Combining multiple deep learning algorithms for prognostic and health management of aircraft

被引：99

作者：

Che, Changchang ^{[1
]}

Wang, Huawei ^{[1
]}

Fu, Qiang ^{[1
]}

Ni, Xiaomei ^{[1
]}

机构：

[1] Nanjing Univ Aeronaut & Astronaut, Coll Civil Aviat, Nanjing, Jiangsu, Peoples R China

来源：

AEROSPACE SCIENCE AND TECHNOLOGY | 2019年 / 94卷

基金：

中国国家自然科学基金;

关键词：

Prognostic and health management (PHM); Long short-term memory (LSTM); Deep belief network (DBN); Condition assessment; Fault classification; Remaining useful life (RUL); SHORT-TERM-MEMORY; REMAINING USEFUL LIFE; FAULT-DIAGNOSIS; BELIEF NETWORK;

D O I：

10.1016/j.ast.2019.105423

中图分类号：

V [航空、航天];

学科分类号：

08 ; 0825 ;

摘要：

The development of airborne sensor monitoring and artificial intelligence technologies provides effective tools for precise prognostic and health management (PHM) of aircraft. This paper presents a PHM model which combines multiple deep learning algorithms for condition assessment, fault classification, sensor prediction, and remaining useful life (RUL) estimation of aircraft systems. A long short-term memory (LSTM) based recurrent network is used to predict multiple multivariate time series of sensors, and deep belief network (DBN) is applied to assess system condition and classify faults of aircraft systems. Then, the RUL can be estimated through the integration of condition assessment and sensor prediction. Finally, the proposed algorithm is validated experimentally using NASA's C-MAPSS dataset, and the results showed a lower error rate and deviation than traditional models. (C) 2019 Elsevier Masson SAS. All rights reserved.

引用

页数：9

共 35 条

[21]

Saxena A., 2008, IEEE 2008 INT C PROG

[22] Rolling bearing fault diagnosis using adaptive deep belief network with dual-tree complex wavelet packet [J].

Shao, Haidong ;

Jiang, Hongkai ;

Wang, Fuan ;

Wang, Yanan .

ISA TRANSACTIONS, 2017, 69 :187-201

[23] Hidden Markov Models for the Prediction of Impending Faults [J].

Soualhi, Abdenour ;

Clerc, Guy ;

Razik, Hubert ;

El Badaoui, Mohamed ;

Guillet, Francois .

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2016, 63 (05) :3271-3281

[24] DeepChart: Combining deep convolutional networks and deep belief networks in chart classification [J].

Tang, Binbin ;

Liu, Xiao ;

Lei, Jie ;

Song, Mingli ;

Tao, Dapeng ;

Sun, Shuifa ;

Dong, Fangmin .

SIGNAL PROCESSING, 2016, 124 :156-161

[25] Remaining useful life estimation of engineered systems using vanilla LSTM neural networks [J].

Wu, Yuting ;

Yuan, Mei ;

Dong, Shaopeng ;

Lin, Li ;

Liu, Yingqi .

NEUROCOMPUTING, 2018, 275 :167-179

[26] Intelligent fault diagnosis approach with unsupervised feature learning by stacked denoising autoencoder [J].

Xia, Min ;

Li, Teng ;

Liu, Lizhi ;

Xu, Lin ;

de Silva, Clarence W. .

IET SCIENCE MEASUREMENT & TECHNOLOGY, 2017, 11 (06) :687-695

[27] Recent advances in prognostics and health management for advanced manufacturing paradigms [J].

Xia, Tangbin ;

Dong, Yifan ;

Xiao, Lei ;

Du, Shichang ;

Pan, Ershun ;

Xi, Lifeng .

RELIABILITY ENGINEERING & SYSTEM SAFETY, 2018, 178 :255-268

[28] In situ identification of shearing parameters for loose lunar soil using least squares support vector machine [J].

Xue, Long ;

Li, Jianqiao ;

Zou, Meng ;

Zong, Wei ;

Huang, Han .

AEROSPACE SCIENCE AND TECHNOLOGY, 2016, 53 :154-161

[29] Fault diagnosis network design for vehicle on-board equipments of high-speed railway: A deep learning approach [J].

Yin, Jiateng ;

Zhao, Wentian .

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2016, 56 :250-259

[30] Aircraft engine health prognostics based on logistic regression with penalization regularization and state-space-based degradation framework [J].

Yu, Jianbo .

AEROSPACE SCIENCE AND TECHNOLOGY, 2017, 68 :345-361

← 1 2 3 4 →