Machine learning for mechanical design of composite materials and composite structures
MechanoEngineering · 01.03.2026 · 1 (1)
DOI: 10.1063/5.0285502 ↗Kurz gefasst
Fachartikel in der Zeitschrift MechanoEngineering, online erschienen am 06.01.2026. Verfasst von Wenwang Wu und 8 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 258 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of Shanghai, National Natural Science Foundation of China.
Abstract (Originalsprache)
In recent years, artificial intelligence (AI) has become deeply integrated into composite materials science and engineering, and it can contribute to new material discovery and performance optimization. This article first summarizes the trends of integration of machine learning algorithms, databases, and specialist knowledge about composite materials and composite structures with the design, fabrication, characterization, and service performance evaluation of these materials and structures. The physical essence and classification of mechanical metamaterials are elaborated as a special category of composite structures. The article then reviews the integration of machine learning-based and data-driven computational engineering of composite materials with intelligent design of composite materials, including machine learning for resins and matrix materials and for interface design and analysis of composite materials, forward prediction and inverse design of composite materials, structural damage characterization and analysis, long-term service safety and duality evaluation of composite materials. It then reviews the application of machine learning to composite structures (especially mechanical metamaterials), including forward prediction for traditional multiscale computations empowered by AI, intelligent structure–performance predictive modeling, pure data-driven approaches for prediction of material properties, physics-embedded machine learning for intelligent design of composite structures, and generative design and inverse design of composite structures. Furthermore, recent advances in machine learning and data-driven design of multifunctional applications of mechanical metamaterials are briefly introduced. Finally, perspectives and future trends of composite materials and structures are briefly discussed, including tailoring of multitopological features on demand and long-term structural integrity of composite materials and composite structures.
Förderung
- National Natural Science Foundation of Shanghai
- National Natural Science Foundation of China
Zitieren
APA
Wu, W., Xu, K., Zhao, J., Yang, H., Yang, X., Yu, H., Jiang, D., Song, Z., & Xiong, J. (2026). Machine learning for mechanical design of composite materials and composite structures. MechanoEngineering, 1(1). https://doi.org/10.1063/5.0285502
Vancouver
Wu W, Xu K, Zhao J, Yang H, Yang X, Yu H, et al. Machine learning for mechanical design of composite materials and composite structures. MechanoEngineering. 2026;1(1). doi:10.1063/5.0285502
BibTeX
@article{Wu2026,
author = {Wu, Wenwang and Xu, Kang and Zhao, Jian and Yang, Huihui and Yang, Xueqin and Yu, Huabin and Jiang, Dongjie and Song, Zhenhua and Xiong, Jian},
title = {Machine learning for mechanical design of composite materials and composite structures},
journal = {MechanoEngineering},
year = {2026},
volume = {1},
number = {1},
doi = {10.1063/5.0285502}
}
EUVIMED