Matches in SemOpenAlex for { <https://semopenalex.org/work/W4362577663> ?p ?o ?g. }
- W4362577663 endingPage "3111" @default.
- W4362577663 startingPage "3087" @default.
- W4362577663 abstract "Abstract This paper presents a new nonlinear non‐intrusive reduced‐order model (NL‐NIROM) that outperforms traditional proper orthogonal decomposition (POD)‐based reduced order model (ROM). This improvement is achieved through the use of auto‐encoder (AE) and self‐attention based deep learning methods. The novelty of this work is that it uses stacked auto‐encoder (SAE) network to project the original high‐dimensional dynamical systems onto a low dimensional nonlinear subspace and predict fluid dynamics using an self‐attention based deep learning method. This paper introduces a new model reduction neural network architecture for fluid flow problem, as well as, a linear non‐intrusive reduced order model (L‐NIROM) based on POD and self‐attention mechanism. In the NL‐NIROM, the SAE network compresses high‐dimensional physical information into several much smaller sized representations in a reduced latent space. These representations are expressed by a number of codes in the middle layer of SAE neural network. Then, those codes at different time levels are trained to construct a set of hyper‐surfaces using self‐attention based deep learning methods. The inputs of the self‐attention based network are previous time levels' codes and the outputs of the network are current time levels' codes. The codes at current time level are then projected back to the original full space by the decoder layers in the SAE network. The capability of the new model, NL‐NIROM, is demonstrated through two test cases: flow past a cylinder, and a lock exchange. The results show that the NL‐NIROM is more accurate than the popular model reduction method namely POD based L‐NIROM." @default.
- W4362577663 created "2023-04-06" @default.
- W4362577663 creator A5025725014 @default.
- W4362577663 creator A5029573210 @default.
- W4362577663 creator A5032850530 @default.
- W4362577663 creator A5034137989 @default.
- W4362577663 creator A5038997706 @default.
- W4362577663 creator A5072175564 @default.
- W4362577663 creator A5082362303 @default.
- W4362577663 date "2023-04-03" @default.
- W4362577663 modified "2023-10-08" @default.
- W4362577663 title "A non‐linear non‐intrusive reduced order model of fluid flow by auto‐encoder and self‐attention deep learning methods" @default.
- W4362577663 cites W1525542318 @default.
- W4362577663 cites W1989516295 @default.
- W4362577663 cites W2001277541 @default.
- W4362577663 cites W2020141363 @default.
- W4362577663 cites W2023491556 @default.
- W4362577663 cites W2035934750 @default.
- W4362577663 cites W2047591100 @default.
- W4362577663 cites W2049753327 @default.
- W4362577663 cites W2068991306 @default.
- W4362577663 cites W2075239037 @default.
- W4362577663 cites W2085767064 @default.
- W4362577663 cites W2088463740 @default.
- W4362577663 cites W2128272608 @default.
- W4362577663 cites W2133431334 @default.
- W4362577663 cites W2154096272 @default.
- W4362577663 cites W2156249715 @default.
- W4362577663 cites W2159840341 @default.
- W4362577663 cites W2161155740 @default.
- W4362577663 cites W2332297685 @default.
- W4362577663 cites W2516020123 @default.
- W4362577663 cites W2525748878 @default.
- W4362577663 cites W2604782537 @default.
- W4362577663 cites W2615904750 @default.
- W4362577663 cites W2738335552 @default.
- W4362577663 cites W2759838493 @default.
- W4362577663 cites W2802073903 @default.
- W4362577663 cites W2809491586 @default.
- W4362577663 cites W2900769969 @default.
- W4362577663 cites W2901661213 @default.
- W4362577663 cites W2919115771 @default.
- W4362577663 cites W2937307539 @default.
- W4362577663 cites W2938722449 @default.
- W4362577663 cites W2947731719 @default.
- W4362577663 cites W2953410468 @default.
- W4362577663 cites W2963008012 @default.
- W4362577663 cites W2963070178 @default.
- W4362577663 cites W2964276189 @default.
- W4362577663 cites W2965742591 @default.
- W4362577663 cites W2986795381 @default.
- W4362577663 cites W2994786560 @default.
- W4362577663 cites W2997402771 @default.
- W4362577663 cites W3006066195 @default.
- W4362577663 cites W3006507139 @default.
- W4362577663 cites W3009859350 @default.
- W4362577663 cites W3021544678 @default.
- W4362577663 cites W3032875641 @default.
- W4362577663 cites W3039458202 @default.
- W4362577663 cites W3072501233 @default.
- W4362577663 cites W3088073297 @default.
- W4362577663 cites W3102002891 @default.
- W4362577663 cites W3108146742 @default.
- W4362577663 cites W3112189530 @default.
- W4362577663 cites W3130814454 @default.
- W4362577663 cites W3141908237 @default.
- W4362577663 cites W3150115442 @default.
- W4362577663 cites W3161273075 @default.
- W4362577663 cites W3175210633 @default.
- W4362577663 cites W3180745686 @default.
- W4362577663 cites W3183800180 @default.
- W4362577663 cites W3212386989 @default.
- W4362577663 cites W4313293844 @default.
- W4362577663 doi "https://doi.org/10.1002/nme.7240" @default.
- W4362577663 hasPublicationYear "2023" @default.
- W4362577663 type Work @default.
- W4362577663 citedByCount "1" @default.
- W4362577663 countsByYear W43625776632023 @default.
- W4362577663 crossrefType "journal-article" @default.
- W4362577663 hasAuthorship W4362577663A5025725014 @default.
- W4362577663 hasAuthorship W4362577663A5029573210 @default.
- W4362577663 hasAuthorship W4362577663A5032850530 @default.
- W4362577663 hasAuthorship W4362577663A5034137989 @default.
- W4362577663 hasAuthorship W4362577663A5038997706 @default.
- W4362577663 hasAuthorship W4362577663A5072175564 @default.
- W4362577663 hasAuthorship W4362577663A5082362303 @default.
- W4362577663 hasConcept C101738243 @default.
- W4362577663 hasConcept C108583219 @default.
- W4362577663 hasConcept C11413529 @default.
- W4362577663 hasConcept C121332964 @default.
- W4362577663 hasConcept C154945302 @default.
- W4362577663 hasConcept C158622935 @default.
- W4362577663 hasConcept C2524010 @default.
- W4362577663 hasConcept C32834561 @default.
- W4362577663 hasConcept C33923547 @default.
- W4362577663 hasConcept C38349280 @default.
- W4362577663 hasConcept C41008148 @default.
- W4362577663 hasConcept C50644808 @default.