State of health estimation for lithium-ion batteries under arbitrary usage using data-driven multi-model fusion

We developed a state-of-health estimation method for lithium-ion batteries using a data-driven multi-model fusion approach. By combining machine learning models and a Kalman filter, our approach provides accurate and robust health estimates under varied operating conditions, enabling safer and more reliable battery management in electric vehicles.

Recommended citation: Zhang, Y., Wik, T., Bergström, J. and Zou, C., 2023. State of health estimation for lithium-ion batteries under arbitrary usage using data-driven multimodel fusion. IEEE Transactions on Transportation Electrification, 10(1), pp.1494-1507.
Download Paper