Li-ion battery design through microstructural optimization using generative AI

Lithium-ion batteries are used across various applications, necessitating tailored cell designs to enhance performance. Optimizing electrode manufacturing parameters is a key route to achieving this, as these parameters directly influence the microstructure and performance of the cells. However, linking process parameters to performance is complex, and experimental or modeling campaigns are often slow and expensive. This study introduces a fast computational optimization framework for electrode manufacturing parameters. A generative model, trained on a small dataset of microstructural images associated with different manufacturing parameters, efficiently generates representative microstructures for new parameters. This model is integrated into a Bayesian optimization loop that includes microstructure generation, characterization, and simulation, aiming to find optimal manufacturing parameters for a particular application. Significant improvement in the energy density of a 4680 cell is achieved through bespoke cell design, highlighting the importance of cell-scale normalization. The framework’s modularity allows its application to various advanced materials manufacturing scenarios. • Generative AI predicts optimal Li-ion battery electrode microstructures rapidly • Bayesian optimization enables an efficient design process to enhance cell performance • The framework’s modularity allows application to various advanced materials The microstructure of lithium-ion battery electrodes strongly affects the cell-level performance. Our study presents a computational design workflow that employs a generative AI from Polaron to rapidly predict optimal manufacturing parameters for battery electrodes. After training a generative model on a small dataset of two-dimensional (2D) microstructural images, we can efficiently generate representative microstructures for new parameters, enabling us to integrate this capability into a Bayesian optimization loop. This allows for the identification of optimal manufacturing conditions that enhance performance, such as energy density. Improved battery performance can accelerate the adoption of electric vehicles and large-scale energy storage systems, contributing to reduced carbon emissions and a sustainable energy future. Our framework’s modularity also makes it applicable to a broad range of advanced materials, potentially transforming how industries approach material design and manufacturing. In this study, we introduce a computational framework using generative AI to optimize lithium-ion battery electrode design. By rapidly predicting ideal manufacturing conditions, our method enhances battery performance and efficiency. This advancement can significantly impact electric vehicle technology and large-scale energy storage, contributing to a sustainable future. The approach’s versatility also opens new possibilities for various advanced materials, revolutionizing how industries design and manufacture high-performance components.