802 工程科学学报，第42卷，第6期 study on lithium-ion batteries used in electric vehicles.Eng Fail battery remaining useful life estimation using importance sampling Aal,2016,70:323 and neural networks.App/Energy,2016,173:134 [13]Sahinoglu G O,Pajovic M,Sahinoglu Z,et al.Battery state-of- [18]Li H,Pan D H,Chen C L P.Intelligent prognostics for battery charge estimation based on regular/recurrent Gaussian process health monitoring using the mean entropy and relevance vector regression.IEEE Trans Ind Electron,018,65(5):4311 machine.IEEE Trans Syst Man Cybern Syst,2014,44(7):851 [14]Andre D,Nuhic A,Soczka-Guth T,et al.Comparative study of a [19]Zhou Y P.Huang M H.Chen Y P.et al.A novel health indicator structured neural network and an extended Kalman filter for state for on-ine lithium-on batteries remaining useful life prediction. of health determination of lithium-ion batteries in hybrid Power Sources,2016,321:1 electricvehicles.Eng Appl Artif Intell,2013,26(3):951 [20]LiuJZ.Yang P,Li L B.A method to estimate the capacity of the [15]Hussein AA.Capacity fade estimation in electric vehicle Li-ion lithium-ion battery based on energy model.Trans China batteries using artificial neural networks.IEEE Trans Ind Appl. Electrotech Soc,2015,30(13):100 2015,51(3):2321 (刘金枝，杨鹏，李练兵.一种基于能量建模的锂离子电池电量 [16]Peng X,Zhang C.Yu Y,et al.Battery remaining useful life 估算方法.电工技术学报，2015,30(13)：100) prediction algorithm based on support vector regression and [21]Liu X B,Li Y,Wang N T,et al.A novel model-driven method for unscented particle filter /2016 IEEE International Conference on lithium-ion battery remaining useful life prediction //13th /EEE Prognostics and Health Management (ICPHM).Ottawa,2016:1 International Conference on Electronic Measurement [17]Wu J,Zhang C B,Chen Z H.An online method for lithium-ion Instruments (ICEMD).Yangzhou,2017:446study  on  lithium-ion  batteries  used  in  electric  vehicles. Eng Fail Anal, 2016, 70: 323 Sahinoglu  G  O,  Pajovic  M,  Sahinoglu  Z,  et  al.  Battery  state-of￾charge  estimation  based  on  regular/recurrent  Gaussian  process regression. IEEE Trans Ind Electron, 2018, 65（5）: 4311 [13] Andre D, Nuhic A, Soczka-Guth T, et al. Comparative study of a structured neural network and an extended Kalman filter for state of  health  determination  of  lithium-ion  batteries  in  hybrid electricvehicles. Eng Appl Artif Intell, 2013, 26（3）: 951 [14] Hussein  A  A.  Capacity  fade  estimation  in  electric  vehicle  Li-ion batteries  using  artificial  neural  networks. IEEE Trans Ind Appl, 2015, 51（3）: 2321 [15] Peng  X,  Zhang  C,  Yu  Y,  et  al.  Battery  remaining  useful  life prediction  algorithm  based  on  support  vector  regression  and unscented particle filter // 2016 IEEE International Conference on Prognostics and Health Management (ICPHM). Ottawa, 2016: 1 [16] [17] 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. Appl Energy, 2016, 173: 134 Li  H,  Pan  D  H,  Chen  C  L  P.  Intelligent  prognostics  for  battery health  monitoring  using  the  mean  entropy  and  relevance  vector machine. IEEE Trans Syst Man Cybern Syst, 2014, 44（7）: 851 [18] Zhou Y P, Huang M H, Chen Y P, et al. A novel health indicator for on-line lithium-ion batteries remaining useful life prediction. J Power Sources, 2016, 321: 1 [19] Liu J Z, Yang P, Li L B. A method to estimate the capacity of the lithium-ion  battery  based  on  energy  model. Trans China Electrotech Soc, 2015, 30（13）: 100 （刘金枝, 杨鹏, 李练兵. 一种基于能量建模的锂离子电池电量 估算方法. 电工技术学报, 2015, 30（13）：100） [20] Liu X B, Li Y, Wang N T, et al. A novel model-driven method for lithium-ion  battery  remaining  useful  life  prediction  //  13th IEEE International Conference on Electronic Measurement & Instruments (ICEMI). Yangzhou, 2017: 446 [21] · 802 · 工程科学学报，第 42 卷，第 6 期