Multiple-imputation-particle-filtering scheme for Uncertainty Characterization in Battery State-of-Charge Estimation Problems with Missing Measurement Data



David E. Acun ̃a Marcos E. Orchard Jorge F. Silva Aramis Pe ́rez


The design of particle-filtering-based algorithms for estimation often has to deal with the problem of missing observations. This requires the implementation of an appropriate methodology for real-time uncertainty characterization, within the estimation process, incorporating knowledge from other available sources of information. This article presents preliminary results of a multiple imputation strategy used to improve the performance of a particle-filtering-based state- of-charge (SOC) estimator for lithium-ion (Li-Ion) battery cells. The proposed uncertainty characterization scheme is tested and validated in a case study where the state-space model requires both voltage and discharge current measurements to estimate the SOC. A sudden disconnection of the battery’s voltage sensor is assumed to cause significant loss of data. The results show that the multiple-imputation particle filter enables reasonable uncertainty characterization for the state estimate as long as the voltage sensor disconnection continues. Furthermore, when the voltage measurements are once more available, the level of uncertainty adjusts to levels that are comparable to the case where data was not lost.

How to Cite

E. Acun ̃a D. ., E. Orchard, M. ., F. Silva, J., & Pe ́rez A. . (2014). Multiple-imputation-particle-filtering scheme for Uncertainty Characterization in Battery State-of-Charge Estimation Problems with Missing Measurement Data. Annual Conference of the PHM Society, 6(1).
Abstract 128 | PDF Downloads 60



particle filtering, state of charge estimation, Multiple Imputation

Andrieu, C., Doucet, A., & Punskaya, E. (2001). Sequen- tial monte carlo methods in practice (A. Doucet, N. de Freitas, & N. Gordon, Eds.). Springer-Verlag.

Candy, J. (2009). Bayesian signal processing: Classical, modern and particle filtering methods. Wiley.

Crisan, D., & Doucet, A. (2002). A survey of convergence results on particle filtering methods for practitioners. IEEE Transactions on Signal Processing, 50(3), 736- 746.

Doucet, A., Godsill, S., & Andrieu, C. (2000). On sequential monte carlo sampling methods for bayesian filtering. Statistics and Computing, 10(2), 197-208.

Graham, J., Olchowski, A., & Gilreath, T. (2007). How many imputations are really needed? some practical clarifications of multiple imputation theory. Prevention Science, 8, 206-213.
Housfater, A., Zhang, X., & Zhou, Y. (2006). Nonlinear fusion of multiple sensors with missing data. IEEE International Conference on Acoustics, Speech and Signal Processing, 4, 961-964.

Liu, J., Kong, A., & Wong, W. (1994). Sequential imputations and Bayesian missing data problems. Journal of the
American Statistical Association, 89(425), 278-288.

Orchard, M., Cerda, M., Olivares, B., & Silva, J. (2012). Sequential monte carlo methods for discharge time prognosis in lithium-ion batteries. International Journal of Prognostics and Health Management, 3, 1-12.

Orchard, M., & Vachtsevanos, G. (2009). A particle-filtering approach for on-line fault diagnosis and failure prognosis. Transactions of the Institute of Measurement and Control, 31, 221-246.

Pattipati, B., Sankavaram, C., & Pattipati, K. (2011). System identification and estimation framework for pivotal automotive battery management system characteristics. IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews, 41(6), 869-884.

Pola, D. (2014). An improved prognosis strategy with temperature-dependent state space models for the analysis of the state-of-health and state-of-charge in lithium-ion batteries. M.Sc. Tesis. Department of Electrical Engineering, Universidad de Chile.

Rubin, D. (1987). Multiple imputation for nonresponse in surveys. Wiley.
Technical Research Papers

Most read articles by the same author(s)