Fault diagnosis of the harmonic reducer based on dual-path convolutional network with multi-channel hybrid attention mechanism

Abstract Harmonic reducers are prone to tooth breakage and other failures due to continuous deformation of the flexure wheel during operation. To identify the fault types of harmonic reducers under different working conditions, a fault diagnosis method (MADCNN-BiGRU) based on Dual-path Convolution Neural Network (DCNN) with Multi-channel Hybrid Attention Mechanism (MCHAM) and Bidirectional Gated Recurrent Unit (BiGRU) was proposed. Firstly, a novel MCHAM focuses on the critical information part of the vibration signal and can effectively suppress the noise and redundant information. Secondly, a new soft threshold function is constructed to regulate the attention weights dynamically. Thirdly, BiGRU obtains feature information for different time series locations to identify the faults correctly. Fourthly, the harmonic reducer test rig is established to collect vibration signals of harmonic reducers with different faults under different working conditions. The comparative experimental results show that MADCNN-BiGRU has excellent capacity for generalization and robustness, and can effectively diagnose under various complicated situations.