EverAdapt: Continuous Adaptation for Dynamic Machine Fault Diagnosis Environments
This work addresses the problem of maintaining model performance across changing environments for fault diagnosis in industrial settings, representing an incremental improvement over existing methods.
The paper tackles catastrophic forgetting in unsupervised domain adaptation for machine fault diagnosis in dynamic environments by introducing the EverAdapt framework, which achieves robust performance through novel components like Continual Batch Normalization and a sample-efficient replay strategy.
Unsupervised Domain Adaptation (UDA) has emerged as a key solution in data-driven fault diagnosis, addressing domain shift where models underperform in changing environments. However, under the realm of continually changing environments, UDA tends to underperform on previously seen domains when adapting to new ones - a problem known as catastrophic forgetting. To address this limitation, we introduce the EverAdapt framework, specifically designed for continuous model adaptation in dynamic environments. Central to EverAdapt is a novel Continual Batch Normalization (CBN), which leverages source domain statistics as a reference point to standardize feature representations across domains. EverAdapt not only retains statistical information from previous domains but also adapts effectively to new scenarios. Complementing CBN, we design a class-conditional domain alignment module for effective integration of target domains, and a Sample-efficient Replay strategy to reinforce memory retention. Experiments on real-world datasets demonstrate EverAdapt superiority in maintaining robust fault diagnosis in dynamic environments. Our code is available: https://github.com/mohamedr002/EverAdapt