Battery (electricity)

Quantum mechanics

Algorithm

Process (computing)

Engineering

State of charge

Materials science

Support vector machine

Operating system

Atomic physics

Power (physics)

Computer science

Electrical impedance

Thermodynamics

Physics

Nonlinear system

Kriging

Artificial intelligence

Charge (physics)

Machine learning

State (computer science)

Electrical engineering

Energy

Due to the significantly complex and nonlinear behavior of li-ion batteries, forecasting the state of charge (SOC) of the batteries is still a great challenge. Therefore, accurate SOC estimation is essential for the proper operation of batteries while the battery is monitored by the battery management system (BMS). To this end, this paper employs informative measurements of electrochemical impedance spectroscopy (EIS) in machine learning models (ML), i.e., linear regression model and Gaussian process regression (GPR), to accurately predict the SOC of li-ion batteries. First, a feature sensitivity analysis of the data is conducted to extract the most reliable features, i.e., the EIS impedances which are highly correlated with SOC, from EIS measurements. Then, the models are fed by the chosen features. The models are designed to train the input features and establish the mapping relationship between the selected features and the SOC. The results demonstrate that the error of the GPR model was found to be less than 3.8%. Considering onboard EIS measurements, this method can be practically embedded in the battery management system for accurate measurements of SOC of li-ion batteries and ensure the proper and efficient operation of battery-powered electric vehicles.

State of charge prediction of EV Li-ion batteries using EIS: A machine learning approach