Deep adaptive sparse residual networks: A lifelong learning framework for rotating machinery fault diagnosis with domain increments

Abstract

Rotating machinery operates continuously for long periods of time under varying conditions in actual industrial environments. The number of fault samples increases with equipment operating time, whereas differences in data distribution are inevitable because of varying operating conditions. As a result, fault diagnosis of rotating machinery poses challenges related to the fault domain increments. In addition, the issue of catastrophic forgetting, where previously learned knowledge significantly affects the model's performance, remains a critical concern. Deep adaptive sparse residual network (DASRN), a new lifelong learning-based method, is proposed to overcome these challenges. The DASRN model is constructed based on an improved deep residual network. The model uses a task-aware dynamic masking strategy to adjust the retention and utilization of blank weights in the network, thereby balancing the model's memory and learning capabilities, mitigating catastrophic forgetting. Furthermore, throughout the entire training process of the model, a dynamic data removal strategy is applied to eliminate easily distinguishable samples. This approach adaptively allocates higher weights to more challenging samples, enhancing the model's learning efficiency while consolidating the sparsity within the model. Finally, the effectiveness of the proposed DASRN is validated on bearing datasets from the Chinese CRH380A high-speed train gearbox and integrated wheelset transmission test rig. Results demonstrate that DASRN provides an effective solution for catastrophic forgetting and domain incremental scenarios in rotating machinery fault diagnosis tasks.