A simulation-data-driven subdomain adaptation adversarial transfer learning network for rolling element bearing fault diagnosis

In recent years, increasing numbers of deep learning methods for fault diagnosis of rolling element bearings (REBS) have been proposed. However, in industry, the scarcity of available data to monitor the health condition of REBS leads to low recognition accuracy of the trained intelligent diagnostic models. To solve this problem, we propose a simulation-data-driven subdomain adaptation adversarial transfer learning (TL) network (SAATLN). Firstly, a defect vibration model is introduced to simulate vibration signals of different types of REBS faults. And the real signal and simulated signal are used as the target domain and source domain of the TL fault diagnosis methods, respectively. Secondly, SAATLN uses the designed residual squeeze-and-excitation (Re-SE) blocks to extract transfer features between different domains. Meanwhile, it combines adversarial learning and subdomain adaptation to adapt the marginal distribution and conditional distribution discrepancies of high-level features. Also, the local maximum mean discrepancy is introduced as the subdomain adaptation metric criterion. Finally, different transfer tasks are performed on the artificially damaged and run-to-failure REBS data sets. The results demonstrate the effectiveness and superiority of the SAATLN in the simulation-data-driven REBS fault diagnosis.