2.793

2018影响因子

(CJCR)

  • 中文核心
  • EI
  • 中国科技核心
  • Scopus
  • CSCD
  • 英国科学文摘

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

一种锂电池SOH估计的KNN-马尔科夫修正策略

赵光财 林名强 戴厚德 武骥 汪玉洁

赵光财, 林名强, 戴厚德, 武骥, 汪玉洁.一种锂电池SOH估计的KNN-马尔科夫修正策略.自动化学报, 2021, 47(2): 453-463 doi: 10.16383/j.aas.c180124
引用本文: 赵光财, 林名强, 戴厚德, 武骥, 汪玉洁.一种锂电池SOH估计的KNN-马尔科夫修正策略.自动化学报, 2021, 47(2): 453-463 doi: 10.16383/j.aas.c180124
Zhao Guang-Cai, Lin Ming-Qiang, Dai Hou-De, Wu Ji, Wang Yu-Jie. A modifled strategy using the KNNMarkov chain for SOH estimation of lithium batteries. Acta Automatica Sinica, 2021, 47(2): 453-463 doi: 10.16383/j.aas.c180124
Citation: Zhao Guang-Cai, Lin Ming-Qiang, Dai Hou-De, Wu Ji, Wang Yu-Jie. A modifled strategy using the KNNMarkov chain for SOH estimation of lithium batteries. Acta Automatica Sinica, 2021, 47(2): 453-463 doi: 10.16383/j.aas.c180124

一种锂电池SOH估计的KNN-马尔科夫修正策略

doi: 10.16383/j.aas.c180124
基金项目: 

国家自然科学基金 61501428

福建省科技攻关项目(引导性项目) 2018H0043

中国科学院科研装备研制项目 YZ201510

详细信息
    作者简介:

    赵光财  中国科学院海西研究院泉州装备制造研究所硕士研究生. 2016年获得中国海洋大学学士学位.主要研究方向为锂电池状态估计. E-mail: zhaoguangcai17@mails.ucas.ac.cn

    戴厚德   中国科学院海西研究院泉州装备制造研究所研究员. 2014年获得慕尼黑工业大学机械工程博士学位.主要研究方向为智能传感器, 信号处理和移动机器人. E-mail:dhd@fjirsm.ac.cn

    武骥   合肥工业大学车辆工程系讲师. 2018年获得中国科学技术大学控制科学与工程博士学位.主要研究方向为复杂系统建模、控制与优化. E-mail: wu.ji@hfut.edu.cn

    汪玉洁   中国科学技术大学自动化系副研究员. 2017年获得中国科学技术大学博士学位.主要研究方向为电动汽车能源管理, 系统建模、状态估计与控制. E-mail:wangyujie@ustc.edu.cn

    通讯作者:

    林名强  中国科学院海西研究院泉州装备制造研究所副研究员. 2016年获中国科学技术大学博士学位. 主要研究方向为计算机视觉, 模式识别, 复杂系统分析与控制. 本文通信作者. E-mail: kdlmq@fjirsm.ac.cn

  • 本文责任编委 曹向辉

A Modified Strategy Using the KNN-Markov Chain for SOH Estimation of Lithium Batteries

Funds: 

National Natural Science Foundation of China 61501428

Project of Science and Technology Department of Fujian Province (Pilot Project) 2018H0043

Research Equipment Development Project of Chinese Academy of Science YZ201510

More Information
    Author Bio:

    ZHAO Guang-Cai  Master student at Quanzhou Institute of Equipment Manufacturing, Haixi Institutes, Chinese Academy of Sciences. He received his bachelor degree from Ocean University of China in 2016. His main research interest is states estimation of Li-ion batteries

    DAI Hou-De  Professor at Quanzhou Institute of Equipment Manufacturing, Haixi Institutes, Chinese Academy of Sciences. He received his Ph. D. degree in mechanical engineering from TU Munchen, Germany, in 2014. His research interest covers intelligent sensors, information processing, and mobile robots

    WU Ji  Lecturer at the School of Automotive and Traffic Engineering, Hefei University of Technology. He received his Ph. D. degree in control science and technology from University of Science and technology of China in 2018. His research interest covers the modeling, control and optimization of the complex systems

    WANG Yu-Jie  Associate researcher in the Department of Automation, University of Science and Technology of China. He received his Ph. D. degree from the University of Science and Technology of China in 2017. His research interest covers energy management of electric vehicles, system modeling, state estimation and control

    Corresponding author: LIN Ming-Qiang  Associate professor at Quanzhou Institute of Equipment Manufacturing, Haixi Institutes, Chinese Academy of Sciences. He received his Ph. D. degree from the University of Science and Technology of China in 2016. His research interest covers computer vision, pattern recognition, and analysis and control of complex systems. Corresponding author of this paper
  • Recommended by Associate Editor CAO Xiang-Hui
  • 摘要: 锂离子电池的健康状态(State of health, SOH)是决定电池使用寿命的关键因素.由于锂电池生产工艺、工作环境和使用习惯等的差异性导致其衰退特性具有较大差异, 因此锂电池SOH难以精确估算.本文采用数据驱动的方式通过对采集的电压数据进行特征提取, 使用贝叶斯正则化神经网络对锂电池SOH进行预测, 同时引入KNN-马尔科夫修正策略对预测结果进行修正.实验结果证明, 贝叶斯正则化算法对锂电池SOH的预测准确度较高, KNN-马尔科夫修正策略提高了预测的精确度和鲁棒性, 组合预测模型对锂电池SOH的平均预测误差小于$1\,\%$, 与采用数据分组处理方法(Group method of data handling, GMDH)、概率神经网络(Probabilistic neural network, PNN)、循环神经网络(Recurrent neural network, RNN)的预测精度进行对比, 该模型的预测精度分别提高了$33.3\,\%$、$48.7\,\%$和$53.1\,\%$.
    Recommended by Associate Editor CAO Xiang-Hui
    1)  本文责任编委 曹向辉
  • 图  1  多层前馈神经网络结构示意图

    Fig.  1  Structure of multilayer feedforward neural network

    图  2  预测模型流程图

    Fig.  2  Flowchart of the proposed prediction model

    图  3  特征提取

    Fig.  3  Feature extraction

    图  4  马尔科夫修正过程修正前后结果对比

    Fig.  4  Comparative results of BRNN and Markov correction

    图  5  MC-BRNN、GMDH、PNN、RNN预测结果对比

    Fig.  5  Comparative results of MC-BRNN, GMDH, PNN and RNN

    表  1  BRNN预测值相对误差及状态划分

    Table  1  BRNN prediction error and state division

    序号实测值预测值相对误差(%)归一化相对误差(%)状态
    10.64450.6431-0.21720.45692
    20.74800.7253-3.03470.14251
    30.96650.9646-0.19650.44962
    40.95020.95080.06310.48653
    50.58020.5695-1.84420.31941
    60.75560.7344-2.80570.16471
    70.92940.93010.07530.48793
    80.92220.94402.36390.79943
    90.68080.69271.74790.65331
    100.86150.8503-1.30010.31231
    110.75560.76190.83380.57063
    120.64450.6431-0.21720.45692
    下载: 导出CSV

    表  2  BRNN预测误差及马尔科夫修正误差

    Table  2  BRNN prediction and Markov correction error

    序号实测值预测值修正前误差(%)修正后误差(%)
    11.00000.98091.90901.4446
    20.99420.97531.88471.4203
    30.99410.97412.00291.5385
    40.98780.97201.58551.1211
    50.96650.96460.1857-0.2787
    60.96070.9623-0.1558-0.6202
    70.95540.93332.20351.7391
    80.93870.9590-2.0253-0.3699
    90.93290.9486-1.57360.0818
    100.92220.9440-2.1778-0.5224
    下载: 导出CSV

    表  3  KNN-马尔科夫修正结果

    Table  3  KNN-Markov correction results

    编号$5\#$电池$6\#$电池$7\#$电池
    有无修正
    MAE (%) 0.470.350.520.430.440.37
    MSE (%$^2$)0.490.370.520.400.480.37
    下载: 导出CSV

    表  4  各算法准确度对比

    Table  4  Comparison of accuracy of each algorithm

    编号$5\#$电池$6\#$电池$7\#$电池
    算法MC-BRNNGMDHPNNRNNMC-BRNNGMDHPNNRNNMC-BRNNGMDHPNNRNN
    MAE ($\%$)0.350.520.640.670.430.610.810.930.370.590.790.83
    MSE ($\%^2$)0.370.670.941.210.400.881.302.350.370.581.571.95
    下载: 导出CSV

    表  5  各算法的时间复杂度对比(s)

    Table  5  Comparison of time complexity of each algorithm (s)

    算法MC-BRNNGMDHPNNRNN
    5号电池1.51011.11840.29944.5942
    6号电池1.43611.19480.24423.7446
    7号电池1.55591.11030.27484.8092
    平均值1.50071.13990.27264.3826
    下载: 导出CSV
  • [1] Cheng K W E, Divakar B P, Wu H J, Ding K, Ho H F. Battery-management system (BMS) and SOC development for electrical vehicles. IEEE Transactions on Vehicular Technology, 2011, 60(1): 76-88 doi: 10.1109/TVT.2010.2089647
    [2] 陈虹, 宫洵, 胡云峰, 刘奇芳, 高炳钊, 郭洪艳.汽车控制的研究现状与展望.自动化学报, 2013, 39(4): 322-346 doi: 10.3724/SP.J.1004.2013.00322

    Chen Hong, Gong Xun, Hu Yun-Feng, Liu Qi-Fang, Gao Bing-Zhao, Guo Hong-Yan. Automotive control: The state of the art and perspective. Acta Automatica Sinica, 2013, 39(4): 322-346 doi: 10.3724/SP.J.1004.2013.00322
    [3] Scrosati B, Garche J. Lithium batteries: Status, prospects and future. Journal of Power Sources, 2010, 195(9): 2419-2430 doi: 10.1016/j.jpowsour.2009.11.048
    [4] Andre D, Appel C, Soczka-Guth T, Sauer D U. Advanced mathematical methods of SOC and SOH estimation for lithium-ion batteries. Journal of Power Sources, 2013, 224: 20-27 doi: 10.1016/j.jpowsour.2012.10.001
    [5] Galeotti M, Ciná L, Giammanco C, Cordiner S, Carlo D A. Performance analysis and SOH (state of health) evaluation of lithium polymer batteries through electrochemical impedance spectroscopy. Energy, 2015, 89: 678-686 doi: 10.1016/j.energy.2015.05.148
    [6] Chen Z, Mi C C, Fu Y H, Xu J, Gong X Z. Online battery state of health estimation based on genetic algorithm for electric and hybrid vehicle applications. Journal of Power Sources, 2013, 240: 184-192 doi: 10.1016/j.jpowsour.2013.03.158
    [7] Mejdoubi A E, Oukaour A, Chaoui H, Gualous H, Sabor J, Slamani Y. State-of-charge and state-of-health lithium-ion batteries' diagnosis according to surface temperature variation. IEEE Transactions on Industrial Electronics, 2016, 63(4): 2391-2402 doi: 10.1109/TIE.2015.2509916
    [8] Liu D T, Pang J Y, Zhou J B, Peng Y, Pecht M. Prognostics for state of health estimation of lithium-ion batteries based on combination Gaussian process functional regression. Microelectronics Reliability, 2013, 53(6): 832-839 doi: 10.1016/j.microrel.2013.03.010
    [9] Moura S J, Chaturvedi N A, Krstić M. Adaptive partial differential equation observer for battery state-of-charge/state-of-health estimation via an electrochemical model. Journal of Dynamic Systems, Measurement, and Control, 2014, 136(1): 011015 doi: 10.1115/1.4024801
    [10] Ng K S, Moo C S, Chen Y P, Hsieh Y C. Enhanced coulomb counting method for estimating state-of-charge and state-of-health of lithium-ion batteries. Applied Energy, 2009, 86(9): 1506-1511 doi: 10.1016/j.apenergy.2008.11.021
    [11] Lievre A, Sari A, Venet P, Hijazi A, Ouattara-Brigaudet M, Pelissier S. Practical online estimation of lithium-ion battery apparent series resistance for mild hybrid vehicles. IEEE Transactions on Vehicular Technology, 2016, 65(6): 4505-4511 doi: 10.1109/TVT.2015.2446333
    [12] Plett G L. Extended Kalman filtering for battery management systems of LiPB-based HEV battery packs: Part 1. Background. Journal of Power Sources, 2004, 134(2): 252-261 doi: 10.1016/j.jpowsour.2004.02.031
    [13] Wu J, Wang Y J, Zhang X, Chen Z H. A novel state of health estimation method of Li-ion battery using group method of data handling. Journal of Power Sources, 2016, 327: 457-464 doi: 10.1016/j.jpowsour.2016.07.065
    [14] Wu J, Zhang C B, Chen Z H. An online method for lithium-ion battery remaining useful life estimation using importance sampling and neural networks. Applied Energy, 2016, 173: 134-140 doi: 10.1016/j.apenergy.2016.04.057
    [15] Klass V, Behm M, Lindbergh G. A support vector machine-based state-of-health estimation method for lithium-ion batteries under electric vehicle operation. Journal of Power Sources, 2014, 270: 262-272 doi: 10.1016/j.jpowsour.2014.07.116
    [16] Eddahech A, Briat O, Bertrand N, Delétage J Y, Vinassa J M. Behavior and state-of-health monitoring of Li-ion batteries using impedance spectroscopy and recurrent neural networks. International Journal of Electrical Power & Energy Systems, 2012, 42(1): 487-494
    [17] Lin H T, Liang T J, Chen S M. Estimation of battery state of health using probabilistic neural network. IEEE Transactions on Industrial Informatics, 2013, 9(2): 679-685 doi: 10.1109/TII.2012.2222650
    [18] Basheer I A, Hajmeer M. Artificial neural networks: fundamentals, computing, design, and application. Journal of Microbiological Methods, 2000, 43(1): 3-31 doi: 10.1016/S0167-7012(00)00201-3
    [19] Lam C H, Shin F G. Formation and dynamics of modules in a dual-tasking multilayer feed-forward neural network. Physical Review E, 1998, 58(3): 3673-3677 doi: 10.1103/PhysRevE.58.3673
    [20] Sun Z, Chen Y, Li X Y, Qin X L, Wang H Y. A Bayesian regularized artificial neural network for adaptive optics forecasting. Optics Communications, 2017, 382: 519-527 doi: 10.1016/j.optcom.2016.08.035
    [21] 杨海深, 傅红卓.基于贝叶斯正则化BP神经网络的股票指数预测.科学技术与工程, 2009, 9(12): 3306-3310, 3318 doi: 10.3969/j.issn.1671-1815.2009.12.029

    Yang Hai-Shen, Fu Hong-Zhuo. Stock index forecast based on Bayesian regularization BP neural network. Science Technology and Engineering, 2009, 9(12): 3306-3310, 3318 doi: 10.3969/j.issn.1671-1815.2009.12.029
    [22] 李红霞, 许士国, 范垂仁.基于贝叶斯正则化神经网络的径流长期预报.大连理工大学学报, 2006, 46(S1): 174-177 https://www.cnki.com.cn/Article/CJFDTOTAL-DLLG2006S1029.htm

    Li Hong-Xia, Xu Shi-Guo, Fan Chui-Ren. Long-term prediction of runoff based on Bayesian regulation neural network. Journal of Dalian University of Technology, 2006, 46(S1): 174-177 https://www.cnki.com.cn/Article/CJFDTOTAL-DLLG2006S1029.htm
    [23] Neal R M. Markov chain sampling methods for dirichlet process mixture models. Journal of Computational and Graphical Statistics, 2000, 9(2): 249-265
    [24] 李新德, 董清泉, 王丰羽, 雒超民.一种基于马尔科夫链的冲突证据组合方法.自动化学报, 2015, 41(5): 914-927 doi: 10.16383/j.aas.2015.c140681

    Li Xin-De, Dong Qing-Quan, Wang Feng-Yu, Luo Chao-Min. A method of conflictive evidence combination based on the Markov chain. Acta Automatica Sinica, 2015, 41(5): 914-927 doi: 10.16383/j.aas.2015.c140681
    [25] NASA. PCoE datasets: battery data set[Online], available: https://ti.arc.nasa.gov/tech/dash/groups/pcoe/prognostic-data-repository/, August 22, 2017.
    [26] 陈峭岩, 魏克新.电动汽车电池SOH的信号统计分析.电源技术, 2016, 40(2): 342-344 doi: 10.3969/j.issn.1002-087X.2016.02.032

    Chen Qiao-Yan, Wei Ke-Xin. Signal Statistic analysis for electric vehicle battery SOH. Chinese Journal of Power Sources, 2016, 40(2): 342-344 doi: 10.3969/j.issn.1002-087X.2016.02.032
    [27] Weng C H, Feng X N, Sun J, Peng H. State-of-health monitoring of lithium-ion battery modules and packs via incremental capacity peak tracking. Applied Energy, 2016, 180: 360-368 doi: 10.1016/j.apenergy.2016.07.126
    [28] 叶涛, 朱学峰, 李向阳, 史步海.基于改进$ k$-最近邻回归算法的软测量建模.自动化学报, 2007, 33(9): 996-999 https://www.cnki.com.cn/Article/CJFDTOTAL-MOTO200709021.htm

    Ye Tao, Zhu Xue-Feng, Li Xiang-Yang, Shi Bu-Hai. Soft sensor modeling based on a modified k-nearest neighbor regression algorithm. Acta Automatica Sinica, 2007, 33(9): 996-999 https://www.cnki.com.cn/Article/CJFDTOTAL-MOTO200709021.htm
    [29] 薛鹏松, 冯民权, 邢肖鹏.基于马尔科夫链改进灰色神经网络的水质预测模型.武汉大学学报(工学版), 2012, 45(3): 319-324 https://www.cnki.com.cn/Article/CJFDTOTAL-WSDD201203010.htm

    Xue Peng-Song, Feng Min-Quan, Xing Xiao-Peng. Water quality prediction model based on Markov chain improving gray neural network. Engineering Journal of Wuhan University, 2012, 45(3): 319-324 https://www.cnki.com.cn/Article/CJFDTOTAL-WSDD201203010.htm
  • 加载中
图(5) / 表(5)
计量
  • 文章访问数:  201
  • HTML全文浏览量:  120
  • PDF下载量:  81
  • 被引次数: 0
出版历程
  • 收稿日期:  2018-03-05
  • 录用日期:  2018-08-01
  • 刊出日期:  2021-02-26

目录

    /

    返回文章
    返回