TY - GEN
T1 - A DEEP LONG SHORT-TERM MEMORY NETWORK FOR BEARING FAULT DIAGNOSIS UNDER TIME-VARYING CONDITIONS
AU - Zhou, Kai
N1 - Funding Information:
This research is supported by National Science Foundation under grant CMMI–2138522.
Publisher Copyright:
© 2022 by ASME.
PY - 2022/11
Y1 - 2022/11
N2 - The fault diagnosis of bearing in machinery system plays a vital role in ensuring the normal operating performance of system. Machine learning-based fault diagnosis using vibration measurement recently has become a prevailing approach, which aims at identifying the fault through exploring the correlation between the measurement and respective fault. Nevertheless, such correlation will become very complex for the practical scenario where the system is operated under time-varying conditions. To fulfill the reliable bearing fault diagnosis under time-varying condition, this study presents a tailored deep learning model, so called deep long short-term memory (LSTM) network. By fully exploiting the strength of this model in characterizing the temporal dependence of time-series vibration measurement, the negative consequence of time-varying conditions can be minimized, thereby improving the diagnosis performance. The published bearing dataset with various time-varying operating speeds is utilized in case illustrations to validate the effectiveness of proposed methodology.
AB - The fault diagnosis of bearing in machinery system plays a vital role in ensuring the normal operating performance of system. Machine learning-based fault diagnosis using vibration measurement recently has become a prevailing approach, which aims at identifying the fault through exploring the correlation between the measurement and respective fault. Nevertheless, such correlation will become very complex for the practical scenario where the system is operated under time-varying conditions. To fulfill the reliable bearing fault diagnosis under time-varying condition, this study presents a tailored deep learning model, so called deep long short-term memory (LSTM) network. By fully exploiting the strength of this model in characterizing the temporal dependence of time-series vibration measurement, the negative consequence of time-varying conditions can be minimized, thereby improving the diagnosis performance. The published bearing dataset with various time-varying operating speeds is utilized in case illustrations to validate the effectiveness of proposed methodology.
KW - bearing fault diagnosis
KW - deep long short-term memory (LSTM) neural network
KW - time-series vibration measurement
KW - time-varying conditions
UR - http://www.scopus.com/inward/record.url?scp=85142611867&partnerID=8YFLogxK
U2 - 10.1115/DETC2022-88808
DO - 10.1115/DETC2022-88808
M3 - Conference article published in proceeding or book
AN - SCOPUS:85142611867
T3 - Proceedings of the ASME Design Engineering Technical Conference
BT - 34th Conference on Mechanical Vibration and Sound (VIB)
PB - American Society of Mechanical Engineers(ASME)
T2 - ASME 2022 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC-CIE 2022
Y2 - 14 August 2022 through 17 August 2022
ER -