Prediction of remaining useful life of battery cell using logistic regression based on strong tracking particle filter

The RUL prediction of battery is an effective approach to improve the battery reliability and service life. This paper proposes a novel evaluation algorithm of battery states which is named logistic regression based on strong tracking particle filter for battery RUL prediction. The core idea of this algorithm is to approximate the non-linear and non-Gaussian process of state update of battery RUL prediction through logistic regression combining least square support vector machine. There are two main contributions: first, we combine logistic regression with least square support vector machine for RUL estimation; second, we introduce logistic regression with particle update by a strong tracking particle filter.

[1]  Arnaud Doucet,et al.  Sequential Monte Carlo Methods to Train Neural Network Models , 2000, Neural Computation.

[2]  Wei Liang,et al.  Remaining useful life prediction of lithium-ion battery with unscented particle filter technique , 2013, Microelectron. Reliab..

[3]  Zhiyu Xiang,et al.  Enhancing particle swarm optimization based particle filter tracker , 2006 .

[4]  Bai Hai-feng,et al.  Application of LS-SVM in Predicting Condition Monitoring Data , 2007 .

[5]  Neil J. Gordon,et al.  A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking , 2002, IEEE Trans. Signal Process..

[6]  M. Pecht,et al.  A case study on battery life prediction using particle filtering , 2012, Proceedings of the IEEE 2012 Prognostics and System Health Management Conference (PHM-2012 Beijing).

[7]  George J. Vachtsevanos,et al.  A particle-filtering approach for on-line fault diagnosis and failure prognosis , 2009 .

[8]  Jianqiu Li,et al.  A review on the key issues for lithium-ion battery management in electric vehicles , 2013 .

[9]  D. Mahinda Vilathgamuwa,et al.  A Sensor Fault Detection and Isolation Method in Interior Permanent-Magnet Synchronous Motor Drives Based on an Extended Kalman Filter , 2013, IEEE Transactions on Industrial Electronics.

[10]  Jay Lee,et al.  Review and recent advances in battery health monitoring and prognostics technologies for electric vehicle (EV) safety and mobility , 2014 .

[11]  Pedro Antonio Gutiérrez,et al.  Logistic Regression by Means of Evolutionary Radial Basis Function Neural Networks , 2011, IEEE Transactions on Neural Networks.

[12]  Kristine L. Bell,et al.  A Tutorial on Particle Filters for Online Nonlinear/NonGaussian Bayesian Tracking , 2007 .

[13]  M. Pecht,et al.  Prognostics of lithium-ion batteries using model-based and data-driven methods , 2012, Proceedings of the IEEE 2012 Prognostics and System Health Management Conference (PHM-2012 Beijing).

[14]  Haifeng Wang,et al.  Comparison of SVM and LS-SVM for Regression , 2005, 2005 International Conference on Neural Networks and Brain.

[15]  Yu Peng,et al.  Dynamic battery remaining useful life estimation: An on-line data-driven approach , 2012, 2012 IEEE International Instrumentation and Measurement Technology Conference Proceedings.