Deep learning-enhanced physical modelling for tape-casting slurry microstructures of solid oxide cell substrates
Source abstract
Abstract
Efficient modelling of tape-cast slurry microstructures is a key requirement for accelerating the manufacturing development 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 process exploration. This work presents a hybrid surrogate modelling framework that combines DEM simulations with deep learning to efficiently model tape-cast slurry microstructures of the fuel-electrode substrate. Our proposed framework captures how processing parameters influence the resulting slurry microstructure at the particle scale, enabling prediction of the slurry microstructure without the cost of full-scale DEM simulations. The hybrid model reliably reproduces key microstructural characteristics and microstructural metrics consistent with physics-based observations of DEM-generated data, demonstrating the robustness of the hybrid modelling strategy. 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. Although certain slurry microstructures still present minor deviations, the approach reduces reliance on computationally intensive 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 could support high-throughput and guide experiments in the SOC manufacturing research field.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Machine Learning in Materials Science · Advanced ceramic materials synthesis · High-Temperature Coating Behaviors
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (41)
Show source-provided references
1. Recycling strategies for solid oxide cells10.1002/aenm.202201805 ↗
2. 9 - solid oxide fuel and electrolysis cells
3. A critical review of key materials and issues in solid oxide cells
4. Components manufacturing for solid oxide fuel cells10.1016/S0167-2738(02)00344-2 ↗
5. Richard E. Mistler · 2000
6. Aqueous suspensions for tape-casting based on acrylic binders10.1016/S0955-2219(97)00115-5 ↗
7. Materials and manufacturing technologies for solid oxide fuel cells10.1007/s10853-010-4279-9 ↗
8. Properties of tape-cast Y-substituted strontium titanate for planar anode substrates in SOFC applications10.1007/s10853-011-5255-8 ↗
9. Flow properties of PLZTN aqueous suspensions for tape casting10.1016/j.ceramint.2010.03.011 ↗
10. A versatile strategy for hybridizing small experimental and large simulation data: A case for ceramic tape-casting process10.1016/j.matdes.2023.112357 ↗
11. Ceramic tape casting: A review of current methods and trends with emphasis on rheological behaviour and flow analysis10.1016/j.mseb.2016.07.011 ↗
12. Tape-casting: Relationship between organic constituents and the physical and mechanical properties of tapes10.1016/0955-2219(95)90360-U ↗
13. ERC Artistic. https://www.erc-artistic.eu/. (Accessed 30 April 2025).
14. Accelerated optimization methods for force-field parametrization in battery electrode manufacturing modeling10.1002/batt.202000049 ↗
15. Carbon-binder migration: A three-dimensional drying model for lithium-ion battery electrodes10.1016/j.ensm.2021.09.015 ↗
16. Investigating electrode calendering and its impact on electrochemical performance by means of a new discrete element method model: Towards a digital twin of li-ion battery manufacturing10.1016/j.jpowsour.2020.229320 ↗
17. The ARTISTIC online calculator: Exploring the impact of lithium-ion battery electrode manufacturing parameters interactively through your browser
18. Data specifications for battery manufacturing digitalization: Current status, challenges, and opportunities10.1002/batt.202200224 ↗
19. The ARTISTIC battery manufacturing digitalization initiative: From fundamental research to industrialization
20. Tape casting of anode supports for solid oxide fuel cells at forschungszentrum Jülich10.1111/j.1744-7402.2012.02839.x ↗
21. ImageNet classification with deep convolutional neural networks
22. Going deeper with convolutions
23. Rich feature hierarchies for accurate object detection and semantic segmentation
24. OverFeat: Integrated recognition, localization and detection using convolutional networks
25. Evolution of image segmentation using deep convolutional neural network: A survey
26. A comprehensive analysis of deep regression10.1109/TPAMI.2019.2910523 ↗
27. Coarse-grained physics-based modelling for tape casting of fuel-electrode supports in solid oxide cells10.1016/j.jpowsour.2025.238655 ↗
28. Surrogate modeling of lithium-ion battery electrode manufacturing by combining physics-based simulation and deep learning10.1002/batt.202500433 ↗
29. Cohesion10.1088/0959-5309/43/5/301 ↗
30. pair_style lj/cut command — LAMMPS documentation. https://docs.lammps.org/pair_lj.html. (Accessed 30 April 2025).
31. Surface energy and contact of elastic solids
32. pair_style granular command — LAMMPS documentation. https://docs.lammps.org/pair_gran.html. (Accessed 30 April 2025).
33. 2025
34. LAMMPS - a flexible simulation tool for particle-based materials modeling at the atomic, meso, and continuum scales10.1016/j.cpc.2021.108171 ↗
35. 2025
36. A hybrid modelling approach coupling physics-based simulation and deep learning for battery electrode manufacturing simulations
37. Very deep convolutional networks for large-scale image recognition
38. Abadi · 2015
39. Chollet · 2015
40. Visualization and analysis of atomistic simulation data with OVITO–the open visualization tool10.1088/0965-0393/18/1/015012 ↗
41. Physics-assisted machine learning for the simulation of the slurry drying in the manufacturing process of battery electrodes: A hybrid time-dependent VGG16-DEM model10.1021/acsami.4c23103 ↗