检索结果-南通市图书馆

Deep convolutional Ritz method: parametric PDE surrogates without labeled data

Applied Mathematics and Mechanics(English Edition) 2023年第7期44卷 1151-1174页

作者： J.n.FUHG A.KARMARKAR T.KADEETHUM H.YOOn n.bouklas Sibley School of Mechanical and Aerospace Engineering Cornell UniversityNew York 14853U.S.A Geomechanics Department Sandia National LaboratoriesAlbuquerque 87123U.S.A.

The parametric surrogate models for partial differential equations(PDEs)are a necessary component for many applications in computational sciences,and the convolutional neural networks(Cnns)have proven to be an excellent tool to generate these surrogates when parametric fields are *** are commonly trained on labeled data based on one-to-one sets of parameter-input and PDE-output ***,residual-based deep convolutional physics-informed neural network(DCPInn)solvers for parametric PDEs have been proposed to build surrogates without the need for labeled *** allow for the generation of surrogates without an expensive *** this work,we present an alternative formulation termed deep convolutional Ritz method(DCRM)as a parametric PDE *** approach is based on the minimization of energy functionals,which lowers the order of the differential operators compared to residualbased *** on studies involving the Poisson equation with a spatially parameterized source term and boundary conditions,we find that Cnns trained on labeled data outperform DCPInns in convergence speed and generalization *** surrogates generated from the DCRM,however,converge significantly faster than their DCPInn counterparts,and prove to generalize faster and better than the surrogates obtained from both Cnns trained on labeled data and *** hints that the DCRM could make PDE solution surrogates trained without labeled data possibly.

关键词： physics-informed constraint physics-informed neural network(PInn) deep energy network convolutional neural network(Cnn)

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

An adhesive and resilient hydrogel for the sealing and treatment of gastric perforation

引用

Bioactive Materials 2022年第8期7卷 52-60页

作者： Jing Chen Julia S.Caserto Ida Ang Kaavian Shariati James Webb Bo Wang Xi Wang nikolaos bouklas Minglin Ma College of Pharmacy Nanjing University of Chinese MedicineNanjing210023China Department of Biological and Environmental Engineering Cornell UniversityIthacaNY14853USA Robert Frederick Smith School of Chemical and Biomolecular Engineering Cornell UniversityIthacaNY14853USA Sibley School of Mechanical and Aerospace Engineering Cornell UniversityIthacaNY14853USA

Adhesive hydrogels have been recently proposed as a potential option to seal and treat gastric perforation(GP)which causes high mortality despite advancements in surgical ***,to be effective,the hydrogels must have sufficient tissue adhesiveness,tough mechanical property,tunable biodegradability and ideally are easy to apply and ***,we report an adhesive and resilient hydrogel for the sealing and treatment of gastric *** hydrogel consists of a bioactive,transglutaminase(TG)-crosslinked gelatin network and a dynamic,borate-crosslinked poly-n-[Tris(hydroxymethyl)methyl]acrylamide(PTH)*** hydrogel can be formed in situ,facilitating easy delivery to the GP and allowing for precise sealing of the *** vivo experiments,using a perforated stomach mouse model,shows that the adhesive hydrogel plug effectively seals GP defects and promotes gastric mucosa ***,this hydrogel represents a promising biomaterial for GP treatment.

关键词： Adhesive hydrogel plug Gastric perforation Thermo-responsive Regeneration

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：