Continual Fault Diagnosis for Rotating Machinery with Fault-Type Increments Based on Adaptive Feature Consolidation Residual Network

To overcome the problem of continuous and adaptive learning in fault-type increments, a novel adaptive feature consolidation residual network (AFCRN) is proposed for continual fault diagnosis for rotating machinery with fault-type increments. Specifically, pseudo-metrics induced by the empirical feature matrix in the feature space consolidate the feature representation by regularizing the drift, which is highly correlated with the previous diagnostic task. Gaussian prototypes are employed to mitigate bias induced by similar diagnostic tasks. Moreover, a new asymmetric cross-entropy loss function is utilized to enable the model classifier to adapt to a continuously updated backbone network, thereby balancing new data with prototypes. Finally, the effectiveness of the proposed method is evaluated through the case study of continuous fault diagnosis. The experimental analysis demonstrates that the designed AFCRN offers significant advantages in fault diagnosis of fault-type increment scenarios.