Circuit breaker fault diagnosis method and system based on multi-signal fusion characteristics

The invention discloses a circuit breaker fault diagnosis method based on a multi-signal fusion feature, and the method comprises the steps: collecting a vibration signal, a coil current signal and a sound signal in a switching-on and switching-off process of a circuit breaker, and carrying out the preprocessing; the preprocessed vibration signals, the preprocessed coil current signals and the preprocessed sound signals correspond to brightness values of three color channels in the RGB image respectively, and the three kinds of signal data are synthesized into color image data; performing feature extraction according to the color image data to obtain multi-signal fusion features, and training the probabilistic neural network model to obtain a fault diagnosis model; performing fault diagnosis on the circuit breaker through the fault diagnosis model, and determining a fault type; the invention further discloses a circuit breaker fault diagnosis system based on the method. According to the method, data are obtai