AI-Assisted Optimization of Crosslinked PVP/PTFE Hybrid Binders for Dry-Processed Lithium-Ion Battery Anodes

This study presents an AI-assisted approach to the design and evaluation of hybrid binder systems composed of crosslinked polyvinylpyrrolidone (PVP) and polytetrafluoroethylene (PTFE) for dry-processed lithium-ion battery (LIB) anodes. While PTFE offers strong mechanical binding, its limited thermal resilience necessitates enhancement through polar, crosslinkable polymers such as PVP. A machine learning (ML) model was trained on experimental and literature-derived datasets to predict binder formulations with optimal thermal and mechanical performance. The suggested binder ratios were validated through thermogravimetric analysis (TGA), electrochemical cycling, and adhesion testing. The AI-guided hybrid binder system demonstrated improved capacity retention (up to 25% over baseline), lower interfacial impedance, and superior thermal integrity. These findings highlight the potential of AI in accelerating material discovery and optimization for next-generation, solvent-free battery manufacturing.