Proceedings of the

The 33rd European Safety and Reliability Conference (ESREL 2023)
3 – 8 September 2023, Southampton, UK

State of Health Estimation of Lithium-Ion Batteries based on Incremental Capacity Curves

Mengyao Geng1, Qiaoqiao Yang1, Huixing Meng1,a and Te Han2

1State Key Laboratory of Explosion Science and Technology, Beijing Institute of Technology, Beijing, China.

2Center for Energy and Environmental Policy Research, Beijing Institute of Technology, Beijing, China.


State of health (SOH) is adopted as a key predictor in the battery management system to ensure the safety and reliability of electric vehicles. In this paper, based on incremental capacity (IC) curves and long short-term memory network (LSTM) with Bayesian optimization, we propose a method for SOH estimation of lithium-ion batteries. Firstly, IC curves are obtained and health features are extracted from partial IC curves. Secondly, LSTM model is established to capture the mapping relationships between health features and SOH. Thirdly, Bayesian optimization is applied to automatically select hyper-parameters of LSTM. Eventually, the effectiveness and superiority of the proposed method are validated on real lithium-ion battery aging datasets from CALCE Prognostics Data Repository.

Keywords: Lithium-ion batteries, Incremental capacity curve, LSTM, Bayesian optimization.

Download PDF