FULL PDF
Abstract
Solid-state batteries (SSBs) offer significant advantages over conventional lithium-ion batteries, including enhanced safety, higher energy density, and improved thermal stability. However, manufacturing SSBs presents unique challenges, especially concerning defect formation during solid electrolyte deposition, layer interfaces, and electrode integration. These defects can drastically impact battery performance, longevity, and safety. This paper presents a comprehensive approach to detecting manufacturing defects in solid-state battery production using AI-driven inline quality control systems. We discuss the integration of advanced imaging techniques, machine learning (ML) algorithms, and real-time data analytics into roll-to-roll (R2R) processing environments. The results demonstrate the efficacy of AI-based models in identifying micro-defects, predicting failure modes, and optimizing manufacturing parameters, paving the way for scalable, high-yield production of reliable solid-state batteries.
View more >>