中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 力学研究所
  3. 中国科学院力学研究所
  4. 流固耦合系统力学重点实验室(2012-)
Prediction of mechanical properties of cross-linked polymer interface by graph convolution network

文献类型：期刊论文

作者王新天洋3,4; Liao LJ(廖丽涓)2,4; Huang CG(黄晨光)1,2,3; Wu XQ(吴先前)2,4
刊名ACTA MECHANICA SINICA
出版日期2026-03-01
卷号42期号:3页码:12
关键词Graph convolutional network Molecular dynamic Adhesive interface Mechanical properties Topology structure
ISSN号0567-7718
DOI10.1007/s10409-024-24627-x
通讯作者Liao, Lijuan(ljl@imech.ac.cn) ; Wu, Xianqian(wuxianqian@imech.ac.cn)
英文摘要Machine learning models have made significant advances in the establishment of structure-property relationships. However, it is still a challenge to predict the mechanical properties of the adhesive interface due to the complexity and randomness of the polymer topologies. In this paper, we employed a graph convolutional network (GCN) model to predict the mechanical properties of a specific cross-linked polymer interfacial system, including yield strength (sigma(y)), ultimate strength (sigma(u)), failure strain (epsilon(u)), and fracture toughness (Gamma) utilizing molecular dynamics simulations. The results showed that the adopted GCN model can predict the mechanical properties with over 88% accuracy. Furthermore, the prediction performances for epsilon(u) and sigma(u) are better than those for Gamma and sigma(y), with R-2 similar to 0.73 for epsilon(u), R-2 similar to 0.64 for sigma(u), R-2 similar to 0.51 for Gamma, and R-2 similar to 0.43 for sigma(y). It is worth noting that the GCN model with the sum aggregator slightly outperforms that with the mean aggregator, and that models with linear regression and fully connected neural network regression provide similar predictions. The influence of input node features on prediction performance was also investigated. It was observed that the node closeness centrality is an important graph parameter in prediction. Specifically, node closeness centrality presents a more significant influence on the global mechanical properties of the adhesive interface, such as epsilon(u), sigma(u), and Gamma. Additionally, sensitivity analysis demonstrated that appropriate hyperparameters can improve computational efficiency without losing accuracy on a restricted set of data. This paper demonstrated the capacity of the GCN model to predict the mechanical properties of the adhesive interface with diverse topologies and provided a possible pathway for improving the mechanical properties of the adhesive interface by tailoring polymer structures in the future.
分类号一类
WOS关键词EPOXY ; EVOLUTION ; FRACTURE
资助项目National Key R&D Program of China[2021YFA0719200] ; National Natural Science Foundation of China[11672314] ; National Natural Science Foundation of China[12272391] ; National Natural Science Foundation of China[12232020] ; CAS Project for Young Scientists in Basic Research[YSBR-096] ; National Supercomputing Center in Shenzhen
WOS研究方向Engineering ; Mechanics
语种英语
WOS记录号WOS:001517048800001
资助机构National Key R&D Program of China ; National Natural Science Foundation of China ; CAS Project for Young Scientists in Basic Research ; National Supercomputing Center in Shenzhen
其他责任者廖丽涓，吴先前
源URL[http://dspace.imech.ac.cn/handle/311007/101877]  
专题力学研究所_流固耦合系统力学重点实验室(2012-)
作者单位1.Chinese Acad Sci, Hefei Inst Phys Sci, Hefei 230031, Peoples R China
2.Univ Chinese Acad Sci, Sch Engn Sci, Beijing 100049, Peoples R China;
3.Univ Chinese Acad Sci, Sch Future Technol, Beijing 100049, Peoples R China;
4.Chinese Acad Sci, Key Lab Mech Fluid Solid Coupling Syst, Inst Mech, Beijing 100190, Peoples R China;
推荐引用方式
GB/T 7714		 王新天洋,Liao LJ,Huang CG,et al. Prediction of mechanical properties of cross-linked polymer interface by graph convolution network[J]. ACTA MECHANICA SINICA,2026,42(3):12.
APA 王新天洋,廖丽涓,黄晨光,&吴先前.(2026).Prediction of mechanical properties of cross-linked polymer interface by graph convolution network.ACTA MECHANICA SINICA,42(3),12.
MLA 王新天洋,et al."Prediction of mechanical properties of cross-linked polymer interface by graph convolution network".ACTA MECHANICA SINICA 42.3(2026):12.

入库方式： OAI收割

来源：力学研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。