|Table of Contents|

Prediction for state of health of lithium-ion battery by improved grey wolf optimization and support vector regression

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

Issue:
2020年02期
Page:
154-161
Research Field:
Publishing date:

Info

Title:
Prediction for state of health of lithium-ion battery by improved grey wolf optimization and support vector regression
Author(s):
Li Longgang1Li Liwei1Yang Yuxin2Luo Yu3
1.College of Electrical Engineering; 2.Library,Qingdao University,Qingdao 266071,China; 3.Weifang Product Quality Inspection Institute,Weifang 261000,China
Keywords:
lithium-ion batteries state of health improved grey wolf optimization algorithm support vector regression parameter joint optimization
PACS:
TM912.1
DOI:
10.14177/j.cnki.32-1397n.2020.44.02.005
Abstract:
To improve the prediction accuracy of state of health(SOH)for lithium-ion batteries,a joint algorithm based on the improved grey wolf optimization and the support vector regression(IGWO-SVR)is proposed by combining improved grey wolf optimization(IGWO)algorithm with the support vector regression(SVR). The core idea of this algorithm is to use the IGWO algorithm to solve the problem of parameter joint optimization in the SVR model. The IGWO-SVR generates a wolf population randomly. The position vector of the wolf is composed of C,σ,ε three parameters of the SVR model. The location information of each grey wolf is used to learn,and the fitness is calculated. The wolves are graded according to the fitness value,and the locations of individual grey wolves are updated. Then the differential evolution operation is carried out to select excellent individuals to enter the next generation population,and the fitness of gray wolf individuals in the new position is recalculated. At the end of the iteration process,the grey wolf location information with optimal fitness in the wolves is extracted and trained as the final SVR model parameters. Experiment on the lithium-ion batteries datasets of NASA demonstrates the effectiveness of the proposed SOH prediction method.

References:

[1] Zheng Linfeng,Zhang Lei,Zhu Jiangguo,et al. Co-estimation of state-of-charge,capacity and resistance for lithium-ion batteries based on a high-fidelity electrochemical model[J]. Applied Energy,2016,180(8):424-434.
[2]Zhao Chen,Yin He,Ma Chengbin. Quantitative efficiency and temperature analysis of battery-ultracapacitor hybrid energy storage systems[J]. IEEE Transactions on Sustainable Energy,2016,7(4):1791-1802.
[3]Song Junghoon,You Seungjae,Dong Hyupjeon,et al. Numerical modeling and experimental validation of pouch-type lithium-ion battery[J]. Journal of Applied Electrochemistry,2014,44(9):1013-1023.
[4]Hu Xiaosong,Jiang Jiuchun,Cao Dongpu,et al. Battery health prognosis for electric vehicles using sample entropy and sparse bayesian predictive modeling[J]. IEEE Transactions on Industrial Electronics,2016,63(4):2645-2656.
[5]Rezvanizaniani S M,Liu Zongchang,Chen Yan,et al. Review and recent advances in battery health monitoring and prognostics technologies for electric vehicle(EV)safety and mobility[J]. Journal of Power Sources,2014,256(12):110-124.
[6]Anthony Barré,Deguilhem B,Sébastien Grolleau,et al. A review on lithium-ion battery ageing mechanisms and estimations for automotive applications[J]. Journal of Power Sources,2013,241(11):680-689.
[7]Wang Shuai,Zhao Lingling,Su Xiaohong,et al. Prognostics of lithium-ion batteries based on battery performance analysis and flexible support vector regression[J]. Energies,2014,7(10):6492-6508.
[8]He Zhiwei,Gao Mingyu,Ma Guojin,et al. Online state-of-health estimation of lithium-ion batteries using dynamic bayesian networks[J]. Journal of Power Sources,2014,267(3):576-583.
[9]Liu Datong,Luo Yue,Liu Jie,et al. Lithium-ion battery remaining useful life estimation based on fusion nonlinear degradation AR model and RPF algorithm[J]. Neural Computing & Applications,2014,25(3-4):557-572.
[10]Song Yuchen,Liu Datong,Yang Chen,et al. Data-driven hybrid remaining useful life estimation approach for spacecraft lithium-ion battery[J]. Microelectronics Reliability,2017,75(6):142-153.
[11]Zhang Yujie,Liu Datong,Yu Jinxiang,et al. EMA remaining useful life prediction with weighted bagging GPR algorithm[J]. Microelectronics Reliability,2017,75(3):253-263.
[12]Dong Hancheng,Jin Xiaoning,Lou Yangbing,et al. Lithium-ion battery state of health monitoring and remaining useful life prediction based on support vector regression-particle filter[J]. Journal of Power Sources,2014,271(11):114-123.
[13]Qin Taichun,Zeng Shengkui,Guo Jianbin. Robust prognostics for state of health estimation of lithium-ion batteries based on an improved PSO-SVR model[J]. Microelectronics Reliability,2015,55(9-10):1280-1284.
[14]刘皓,胡明昕,朱一亨,等. 基于遗传算法和支持向量回归的锂电池健康状态预测[J]. 南京理工大学学报,2018,42(3):329-334.
Liu Hao,Hu Mingxin,Zhu Yiheng,et al. Health status prediction of lithium batteries based on genetic algorithm and support vector regression[J]. Journal of Nanjing University of Science and Technology,2018,42(3):329-334.
[15] 陈建新,候建明,王鑫,等. 基于局部信息融合及支持向量回归集成的锂电池健康状态预测[J]. 南京理工大学学报,2018,42(1):48-55.
Chen Jianxin,Hou Jianming,Wang Xin,et al. Health status prediction of lithium batteries based on local information fusion and support vector regression[J]. Journal of Nanjing University of Science and Technology,2018,42(1):48-55.
[16]VAPNIK V N. 统计学习理论的本质[M]. 张学工 译. 北京:清华大学出版社,2000:96-101.
[17]Mirjalili S,Mirjalili S M,Lewis A. Grey wolf optimizer[J]. Advances in Engineering Software,2014,69(3):46-61.
[18]刘波,王凌,金以慧. 差分进化算法研究进展[J]. 控制与决策,2007,22(7):721-729.
Liu Bo,Wang Ling,Jin Yihui. Research progress of differential evolution algorithm[J]. Control and Decision-making,2007,22(7):721-729.
[19]Saha B,Goebel K. Battery data set[R]. California,US:NASA Ames Prognostics Data Repository,2007.
[20]徐成善,卢兰光,任东生,等. 车用锂离子电池放电区间与容量衰减关系的研究[J]. 汽车工程,2017,39(10):1141-1144.
Xu Chengshan,Lu Languang,Ren Dongsheng,et al. Research on the relationship between discharge interval and capacity attenuation of automotive lithium-ion batteries[J]. Automotive Engineering,2017,39(10):1141-1144.
[21]Sun B,Jiang J,Zheng F,et al. Practical state of health estimation of power batteries based on Delphi method and grey relational grade analysis[J]. Journal of Power Sources,2015,282:146-157.

Memo

Memo:
-
Last Update: 2020-04-20