This research explores the advancement of innovative and highly scalable continuous dry coating processes for next-generation batteries by integrating machine learning (ML)/artificial intelligence (AI) with intelligent quality assurance and process monitoring. The study enhances solvent-free electrode manufacturing processes, specifically extrusion and dry transfer, through AI-based inline process control and a connected database, utilizing the DRYtraec® method. Advanced sensor technology was incorporated into a pilot plant, enabling automated data analysis and AI-supported modeling through digital twins. Machine learning models, particularly deep neural networks (DNNs) and convolutional neural networks (CNNs), were developed to optimize process parameters, leading to improved efficiency and product quality while reducing waste. Virtual sensors predict measurement values and detect anomalies early, ensuring high reliability in process monitoring. An active learning framework continuously refines AI models by integrating new production data, while Bayesian optimization (BO) identifies optimal process parameters. The integration of digital twins (DTs) facilitates real-time predictions, enhancing adaptability to evolving conditions. This study highlights the transformative potential of AI/ML in revolutionizing electrode manufacturing, contributing to the development of high-quality battery cells. The implemented methods are independent of the active material used, thereby enabling the production of green, sustainable cells.
1 November 2026 in IEEE Robotics and Automation Letters