Invariant Feature Purification Method for Domain Generalization of Rolling Bearing Fault Diagnosis

The operational data of rolling bearings under different working conditions vary greatly, leading to poor generalization ability of fault diagnosis models under unknown working conditions. The current domain generalization methods used in vibration fault diagnosis have not yet solved the problem of extracting invariant features. This article proposes an invariant feature purification method for domain generalization (IFPDG) in rolling bearing fault diagnosis to address this issue. This method iterates the model through two stages of game theory, ensuring that only invariant features exist in the feature space. During the global training phase, interference from domain-related features is eliminated through a phase attention mechanism and feature decoupling loss. During the adversarial training phase, interference from inefficient features is eliminated through feature masks. The experimental verification of this method is conducted on the CWRU dataset and the NEFU_FDDG dataset. Especially in ablation experiments, it is confirmed that this method has advantages in generalization performance by comparing with four variants.