{"title":"热性能可定制互穿相复合材料反设计的深度学习模型","authors":"Kaiyu Wang, Xin-Lin Gao","doi":"10.1016/j.coco.2025.102579","DOIUrl":null,"url":null,"abstract":"<div><div>A new deep learning model is developed for inverse design of interpenetrating phase composites (IPCs) with customizable thermal properties, including the components of the thermal conductivity (TC) and coefficient of thermal expansion (CTE) tensors. Hybrid triply periodic minimal surface (TPMS) structures are mathematically designed as the reinforcement phase to construct the new IPCs, which display orthotropic, tetragonal and cubic material symmetries. The effective TC and CTE tensors of the IPCs are determined using a finite element-based numerical homogenization method. A robust dataset containing six geometrical parameters and six thermal properties (including the three non-zero components of the TC and CTE tensors, respectively) is generated to establish the topology-property mapping. This is followed by the construction of a new tandem dual-network model, including a forward sub-model and an inverse sub-model, to predict the thermal properties and design the topologies of the hybrid TPMS-based IPCs. The hyperparameters are optimized for both the forward and inverse sub-models, which enables the newly proposed dual-network model to have excellent prediction and design capabilities. In addition, examples are provided to show that the thermal properties of the inversely designed IPCs match well with the targeted values within and beyond the original dataset. The current deep learning model provides a new tool for the forward prediction of thermal properties and inverse design of topologies of IPCs.</div></div>","PeriodicalId":10533,"journal":{"name":"Composites Communications","volume":"59 ","pages":"Article 102579"},"PeriodicalIF":7.7000,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Deep learning model for inverse design of interpenetrating phase composites with customizable thermal properties\",\"authors\":\"Kaiyu Wang, Xin-Lin Gao\",\"doi\":\"10.1016/j.coco.2025.102579\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>A new deep learning model is developed for inverse design of interpenetrating phase composites (IPCs) with customizable thermal properties, including the components of the thermal conductivity (TC) and coefficient of thermal expansion (CTE) tensors. Hybrid triply periodic minimal surface (TPMS) structures are mathematically designed as the reinforcement phase to construct the new IPCs, which display orthotropic, tetragonal and cubic material symmetries. The effective TC and CTE tensors of the IPCs are determined using a finite element-based numerical homogenization method. A robust dataset containing six geometrical parameters and six thermal properties (including the three non-zero components of the TC and CTE tensors, respectively) is generated to establish the topology-property mapping. This is followed by the construction of a new tandem dual-network model, including a forward sub-model and an inverse sub-model, to predict the thermal properties and design the topologies of the hybrid TPMS-based IPCs. The hyperparameters are optimized for both the forward and inverse sub-models, which enables the newly proposed dual-network model to have excellent prediction and design capabilities. In addition, examples are provided to show that the thermal properties of the inversely designed IPCs match well with the targeted values within and beyond the original dataset. The current deep learning model provides a new tool for the forward prediction of thermal properties and inverse design of topologies of IPCs.</div></div>\",\"PeriodicalId\":10533,\"journal\":{\"name\":\"Composites Communications\",\"volume\":\"59 \",\"pages\":\"Article 102579\"},\"PeriodicalIF\":7.7000,\"publicationDate\":\"2025-09-12\",\"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/S2452213925003328\",\"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}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Composites Communications","FirstCategoryId":"88","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2452213925003328","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}
Deep learning model for inverse design of interpenetrating phase composites with customizable thermal properties
A new deep learning model is developed for inverse design of interpenetrating phase composites (IPCs) with customizable thermal properties, including the components of the thermal conductivity (TC) and coefficient of thermal expansion (CTE) tensors. Hybrid triply periodic minimal surface (TPMS) structures are mathematically designed as the reinforcement phase to construct the new IPCs, which display orthotropic, tetragonal and cubic material symmetries. The effective TC and CTE tensors of the IPCs are determined using a finite element-based numerical homogenization method. A robust dataset containing six geometrical parameters and six thermal properties (including the three non-zero components of the TC and CTE tensors, respectively) is generated to establish the topology-property mapping. This is followed by the construction of a new tandem dual-network model, including a forward sub-model and an inverse sub-model, to predict the thermal properties and design the topologies of the hybrid TPMS-based IPCs. The hyperparameters are optimized for both the forward and inverse sub-models, which enables the newly proposed dual-network model to have excellent prediction and design capabilities. In addition, examples are provided to show that the thermal properties of the inversely designed IPCs match well with the targeted values within and beyond the original dataset. The current deep learning model provides a new tool for the forward prediction of thermal properties and inverse design of topologies of IPCs.
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.