Fraunhofer initiates TRAICELL project aimed at enhancing the efficiency of battery cell manufacturing
The German research institute Fraunhofer FFB has launched a three-year project called TRAICELL, aimed at optimising battery cell production through the use of advanced machine learning techniques and detailed data tracking throughout the manufacturing process. Funded by the German Federal Ministry of Education and Research, the initiative seeks to create prototypes and scale production stages that enable precise tracking of production and quality data down to the level of individual electrode layers.
At the heart of TRAICELL's approach is the tracking of production and quality data across production layers, allowing for detailed monitoring and control. The project also focuses on optimising critical processes like mixing and coating to enhance efficiency and product quality.
In addition, machine learning models will be developed and implemented to predict the quality of battery cells during early production phases. This capability aims to minimise waste, reduce production times, and improve material yield by detecting defects or quality issues early on.
The TRAICELL project consortium includes Fraunhofer FFB, electrode and cell manufacturer UniverCell, quality assurance provider BST, and AI developer Merantix Momentum. The collaboration ensures both technological innovation and practical applicability from pilot to near-series production scales.
Professor Achim Kampker, PEM Director, emphasised the need for faster transfer of innovative solutions from research to industry, specifically in digitalized battery cell production. He emphasised the importance of making reliable quality predictions during the forming process to reduce production times and detect rejects at an early stage.
TRAICELL's ultimate goal is to create three near-series prototypes and three scaling stages of battery production. The consortium will develop and test the systems on various scales, from pilot to near-series production, with the aim of enhancing battery cell manufacturing workflows, aiming for higher quality, reduced waste, and more efficient industrial-scale battery production.
Data-and-cloud-computing technology plays a crucial role in TRAICELL, as the project utilizes advanced digital tracking and machine learning models to optimize battery cell production. The technology enables precise monitoring and control of production and quality data, allowing for earlier detection of defects and improved efficiency.