History-Agnostic Battery Degradation Inference

Abstract

Lithium-ion batteries (LIBs) have attracted widespread attention as an efficient energy storage device on electric vehicles (EV) to achieve emission-free mobility. However, the performance of LIBs deteriorates with time and usage, and the state of health of used batteries are difficult to quantify and to date are poorly understood. Having accurate estimations of a battery's remaining life across different life stages would benefit maintenance, safety, and serve as a means of qualifying used batteries for second-life applications. Since the full history of a battery may not always be available in downstream applications, in this study, we demonstrate a deep learning framework that enables dynamic degradation trajectory prediction, while requiring only the most recent battery usage information. Specifically, our model takes a rolling window of current and voltage time-series inputs, and predicts the near-term and long-term capacity fade via a recurrent neural network. We exhaustively benchmark our model against a naive extrapolating model by evaluating the error on reconstructing the discharge capacity profile under different settings. We show that our model's performance in accurately inferring the battery's degradation profile is "agnostic" with respect to cell cycling history and its current state of health.

Data science accelerates energy device development

“…For example, in a recent study by Ansari et al, a recurrent neural network model was proposed, taking a rolling window of current and voltage time-series inputs to predict the continuous battery capacity fade curves in the near-term and long-term future. 12 Alternatively, when data is scarce, state-of-the-art data-driven models for predicting device lifetime usually follow a standardized workflow that includes structuring data, identifying relevant features, and then using supervised ML models to predict the device's health or its remaining useful life. For example, Paulson et al 13 used regression models to predict battery cycle life from aging tests of over hundreds of cells.…”