SOC Prediction Method of a New Lithium Battery Based on GA-BP Neural Network

  • Kai GuanEmail author
  • Zhiqiang Wei
  • Bo Yin
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 355)


The prediction of a battery’s state of charge (SOC) is one of the key tasks of battery management. Lithium battery internal chemical reactions are complex and have many factors; its SOC prediction has strong nonlinear characteristics. This paper discussed a SOC prediction model which is based on hybrid genetic algorithm and BP neural network. Set BP neural network’s training error as genetic algorithm fitness value, and then iterate to find the optimal individual as the neural network initialization thresholds and weights. Simulation results show that this method can accurately predict the new kind of a lithium battery’s SOC and have higher accuracy compared with BP neural network.


State of charge Genetic algorithm BP neural networks Prediction method 



This work was financially supported by National 863 Plan Project (2014AA052303-5).


  1. 1.
    Kumar P, Kolar AK. Effect of cathode design on the performance of an air-breathing PEM fuel cell. Int J Hydrogen Energy. 2010;35(2):671–81.CrossRefGoogle Scholar
  2. 2.
    Wu C, Wang F. The research an application on neural network. Harbin: Northeast Agricultural University; 2007 (In Chinese).Google Scholar
  3. 3.
    Li Y. Analysis and improvement applications of BP neural network. Huainan: Anhui University of Science and Technology; 2012 (In Chinese).Google Scholar
  4. 4.
    Wang J, Zhou S, Ye S. Weather threat modeling and assessment based on genetic algorithm and BP neural networks. Institute of Meteorology. PLA Univ Sci Technol. 2012;19(03):74–7 (In Chinese).Google Scholar
  5. 5.
    Li H. Research on battery management system of electric vehicle. Zibo: Shandong University of Technology; 2008 (In Chinese).Google Scholar
  6. 6.
    Ma Y, Chen Q, Qi Z. Research on the SOC definition and measurement method of batteries used in Evs. J Tsinghua Univ (Sci&Tech). 2001;41(11):95–7 (In Chinese).Google Scholar
  7. 7.
    Lin C, Wang J, Chen Q. Methods for state of charge estimation of EV batteries and their application. J Battery Bimonthly. 2004;34(05):376–8 (In Chinese).Google Scholar
  8. 8.
    Ma A. Design of smart management system of Li-ion battery. Beijing: Beijing Jiaotong University; 2008 (In Chinese).Google Scholar
  9. 9.
    Pan W, Liu X. Research on estimating SOC of lithium-ion battery based on improved Kalman filter. Comput Simul. 2014;31(03):148–50 (In Chinese).Google Scholar
  10. 10.
    Huang Y, Tang H. Prediction of lithium-ion battery SOC in EV based on genetic neural network. J Mech Electr Eng. 2013;30(10):1255–8 (In Chinese).Google Scholar
  11. 11.
    Shi P, Bu C, Zhao Y. The ANN models for SOC/BRC estimation of Li-ion battery//2005 I.E. International Conference on Information Acquisition. IEEE; 2005. p. 560–4 (In Chinese).Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.College of Information Science and EngineeringOcean University of ChinaQingdaoChina

Personalised recommendations