Fan gearbox fault diagnosis method and system based on improved EEMD and speech spectrum analysis

The invention discloses a fan gearbox fault diagnosis method and system based on improved EEMD and speech spectrum analysis. The method comprises the following steps: obtaining a healthy or fault vibration signal of a fan gearbox; optimizing the EEMD method by using a tsPSO method to obtain a final series of eigenmode function components; screening eigenmode function components, and performing spectrogram analysis on the selected components to obtain a fault feature spectrogram; and taking the fault characteristic spectrogram as input data, establishing a convolutional neural network model, finally obtaining an intelligent diagnosis model of the fault of the fan gearbox, and carrying out fault identification and diagnosis on the vibration signal of the fan gearbox by using the obtained model. According to the method, relatively accurate numerical parameters of the EEMD method can be adaptively obtained according to the characteristic optimization of the signal, the decomposition accuracy of the EEMD method is