Machine‐learning‐assisted design and optimization of auxetic structures: a bioinspired approach to mimic natural tissues

Tools

Shirzad, M, Chashmi, MJ, Khakzadkelarijani, S, Kang, J, Bodaghi, M ORCID: https://orcid.org/0000-0002-0707-944X and Nam, SY, 2025. Machine‐learning‐assisted design and optimization of auxetic structures: a bioinspired approach to mimic natural tissues. Advanced Engineering Materials. ISSN 1438-1656

Preview

Text
2487990_Bodaghi.pdf - Post-print
Download (1MB) | Preview

Official URL: https://doi.org/10.1002/adem.202500377

Abstract

Auxetic structures, known for their unique mechanical properties, have gained significant attention across diverse fields. This study designs, manufactures, and optimizes bioinspired auxetic structures for biomedical applications, specifically bone and tendon tissue regeneration. A comparative analysis is conducted to evaluate the compressive and tensile properties of various auxetic designs. All structures are optimized using a cost-effective methodology that integrates the finite element method with data-driven supervised machine learning, maximizing Young's modulus with minimal porosity changes. The findings reveal that design variables significantly influence both auxeticity and mechanical properties. For instance, Young's modulus increases by 135.5% in sharp sinus (SS) and curved sinus (CS) structures while maintaining similar auxeticity. In contrast, the star (St) design shows a 76.5% increase in Young's modulus, with auxeticity increasing from −0.45 to −0.915. The modified re-entrant (M-Re) structure exhibits higher Poisson's ratio values, closely mimicking cancellous bone. Additionally, structures with higher auxeticity using re-entrant (Re) designs prove suitable for tendon tissue engineering. SS, CS, and St structures offer versatility in achieving a diverse Young's modulus range, making them well-suited for tendon tissue engineering alongside the Re structure.

Item Type:	Journal article
Publication Title:	Advanced Engineering Materials
Creators:	Shirzad, M., Chashmi, M.J., Khakzadkelarijani, S., Kang, J., Bodaghi, M. and Nam, S.Y.
Publisher:	Wiley
Date:	17 August 2025
ISSN:	1438-1656
Identifiers:	Number Type 10.1002/adem.202500377 DOI 2487990 Other
Rights:	This is the peer reviewed version of the following article: SHIRZAD, M, CHASHMI, MJ, KHAKZADKELARIJANI, S, KANG, J, BODAGHI, M and NAM, SY, 2025. Machine‐learning‐assisted design and optimization of auxetic structures: a bioinspired approach to mimic natural tissues. Advanced Engineering Materials, which has been published in final form at https://doi.org/10.1002/adem.202500377. This article may be used for non-commercial purposes in accordance with Wiley Terms and Conditions for Use of Self-Archived Versions. This article may not be enhanced, enriched or otherwise transformed into a derivative work, without express permission from Wiley or by statutory rights under applicable legislation. Copyright notices must not be removed, obscured or modified. The article must be linked to Wiley’s version of record on Wiley Online Library and any embedding, framing or otherwise making available the article or pages thereof by third parties from platforms, services and websites other than Wiley Online Library must be prohibited.
Divisions:	Schools > School of Science and Technology
Record created by:	Jonathan Gallacher
Date Added:	27 Aug 2025 10:28
Last Modified:	27 Aug 2025 10:31
URI:	https://irep.ntu.ac.uk/id/eprint/54265