Aging feature Extracting Strategy Considering Battery Usage Conditions and Optimized ELM-Based Accurate SOH Estimation

Accurate State of Health (SOH) estimation is of great significance for battery maintenance and safe driving of electric vehicles. This paper first constructs effective aging features based on the characteristics of similar triangles formed by the charging voltage curve, and then designs an aging feature extracting strategy considering the battery's actual usage conditions. To establish an accurate SOH estimation model, particle swarm optimization algorithm is used to optimize the parameters of Extreme Learning Machine (ELM). The experimental results show that the constructed aging features are reasonable, and the established optimized ELM-based data-driven model has a high SOH estimation accuracy.