Accurate state of health estimation for lithium-ion batteries under random charging scenarios

Accurate state of health (SOH) knowledge is critical for reliable operations of lithium-ion batteries. However, short-term random charging operations of lithium-ion batteries are not conducive to reliable SOH estimation. To solve it, a charging voltage prediction and machine learning based estimation are employed to supply precise estimation. Firstly, the correlated feature variables in terms of SOH are determined by analyzing the raw charging voltage distribution. Then, the wide range charging voltage is predicted via the constructed polynomials and short-term measures. Next, the extreme learning machine algorithm is employed to achieve online SOH estimation. Finally, the feasibility of the proposed voltage estimation method is verified at different aging cycles and different charging intervals, and the reliability of SOH estimation is investigated in the full lifetime range and at different state of charge (SOC) charging intervals. The experimental results manifest that the proposed method can supply reliable SOH estimation with the error of less than 2.02% based on only the shortterm random charging scenarios, furnishing reliable and safe operation guideline for lithium-ion battery systems.

Automated summary

This article proposes a method based on charging voltage prediction and machine learning for reliable estimation of lithium-ion battery state of health (SOH). Correlated feature variables are identified by analyzing the raw charging voltage distribution, and a polynomial-based prediction model is used to estimate a wide range of charging voltage. The extreme learning machine algorithm is then employed for online SOH estimation. Experimental results demonstrate that the proposed method can provide reliable SOH estimation with an error of less than 2.02% in short-term random charging scenarios.