State-of-Health Estimation and Remaining-Useful-Life Prediction for Lithium-Ion Battery Using a Hybrid Data-Driven Method

Lithium-ion (Li-ion) batteries have been widely applied in industrial applications. It is desired to predict the health state of batteries to achieve optimal operation and health management. However, accuracy is the biggest bottleneck for battery health prediction. In this paper, a new hybrid ensemble data-driven method is proposed to accurately predict the state-of-health (SOH) and remaining-useful-life (RUL) of Li-ion batteries. A health indicator is selected as feature inputs to predict the degradation trend of battery, after the Pearson correlation analysis. Two random learning algorithms are integrated to extract the inherent relationship between the extracted health indicator and practical SOH due to their good learning performance. Based on the estimated SOH, the nonlinear autoregressive (NAR) structure is designed to reduce the RUL prediction error of each learning model since the NAR structure makes good use of historical and current information. Finally, in order to quantitatively evaluate the prediction interval of the RUL, a Bootstrap-based uncertainty management method is designed. Test results on two publicly available datasets show that the proposed hybrid data-driven method can accurately predict the SOH and RUL of batteries. The proposed method does not require any other additional hardware or system downtime, which makes it suitable for online practical applications, such as energy storage systems and electric vehicles.