Abstract
This paper addresses the State of health (SOH) estimation for system in the prognostics and health management (PHM) of the electronics systems. Due to complicated operation conditions, it is necessary to derive and implement the prognostics with uncertain situations. In this paper, a Bayesian filtering approach based on the adaptive learning for the Gaussian process regression (GPR) model is presented for the SOH estimation of system under uncertain conditions. Instead of assuming the certain state space model for the degradation trend directly, the distribution of the degradation process is investigated to learn from the inputs based on available measurements. In order to capture the time-varying degradation behavior, the proposed method represents the statistical property of the degradation process through distribution learning with the GPR model. By exploiting the distribution information of degradation process, the particle filter can be implemented to predict the SOH of system. Experiments and comparison analysis are provided to demonstrate the efficiency of the proposed approach.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Nishi Y (2001) Lithium ion secondary batteries; Past 10 years and the future. J Power Sources 100:101–106
Wakihara M (2001) Recent developments in Lithium ion batteries. Mater Sci Eng Rep 33:109–134
Vichare NM, Pecht MG (2006) Prognostics and health management of electronics. IEEE Trans Compon Packag Technol 29:222–229
Saha B, Goebel K, Christophersen J (2009) Comparison of prognostic algorithms for estimating remaining useful life of batteries. Trans Inst Meas Control 31:293–308
Saha B, Goebel K et al (2009) Prognostics methods for battery health monitoring using a Bayesian framework. IEEE Trans Instrum Meas 58:291–296
Zhang J, Lee J (2011) A review on prognostics and health monitoring of Li-ion battery. J Power Sources 196:6007–6014
Liu D, Pang J et al (2013) Prognostics for state of health estimation of Lithium-ion batteries based on combination Gaussian process functional regression. Microelectron Reliab 53:832–839
Saha B, Goebel K (2008) Uncertainty management for diagnostics and prognostics of batteries using Bayesian techniques. In: 2008 IEEE aerospace conference. IEEE, pp 1–8
Chen C, Pecht M (2012) Prognostics of Lithium-ion batteries using model-based and data-driven methods. In: 2012 IEEE conference on prognostics and system health management (PHM). IEEE, pp 1–6
Williard N, He W, Pecht M (2012) Model based battery management system for condition based maintenance. In: MFPT, (2012) Proceedings: the prognostics and health management solutions conference. Dayton, OH
He W, Williard N et al (2012) State of charge estimation for electric vehicle batteries under an adaptive filtering framework. In: 2012 IEEE conference on prognostics and system health management (PHM), IEEE, pp 1–5
Liao L, Kottig F (2014) Review of hybrid prognostics approaches for remaining useful life prediction of engineered systems, and an application to battery life prediction. IEEE Trans Reliab 63:191–207
Burgess WL (2009) Valve regulated lead acid battery float service life estimation using a Kalman filter. J Power Sources 191:16–21
Hu C, Youn BD, Chung J (2012) A multiscale framework with extended Kalman filter for lithium-ion battery SOC and capacity estimation. Appl Energy 92:694–704
Saha B, Goebel K et al (2009) Prognostics methods for battery health monitoring using a Bayesian framework. IEEE Trans Instrum Meas 58:291–296
Ko J, Fox D (2009) GP-BayesFilters: Bayesian filtering using Gaussian process prediction and observation models. Auton Robots 27:75–90
Saha B, Goebel K (2007) Battery data set. NASA AMES prognostics data repository
Acknowledgments
The work is supported by China Postdoctoral Science Foundation (Grant No. 2013M542284) and the Postdoctoral Science Foundation funded project of Sichuan University.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Li, F., Wang, Y., Wu, D. (2015). Prognostics for State of Health Estimation of Battery System Under Uncertainty Based on Adaptive Learning Technique. In: Xu, J., Nickel, S., Machado, V., Hajiyev, A. (eds) Proceedings of the Ninth International Conference on Management Science and Engineering Management. Advances in Intelligent Systems and Computing, vol 362. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-47241-5_27
Download citation
DOI: https://doi.org/10.1007/978-3-662-47241-5_27
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-47240-8
Online ISBN: 978-3-662-47241-5
eBook Packages: EngineeringEngineering (R0)