A new neural network model for the state-of-charge estimation in the battery degradation process

LiuWang Kang, Xuan Zhao and Jian Ma

Applied Energy, 2014, vol. 121, issue C, 20-27

Abstract: Battery state-of-charge (SOC) is a key parameter of the battery management system in the electric vehicle. To predict the practicable capacity of the battery in the degradation process, the cycle life model is built based on the aging cycle tests of the 6Ah Lithium Ion battery. Combined with the cycle life model, a new Radial Basis Function Neural Network (RBFNN) model is proposed to eliminate the battery degradation’s effect on the SOC estimation accuracy of the original trained model. This proposed model is verified through the 6Ah Lithium Ion battery. First, Urban Dynamometer Driving Schedule (UDDS) and Economic Commission of Europe (ECE) cycles are experimented on the batteries under different temperatures and aging levels. Then, the robustness of the new RBFNN model against different aging levels, temperatures and loading profiles is tested with the datasets of the experiments and compared against the conventional neural network model. The simulations show that the new model can improve the accuracy of the SOC estimation effectively and has a good robustness against varying aging cycles, temperatures and loading profiles. Finally, the measurement of actual aging cycles of the battery in electric vehicles is discussed for the SOC estimation.

Keywords: State-of-charge; Electric vehicle; Cycle life model; Neural network; Robustness analysis (search for similar items in EconPapers)
Date: 2014
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (59)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0306261914000956
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:appene:v:121:y:2014:i:c:p:20-27

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/bibliographic
http://www.elsevier. ... 405891/bibliographic

DOI: 10.1016/j.apenergy.2014.01.066

Access Statistics for this article

Applied Energy is currently edited by J. Yan

More articles in Applied Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().