Modeling and Estimation of Lithium-ion Battery State of Charge Using Intelligent Techniques
The Li-ion battery is an energy storage system in consumer and industrial applications. Because of their cell and pack level protection, the Li-ion battery requires a battery management system. The important function of the battery management system is to monitor the Li-ion battery state of charge (SOC), to indicate the charge level of the battery. In this research article, efficient intelligent techniques-based SOC estimation algorithm is presented. The proposed techniques are feedforward neural network and layer recurrent neural network with a Scaled Conjugate Gradient (SCG) and Levenberg-Marquardt (LM) training methods. The proposed estimators are applied on 18650 single-cell Li-ion battery to test the performance of the neural networks to estimate the SOC. A real-time experiment carried out on 18650 single-cell Li-ion battery, and experimental results and characteristics are analyzed. The battery cell voltage and current obtained from experimental results are used as the input parameter to proposed networks and battery SOC as the output. The proposed estimation is carried out in the MATLAB. The simulation results show that layer recurrent neural network with LM training method has the best performance to estimate the Li-ion battery SOC in terms of accurate measurement with actual SOC and highest convergence speed.
KeywordsFeedforward neural network Levenberg-Marquardt Li-ion battery Recurrent neural network Scaled conjugate gradient State of charge
Author would like to thank the Research and development in battery division of Central Electrochemical Research Institute, Council of Scientific and Industrial Research in India, for the financial assistance. The work presented in this paper is a part of the In House Project (IHP) “Design and Development of 1 kWh Solar Energy Storage System using Li-ion Battery cells,” funded by Central Electrochemical Research Institute, India.
- 2.Chang WY (2013) The state of charge estimating methods for battery: a review. ISRN Appl MathGoogle Scholar
- 3.Pang S, Farrell J, Du J, Barth M (2001) Battery state of charge estimation. In: Proceedings of the 2001 American control conference, pp 1644–1649. June 2001Google Scholar
- 5.Berrueta A, San Martin I, Sanchis P, Ursua A (2016) Comparison of state-of-charge estimation methods for stationary Lithium-ion batteries. In: 42nd annual conference of the IEEE industrial electronics society, pp 2010–2015. Dec 2016Google Scholar
- 6.Kribsky P, Krivka J, Valda L, Zahour J (2014) Li-ion state of charge estimation methods. In: 22nd telecommunications forum, pp 649–651. Nov 2014Google Scholar
- 9.Jeon S, Yun JJ, Bae S (Oct 2015) Comparative study on the battery state-of-charge estimation method. Indian J Sci Technol 8(26)Google Scholar
- 13.Yadaiah N, Sowmya G (2006) Neural network based state estimation of dynamical systems. In: International joint conference on neural networks, pp 1042–1049. July 2006Google Scholar
- 17.Youssef C, Omar D, Ahmed G, Fatima E, Najia ES (2017) Designand simulation of an accurate neural network state-of-charge estimator for Lithium ion battery pack. Int Rev Autom Control 10(2):186–192Google Scholar
- 19.Narang SB, Singh M, Pubby K (2015) Comparison of feed forward neural network training methods for visual character recognition. Adv Comput Sci Inf Technol 2(4):366–369Google Scholar
- 20.Prerana ParveenSehgal (2015) Comparative study of GD, LM and SCG method of neural network for thyroid disease diagnosis. Int J Appl Res 1(10):34–39Google Scholar
- 21.Cetisli B, Barkana A (Mar 2009) Speeding up the scaled conjugate gradient algorithm and its application in neuro-fuzzy classifier training. Soft Comput, pp 365–378Google Scholar
- 23.Lv, Xing Y, Zhang J, Na X, Li Y, Liu T, Cao D, Wang FY (2017) Levenberg-marquardt backpropagation training of multilayer neural networks for state estimation of a safety critical cyber-physical system. IEEE Trans Ind InfGoogle Scholar
- 24.Ismail M, Dlyma R, Elrakaybi A, Ahmed R, Habibi S (2017) Battery state of charge estimation using an artifical neural network. IEEE Transp Electrif Conf Expo, pp 342–349Google Scholar