Fault diagnosis via multi-sensor fusion with auxiliary contrastive learning and phased fine-tuning

Abstract

Typically, deep learning-based fault diagnosis models fail to fully utilize the potential information in large amounts of normal state data and encounter difficulties when learning from limited fault samples. To address these challenges, this study proposes an auxiliary contrastive learning framework designed for multi-sensor data. The framework incorporates auxiliary classifiers after each sensor-specific branch to enhance feature representation, and enables model pretraining using only normal condition data. In addition, a phased fine-tuning strategy is developed, which combines full-model fine-tuning with lightweight adapter tuning to improve the adaptability of the fine-tuning process. A novel multi-sensor data augmentation technique is also introduced to enrich the contrastive learning tasks by generating structurally diverse negative samples. By enabling the effective utilization of normal condition data in model training, the proposed framework offers a new perspective for fault diagnosis applications. Experimental results on three benchmark datasets demonstrate that the proposed method significantly improves the generalization capability of the pre-trained model. Furthermore, the phased fine-tuning strategy exhibits high adaptability to the target tasks. Compared to other data fusion methods, the proposed auxiliary contrastive learning framework achieves notable performance advantages.