TY - GEN
T1 - SEMI-SUPERVISED AUTOENCODER WITH JOINT LOSS LEARNING FOR BEARING FAULT DETECTION
AU - Zhou, Kai
AU - Zhang, Yang
AU - Tang, Jiong
N1 - Publisher Copyright:
Copyright © 2023 by ASME.
PY - 2023/11
Y1 - 2023/11
N2 - Timely and accurate bearing fault detection plays an important role in various industries. Data-driven deep learning methods have recently become a prevailing approach for bearing fault detection. Despite the success of deep learning, fault diagnosis performance is hinged upon the size of labeled data, the acquisition of which oftentimes is expensive in actual practice. Unlabeled data, on the other hand, are inexpensive. To fully utilize a large amount of unlabeled data together with limited labeled data to enhance fault detection performance, in this research, we develop a semi-supervised learning method built upon the autoencoder. In this method, a joint loss is established to account for the effects of both the labeled and unlabeled data, which is subsequently used to direct the backpropagation training. Systematic case studies using the Case Western Reserve University (CWRU) rolling bearing dataset are carried out, in which the effectiveness of this new method is verified by comparing it with other benchmark models.
AB - Timely and accurate bearing fault detection plays an important role in various industries. Data-driven deep learning methods have recently become a prevailing approach for bearing fault detection. Despite the success of deep learning, fault diagnosis performance is hinged upon the size of labeled data, the acquisition of which oftentimes is expensive in actual practice. Unlabeled data, on the other hand, are inexpensive. To fully utilize a large amount of unlabeled data together with limited labeled data to enhance fault detection performance, in this research, we develop a semi-supervised learning method built upon the autoencoder. In this method, a joint loss is established to account for the effects of both the labeled and unlabeled data, which is subsequently used to direct the backpropagation training. Systematic case studies using the Case Western Reserve University (CWRU) rolling bearing dataset are carried out, in which the effectiveness of this new method is verified by comparing it with other benchmark models.
KW - autoencoder
KW - deep learning
KW - fault detection
KW - joint loss
KW - Rolling bearing
KW - semi-supervised learning
UR - http://www.scopus.com/inward/record.url?scp=85178591173&partnerID=8YFLogxK
U2 - 10.1115/DETC2023-112654
DO - 10.1115/DETC2023-112654
M3 - Conference article published in proceeding or book
AN - SCOPUS:85178591173
T3 - Proceedings of the ASME Design Engineering Technical Conference
BT - 35th Conference on Mechanical Vibration and Sound (VIB)
PB - American Society of Mechanical Engineers(ASME)
T2 - ASME 2023 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC-CIE 2023
Y2 - 20 August 2023 through 23 August 2023
ER -