Replay-guided Test-time Adaptation for Fault Diagnosis Under Unseen Operating Conditions

TL;DR

This paper introduces a novel replay-guided test-time adaptation framework combining offline domain generalization and online replay mechanisms to improve fault diagnosis in machinery under unseen, dynamic operating conditions.

Contribution

It proposes an integrated approach that enables real-time adaptation of fault diagnosis models to changing environments using a dual-memory replay system.

Findings

Achieves competitive performance on real-world motor dataset

Effectively adapts to unseen operating conditions

Reduces forgetting of previously learned knowledge

Abstract

In modern industrial systems, machinery frequently operates under dynamic environments with continuously varying loads and speeds. Consequently, deep learning-based fault diagnosis models often suffer from severe performance degradation under unseen operating conditions due to complex data distribution shifts. Since existing methods predominantly rely on static offline training, they lack the capability to dynamically adapt to these continuous variations. To address this issue, an integrated framework combining offline domain generalization (DG) and online test-time adaptation (OTTA) is proposed. Initially, a model with preliminary generalization capability is obtained offline by extracting domain-invariant features via adversarial learning. During the online phase, a dual-memory replay mechanism is developed. By selectively storing high-confidence online pseudo-labeled samples and replaying them with historical offline data, the model facilitates adaptation to changing data distributions and helps reduce forgetting of previously learned knowledge Experiments on a real-world motor dataset show that the proposed approach achieves competitive performance under the considered unseen operating conditions.