State of Health Estimation of Lithium-ion Batteries Based on Machine Learning with Mechanical-Electrical Features

         A SOH estimation method based on mechanical-electrical response is presented. A series of degradation experiments are designed to generate battery aging datasets, and five health features are directly extracted from the stress-voltage profile. The LSTM network is introduced to map the relationship between health features and the SOH. This work can provide a broader field for battery energy management.

July 2024