Multi-modal Fault Diagnosis with Dual Disentanglement

This paper addresses the challenge of fault diagnosis under unseen working conditions, a crucial problem in real-world applications. It proposes a novel multi-modal approach leveraging dual disentanglement and cross-domain fusion to improve model generalization. The use of multi-modal data and domain adaptation techniques is a significant contribution. The availability of code is also a positive aspect.

• •Addresses the performance decline of fault diagnosis models under unseen working conditions.
• •Employs a dual disentanglement framework to separate modality-invariant/specific and domain-invariant/specific features.
• •Utilizes a cross-domain mixed fusion strategy for data augmentation.
• •Integrates multi-modal heterogeneous information through a triple-modal fusion mechanism.
• •Demonstrates superior performance compared to existing methods on induction motor fault diagnosis.