TY - GEN
T1 - Remaining Useful Life Prediction of Aircraft Auxiliary Power Unit with On-wing Sensing Data
AU - Liu, Liansheng
AU - Wang, Lulu
AU - Wang, Shaonian
AU - Liu, Daotong
AU - Peng, Yu
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2019/1/4
Y1 - 2019/1/4
N2 - As one key subsystem of the aircraft, Auxiliary Power Unit (APU) is mainly utilized to provide compressed air for starting the main engines. Besides, APU also supplies air conditioning and electrical power in the cabin when the aircraft is at the gate. Its reliability determines the flight quality at a large degree. In the future all-electric aircraft, APU will also be adopted to provide some additional thrust. The safety of the more/all-electric aircraft will also depend on the APU condition. Therefore, how to predict the Remaining Useful Life (RUL) of the on-wing APU has become an important research interest. In this study, one kind of data-driven RUL prediction approach for APU is proposed, which is based on the combination of mutual information and Gaussian Process Regression. By predicting the RUL of APU, the condition-based maintenance can be scheduled more reasonably and precisely. The effectiveness of the proposed approach is evaluated by utilizing the on-wing sensing data of APU APS3200 from the Shenyang Maintenance Base of China Southern Airlines Company Limited.
AB - As one key subsystem of the aircraft, Auxiliary Power Unit (APU) is mainly utilized to provide compressed air for starting the main engines. Besides, APU also supplies air conditioning and electrical power in the cabin when the aircraft is at the gate. Its reliability determines the flight quality at a large degree. In the future all-electric aircraft, APU will also be adopted to provide some additional thrust. The safety of the more/all-electric aircraft will also depend on the APU condition. Therefore, how to predict the Remaining Useful Life (RUL) of the on-wing APU has become an important research interest. In this study, one kind of data-driven RUL prediction approach for APU is proposed, which is based on the combination of mutual information and Gaussian Process Regression. By predicting the RUL of APU, the condition-based maintenance can be scheduled more reasonably and precisely. The effectiveness of the proposed approach is evaluated by utilizing the on-wing sensing data of APU APS3200 from the Shenyang Maintenance Base of China Southern Airlines Company Limited.
KW - Auxiliary power unit
KW - Condition based maintenance
KW - On-wing sensing data
KW - Remaining useful life
UR - https://www.scopus.com/pages/publications/85061832638
U2 - 10.1109/PHM-Chongqing.2018.00044
DO - 10.1109/PHM-Chongqing.2018.00044
M3 - 会议稿件
AN - SCOPUS:85061832638
T3 - Proceedings - 2018 Prognostics and System Health Management Conference, PHM-Chongqing 2018
SP - 223
EP - 228
BT - Proceedings - 2018 Prognostics and System Health Management Conference, PHM-Chongqing 2018
A2 - Ding, Ping
A2 - Li, Chuan
A2 - Yang, Shuai
A2 - Ding, Ping
A2 - Sanchez, Rene-Vinicio
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2018 Prognostics and System Health Management Conference, PHM-Chongqing 2018
Y2 - 26 October 2018 through 28 October 2018
ER -