Prediction of future capacity and internal resistance of Li-ion cells from one cycle of input data

There is a large demand for models able to predict the future capacity retention and internal resistance (IR) of Lithium-ion battery cells with as little testing possible. We provide data-centric model accurately predicting cell’s entire IR trajectory from one single cycle input data. This represents significant reduction in amount data needed over previous works. Our approach characterises curve through small number key points, which, once predicted interpolated, describe full curve. With this remaining useful life an 8.6% mean absolute percentage error when input-cycle within first 100 cycles.