A New Approach to Battery Capacity Prediction Based on Hybrid ARMA and ANN Model

Abstract:

Research on battery prognostics and health monitoring (PHM) is important in many engineering areas, and battery capacity is a good indicator of battery condition, this paper introduces a new approach to predict battery capacity use hybrid ARMA and ANN model. First, two time series forecast models ARMA and ANN are introduced, since these two models have their own shortcoming in forecasting nonlinear and linear time series respectively, hybrid ARMA and ANN model are established in order to combine both advantage of the two and get more precise prediction result. Then capacity data applied in this paper is described, prediction results and errors based on these data and among three models are compared. At last, the conclusion that hybrid model shows the best performance and will provide a new approach to realize battery capacity predictor is given.

• Periodical: Applied Mechanics and Materials (Volumes 190-191)
• Pages: 241-244
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.190-191.241
• Online since: July 2012
• Authors: Han Cheng Dong, San Tong Zhang, Qing Hua Li, Chang Hong Wang
• Keywords: ARMA, Artificial Neural Network (ANN), Battery Capacity Prediction, Hybrid ARMA and ANN Model, Time Series

References

[1] Jingliang Zhang, Jay Lee, A review on prognostics and health monitoring of Li-ion battery, Journal of Power Sources 196 (2011) 6007–6014.

DOI: 10.1016/j.jpowsour.2011.03.101

[2] C. Chan, E.W.C. Lo, S. Weixiang, The available capacity computation model based on artificial neural network for lead–acid batteries in electric vehicles, Journal of Power Sources 87 (1–2) (2000) 201–204.

DOI: 10.1016/s0378-7753(99)00502-9

[3] J. Kozlowski, Electrochemical cell prognostics using online impedance measurements and model-based data fusion techniques, in: 2003 IEEE Aerospace Conference, Proceedings, Anonymous 7, (2003).

DOI: 10.1109/aero.2003.1234169

[4] Mohammad Rezvani, Mohamed AbuAli, A Comparative Analysis of Techniques for Electric Vehicle Battery Prognostics and Health Management (PHM), SAE international, (2011).

DOI: 10.4271/2011-01-2247

[5] Sudhakar M. Pandit, Shien-Ming Wu, Time Series and System Analysis with Applications, (1990).

[6] G. Zhang, E.B. Patuwo, M.Y. Hu, Forecasting with artificial neural networks: the state of the art, Int. J. Forecasting 14 (1998) 35–62.

DOI: 10.1016/s0169-2070(97)00044-7

[7] P. P. Zhang, Time series forecasting using a hybrid ARIMA and neural network model, Neurocomputing, vol. 50, p.159–175, (2003).

DOI: 10.1016/s0925-2312(01)00702-0

[7] P. P. Zhang, Time series forecasting using a hybrid ARIMA and neural network model, Neurocomputing, vol. 50, p.159–175, (2003).

DOI: 10.1016/s0925-2312(01)00702-0

[8] J.W. Denton, How good are neural networks for causal forecasting? J. Bus. Forecasting 14 (1995) 17–20.

[9] Mehdi Khashei, Mehdi Bijari, A New Hybrid Methodology for Nonlinear Time Series Forecasting, Modelling and Simulation in Engineering, Volume 2011, (2011).

DOI: 10.1155/2011/379121

[10] K. Goebel, B. Saha, A. Saxena, J. R. Celaya, and J. Christophersen, Prognostics in battery health management, IEEE Instrum. Meas. Mag., vol. 11, no. 4, p.33–40, Aug. (2008).

DOI: 10.1109/mim.2008.4579269