The Comparative Experiments between the Vibration Signal and the Current signal of Rotor System based on Deep Learning Method

Abstract

for comparative experiments between the vibration signal and the current signal, an intelligent fault diagnosis method based on multiclass convolutional neural network (MCNN) has been proposed to investigate the vibration and current signal for identifying those faults in complex rotor system. Firstly, the vibration and current signal, including bearing and structural faults, were recorded simultaneously under steady-state for each operation condition (three kinds of speed). Secondly, the signal processing technique is chosen to solve the problem of modeling noise instances as true underlying relationship for MCNN. Finally, a one-versus-one and a comprehensive MCNN have been trained with both signal at various operating conditions individually and collectively, respectively. And the experimental results revealed that the accuracy of the vibration signal is better than the current signal whether it is structure faults or the external bearing faults. Moreover, the fault diagnosis performance of a one-versus-one or a comprehensive MCNN is investigated for the wide range of MCNN parameters. The experimental results shown that the vibration signal of the bearing with the high-pass filter and envelop has stable accuracy.