Lithium-ion battery remaining useful life estimation with an optimized Relevance Vector Machine algorithm with incremental learning

被引:218
作者
Liu, Datong [1 ]
Zhou, Jianbao [1 ]
Pan, Dawei [2 ]
Peng, Yu [1 ]
Peng, Xiyuan [1 ]
机构
[1] Harbin Inst Technol, Dept Automat Test & Control, Harbin 150080, Peoples R China
[2] Harbin Engn Univ, Dept Informat & Commun Engn, Harbin 150001, Peoples R China
基金
高等学校博士学科点专项科研基金; 中国国家自然科学基金;
关键词
Remaining useful life; Relevance Vector Machine; Incremental learning; Lithium-ion battery; PROGNOSTICS; MODEL; PREDICTION; STATE;
D O I
10.1016/j.measurement.2014.11.031
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Lithium-ion battery plays a key role in most industrial systems, which is critical to the system availability. It is important to evaluate the performance degradation and estimate the remaining useful life (RUL) for those batteries. With the capability of uncertainty representation and management, Relevance Vector Machine (RVM) becomes an effective approach for lithium-ion battery RUL estimation. However, small sample size and low precision of multi-step prediction limits its application in battery RUL estimation for sparse RVM algorithm. Due to the continuous on-line update of monitoring data, to improve the prediction performance of battery RUL model, dynamic training and on-line learning capability is desirable. Another challenge in on-line and real-time processing is the operating efficiency and computational complexity. To address these issues, this paper implements a flexible and effective on-line training strategy in RVM algorithm to enhance the prediction ability, and presents an incremental optimized RVM algorithm to the model via efficient on-line training. The proposed on-line training strategy achieves a better prediction precision as well as improves the operating efficiency for battery RUL estimation. Experiments based on NASA battery data set show that the proposed method yields a satisfied performance in RUL estimation of lithium-ion battery. (C) 2014 Elsevier Ltd. All rights reserved.
引用
收藏
页码:143 / 151
页数:9
相关论文
共 34 条
[1]   Advanced mathematical methods of SOC and SOH estimation for lithium-ion batteries [J].
Andre, Dave ;
Appel, Christian ;
Soczka-Guth, Thomas ;
Sauer, Dirk Uwe .
JOURNAL OF POWER SOURCES, 2013, 224 :20-27
[2]  
[Anonymous], P 9 INT WORKSH ART I
[3]  
[Anonymous], 1999, INT JOINT C ART INT
[4]  
[Anonymous], 2007, BATTERY DATA SET NAS
[5]   MAXIMUM LIKELIHOOD FROM INCOMPLETE DATA VIA EM ALGORITHM [J].
DEMPSTER, AP ;
LAIRD, NM ;
RUBIN, DB .
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-METHODOLOGICAL, 1977, 39 (01) :1-38
[6]   Dynamic lithium-ion battery model for system simulation [J].
Gao, LJ ;
Liu, SY ;
Dougal, RA .
IEEE TRANSACTIONS ON COMPONENTS AND PACKAGING TECHNOLOGIES, 2002, 25 (03) :495-505
[7]   Prognostics in battery health management [J].
Goebel, Kai ;
Saha, Bhaskar ;
Saxena, Abhinav ;
Celaya, Jose R. ;
Christophersen, Jon P. .
IEEE INSTRUMENTATION & MEASUREMENT MAGAZINE, 2008, 11 (04) :33-40
[8]   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
[9]   Lithium-ion battery remaining useful life estimation based on fusion nonlinear degradation AR model and RPF algorithm [J].
Liu, Datong ;
Luo, Yue ;
Liu, Jie ;
Peng, Yu ;
Guo, Limeng ;
Pecht, Michael .
NEURAL COMPUTING & APPLICATIONS, 2014, 25 (3-4) :557-572
[10]   Satellite Lithium-Ion Battery Remaining Cycle Life Prediction with Novel Indirect Health Indicator Extraction [J].
Liu, Datong ;
Wang, Hong ;
Peng, Yu ;
Xie, Wei ;
Liao, Haitao .
ENERGIES, 2013, 6 (08) :3654-3668