GHOST project partner VUB presented promising results from the project at the hybrid 34th International Electric Vehicle Exhibition & Symposium (EVS34) on June 25-28 2021.
Paper abstract: The global electric vehicle (EV) is expanding enormously, foreseeing a 17.4% increase of compound annual growth rate (CAGR) by the end of 2027 as forecasted, the lithium-ion battery is considered as the most widely used battery technology in EV. The accurate and reliable diagnostic and prognostic of battery state guarantee the safe operation of EV and are crucial for durable electric vehicles. Research focusing on lithium-ion battery life degradation has grown more important in recent years focusing to have long-life batteries. In the presented work in EVS34, an aging model is built for the state of health (SoH) estimation for LTO-anode based lithium-ion battery. First, electrochemical impedance spectroscopy (EIS) is used to study the deterioration in battery performance while cycling the battery as part of a years-long campaign, measurements such as charge transfer resistance and ohmic resistance are analysed for different operational conditions and selected as key characteristic parameters for the model. Then, an estimation model based on the backpropagation neural network (BPNN) along with the characteristic parameters is trained and validated with a real-life driving profile. The developed model shows a relatively accurate estimation of SoH with a mean square error (MSE) of 0.002.
