Surrogate-Model Prediction of Mechanical Response in Architected Ti6Al4V Cylindrical TPMS Metamaterials
Metals · 15.12.2025 · 15 (12) · 1372
DOI: 10.3390/met15121372 ↗Kurz gefasst
Fachartikel in der Zeitschrift Metals, online erschienen am 15.12.2025. Verfasst von Mansoureh Rezapourian und 4 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 76 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Estonian Research Council.
Abstract (Originalsprache)
A Machine Learning (ML)-based surrogate modeling framework is presented for mapping structure–property relationships in architected Ti6Al4V cylindrical TPMS metamaterials subjected to quasi-static compression. A Python–nTop pipeline automatically generated 3456 cylindrical shell lattices (Gyroid, Diamond, Split-P), and ABAQUS/Explicit simulations with a Johnson–Cook failure model for Ti6Al4V quantified their mechanical response. From 3024 valid designs, key mechanical properties targets including elastic modulus (E), yield stress (Y), ultimate strength (U), plateau stress (PL), and energy absorption (EA) were extracted alongside geometric descriptors such as surface area (SA), surface-area-to-volume ratio (SA/VR), and relative density (RD). A multi-output surrogate model (feedforward neural network) trained on the simulated set accurately predicts these properties directly from seven design parameters (thickness; unit cell counts in X, Y, and Z directions; unit cell orientation; height; diameter), enabling rapid property estimation across large design spaces. Topology-dependent trends indicate that Split-P exhibits the highest strength, energy absorption, and total SA, and shows the largest variation in SA/VR; Gyroid exhibits the lowest SA with a moderate SA/VR; and Diamond is the most compliant lattice and maintains a higher SA/VR than Gyroid despite lower SA. RD increases with both SA and SA/VR across all topologies. The framework provides a reusable computational tool for architectured lattices, enabling quick prescreening of implant designs without repeated finite-element analyses.
Förderung
- Estonian Research Council
Zitieren
APA
Rezapourian, M., Darabi, A. C., Khoshbin, M., Schmauder, S., & Hussainova, I. (2025). Surrogate-Model Prediction of Mechanical Response in Architected Ti6Al4V Cylindrical TPMS Metamaterials. Metals, 15(12), 1372. https://doi.org/10.3390/met15121372
Vancouver
Rezapourian M, Darabi AC, Khoshbin M, Schmauder S, Hussainova I. Surrogate-Model Prediction of Mechanical Response in Architected Ti6Al4V Cylindrical TPMS Metamaterials. Metals. 2025;15(12):1372. doi:10.3390/met15121372
BibTeX
@article{Rezapourian2025,
author = {Rezapourian, Mansoureh and Darabi, Ali Cheloee and Khoshbin, Mohammadreza and Schmauder, Siegfried and Hussainova, Irina},
title = {Surrogate-Model Prediction of Mechanical Response in Architected Ti6Al4V Cylindrical TPMS Metamaterials},
journal = {Metals},
year = {2025},
volume = {15},
number = {12},
pages = {1372},
doi = {10.3390/met15121372}
}
EUVIMED