Gast ::
| Hauptseite > Publikationsdatenbank > Deep learning-enhanced physical modelling for tape-casting slurry microstructures of solid oxide cell substrates |
| Hauptseite > Publikationsdatenbank > Deep learning-enhanced physical modelling for tape-casting slurry microstructures of solid oxide cell substrates |
| Journal Article | FZJ-2026-02878 |
; ; ; ; ; ;
2026
Elsevier
New York, NY [u.a.]
This record in other databases:
Please use a persistent id in citations: doi:10.1016/j.jpowsour.2026.240447 doi:10.34734/FZJ-2026-02878
Abstract: Efficient modelling of tape-cast slurry microstructures is a key requirement for accelerating the manufacturingdevelopment of solid oxide cell (SOC) fuel-electrode substrates. While physics-based discrete element method(DEM) simulations provide high-fidelity microstructural insight, their computational cost restricts rapid processexploration. This work presents a hybrid surrogate modelling framework that combines DEM simulations withdeep learning to efficiently model tape-cast slurry microstructures of the fuel-electrode substrate. Our proposedframework captures how processing parameters influence the resulting slurry microstructure at the particlescale, enabling prediction of the slurry microstructure without the cost of full-scale DEM simulations. Thehybrid model reliably reproduces key microstructural characteristics and microstructural metrics consistentwith physics-based observations of DEM-generated data, demonstrating the robustness of the hybrid modellingstrategy. Our hybrid surrogate approach minimised the computational cost versus the pure DEM simulation,reducing the calculation time from 1230 to 30 min for the whole slurry simulation process. Althoughcertain slurry microstructures still present minor deviations, the approach reduces reliance on computationallyintensive DEM simulations and supports faster validation and early-stage optimisation. As a proof of concept,our work provides a foundation for developing data-efficient and scalable digital modelling tools that couldsupport high-throughput and guide experiments in the SOC manufacturing research field.
; 
; 
; Clarivate Analytics Master Journal List ; Current Contents - Engineering, Computing and Technology ; Current Contents - Physical, Chemical and Earth Sciences ; Ebsco Academic Search ; Essential Science Indicators ; IF >= 5 ; JCR ; SCOPUS ; Science Citation Index Expanded ; Web of Science Core Collection
|
The record appears in these collections: |
PDF