Optimal Transport-Based Multisource Student Teacher Learning Network for Bearing Fault Diagnosis Under Variable Working Conditions

• Published in: IEEE sensors journal Vol. 22; no. 16; pp. 16392 - 16401
• Main Authors: Shen, Changqing, Xia, Yu, Jiang, Xingxing, Chen, Zaigang, Kong, Lin, Zhu, Zhongkui
• Format: Journal Article
• Language: English
• Published: New York IEEE 15.08.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Ablation; Deep learning; Effectiveness; Employee welfare; Fault diagnosis; Learning; Machinery; multi-source domain adaptation; Optimization; Sensors; student-teacher learning; Task analysis; Task complexity; Teachers; Training; variable working conditions; Vibrations; Working conditions

Fault diagnosis approaches based on deep learning (DL) are subject to a prerequisite that training samples follow the same distribution as the test samples. Traditional transfer learning (TL)-based fault diagnosis approaches are mainstreamed on a single-source transfer and consider simple variable w...