FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4306982088> ?p ?o ?g. }

• W4306982088 endingPage "105516" @default.
• W4306982088 startingPage "105516" @default.
• W4306982088 abstract "Recently, surrogate models based on deep learning have attracted much attention for engineering analysis and optimization. Since constructing data pairs in most engineering problems is time-consuming, data acquisition is becoming the predictive capability bottleneck of most deep surrogate models, which also exist in surrogate for thermal analysis and design. In contrast with data-driven learning, enforcing the physical laws in building surrogates has emerged as a promising alternative to reduce the dependence on annotated data. This paper develops a physics-informed convolutional neural network (CNN) for the thermal simulation surrogate without labeled data. Firstly, we leverage the finite difference method to integrate heat conduction equation and loss function construction, guiding surrogate model training to minimize the violation of physical laws. Since the solution is sensitive to boundary conditions, we properly impose hard constraints by padding in the Dirichlet and Neumann boundaries. The proposed network can learn a mapping from heat source layout to the steady-state temperature field without labeled data, which equals solving an entire family of partial difference equations (PDEs). Moreover, the neural network architecture is well-designed to improve the prediction accuracy of the problem at hand, and pixel-level online hard example mining is proposed to overcome the imbalance of optimization difficulty in the computation domain, which is beneficial to the network training of physics-informed learning. The experiments demonstrate that the proposed method can provide comparable predictions with numerical methods and data-driven deep learning models. We also conduct various ablation studies to investigate the effectiveness of the proposed network components and training methods in this paper. Furthermore, the developed methods can be applied to other design and optimization applications which need to solve parameterized PDEs." @default.
• W4306982088 created "2022-10-22" @default.
• W4306982088 creator A5025167286 @default.
• W4306982088 creator A5055462963 @default.
• W4306982088 creator A5063971188 @default.
• W4306982088 creator A5074772585 @default.
• W4306982088 creator A5089866078 @default.
• W4306982088 date "2023-01-01" @default.
• W4306982088 modified "2023-10-18" @default.
• W4306982088 title "Physics-informed convolutional neural networks for temperature field prediction of heat source layout without labeled data" @default.
• W4306982088 cites W1812475363 @default.
• W4306982088 cites W2120835681 @default.
• W4306982088 cites W2562560103 @default.
• W4306982088 cites W2566242503 @default.
• W4306982088 cites W2612256155 @default.
• W4306982088 cites W2789697449 @default.
• W4306982088 cites W2806642578 @default.
• W4306982088 cites W2899283552 @default.
• W4306982088 cites W2903660960 @default.
• W4306982088 cites W2908541468 @default.
• W4306982088 cites W2948230027 @default.
• W4306982088 cites W2994789389 @default.
• W4306982088 cites W2998366519 @default.
• W4306982088 cites W3006689658 @default.
• W4306982088 cites W3007593704 @default.
• W4306982088 cites W3014261756 @default.
• W4306982088 cites W3083226824 @default.
• W4306982088 cites W3087889215 @default.
• W4306982088 cites W3096600878 @default.
• W4306982088 cites W3111914315 @default.
• W4306982088 cites W3120751998 @default.
• W4306982088 cites W3137474564 @default.
• W4306982088 cites W3178968719 @default.
• W4306982088 cites W3217374538 @default.
• W4306982088 cites W4235892290 @default.
• W4306982088 cites W4250482878 @default.
• W4306982088 doi "https://doi.org/10.1016/j.engappai.2022.105516" @default.
• W4306982088 hasPublicationYear "2023" @default.
• W4306982088 type Work @default.
• W4306982088 citedByCount "11" @default.
• W4306982088 countsByYear W43069820882022 @default.
• W4306982088 countsByYear W43069820882023 @default.
• W4306982088 crossrefType "journal-article" @default.
• W4306982088 hasAuthorship W4306982088A5025167286 @default.
• W4306982088 hasAuthorship W4306982088A5055462963 @default.
• W4306982088 hasAuthorship W4306982088A5063971188 @default.
• W4306982088 hasAuthorship W4306982088A5074772585 @default.
• W4306982088 hasAuthorship W4306982088A5089866078 @default.
• W4306982088 hasBestOaLocation W43069820882 @default.
• W4306982088 hasConcept C108583219 @default.
• W4306982088 hasConcept C119857082 @default.
• W4306982088 hasConcept C131675550 @default.
• W4306982088 hasConcept C149635348 @default.
• W4306982088 hasConcept C153083717 @default.
• W4306982088 hasConcept C154945302 @default.
• W4306982088 hasConcept C202444582 @default.
• W4306982088 hasConcept C2780513914 @default.
• W4306982088 hasConcept C33923547 @default.
• W4306982088 hasConcept C41008148 @default.
• W4306982088 hasConcept C50644808 @default.
• W4306982088 hasConcept C81363708 @default.
• W4306982088 hasConcept C9652623 @default.
• W4306982088 hasConceptScore W4306982088C108583219 @default.
• W4306982088 hasConceptScore W4306982088C119857082 @default.
• W4306982088 hasConceptScore W4306982088C131675550 @default.
• W4306982088 hasConceptScore W4306982088C149635348 @default.
• W4306982088 hasConceptScore W4306982088C153083717 @default.
• W4306982088 hasConceptScore W4306982088C154945302 @default.
• W4306982088 hasConceptScore W4306982088C202444582 @default.
• W4306982088 hasConceptScore W4306982088C2780513914 @default.
• W4306982088 hasConceptScore W4306982088C33923547 @default.
• W4306982088 hasConceptScore W4306982088C41008148 @default.
• W4306982088 hasConceptScore W4306982088C50644808 @default.
• W4306982088 hasConceptScore W4306982088C81363708 @default.
• W4306982088 hasConceptScore W4306982088C9652623 @default.
• W4306982088 hasLocation W43069820881 @default.
• W4306982088 hasLocation W43069820882 @default.
• W4306982088 hasOpenAccess W4306982088 @default.
• W4306982088 hasPrimaryLocation W43069820881 @default.
• W4306982088 hasRelatedWork W2731899572 @default.
• W4306982088 hasRelatedWork W2999805992 @default.
• W4306982088 hasRelatedWork W3116150086 @default.
• W4306982088 hasRelatedWork W3133861977 @default.
• W4306982088 hasRelatedWork W4200173597 @default.
• W4306982088 hasRelatedWork W4223943233 @default.
• W4306982088 hasRelatedWork W4291897433 @default.
• W4306982088 hasRelatedWork W4312417841 @default.
• W4306982088 hasRelatedWork W4321369474 @default.
• W4306982088 hasRelatedWork W4380075502 @default.
• W4306982088 hasVolume "117" @default.
• W4306982088 isParatext "false" @default.
• W4306982088 isRetracted "false" @default.
• W4306982088 workType "article" @default.