State of Health Estimation for Lithium-Ion Batteries Based on Healthy Features and Long Short-Term Memory

Yitao Wu,Yonggang Liu,Jiangwei Shen,Zheng Chen,Zhenzhen Lei,Qiao Xue

doi:10.1109/access.2020.2972344

Abstract

Precise estimation of state of health (SOH) are of great importance for proper operation of lithium-ion batteries equipped in electric vehicles. For real applications, it is however difficult to estimate battery SOH due to stochastic operation, which in turn speeds up aging process of the battery. To attain the precise SOH estimation, an efficient estimation manner based on machine learning is proposed in this study. Firstly, the voltage profile during charging and discharging process and incremental capacity variation are acquired through the cycle life test, and the healthy features correlating to battery degradation are extracted. Secondly, the grey relation analysis and entropy weight method are employed to analyze the healthy features. Finally, the long short-term memory is established to achieve the SOH estimation of battery. The experimental results highlight that the proposed method can effectively predict the battery SOH with preferable accuracy, stability and robustness.

Highlights

Lithium-ion batteries have been widely equipped in electric vehicles (EVs) due to their advantages of high energy, power density and long lifespan [1]–[3]
It should be carefully concerned that at least how much training data is enough for the long short-term memory (LSTM) to achieve acceptable prediction performance
The data of cell 1 is utilized to analyze the effect on state of health (SOH) prediction with respect to different data size, and the data of other cells are adopted to evaluate the model performance on different batteries