[1B3] Fault diagnosis for rotating machine based on Mel spectrogram and residual neural network
F Tu, S Yang and J Yang
Sichuan University, China
Current methods for processing acoustic signals for fault diagnosis are commonly based on the method of processing the vibration signals. It is difficult to obtain the information only existing in the acoustic signal. Therefore, considering the fault diagnosis based on the acoustic signal, a method based on the logarithmic Mel (LM) spectrogram and a residual neural network (ResNet) is proposed. Firstly, to correspond with the auditory perception, the acoustic signal is processed and linearly represented in the LM spectrogram. Secondly, the ResNet model is introduced to extract the fault information from the LM spectrogram for the identification of the different types of fault. By training two datasets obtained from the gearbox platform, the different types of fault and the faults at different components of the gearbox are separately classified. The comparison results of different inputs with the LM spectrogram for training the ResNet model show that the LM spectrogram as the input could achieve the best classification accuracy. The comparison results of different classic deep learning models with the ResNet model demonstrate that the proposed methods can effectively extract features from acoustic signals in the LM spectrogram for the fault classification of the gearbox.
Keywords: Mel spectrogram, acoustic signal processing, gearbox fault identification, deep learning.
Keywords: Mel spectrogram, acoustic signal processing, gearbox fault identification, deep learning.
