Li-ion battery SOH estimation based on data-driven and hybrid model
Health monitoring of Li-ion battery is important.A hybrid estimation model that combines data-driven and empirical models is proposed.It first uses a data-driven approach based on a long short-term memory(LSTM)model to perform an initial estimation of the state of health(SOH)of Li-ion battery.The online estimates obtained under operating conditions are then used to fit a double-exponential empirical model.Further,the error and gain between the observed values and the estimates are used to update the parameters of the double exponential model iteratively,enabling more accurate real-time SOH estimation.The hybrid estimation model can accurately estimate the SOH of Li-ion battery,with the average mean absolute error(MAE)and the average root mean square error(RMSE)of the estimation results being 0.003 3 and 0.004 2,respectively,when the correction cycle of the observer is a single cycle.Its performance is superior to the SOH estimation using only the LSTM data-driven approach.
Li-ion batteryempirical modelhybrid modeldata-drivenstate of health(SOH)
万方数据
维普
