Constituent-Material-Anchored Continual Learning for Full Stress–Strain Prediction of Multi-Material PETG/PC-ABS MEX Laminates
Polymers · 24.06.2026 · 18 (13) · 1573
DOI: 10.3390/polym18131573 ↗Kurz gefasst
Fachartikel in der Zeitschrift Polymers, online erschienen am 24.06.2026. Verfasst von Ramachandran Avala Subramanian und 5 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Electrical Engineering and Computer Science, VSB-Technical University of Ostrava, 17. Listopadu 15/2172, 70800 Ostrava, Czech Republic. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: VSB - Technical University of Ostrava, European Union, European Regional Development Fund.
Abstract (Originalsprache)
Predicting the tensile response of multi-material parts produced by material extrusion (MEX) remains difficult because the final behavior depends on both the constituent polymers and the quality and arrangement of dissimilar interfaces. This study introduces a constituent-material-anchored, phase-aware continual-learning framework for full stress–strain curve prediction of PETG/PC-ABS laminate coupons. Experimentally measured PETG and PC-ABS reference curves were combined through a rule-of-mixtures baseline; an XGBoost residual model then learned pointwise corrections using strain, baseline stress, mechanical phase label, and PETG thickness fraction as inputs. Validation used five PETG reference coupons, five PC-ABS reference coupons, five C1 laminate coupons, two C2 out-of-distribution coupons, and three coupons for each model-suggested Rank 1–3 architecture. UTS agreement alone was not sufficient: Rank 2 had a zero-shot UTS error of only −0.18% but a full-curve RMSE of 20.74%. After the first architecture-specific coupon was introduced, RMSE decreased from 12.34% to 2.72% for C1, from 18.60% to 6.38% for C2, from 21.04% to 6.93% for Rank 1, from 20.74% to 7.50% for Rank 2, and from 19.40% to 7.48% for Rank 3. The framework therefore provides a data-efficient, interpretable proof of concept for laminate screening and tensile-curve prediction, while its broader statistical robustness and extension to other loading modes require larger datasets.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Faculty of Electrical Engineering and Computer Science, VSB-Technical University of Ostrava, 17. Listopadu 15/2172, 70800 Ostrava, Czech Republic.
- Faculty of Mechanical Engineering, VSB-Technical University of Ostrava, 17. Listopadu 15/2172, 70800 Ostrava, Czech Republic.
ORCID-Profile: Ramachandran Avala Subramanian, Mahalingam Nainaragaram Ramasamy, Michal Prauzek, Quoc-Phu Ma, Jaromir Konecny, Ales Sliva
Förderung
- VSB - Technical University of Ostrava
- European Union
- European Regional Development Fund
- VSB-TU Ostrava
- Ministry of Education, Youth and Sports
Zitieren
APA
Subramanian, R. A., Ramasamy, M. N., Prauzek, M., Ma, Q. P., Konecny, J., & Sliva, A. (2026). Constituent-Material-Anchored Continual Learning for Full Stress–Strain Prediction of Multi-Material PETG/PC-ABS MEX Laminates. Polymers, 18(13), 1573. https://doi.org/10.3390/polym18131573
Vancouver
Subramanian RA, Ramasamy MN, Prauzek M, Ma QP, Konecny J, Sliva A. Constituent-Material-Anchored Continual Learning for Full Stress–Strain Prediction of Multi-Material PETG/PC-ABS MEX Laminates. Polymers. 2026;18(13):1573. doi:10.3390/polym18131573
BibTeX
@article{Subramanian2026,
author = {Subramanian, Ramachandran Avala and Ramasamy, Mahalingam Nainaragaram and Prauzek, Michal and Ma, Quoc-Phu and Konecny, Jaromir and Sliva, Ales},
title = {Constituent-Material-Anchored Continual Learning for Full Stress–Strain Prediction of Multi-Material PETG/PC-ABS MEX Laminates},
journal = {Polymers},
year = {2026},
volume = {18},
number = {13},
pages = {1573},
doi = {10.3390/polym18131573}
}
EUVIMED