Multi-source transfer learning network to complement knowledge for intelligent diagnosis of machines with unseen faults

Most of the current successes of deep transfer learning-based fault diagnosis require two assumptions: 1) the health state set of source machines should overlap that of target machines; 2) the number of target machine samples is balanced across health states. However, such assumptions are unrealistic in engineering scenarios, where target machines suffer from fault types that are not seen in source machines and the target machines are mostly in a healthy state with only occasional faults. As a result, the diagnostic knowledge from source machines may not cover all fault types of target machines nor address imbalanced target samples. Therefore, we propose a framework, called a multi-source transfer learning network (MSTLN), to aggregate and transfer diagnostic knowledge from multiple source machines by combining multiple partial distribution adaptation sub-networks (PDA-Subnets) and a multi-source diagnostic knowledge fusion module. The former weights target samples by counter-balancing factors to jointly adapt partial distributions of source and target pairs, and the latter releases negative effects due to discrepancy among multiple source machines and further fuses diagnostic decisions output from multiple PDA-Subnets. Two case studies demonstrate that MSTLN can reduce the misdiagnosis rate and obtain better transfer performance for imbalanced target samples than other conventional methods.

Automated summary

Current successes in deep transfer learning-based fault diagnosis often rely on assumptions that may not hold true in engineering scenarios. Thus, a framework called a multi-source transfer learning network has been proposed to address issues such as uncovering all fault types of target machines and imbalanced target samples.