FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386643071> ?p ?o ?g. }

• W4386643071 endingPage "108619" @default.
• W4386643071 startingPage "108619" @default.
• W4386643071 abstract "Perception of the full state is an essential technology to support the monitoring, analysis, and design of physical systems, one of whose challenges is to recover global field from sparse observations. Well-known for brilliant approximation ability, deep neural networks have been attractive to data-driven heat and flow field reconstruction studies for practical systems. However, limited by network structure, existing researches mostly learn the reconstruction mapping in finite-dimensional space that usually has poor transferability to the variable resolution of outputs. This paper extends the new paradigm of neural operators and proposes an end-to-end physical field reconstruction method with both excellent performance and mesh transferability named RecFNO. The proposed method aims to learn the mapping from sparse observations to flow and heat fields in infinite-dimensional space, contributing to a more powerful nonlinear fitting capacity and resolution-invariant characteristic. According to different usage scenarios, three types of embeddings are first developed to model the sparse observation inputs: MLP, mask, and Voronoi embedding. The MLP embedding is propitious to more sparse input, while the others benefit from spatial information preservation and perform better with the increase of observation data. Then, stacked Fourier layers are adopted to reconstruct physical field in Fourier space that regularizes the overall recovered field by Fourier modes superposition. Benefiting from the operator in infinite-dimensional space, the proposed method obtains remarkable accuracy and better resolution transferability among meshes. The experiments conducted on fluid mechanics and thermology problems show that the proposed method outperforms existing POD-based and CNN-based methods in most cases and has the capacity to achieve zero-shot super-resolution." @default.
• W4386643071 created "2023-09-13" @default.
• W4386643071 creator A5001113052 @default.
• W4386643071 creator A5055462963 @default.
• W4386643071 creator A5063971188 @default.
• W4386643071 creator A5072409965 @default.
• W4386643071 creator A5089291482 @default.
• W4386643071 creator A5089866078 @default.
• W4386643071 date "2024-01-01" @default.
• W4386643071 modified "2023-10-18" @default.
• W4386643071 title "RecFNO: A resolution-invariant flow and heat field reconstruction method from sparse observations via Fourier neural operator" @default.
• W4386643071 cites W1723433682 @default.
• W4386643071 cites W1903029394 @default.
• W4386643071 cites W2120101088 @default.
• W4386643071 cites W2169207653 @default.
• W4386643071 cites W2177066871 @default.
• W4386643071 cites W2346717862 @default.
• W4386643071 cites W2585298970 @default.
• W4386643071 cites W2590991739 @default.
• W4386643071 cites W2765811365 @default.
• W4386643071 cites W2907100627 @default.
• W4386643071 cites W2949650570 @default.
• W4386643071 cites W2996132844 @default.
• W4386643071 cites W2998104826 @default.
• W4386643071 cites W3005641041 @default.
• W4386643071 cites W3036785040 @default.
• W4386643071 cites W3087138088 @default.
• W4386643071 cites W3100255097 @default.
• W4386643071 cites W3100345157 @default.
• W4386643071 cites W3109972557 @default.
• W4386643071 cites W3121293212 @default.
• W4386643071 cites W3121951452 @default.
• W4386643071 cites W3135143354 @default.
• W4386643071 cites W3168201306 @default.
• W4386643071 cites W3196881815 @default.
• W4386643071 cites W3200336025 @default.
• W4386643071 cites W3203806521 @default.
• W4386643071 cites W3204011834 @default.
• W4386643071 cites W3205027881 @default.
• W4386643071 cites W3206806480 @default.
• W4386643071 cites W3208290324 @default.
• W4386643071 cites W3211072199 @default.
• W4386643071 cites W4288825670 @default.
• W4386643071 cites W4306249448 @default.
• W4386643071 cites W4308421455 @default.
• W4386643071 cites W4313524459 @default.
• W4386643071 doi "https://doi.org/10.1016/j.ijthermalsci.2023.108619" @default.
• W4386643071 hasPublicationYear "2024" @default.
• W4386643071 type Work @default.
• W4386643071 citedByCount "0" @default.
• W4386643071 crossrefType "journal-article" @default.
• W4386643071 hasAuthorship W4386643071A5001113052 @default.
• W4386643071 hasAuthorship W4386643071A5055462963 @default.
• W4386643071 hasAuthorship W4386643071A5063971188 @default.
• W4386643071 hasAuthorship W4386643071A5072409965 @default.
• W4386643071 hasAuthorship W4386643071A5089291482 @default.
• W4386643071 hasAuthorship W4386643071A5089866078 @default.
• W4386643071 hasBestOaLocation W43866430711 @default.
• W4386643071 hasConcept C102519508 @default.
• W4386643071 hasConcept C104317684 @default.
• W4386643071 hasConcept C11413529 @default.
• W4386643071 hasConcept C121684516 @default.
• W4386643071 hasConcept C134306372 @default.
• W4386643071 hasConcept C154945302 @default.
• W4386643071 hasConcept C158448853 @default.
• W4386643071 hasConcept C17020691 @default.
• W4386643071 hasConcept C185592680 @default.
• W4386643071 hasConcept C202444582 @default.
• W4386643071 hasConcept C27753989 @default.
• W4386643071 hasConcept C31487907 @default.
• W4386643071 hasConcept C33923547 @default.
• W4386643071 hasConcept C41008148 @default.
• W4386643071 hasConcept C41608201 @default.
• W4386643071 hasConcept C50644808 @default.
• W4386643071 hasConcept C55493867 @default.
• W4386643071 hasConcept C86339819 @default.
• W4386643071 hasConcept C9652623 @default.
• W4386643071 hasConceptScore W4386643071C102519508 @default.
• W4386643071 hasConceptScore W4386643071C104317684 @default.
• W4386643071 hasConceptScore W4386643071C11413529 @default.
• W4386643071 hasConceptScore W4386643071C121684516 @default.
• W4386643071 hasConceptScore W4386643071C134306372 @default.
• W4386643071 hasConceptScore W4386643071C154945302 @default.
• W4386643071 hasConceptScore W4386643071C158448853 @default.
• W4386643071 hasConceptScore W4386643071C17020691 @default.
• W4386643071 hasConceptScore W4386643071C185592680 @default.
• W4386643071 hasConceptScore W4386643071C202444582 @default.
• W4386643071 hasConceptScore W4386643071C27753989 @default.
• W4386643071 hasConceptScore W4386643071C31487907 @default.
• W4386643071 hasConceptScore W4386643071C33923547 @default.
• W4386643071 hasConceptScore W4386643071C41008148 @default.
• W4386643071 hasConceptScore W4386643071C41608201 @default.
• W4386643071 hasConceptScore W4386643071C50644808 @default.
• W4386643071 hasConceptScore W4386643071C55493867 @default.
• W4386643071 hasConceptScore W4386643071C86339819 @default.
• W4386643071 hasConceptScore W4386643071C9652623 @default.
• W4386643071 hasFunder F4320321001 @default.
• W4386643071 hasLocation W43866430711 @default.

• next