Cloud-based in-situ battery life prediction and classification using machine learning

Abstract

In-situ battery life prediction and classification can advance lithium-ion battery prognostics and health management. A novel physical features-driven moving-window battery life prognostics method is developed in this paper, which can be used to predict the battery remaining useful life (RUL) and knee-point, and for the first time to classify the battery life in real-time. The relationship between the physical features and battery life is captured by using machine learning. The proposed methodology is validated based on experimental data of more than 100 cell samples. The results show that the method predicts accurate RUL and knee-point, with the root mean squared error and mean absolute percentage error being, respectively, low to 55 cycles and 3.55%. The battery life is also classified accurately based on the data of only one single cycle, with the sorting accuracy up to 91.84%, facilitating fast and efficient sorting/screening of retired batteries in the future. Both the prediction and classification accuracies decrease as the moving-window moves forward, indicating accurate life prediction can still be obtained even when the battery has been put in operation for years.