A Robust Deep Neural Network for Rolling Element Fault Diagnosis under Various Operating and Noisy Conditions.

This study proposes a new intelligent diagnostic method for bearing faults in rotating machinery. The method uses a combination of nonlinear mode decomposition based on the improved fast kurtogram, gramian angular field, and convolutional neural network to detect the bearing state of rotating machinery. The nonlinear mode decomposition based on the improved fast kurtogram inherits the advantages of the original algorithm while improving the computational efficiency and signal-to-noise ratio. The gramian angular field can construct a two-dimensional image without destroying the time relationship of the signal. Therefore, the proposed method can perform fault diagnosis on rotating machinery under complex operating conditions. The proposed method is verified on the Paderborn dataset under heavy noise and multiple operating conditions to evaluate its effectiveness. Experimental results show that the proposed model outperforms wavelet denoising and the traditional adaptive decomposition method. The proposed model achieves over 99.6% accuracy in all four operating conditions provided by this dataset, and 93.8% accuracy in a strong noise environment with a signal-to-noise ratio of -4 dB.