{"title":"HyperCAN:超网络驱动的超材料深度参数化构造模型","authors":"Li Zheng, Dennis M. Kochmann, Siddhant Kumar","doi":"arxiv-2408.06017","DOIUrl":null,"url":null,"abstract":"We introduce HyperCAN, a machine learning framework that utilizes\nhypernetworks to construct adaptable constitutive artificial neural networks\nfor a wide range of beam-based metamaterials exhibiting diverse mechanical\nbehavior under finite deformations. HyperCAN integrates an input convex network\nthat models the nonlinear stress-strain map of a truss lattice, while ensuring\nadherence to fundamental mechanics principles, along with a hypernetwork that\ndynamically adjusts the parameters of the convex network as a function of the\nlattice topology and geometry. This unified framework demonstrates robust\ngeneralization in predicting the mechanical behavior of previously unseen\nmetamaterial designs and loading scenarios well beyond the training domain. We\nshow how HyperCAN can be integrated into multiscale simulations to accurately\ncapture the highly nonlinear responses of large-scale truss metamaterials,\nclosely matching fully resolved simulations while significantly reducing\ncomputational costs. This offers new efficient opportunities for the multiscale\ndesign and optimization of truss metamaterials.","PeriodicalId":501309,"journal":{"name":"arXiv - CS - Computational Engineering, Finance, and Science","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"HyperCAN: Hypernetwork-Driven Deep Parameterized Constitutive Models for Metamaterials\",\"authors\":\"Li Zheng, Dennis M. Kochmann, Siddhant Kumar\",\"doi\":\"arxiv-2408.06017\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We introduce HyperCAN, a machine learning framework that utilizes\\nhypernetworks to construct adaptable constitutive artificial neural networks\\nfor a wide range of beam-based metamaterials exhibiting diverse mechanical\\nbehavior under finite deformations. HyperCAN integrates an input convex network\\nthat models the nonlinear stress-strain map of a truss lattice, while ensuring\\nadherence to fundamental mechanics principles, along with a hypernetwork that\\ndynamically adjusts the parameters of the convex network as a function of the\\nlattice topology and geometry. This unified framework demonstrates robust\\ngeneralization in predicting the mechanical behavior of previously unseen\\nmetamaterial designs and loading scenarios well beyond the training domain. We\\nshow how HyperCAN can be integrated into multiscale simulations to accurately\\ncapture the highly nonlinear responses of large-scale truss metamaterials,\\nclosely matching fully resolved simulations while significantly reducing\\ncomputational costs. This offers new efficient opportunities for the multiscale\\ndesign and optimization of truss metamaterials.\",\"PeriodicalId\":501309,\"journal\":{\"name\":\"arXiv - CS - Computational Engineering, Finance, and Science\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-08-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Computational Engineering, Finance, and Science\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2408.06017\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Computational Engineering, Finance, and Science","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2408.06017","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
HyperCAN: Hypernetwork-Driven Deep Parameterized Constitutive Models for Metamaterials
We introduce HyperCAN, a machine learning framework that utilizes
hypernetworks to construct adaptable constitutive artificial neural networks
for a wide range of beam-based metamaterials exhibiting diverse mechanical
behavior under finite deformations. HyperCAN integrates an input convex network
that models the nonlinear stress-strain map of a truss lattice, while ensuring
adherence to fundamental mechanics principles, along with a hypernetwork that
dynamically adjusts the parameters of the convex network as a function of the
lattice topology and geometry. This unified framework demonstrates robust
generalization in predicting the mechanical behavior of previously unseen
metamaterial designs and loading scenarios well beyond the training domain. We
show how HyperCAN can be integrated into multiscale simulations to accurately
capture the highly nonlinear responses of large-scale truss metamaterials,
closely matching fully resolved simulations while significantly reducing
computational costs. This offers new efficient opportunities for the multiscale
design and optimization of truss metamaterials.