[1]刘金江,颜伏伍*,杜常清.基于改进RVM算法的三元锂离子电池SOC估计[J].四川师范大学学报(自然科学版),2018,(05):703-710.[doi:10.3969/j.issn.1001-8395.2018.05.022]
 LIU Jinjiang,YAN Fuwu,DU Changqing.Ternary Lithium Ion Battery State of Charge Estimation Based on Adapted Relevant Vector Machine[J].Journal of SichuanNormal University,2018,(05):703-710.[doi:10.3969/j.issn.1001-8395.2018.05.022]
点击复制

基于改进RVM算法的三元锂离子电池SOC估计()
分享到:

《四川师范大学学报(自然科学版)》[ISSN:1001-8395/CN:51-1295/N]

卷:
期数:
2018年05期
页码:
703-710
栏目:
基础理论
出版日期:
2018-06-15

文章信息/Info

Title:
Ternary Lithium Ion Battery State of Charge Estimation Based on Adapted Relevant Vector Machine
文章编号:
1001-8395(2018)05-0703-08
作者:
刘金江12 颜伏伍12* 杜常清12
1.武汉理工大学 现代汽车零部件技术湖北省重点实验室, 湖北 武汉 430070; 2.汽车零部件技术湖北省协同创新中心, 湖北 武汉 430070
Author(s):
LIU Jinjiang12 YAN Fuwu12 DU Changqing12
1.Hubei Key Laboratory of Advanced Technology for Automotive Components, Wuhan University of Technology, Wuhan 430070, Hubei; 2.Hubei Collaborative Innovation Center for Automotive Components Technology, Wuhan 430070, Hubei
关键词:
三元锂离子电池 荷电状态 相关向量机 拟合能力 泛化能力
Keywords:
ternary lithium ion battery state of charge relevant vector machine fitting ability generalization ability
分类号:
TM912
DOI:
10.3969/j.issn.1001-8395.2018.05.022
文献标志码:
A
摘要:
三元锂离子电池荷电状态的估计,由于构建模型复杂,受到外界干扰因素影响较大,导致预测精度达不到理想效果,但荷电状态的估计精度对于电池管理系统而言至关重要,因此不断提高估计精度是业内的研究重点.根据已有的相关向量机算法提出了3种改进算法,即循环相关向量机、自回归相关向量机和自回归循环相关向量机,分别对3 600组大样本训练数据进行学习建模,并对另外3 600组大样本数据进行荷电状态的估计,通过与最小二乘支持向量机对比表明,提出的基于自回归循环相关向量机的三元锂离子电池SOC的估计,具有稀疏性好、拟合与泛化能力
Abstract:
Due to the complexity of model building and the influence of external disturbances, the prediction accuracy of the state of charge of the ternary lithium ion battery can not achieve the desired effect. However, the estimation accuracy of the state of charge is very crucial to the battery management system. In this paper, three adapted algorithms are proposed on the basis of the existing relevance vector machine, they are recurrent relevance vector machine, autoregressive relevance vector machine, and autoregressive relevance recurrent vector machine. Then we construct model using 3 600 groups of large sample training data, and predict the state of charge using the other 3 600 groups of large sample data. Through comparing with the least square support vector machine, we draw the conclusion thatt the estimation of the state of charge of the ternary lithium ion battery based on the autoregressive recurrent relevance vector machine proposed in this paper has the advantages of good sparsity, good fitting ability, strong generalization ability, and short running time.

参考文献/References:

[1] HANNAN M A, LIPU M S H, HUSSAIN A, et al. A review of lithiumion battery state of charge estimation and management system in electric vehicle applications:challenges and recommendations[J]. Renewable & Sustainable Energy Reviews,2017,78:834-854.
[2] ZHENG L, ZHANG L, ZHU J, 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,2016,180:424-434.
[3] KONG S N, MOO C S, CHEN Y P, et al. Enhanced coulomb counting method for estimating state-of-charge and state-of-health of lithium-ion batteries[J]. Applied Energy,2009,86(9):1506-1511.
[4] TING T O, MAN K L, LIM E G, et al. Tuning of kalman filter parameters via genetic algorithm for state of charge estimation in battery management system[J]. Scientific World Journal,2014,2014:176052-176052.
[5] YATSUI M W, BAI H. Kalman filter based state of charge estimation for lithium Ion batteries in hybrid electric vehicles using pulse charging[C]//Vehicle Power and Propulsion Conference. New York: IEEE,2011:1-5.
[6] ZHU Z, SUN J, LIU D. Online state of charge EKF estimation for LiFePO4 battery management systems[C]//International Symposium on Intelligent Signal Processing and Communications Systems. New York:IEEE,2013:609-614.
[7] SUN F, HU X, YUAN Z, et al. Adaptive unscented kalman filtering for state of charge estimation of a lithiumion battery for electric vehicles[J]. Energy,2011,36(5):3531-3540.
[8] 乔波强,侯振义,王佑民. 相关向量机在蓄电池剩余容量预测中的应用[J]. 电源技术,2012,36(10):1503-1505.
[9] HE W, WILLIARD N, CHEN C, et al. State of charge estimation for Li-ion batteries using neural network modeling and unscented Kalman filter-based error cancellation[J]. International Journal of Electrical Power & Energy Systems,2014,62(11):783-791.
[10] CHEN Y, LONG B, LEI X. The battery state of charge estimation based weighted least squares support vector machine[C]//Asia-Pacific Power and Energy Engineering Conference. New York:IEEE Computer Society,2011:1-4.
[11] TIPPING M E. Sparse bayesian learning and the relevance vector machine[J]. J Machine Learning Research,2001,1:211-244.
[12] 侯江娜,孙玉坤,王鹏飞. 基于RVM算法的蓄电池SOC预测[J]. 电源技术,2015,39(3):523-526.
[13] 高向阳,张骏,宁宁. 基于相关向量机的蓄电池荷电状态预测[J]. 电源技术,2010,34(12):1273-1275.
[14] TIPPING M E. The relevance vector machine[C]//Advances in Neural Information Processing Systems. DBLP,2000:652-658.
[15] FAUL A, AVENUSE J J T. Fast marginal likelihood maximisation for sparse bayesian models[J]. Proceedings of the Ninth International Workshop on Artificial Intelligence & Statistics,2003:3-6.
[16] WU X, MI L, TAN W, et al. State of charge(SOC)estimation of Ni-MH battery based on least square support vector machines[J]. Advanced Materials Research,2011,211/212(1):1204-1209.

备注/Memo

备注/Memo:
收稿日期:2018-02-07 接受日期:2018-03-30
基金项目:国家自然科学基金(51775393)和湖北省新能源智能汽车平台建设(2016BEC116)
*通信作者简介:颜伏伍(1967—),男,教授,主要从事汽车排放控制技术、汽车动力系统及控制技术的研究,E-mail:yanfuwu@vip.sina.com
更新日期/Last Update: 2018-04-15