Auto-encoder LSTM for Li-ion SOH prediction : a comparative study on various benchmark datasets

被引：12

作者：

Audin, Paul ^{[1
]}

Jorge, Ines ^{[1
]}

Mesbahi, Tedjani ^{[1
]}

Samet, Ahmed ^{[1
]}

De Beuvron, Francois De Bertrand ^{[1
]}

Bone, Romuald ^{[1
]}

机构：

[1] Univ Strasbourg, INSA Strasbourg, CNRS UMR 7357, ICube, F-67000 Strasbourg, France

来源：

20TH IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA 2021) | 2021年

关键词：

Lithium Ion batteries; Electric Vehicles; Predictive prognostics; Machine learning; Deep Learning; Feature extraction; State of Health; Remaining Useful Life; ELECTRIC VEHICLE-BATTERIES; SHORT-TERM-MEMORY; MODEL; PROGNOSTICS; CNN;

D O I：

10.1109/ICMLA52953.2021.00246

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Lithium-ion batteries are used in most battery powered devices. Today's research on Lithium-ion batteries mainly focuses on better energy management strategies and predictive maintenance. In this paper, a new approach based on autoencoders and long short-term memory neural networks applied to usage data (voltage, current, temperature) is used to make a State of Health prediction. Encouraging results are obtained when conducting tests on various battery ageing datasets published by Sandia National Laboratories, the Massachusetts Institute of Technology and NASA's Prognostics Center of Excellence.

引用

页码：1529 / 1536

页数：8

共 24 条

[1] Long Short-Term Memory Approach to Estimate Battery Remaining Useful Life Using Partial Data [J].

Chinomona, Benvolence ;

Chung, Chunhui ;

Chang, Lien-Kai ;

Su, Wei-Chih ;

Tsai, Mi-Ching .

IEEE ACCESS, 2020, 8 :165419-165431

[2] Recycling and environmental issues of lithium-ion batteries: Advances, challenges and opportunities [J].

Costa, C. M. ;

Barbosa, J. C. ;

Goncalves, R. ;

Castro, H. ;

Del Campo, F. J. ;

Lanceros-Mendez, S. .

ENERGY STORAGE MATERIALS, 2021, 37 :433-465

[3]

Ding YR, 2018, IEEE INT C INT ROBOT, P7391, DOI 10.1109/IROS.2018.8594161

[4] Physics-based prognostics of lithium-ion battery using non-linear least squares with dynamic bounds [J].

Downey, Austin ;

Lui, Yu-Hui ;

Hu, Chao ;

Laflamme, Simon ;

Hu, Shan .

RELIABILITY ENGINEERING & SYSTEM SAFETY, 2019, 182 :1-12

[5] Prognostics of lithium-ion batteries based on Dempster-Shafer theory and the Bayesian Monte Carlo method [J].

He, Wei ;

Williard, Nicholas ;

Osterman, Michael ;

Pecht, Michael .

JOURNAL OF POWER SOURCES, 2011, 196 (23) :10314-10321

[6]

Kozlowski JD, 2001, AEROSP CONF PROC, P3149, DOI 10.1109/AERO.2001.931332

[7] Intelligent Prognostics for Battery Health Monitoring Using the Mean Entropy and Relevance Vector Machine [J].

Li, Hong ;

Pan, Donghui ;

Chen, C. L. Philip .

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2014, 44 (07) :851-862

[8] A Directed Acyclic Graph Network Combined With CNN and LSTM for Remaining Useful Life Prediction [J].

Li, Jialin ;

Li, Xueyi ;

He, David .

IEEE ACCESS, 2019, 7 :75464-75475

[9] Remaining useful life prediction for lithium-ion batteries based on a hybrid model combining the long short-term memory and Elman neural networks [J].

Li, Xiaoyu ;

Zhang, Lei ;

Wang, Zhenpo ;

Dong, Peng .

JOURNAL OF ENERGY STORAGE, 2019, 21 :510-518

[10] A Data-Driven Approach With Uncertainty Quantification for Predicting Future Capacities and Remaining Useful Life of Lithium-ion Battery [J].

Liu, Kailong ;

Shang, Yunlong ;

Ouyang, Quan ;

Widanage, Widanalage Dhammika .

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2021, 68 (04) :3170-3180

← 1 2 3 →