This dissertation focuses on advancing cell finalization in lithium-ion battery production through data-driven approaches. Operando gassing analysis is introduced to study cell internal processes, such as gas evolution and SEI formation, thereby enabling the reduction of formation time while preserving cell quality. Concurrently, machine learning techniques are employed to predict battery cycle life using production data, facilitating early detection of defective cells. The findings provide scalable and material-independent methods for shortening cell finalization while simultaneously ensuring quality.
«
This dissertation focuses on advancing cell finalization in lithium-ion battery production through data-driven approaches. Operando gassing analysis is introduced to study cell internal processes, such as gas evolution and SEI formation, thereby enabling the reduction of formation time while preserving cell quality. Concurrently, machine learning techniques are employed to predict battery cycle life using production data, facilitating early detection of defective cells. The findings provide scal...
»