Method to enhance deep learning fault diagnosis by generating adversarial samples

Modern industrial fields utilize complex mechanical equipment and machinery, which are closely linked, and equipment faults are difficult to express. Therefore, fault diagnosis is important to ensure the safety of complex mechanical equipment in modern industries. Deep learning has achieved excellent results with recent fault diagnosis methods. At present, three common deep learning models (MLP, CNN, and RNN models) can achieve diagnosis rates close to 100% with original fault diagnosis data and a signal-to-noise ratio above 10 dB. However, we found that the diagnostic rate of these three models was completely incorrect when an adversarial sample with a signal-to-noise ratio noise greater than 10 dB was added to the original sample. We propose a GAN-based adversarial signal generative adversarial network (AdvSGAN) in this paper. We conduct experiments on the CWRU dataset and conclude that we can easily obtain adversarial noise and generate training samples through AdvSGAN. With the addition of adversarial data training, the diagnostic rate of the model on these adversarial samples increased from less than 5% to 98.69%, 97.38% and 96.94%. Hence, this method increases the reliability of our deep learning model. • In fault diagnosis based on deep learning methods, although there has been a high diagnosis rate, there will be errors in the diagnosis of adversarial signals. • The Adv-SGAN method based on GAN is proposed, which can efficiently to find adversarial samples. • The adversarial samples produced by the Adv-SGAN can maintain a high degree of consistency with the original samples. • The model diagnosis rate of adversarial samples can improve after adversarial training.