A generic battery-cycling optimization framework with learned sampling and early stopping strategies.

Battery optimization is challenging due to the huge cost and time required to evaluate different configurations in experiments or simulations. Optimizing the cycling performance is especially costly since battery cycling is extremely time consuming. Here, we introduce an optimization framework building on recent advances in machine learning, which optimizes battery parameters efficiently to significantly reduce the total cycling time. It consists of a pruner and a sampler. The pruner, using the Asynchronous Successive Halving Algorithm and Hyperband, stops unpromising cycling batteries to save the budget for further exploration. The sampler, using Tree of Parzen Estimators, predicts the next promising configurations based on query history. The framework can deal with categorical, discrete, and continuous parameters and can run in an asynchronously parallel way to allow multiple simultaneous cycling cells. We demonstrated the performance by a parameter-fitting problem for calendar aging. Our framework can foster both simulations and experiments in the battery field.