Pumped storage station detection method and system based on voiceprint recognition

The invention provides a pumped storage station detection method and system based on voiceprint recognition. The method comprises the steps that sound signals of operation of a main transformer and a water turbine are acquired; processing each frame of the sound signal through a Hamming window, and then performing Fourier transform to obtain a short-time stable signal; the short-time time domain and the short-time frequency domain of the short-time stationary signal are extracted, the short-time time domain comprises at least one of short-time energy, a short-time average zero-crossing rate and short-time energy entropy, and the short-time frequency domain comprises a Mel frequency cepstrum coefficient; performing multi-modal feature dimension reduction on the short-time time domain based on a PCA algorithm, and improving the recognition rate of the sound signal on the short-time frequency domain based on a weighted optimization algorithm to obtain voiceprint enhancement features; and recognizing the category