A compound fault diagnosis method based on Multi-task Learning with Multi-gate Mixture-of-Experts

Abstract

At present, the research object of fault diagnosis focuses on single fault diagnosis. This method of diagnosis does not consider the relationship between mechanical equipment faults, and cannot fully identify the type of fault. In the actual industrial process, mechanical equipment is mostly complex system, and compound fault diagnosis is more in line with industrial needs. In order to solve the problem of compound fault diagnosis of mechanical equipment and improve the accuracy of fault identification, this paper establishes a compound fault diagnosis model for gearbox by means of multi-task learning, uses multi-gated networks to extract features from the task sharing layer, and finally classifies the fault through the task specific layer. The experimental results show that, the compound fault diagnosis method based on Multi-task Learning with Multi-gate Mixture-of-Experts (ML-MMoE) can accurately identify compound fault types under different working conditions.