High-voltage circuit breaker fault diagnosis method and system based on voiceprint signal

The invention belongs to the field of high-voltage circuit breaker fault detection, and particularly relates to a voiceprint signal-based high-voltage circuit breaker fault diagnosis method and system, and the method can comprehensively describe the energy distribution of each frequency band through an obtained energy feature vector, integrates the sharp sudden change of a time domain waveform and the energy concentration characteristics of a frequency domain, and achieves the fault diagnosis of a high-voltage circuit breaker. Therefore, multiple features of the complex fault are described more completely, and the accuracy of fault identification is improved. According to the invention, based on the excellent feature expression capability and in combination with the efficient classification capability of the support vector machine, various fault modes can be identified with high precision; the kernel skill is introduced into the SVM to mine the inherent nonlinear mode of the data, the generalization is good,