Ensemble Surrogate Models for Fast LIB Performance Predictions

Battery Cell design and control have been widely explored through modeling simulation. On the one hand, Doyle’s pseudo-two-dimensional (P2D) model Single Particle Models are among most popular electrochemical models capable of predicting battery performance therefore guiding cell characterization. other empirical obtained, for example, by Machine Learning (ML) methods represent a simpler computationally more efficient complement to used Management System (BMS) purposes. This article proposes ML-based ensemble be estimation an LIB across wide range input material characteristics parameters evaluates 1. Deep ensembles simulation convergence classification 2. structured regressors energy power predictions. The results improvement on state-of-the-art surrogate indicate that deep promising direction design.