FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3215085381> ?p ?o ?g. }

• W3215085381 endingPage "104703" @default.
• W3215085381 startingPage "104703" @default.
• W3215085381 abstract "In the present work, two machine learning based constitutive models for finite deformations are proposed. Using input convex neural networks, the models are hyperelastic, anisotropic and fulfill the polyconvexity condition, which implies ellipticity and thus ensures material stability. The first constitutive model is based on a set of polyconvex, anisotropic and objective invariants. The second approach is formulated in terms of the deformation gradient, its cofactor and determinant, uses group symmetrization to fulfill the material symmetry condition, and data augmentation to fulfill objectivity approximately. The extension of the dataset for the data augmentation approach is based on mechanical considerations and does not require additional experimental or simulation data. The models are calibrated with highly challenging simulation data of cubic lattice metamaterials, including finite deformations and lattice instabilities. A moderate amount of calibration data is used, based on deformations which are commonly applied in experimental investigations. While the invariant-based model shows drawbacks for several deformation modes, the model based on the deformation gradient alone is able to reproduce and predict the effective material behavior very well and exhibits excellent generalization capabilities. In addition, the models are calibrated with transversely isotropic data, generated with an analytical polyconvex potential. For this case, both models show excellent results, demonstrating the straightforward applicability of the polyconvex neural network constitutive models to other symmetry groups." @default.
• W3215085381 created "2021-12-06" @default.
• W3215085381 creator A5020327359 @default.
• W3215085381 creator A5021838259 @default.
• W3215085381 creator A5045453698 @default.
• W3215085381 creator A5046930021 @default.
• W3215085381 creator A5059390379 @default.
• W3215085381 date "2022-02-01" @default.
• W3215085381 modified "2023-10-17" @default.
• W3215085381 title "Polyconvex anisotropic hyperelasticity with neural networks" @default.
• W3215085381 cites W1588906972 @default.
• W3215085381 cites W1606775516 @default.
• W3215085381 cites W1965424663 @default.
• W3215085381 cites W1969413871 @default.
• W3215085381 cites W1977063638 @default.
• W3215085381 cites W1988115241 @default.
• W3215085381 cites W2007515850 @default.
• W3215085381 cites W2019099211 @default.
• W3215085381 cites W2042299302 @default.
• W3215085381 cites W2046312530 @default.
• W3215085381 cites W2046930772 @default.
• W3215085381 cites W2049957327 @default.
• W3215085381 cites W2056811663 @default.
• W3215085381 cites W2064306347 @default.
• W3215085381 cites W2068736448 @default.
• W3215085381 cites W2073375312 @default.
• W3215085381 cites W2075625830 @default.
• W3215085381 cites W2088703872 @default.
• W3215085381 cites W2090128972 @default.
• W3215085381 cites W2099344367 @default.
• W3215085381 cites W2105034427 @default.
• W3215085381 cites W2119618818 @default.
• W3215085381 cites W2128104451 @default.
• W3215085381 cites W2129888542 @default.
• W3215085381 cites W2167879196 @default.
• W3215085381 cites W2261676784 @default.
• W3215085381 cites W2345737627 @default.
• W3215085381 cites W2523870871 @default.
• W3215085381 cites W2604585076 @default.
• W3215085381 cites W2759450335 @default.
• W3215085381 cites W2765802355 @default.
• W3215085381 cites W2771368987 @default.
• W3215085381 cites W2772087755 @default.
• W3215085381 cites W2908367391 @default.
• W3215085381 cites W2911846113 @default.
• W3215085381 cites W2946264706 @default.
• W3215085381 cites W2962685710 @default.
• W3215085381 cites W2964140572 @default.
• W3215085381 cites W2999081549 @default.
• W3215085381 cites W3003817117 @default.
• W3215085381 cites W3006475788 @default.
• W3215085381 cites W3015176898 @default.
• W3215085381 cites W3025008035 @default.
• W3215085381 cites W3033580147 @default.
• W3215085381 cites W3041081887 @default.
• W3215085381 cites W3041771560 @default.
• W3215085381 cites W3042244068 @default.
• W3215085381 cites W3044636444 @default.
• W3215085381 cites W3080820473 @default.
• W3215085381 cites W3086358797 @default.
• W3215085381 cites W3102413575 @default.
• W3215085381 cites W3103145119 @default.
• W3215085381 cites W3105843381 @default.
• W3215085381 cites W3111771697 @default.
• W3215085381 cites W3136943383 @default.
• W3215085381 cites W3157127629 @default.
• W3215085381 cites W3159503685 @default.
• W3215085381 cites W3163993681 @default.
• W3215085381 doi "https://doi.org/10.1016/j.jmps.2021.104703" @default.
• W3215085381 hasPublicationYear "2022" @default.
• W3215085381 type Work @default.
• W3215085381 sameAs 3215085381 @default.
• W3215085381 citedByCount "46" @default.
• W3215085381 countsByYear W32150853812022 @default.
• W3215085381 countsByYear W32150853812023 @default.
• W3215085381 crossrefType "journal-article" @default.
• W3215085381 hasAuthorship W3215085381A5020327359 @default.
• W3215085381 hasAuthorship W3215085381A5021838259 @default.
• W3215085381 hasAuthorship W3215085381A5045453698 @default.
• W3215085381 hasAuthorship W3215085381A5046930021 @default.
• W3215085381 hasAuthorship W3215085381A5059390379 @default.
• W3215085381 hasBestOaLocation W32150853812 @default.
• W3215085381 hasConcept C101842124 @default.
• W3215085381 hasConcept C120665830 @default.
• W3215085381 hasConcept C121332964 @default.
• W3215085381 hasConcept C134306372 @default.
• W3215085381 hasConcept C135628077 @default.
• W3215085381 hasConcept C147370603 @default.
• W3215085381 hasConcept C154945302 @default.
• W3215085381 hasConcept C163892269 @default.
• W3215085381 hasConcept C184050105 @default.
• W3215085381 hasConcept C190470478 @default.
• W3215085381 hasConcept C202973686 @default.
• W3215085381 hasConcept C24890656 @default.
• W3215085381 hasConcept C2781204021 @default.
• W3215085381 hasConcept C28826006 @default.
• W3215085381 hasConcept C33923547 @default.
• W3215085381 hasConcept C37914503 @default.

• next