001] The invention belongs to the field of circuit breaker fault diagnosis, in particular to a high voltage circuit breaker fault diagnosis method based on self-adaptive gray relational analysis. Background technique [0002] With the development of social economy, the scale of power grid is getting larger and larger, and people put forward higher requirements for the safe operation of power system. As an important switchgear in the power system, the high-voltage circuit breaker plays the role of control and protection. Its good operation status is the key to the normal and safe operation of the substation and the power system. Therefore, identifying the fault state of the high-voltage circuit breaker in time can avoid equipment damage or system disconnection, and improve the reliability of power grid operation. [0003] According to relevant data, the maintenance cost of high-voltage circuit breakers accounts for more than 50% of the substation, and 60% o...

AI Technical Summary

Problems solved by technology

[0004] In terms of fault identification of high-voltage circuit breakers, researches at home and abroad are increasing day by day: some use wavelet packet decomposition algorithm to process closing vibration signals, and then establish neural network models to realize fault diagnosis; some use EMD (empirical mode decomposition) to decompose high-voltage Calculate the energy entropy of each IMF from the acoustic wave signal of the circuit breaker, and finally use statistics to realize fault identification; some first analyze the current signal of the opening and closing coil through the decentralized envelope method, and then construct a vector machine to realize fault identification; some use gray correlation Analyze and establish the fault reliability, and then use the Monte Carlo simulation method to simulate the reliability to realize fault diagnosis, but the discrimination of the traditional gray relational degree is not enough, and there is still a problem of algorithm efficiency

Although these methods can effectively identify the fault state of the circuit breaker, the feature extraction method is relatively complicated, or the diagnosis results are limited by the sample size, which limits the universality of the system application.

Images