Bearing fault diagnosis based on high-confidence pseudo-labels and dual-view multi-adversarial sparse joint attention network under variable working conditions

Domain adaptive technology has been extensively employed in the research of bearing fault diagnosis under cross-different working conditions. Nevertheless, most studies ignore the two domains' conditional distribution alignment and domain-invariant features' discriminative properties. Hence, this paper proposes a dual-view multi-adversarial network combined with improved pseudo-label learning (DMNIPL) to address the cross-different working fault diagnosis of bearings when the target domain sample labels are unavailable. Specifically, the proposed model uses pseudo-label learning to generate labels for unlabeled target domain samples and achieves conditional distribution alignment between the source and target domains through adversarial training. The adversarial training process is between the local-domain discriminator module involving multiple domain discriminators and the feature extractor. Since pseudo-labels with low-confidence interfere with model training, this work introduces an adaptive dynamic threshold to filter pseudo-labels. Additionally, two independent health state classifiers are designed to classify the same fault sample, enhance the model's learning ability on discriminable features. Furthermore, we combine spatial and channel attention, use sparse operations, and propose the sparse joint attention (SJA) scheme to enhance the model's ability to capture fault features. Finally, the effectiveness and advancement of the proposed method are verified using two datasets. Experimental results show that the accuracy of the proposed method can achieve more than 95% in 12 diagnostic tasks, which is higher than other methods. This research work provides a reliable fault diagnosis method to detect the health status of rotating machinery equipment.