{"title":"Machine learning-assisted dual-objective synergistic optimization for mechanical and electrical properties of CNTs/Cu composites","authors":"XianFeng Zhao, ChangChun Ge","doi":"10.1016/j.coco.2025.102583","DOIUrl":null,"url":null,"abstract":"<div><div>Overcoming the tensile strength-electrical conductivity trade-off in CNTs/Cu composites remains challenging due to complex multi-parameter coupling. We present a novel machine learning (ML)-assisted synergistic design framework enabling simultaneous optimization of both properties. Systematically evaluating seven ML algorithms under diverse preprocessing strategies, we established an effective modeling approach for limited datasets, achieving sub-10 % prediction errors for ultimate tensile strength and conductivity. Crucially, integrating ML predictions with Pareto optimization via the weighted Tchebycheff methodology generated experimentally validated, manufacturable process parameter sets, resolving conventional trial-and-error limitations. Experimental fabrication and comprehensive characterization confirmed the framework's accuracy, practicality, scalability, and engineering significance. This research establishes an intelligent pathway for the synergistic design of advanced metal matrix composites.</div></div>","PeriodicalId":10533,"journal":{"name":"Composites Communications","volume":"59 ","pages":"Article 102583"},"PeriodicalIF":7.7000,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Composites Communications","FirstCategoryId":"88","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2452213925003365","RegionNum":2,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MATERIALS SCIENCE, COMPOSITES","Score":null,"Total":0}
引用次数: 0
Abstract
Overcoming the tensile strength-electrical conductivity trade-off in CNTs/Cu composites remains challenging due to complex multi-parameter coupling. We present a novel machine learning (ML)-assisted synergistic design framework enabling simultaneous optimization of both properties. Systematically evaluating seven ML algorithms under diverse preprocessing strategies, we established an effective modeling approach for limited datasets, achieving sub-10 % prediction errors for ultimate tensile strength and conductivity. Crucially, integrating ML predictions with Pareto optimization via the weighted Tchebycheff methodology generated experimentally validated, manufacturable process parameter sets, resolving conventional trial-and-error limitations. Experimental fabrication and comprehensive characterization confirmed the framework's accuracy, practicality, scalability, and engineering significance. This research establishes an intelligent pathway for the synergistic design of advanced metal matrix composites.
期刊介绍:
Composites Communications (Compos. Commun.) is a peer-reviewed journal publishing short communications and letters on the latest advances in composites science and technology. With a rapid review and publication process, its goal is to disseminate new knowledge promptly within the composites community. The journal welcomes manuscripts presenting creative concepts and new findings in design, state-of-the-art approaches in processing, synthesis, characterization, and mechanics modeling. In addition to traditional fiber-/particulate-reinforced engineering composites, it encourages submissions on composites with exceptional physical, mechanical, and fracture properties, as well as those with unique functions and significant application potential. This includes biomimetic and bio-inspired composites for biomedical applications, functional nano-composites for thermal management and energy applications, and composites designed for extreme service environments.