Subdomain Adaptation Transfer Learning Network for Fault Diagnosis of Roller Bearings

• Published in: IEEE transactions on industrial electronics (1982) Vol. 69; no. 8; pp. 8430 - 8439
• Main Authors: Wang, Zhijian, He, Xinxin, Yang, Bin, Li, Naipeng
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.08.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation; Adaptation models; Bearing; Classification; Convolution; Data acquisition; domain adaptation; Domains; Fault diagnosis; Feature extraction; Kernel; Learning; pseudo label learning; Roller bearings; subdomain adaptation; Training; Transfer learning

Due to the data distribution discrepancy, fault diagnosis models, trained with labeled data in one scene, likely fails in classifying by unlabeled data acquired from the other scenes. Transfer learning is capable to generalize successful application trained in one scene to the fault diagnosis in the...