TY - GEN
T1 - Remaining Useful Life Prediction of Aero-Engine using CNN-LSTM and mRMR Feature Selection
AU - Zhou, Zhikun
AU - Yang, Lechang
AU - Wang, Zhe
AU - Yao, Yuantao
PY - 2022/12
Y1 - 2022/12
N2 - Remaining useful life (RUL) prediction is critical in prognostics and health management (PHM) applications, where the trend of data-driven approaches using operational data from complex systems to establish degradation processes has attracted increasing attention. In order to solve the problem of feature screening and life prediction in the remaining service life prediction of aero-engine, this paper proposes Max-Relevance and Min-Redundancy (mRMR) method to screen sensor features by calculating the mutual information between features, uses the advantage of LSTM network in processing time series data, constructs samples by time window sliding, and designs the RUL direct prediction framework of CNN-LSTM network. The validation experiments were carried out on the C-MPASS dataset. Experimental results show that compared with other single deep learning and traditional models, the proposed hybrid model has lower regression analysis error and degradation prediction error, and can obtain more accurate remaining useful life prediction results. © 2022 IEEE.
AB - Remaining useful life (RUL) prediction is critical in prognostics and health management (PHM) applications, where the trend of data-driven approaches using operational data from complex systems to establish degradation processes has attracted increasing attention. In order to solve the problem of feature screening and life prediction in the remaining service life prediction of aero-engine, this paper proposes Max-Relevance and Min-Redundancy (mRMR) method to screen sensor features by calculating the mutual information between features, uses the advantage of LSTM network in processing time series data, constructs samples by time window sliding, and designs the RUL direct prediction framework of CNN-LSTM network. The validation experiments were carried out on the C-MPASS dataset. Experimental results show that compared with other single deep learning and traditional models, the proposed hybrid model has lower regression analysis error and degradation prediction error, and can obtain more accurate remaining useful life prediction results. © 2022 IEEE.
KW - aero-engine
KW - component
KW - Long and short term memory neural network
KW - performance degradation
KW - remaining useful life
UR - http://www.scopus.com/inward/record.url?scp=85151709555&partnerID=8YFLogxK
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85151709555&origin=recordpage
U2 - 10.1109/SRSE56746.2022.10067318
DO - 10.1109/SRSE56746.2022.10067318
M3 - RGC 32 - Refereed conference paper (with host publication)
T3 - International Conference on System Reliability and Safety Engineering, SRSE
SP - 41
EP - 45
BT - 2022 4th International Conference on System Reliability and Safety Engineering (SRSE 2022)
PB - IEEE
T2 - 4th International Conference on System Reliability and Safety Engineering, SRSE 2022
Y2 - 15 December 2022 through 18 December 2022
ER -