Deep multiple auto-encoder with attention mechanism network: A dynamic domain adaptation method for rotary machine fault diagnosis under different working conditions

Abstract

Intelligent fault diagnosis methods based on deep learning have achieved noteworthy application results in health diagnosis of rotating machinery. However, the fault data distribution discrepancy caused by different working conditions in real industrial scenarios can deteriorate the diagnosis performance of model. And extracted features by multi-ensemble deep auto-encoder neglect the contribution degree of each deep auto-encoder. Inspire by the demands, a dynamic domain adaptation method based on deep multiple auto-encoders with attention mechanism (DMAEAM-DDA) is proposed for rotary machine fault diagnosis under different working conditions. Firstly, combined with attention mechanism, pre-trained multiple deep auto-encoder with six different activation functions are utilized to construct deep multiple auto-encoder with attention mechanism network for extracting feature. Then the dynamic domain factor is calculated to automatically assign the weight of the marginal and conditional distribution for learning domain invariant fault features. Finally, two rotary machine experiments are employed to verify the availability of the proposed DMAEAM-DDA method, and the results show the proposed DMAEAM-DDA method has better superiority and outstanding stability compared to other methods.