A high-voltage circuit breaker mechanical fault diagnosis method

The invention relates to a mechanical fault diagnosis method for a high-voltage circuit breaker. Firstly, a high-voltage circuit breaker vibration signal is acquired through an acquisition device; secondly, CEEMDAN decomposition is performed on the vibration signal, and a time-frequency matrix with equal bandwidth is constructed by adopting a frequency band division method based on the combinationof Hilbert transformation and band-pass filtering; time periods are divided to construct a block energy matrix, and time-frequency entropies are extracted from the normalized energy matrixes in the time domain direction and the frequency domain direction respectively; thirdly, normalization processing is conducted on the vibration signals of all the frequency bands through a normal state cumulative distribution function (NCDF), and the singular entropy of the time-frequency matrixes of all the blocks is extracted; and finally, an integrated extreme learning machine is used as a classifier foridentifying the mechanica