Multiple health indicators assisting data-driven prediction of the later service life for lithium-ion batteries

Data-driven method is an efficient tool for diagnostics and prognostics of lithium-ion batteries during their manufacturing and service period. Accurately predicting the later service life of batteries is a meaningful task. Still, it remains a challenge due to the nonlinear rapid capacity decay caused by the accumulation of inner electrochemical deterioration. Here, we use a classic deep neural network algorithm to study the degradation laws in later battery service life under the common role of multiple health indicators. A battery cyclic data pre-processing method is proposed and several characteristic parameters with a high correlation to battery life are carefully selected. Our models achieve an average test error within 5% using any continuous 30 cycles of data to predict the battery capacity curve in the next 200 cycles. This study highlights the promise of combining deliberate data processes with health indicators in data-driven modeling to predict the later service life of lithium-ion batteries.