Battery design optimization

Abstract

A method for optimising battery design comprising receiving one or more battery performance targets indicating design constraints on one or more battery performance characteristics, applying one or more trained machine learning models to search and determine one or more optimal battery designs. The machine learning model(s) adapted to replace one or more replace complex computing intensive battery design physical/mechanical models for creating a plurality of battery designs complying with the design constraint(s) and compute their performance scores are trained to learn the physical/mechanical model(s), created using experimental data collected for a plurality of batteries, using a plurality of training samples extracted from simulations of the physical/mechanical model(s).