Use case 4
UC4Optimise wire cladding with recycled alloys
Wire-based cladding with recycled alloys
AI-driven process robustness for wire-based laser and hybrid laser-plasma cladding — a digital twin that delivers consistent quality with variable recycled Al alloy feedstock.
The project's most demanding test of scientific reasoning under manufacturing uncertainty. KTH teaches the DFT → CALPHAD → CFD → MPF causal chain linking impurity levels and process parameters to microstructure and hardness. Synergy with Horizon Europe RESTORE (FPS): RESTORE develops recycled wire feedstock; SimuLingua provides the AI simulation framework to optimize it.
- Lead partner
- KTH Royal Institute of Technology
- Consortium partners
- KTH, FLOWPHYS
Related projects
- RESTORE — Horizon Europe sister project — recycled wire feedstock and hybrid laser-plasma cladding (FPS).
Target KPIs
- 100 process parameter sets × 3 recycled Al wire grades
- 20 optimal windows via full DFT–CFD–MPF simulation chain
- 5 experimentally-ready process maps with >90% property achievement at ±10% impurity variation
- 30–50% recycled content validated in silico
- Process window: <6 months computationally vs 12–18 months baseline
- <20 virtual trials vs >100 experimental DoE trials
- Hardness uniformity <10%; defect density <2% porosity
Validation: WP13 (definition) → WP14 (in-silico screening) → WP15 (experimental validation). Reports published as D14.x and D15.x deliverables become public.