Aero-engine remaining useful life estimation based on 1-dimensional FCN-LSTM neural networks

Wei Zhang, Feng Jin, Guigang Zhang, Baicheng Zhao, Yuqing Hou

科研成果: 书/报告/会议事项章节会议稿件同行评审

9 引用 (Scopus)

摘要

To estimate the remaining useful life of aero-engines rapidly and accurately, a 1-Dimensional Fully-Convolutional LSTM algorithm is proposed. First, SVM is utilized as anomaly detector to find failures and it will help label training data. Then, K-means clustering with new operational features for multiple operation modes is employed. Finally, Convolutional neural network and LSTM are combined in parallel as the main estimating algorithm. The proposition is evaluated on the publicly available health monitoring dataset C-MAPSS of aircraft turbofan engines provided by NASA. The prognostic accuracy of the proposed algorithm is benchmarked against single LSTM and 1-D CNN and demonstrated to be more efficient.

源语言英语
主期刊名Proceedings of the 38th Chinese Control Conference, CCC 2019
编辑Minyue Fu, Jian Sun
出版商IEEE Computer Society
4913-4918
页数6
ISBN(电子版)9789881563972
DOI
出版状态已出版 - 7月 2019
活动38th Chinese Control Conference, CCC 2019 - Guangzhou, 中国
期限: 27 7月 201930 7月 2019

出版系列

姓名Chinese Control Conference, CCC
2019-July
ISSN(印刷版)1934-1768
ISSN(电子版)2161-2927

会议

会议38th Chinese Control Conference, CCC 2019
国家/地区中国
Guangzhou
时期27/07/1930/07/19

指纹

探究 'Aero-engine remaining useful life estimation based on 1-dimensional FCN-LSTM neural networks' 的科研主题。它们共同构成独一无二的指纹。

引用此