Data-driven process maps for functionally graded foams in foam additive manufacturing: Accuracy and interpretability across six models
Abstract
Experimental PLA-CO 2 FAM dataset linking six controllable parameters to strand density.• MLP and Random Forest show comparable best performance on a common held-out test split.• Random Forest provides the strongest non-neural empirical reference and best external-validation performance.• Polynomial surrogates provide closed-form, differentiable maps for exploratory sensitivity inspection.• Process maps quantify 𝑇 𝑒 -𝑆 𝑒 interactions at fixed (𝑃 𝑎 , 𝑡 𝑎 , 𝑡 𝑑 ).
Fields of Study & Subjects
Heat and Mass Transfer in Porous Media
Additive Manufacturing and 3D Printing Technologies
Pickering emulsions and particle stabilization
Publication details
- Journal / source
- Materials & Design
- Publisher
- Elsevier BV
- Volume
- 268
- Pages
- 116463–116463
- Publication date
- 20 June 2026
- Language
- EN