Matches in SemOpenAlex for { <https://semopenalex.org/work/W4286560900> ?p ?o ?g. }
- W4286560900 abstract "Abstract Based on physics-informed deep learning method, the deep learning model is proposed for thermal fluid fields reconstruction. This method applied fully-connected layers to establish the mapping function from design variables and space coordinates to physical fields of interest, and then the performance characteristics Nusselt number Nu and Fanning friction factor f can be calculated from the reconstructed fields. Compared with reconstruction model based on convolutional neural network, the improved model shows no constrains on mesh generation and it improves the physical interpretability by introducing conservation laws in loss functions. To validate this method, the forced convection of the water-Al 2 O 3 nanofluids is utilized to construct training dataset. As shown in this paper, this deep neural network can reconstruct the physical fields and consequently the performance characteristics accurately. In the comparisons with other classical machine learning methods, our reconstruction model is superior for predicting performance characteristics. In addition to the effect of training size on prediction power, the extrapolation performance (an important but rarely investigated issue) for important design parameters are also explored on unseen testing datasets." @default.
- W4286560900 created "2022-07-22" @default.
- W4286560900 creator A5014071718 @default.
- W4286560900 creator A5014661038 @default.
- W4286560900 creator A5021686377 @default.
- W4286560900 date "2022-07-22" @default.
- W4286560900 modified "2023-10-16" @default.
- W4286560900 title "Thermal fluid fields reconstruction for nanofluids convection based on physics-informed deep learning" @default.
- W4286560900 cites W1972067347 @default.
- W4286560900 cites W1994923610 @default.
- W4286560900 cites W1998669031 @default.
- W4286560900 cites W2016213857 @default.
- W4286560900 cites W2080027181 @default.
- W4286560900 cites W2086187432 @default.
- W4286560900 cites W2092142860 @default.
- W4286560900 cites W2113858311 @default.
- W4286560900 cites W2122625849 @default.
- W4286560900 cites W2137983211 @default.
- W4286560900 cites W2302255633 @default.
- W4286560900 cites W2329187271 @default.
- W4286560900 cites W2335524910 @default.
- W4286560900 cites W2402268235 @default.
- W4286560900 cites W2515505748 @default.
- W4286560900 cites W2534240011 @default.
- W4286560900 cites W2765372738 @default.
- W4286560900 cites W2770660451 @default.
- W4286560900 cites W2786729166 @default.
- W4286560900 cites W2889821621 @default.
- W4286560900 cites W2902480423 @default.
- W4286560900 cites W2942746260 @default.
- W4286560900 cites W2946771678 @default.
- W4286560900 cites W2948230027 @default.
- W4286560900 cites W2948551291 @default.
- W4286560900 cites W2953532183 @default.
- W4286560900 cites W2967579748 @default.
- W4286560900 cites W2973886134 @default.
- W4286560900 cites W2977204010 @default.
- W4286560900 cites W2981347089 @default.
- W4286560900 cites W2992413717 @default.
- W4286560900 cites W2994823220 @default.
- W4286560900 cites W2998366519 @default.
- W4286560900 cites W3003922491 @default.
- W4286560900 cites W3005641041 @default.
- W4286560900 cites W3013946059 @default.
- W4286560900 cites W3014446153 @default.
- W4286560900 cites W3015865829 @default.
- W4286560900 cites W3021518412 @default.
- W4286560900 cites W3043174105 @default.
- W4286560900 cites W3047001618 @default.
- W4286560900 cites W3096600878 @default.
- W4286560900 cites W3098546160 @default.
- W4286560900 cites W3099892132 @default.
- W4286560900 cites W3100989476 @default.
- W4286560900 cites W3104397553 @default.
- W4286560900 cites W3105648287 @default.
- W4286560900 cites W3109972557 @default.
- W4286560900 cites W3111914315 @default.
- W4286560900 cites W3123883114 @default.
- W4286560900 cites W3169901851 @default.
- W4286560900 cites W3197473870 @default.
- W4286560900 cites W3206859690 @default.
- W4286560900 cites W4244843663 @default.
- W4286560900 doi "https://doi.org/10.1038/s41598-022-16463-1" @default.
- W4286560900 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35869129" @default.
- W4286560900 hasPublicationYear "2022" @default.
- W4286560900 type Work @default.
- W4286560900 citedByCount "6" @default.
- W4286560900 countsByYear W42865609002022 @default.
- W4286560900 countsByYear W42865609002023 @default.
- W4286560900 crossrefType "journal-article" @default.
- W4286560900 hasAuthorship W4286560900A5014071718 @default.
- W4286560900 hasAuthorship W4286560900A5014661038 @default.
- W4286560900 hasAuthorship W4286560900A5021686377 @default.
- W4286560900 hasBestOaLocation W42865609001 @default.
- W4286560900 hasConcept C108583219 @default.
- W4286560900 hasConcept C119857082 @default.
- W4286560900 hasConcept C121332964 @default.
- W4286560900 hasConcept C130230704 @default.
- W4286560900 hasConcept C132459708 @default.
- W4286560900 hasConcept C134306372 @default.
- W4286560900 hasConcept C153294291 @default.
- W4286560900 hasConcept C154945302 @default.
- W4286560900 hasConcept C182748727 @default.
- W4286560900 hasConcept C196558001 @default.
- W4286560900 hasConcept C204530211 @default.
- W4286560900 hasConcept C21946209 @default.
- W4286560900 hasConcept C2781067378 @default.
- W4286560900 hasConcept C33923547 @default.
- W4286560900 hasConcept C41008148 @default.
- W4286560900 hasConcept C50644808 @default.
- W4286560900 hasConcept C57879066 @default.
- W4286560900 hasConcept C81363708 @default.
- W4286560900 hasConceptScore W4286560900C108583219 @default.
- W4286560900 hasConceptScore W4286560900C119857082 @default.
- W4286560900 hasConceptScore W4286560900C121332964 @default.
- W4286560900 hasConceptScore W4286560900C130230704 @default.
- W4286560900 hasConceptScore W4286560900C132459708 @default.
- W4286560900 hasConceptScore W4286560900C134306372 @default.
- W4286560900 hasConceptScore W4286560900C153294291 @default.
- W4286560900 hasConceptScore W4286560900C154945302 @default.