FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4324107262> ?p ?o ?g. }

• W4324107262 endingPage "115972" @default.
• W4324107262 startingPage "115972" @default.
• W4324107262 abstract "Elements of the periodic homogenization framework and deep neural network were seamlessly connected for the first time to construct a new micromechanics theory for thermoconductive composites called physically informed Deep Homogenization Network (DHN). This method utilizes a two-scale expansion of the temperature field of spatially uniform composites in terms of macroscopic and fluctuating contributions. The latter is estimated using deep neural network layers. The DHN is trained on a set of collocation points to obtain the fluctuating temperature field over the unit cell domain by minimizing a cost function given in terms of residuals of strong form steady-state heat conduction governing differential equations. Novel use of a periodic layer with several independent periodic functions with adjustable training parameters ensures that periodic boundary conditions of temperature and temperature gradients at the unit cell edges are exactly satisfied. Automatic differentiation is utilized to correctly compute the fluctuating temperature gradients. Homogenized properties and local temperature and gradient distributions of unit cells reinforced by unidirectional fiber or weakened by a hole are compared with finite-element reference results, demonstrating remarkable correlation but without discontinuities associated with temperature gradient distributions in the finite-element simulations. We also illustrate that the DHN enhanced with transfer learning provides a substantially more efficient and accurate simulation of multiple random fiber distributions relative to training the network from scratch." @default.
• W4324107262 created "2023-03-14" @default.
• W4324107262 creator A5001563204 @default.
• W4324107262 creator A5018399001 @default.
• W4324107262 creator A5060874855 @default.
• W4324107262 creator A5061335705 @default.
• W4324107262 creator A5068784253 @default.
• W4324107262 date "2023-05-01" @default.
• W4324107262 modified "2023-10-18" @default.
• W4324107262 title "Physically informed deep homogenization neural network for unidirectional multiphase/multi-inclusion thermoconductive composites" @default.
• W4324107262 cites W1880308307 @default.
• W4324107262 cites W2004534757 @default.
• W4324107262 cites W2014065324 @default.
• W4324107262 cites W2017118347 @default.
• W4324107262 cites W2051289112 @default.
• W4324107262 cites W2052089155 @default.
• W4324107262 cites W2059859393 @default.
• W4324107262 cites W2062497595 @default.
• W4324107262 cites W2068183989 @default.
• W4324107262 cites W2072954894 @default.
• W4324107262 cites W2163387698 @default.
• W4324107262 cites W2465381142 @default.
• W4324107262 cites W2749253576 @default.
• W4324107262 cites W2889437057 @default.
• W4324107262 cites W2895424432 @default.
• W4324107262 cites W2899283552 @default.
• W4324107262 cites W2909549714 @default.
• W4324107262 cites W2971082399 @default.
• W4324107262 cites W2998847955 @default.
• W4324107262 cites W3006366309 @default.
• W4324107262 cites W3006813881 @default.
• W4324107262 cites W3015639472 @default.
• W4324107262 cites W3020474415 @default.
• W4324107262 cites W3022768346 @default.
• W4324107262 cites W3023684275 @default.
• W4324107262 cites W3043516796 @default.
• W4324107262 cites W3082071833 @default.
• W4324107262 cites W3085027998 @default.
• W4324107262 cites W3089304733 @default.
• W4324107262 cites W3092743582 @default.
• W4324107262 cites W3121219033 @default.
• W4324107262 cites W3136461437 @default.
• W4324107262 cites W3155187831 @default.
• W4324107262 cites W3156166459 @default.
• W4324107262 cites W3172868201 @default.
• W4324107262 cites W3194528394 @default.
• W4324107262 cites W3195330636 @default.
• W4324107262 cites W3198251555 @default.
• W4324107262 cites W4221156459 @default.
• W4324107262 cites W4226480439 @default.
• W4324107262 cites W4280647708 @default.
• W4324107262 cites W4283067940 @default.
• W4324107262 cites W4283788483 @default.
• W4324107262 cites W4285679264 @default.
• W4324107262 cites W4313334586 @default.
• W4324107262 cites W4313368296 @default.
• W4324107262 cites W4313479310 @default.
• W4324107262 doi "https://doi.org/10.1016/j.cma.2023.115972" @default.
• W4324107262 hasPublicationYear "2023" @default.
• W4324107262 type Work @default.
• W4324107262 citedByCount "2" @default.
• W4324107262 countsByYear W43241072622023 @default.
• W4324107262 crossrefType "journal-article" @default.
• W4324107262 hasAuthorship W4324107262A5001563204 @default.
• W4324107262 hasAuthorship W4324107262A5018399001 @default.
• W4324107262 hasAuthorship W4324107262A5060874855 @default.
• W4324107262 hasAuthorship W4324107262A5061335705 @default.
• W4324107262 hasAuthorship W4324107262A5068784253 @default.
• W4324107262 hasConcept C112675119 @default.
• W4324107262 hasConcept C121332964 @default.
• W4324107262 hasConcept C130217890 @default.
• W4324107262 hasConcept C134306372 @default.
• W4324107262 hasConcept C135628077 @default.
• W4324107262 hasConcept C137109543 @default.
• W4324107262 hasConcept C154945302 @default.
• W4324107262 hasConcept C15627037 @default.
• W4324107262 hasConcept C159985019 @default.
• W4324107262 hasConcept C172100665 @default.
• W4324107262 hasConcept C182310444 @default.
• W4324107262 hasConcept C18903297 @default.
• W4324107262 hasConcept C192562407 @default.
• W4324107262 hasConcept C2778722038 @default.
• W4324107262 hasConcept C33923547 @default.
• W4324107262 hasConcept C41008148 @default.
• W4324107262 hasConcept C50644808 @default.
• W4324107262 hasConcept C57879066 @default.
• W4324107262 hasConcept C62520636 @default.
• W4324107262 hasConcept C86803240 @default.
• W4324107262 hasConcept C97355855 @default.
• W4324107262 hasConceptScore W4324107262C112675119 @default.
• W4324107262 hasConceptScore W4324107262C121332964 @default.
• W4324107262 hasConceptScore W4324107262C130217890 @default.
• W4324107262 hasConceptScore W4324107262C134306372 @default.
• W4324107262 hasConceptScore W4324107262C135628077 @default.
• W4324107262 hasConceptScore W4324107262C137109543 @default.
• W4324107262 hasConceptScore W4324107262C154945302 @default.
• W4324107262 hasConceptScore W4324107262C15627037 @default.
• W4324107262 hasConceptScore W4324107262C159985019 @default.

• next