Data-driven machine learning modelling for the manufacturing of the fuel electrode support in solid oxide cells

tape casting typically involves a multi-stage process, demanding precise control over tape thicknessand density. However, conventional SOC manufacturing processes are resource-intensive and oftenrely on industry/R&D unpublished knowledge and trial-and-error practices to achieve the targetproperties of the resulting tape. Hence, machine learning (ML) was employed for predicting thethickness and density across three distinct stages of the fabrication process: tape casting, sintering,and NiO-reduction process. Our developed ML models (e.g., Extra Trees and Ridge Regressions)demonstrate exceptional accuracy (R2 > 0.9) for each specific prediction task. Concurrently,experimental data analysis was conducted to elucidate the impact of the manufacturing parameterson the tape properties. Our data-driven ML approach offers a pathway towards achieving precise tapeproperty control and advancing more efficient SOC support manufacturing.