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

Abstract

As one of the key parameters to characterize the life of lithium‐ion batteries, the state of health (SOH) is of great importance in ensuring the reliability and safety of the battery system. Considering the complexity of practical application scenarios, a novel method based on mechanical‐electrical feature extraction and machine learning is proposed to accurately estimate the SOH. A series of degradation experiments are designed to generate battery aging datasets, including the stress and voltage changes. Health features are directly extracted from the stress‐voltage profile and the mechanical‐electrical health feature factors are obtained through correlation analysis. The long short‐term memory (LSTM) network is introduced to map the relationship between mechanical‐electrical responses and the SOH, where the health feature factors are selected as input vectors. The effectiveness of the proposed method is demonstrated by battery datasets under different conditions, from which the estimated errors are less than 1.5%. This work demonstrates that the analysis and utilization of mechanical‐electrical parameters can not only realize accurate SOH estimation, but also provide a broader field for battery energy management.