Time-frequency supervised contrastive learning via pseudo-labeling: An unsupervised domain adaptation network for rolling bearing fault diagnosis under time-varying speeds

Abstract

The varying speed can cause the significant data distribution shift of bearings, making it difficult for deep learning-based bearing fault diagnosis models to ensure good generalization. Domain adaptation methods have been developed to address the domain shifts, while they struggle with the class-invariant features extraction under variable speed. Accordingly, a time–frequency supervised contrastive learning framework (TF-SupCon) is proposed for unsupervised cross-speed fault diagnosis of bearing. TF-SupCon adopts a pre-training-downstream task framework that aims to extract speed immune class-invariant features. During the pre-training phase, the physical consistency of the time-domain information and the frequency-domain information of bearing signal, a general feature applicable to different speed conditions, is learned in a targeted manner through supervised contrastive learning. Additionally, a K-Nearest Neighbor (KNN) algorithm based on cosine distance is designed to assign pseudo-labels to unlabeled target domain data, enabling cross-domain supervised contrastive pre-training. In the downstream task, unsupervised cross-domain fault diagnosis is performed using a KNN classifier and the speed immune time–frequency features by the trained encoders. It is worth noting that the same metric is maintained throughout both the pre-training phase and the downstream task, ensuring organic connection between the two stages. The superiority of TF-SupCon was demonstrated through a variety of fault diagnosis experiments conducted on both public and self-collected datasets. Lastly, the distances between time-domain and frequency-domain features of different categories were studied to verify the physical consistency between the features.