Matches in SemOpenAlex for { <https://semopenalex.org/work/W4220974482> ?p ?o ?g. }
- W4220974482 endingPage "117303" @default.
- W4220974482 startingPage "117303" @default.
- W4220974482 abstract "Two deep learning methods, Multi-Layer Perceptron (MLP) network and Convolution Neural Network (CNN) are evaluated to predict drag forces in dense suspensions of ellipsoidal particles using data from Particle Resolved Simulations (PRS). The MLP is trained on the mean flow Reynolds number, solid fraction of the suspension, the aspect ratio of the particle, and orientation to flow direction. The CNN is given an additional 3D spatial map of the particle of interest and its immediate neighborhood via a distance function. The prediction capability of the trained networks is tested at different levels of complexity: on an unseen particle arrangement (Level 1), to all arrangements of an unseen numerical experiment (Level 2), and finally to all experiments of an unseen Reynolds number, solid fraction or aspect ratio (Level 3). The CNN is shown to perform better than the MLP for all testing levels except when testing on an unseen aspect ratio." @default.
- W4220974482 created "2022-04-03" @default.
- W4220974482 creator A5044512850 @default.
- W4220974482 creator A5069203741 @default.
- W4220974482 creator A5074615163 @default.
- W4220974482 creator A5081622450 @default.
- W4220974482 creator A5086827394 @default.
- W4220974482 date "2022-03-01" @default.
- W4220974482 modified "2023-09-30" @default.
- W4220974482 title "Deep learning methods for predicting fluid forces in dense particle suspensions" @default.
- W4220974482 cites W1128244265 @default.
- W4220974482 cites W1974237820 @default.
- W4220974482 cites W1974959902 @default.
- W4220974482 cites W1995619639 @default.
- W4220974482 cites W1999677400 @default.
- W4220974482 cites W2002300121 @default.
- W4220974482 cites W2003446883 @default.
- W4220974482 cites W2036291456 @default.
- W4220974482 cites W2040776902 @default.
- W4220974482 cites W2040870580 @default.
- W4220974482 cites W2046876896 @default.
- W4220974482 cites W2051841734 @default.
- W4220974482 cites W2056084404 @default.
- W4220974482 cites W2057039961 @default.
- W4220974482 cites W2058420578 @default.
- W4220974482 cites W2070629872 @default.
- W4220974482 cites W2078672534 @default.
- W4220974482 cites W2082128114 @default.
- W4220974482 cites W2116360511 @default.
- W4220974482 cites W2134771719 @default.
- W4220974482 cites W2154548938 @default.
- W4220974482 cites W2488057392 @default.
- W4220974482 cites W2534240011 @default.
- W4220974482 cites W2560005819 @default.
- W4220974482 cites W2585298970 @default.
- W4220974482 cites W2592031414 @default.
- W4220974482 cites W2610982944 @default.
- W4220974482 cites W2804809342 @default.
- W4220974482 cites W2809254203 @default.
- W4220974482 cites W2865180868 @default.
- W4220974482 cites W2887242218 @default.
- W4220974482 cites W2902480423 @default.
- W4220974482 cites W2903431909 @default.
- W4220974482 cites W2907522752 @default.
- W4220974482 cites W2919115771 @default.
- W4220974482 cites W2923480254 @default.
- W4220974482 cites W2948230027 @default.
- W4220974482 cites W3026434510 @default.
- W4220974482 cites W3043234079 @default.
- W4220974482 cites W3089571701 @default.
- W4220974482 cites W3103368639 @default.
- W4220974482 cites W3105648287 @default.
- W4220974482 cites W3123447337 @default.
- W4220974482 cites W3135692122 @default.
- W4220974482 cites W3183406235 @default.
- W4220974482 cites W4249342445 @default.
- W4220974482 cites W4253667136 @default.
- W4220974482 doi "https://doi.org/10.1016/j.powtec.2022.117303" @default.
- W4220974482 hasPublicationYear "2022" @default.
- W4220974482 type Work @default.
- W4220974482 citedByCount "7" @default.
- W4220974482 countsByYear W42209744822022 @default.
- W4220974482 countsByYear W42209744822023 @default.
- W4220974482 crossrefType "journal-article" @default.
- W4220974482 hasAuthorship W4220974482A5044512850 @default.
- W4220974482 hasAuthorship W4220974482A5069203741 @default.
- W4220974482 hasAuthorship W4220974482A5074615163 @default.
- W4220974482 hasAuthorship W4220974482A5081622450 @default.
- W4220974482 hasAuthorship W4220974482A5086827394 @default.
- W4220974482 hasBestOaLocation W42209744822 @default.
- W4220974482 hasConcept C105341887 @default.
- W4220974482 hasConcept C111368507 @default.
- W4220974482 hasConcept C11413529 @default.
- W4220974482 hasConcept C121332964 @default.
- W4220974482 hasConcept C127313418 @default.
- W4220974482 hasConcept C1276947 @default.
- W4220974482 hasConcept C149629883 @default.
- W4220974482 hasConcept C154945302 @default.
- W4220974482 hasConcept C16345878 @default.
- W4220974482 hasConcept C182748727 @default.
- W4220974482 hasConcept C185592680 @default.
- W4220974482 hasConcept C196558001 @default.
- W4220974482 hasConcept C202444582 @default.
- W4220974482 hasConcept C2524010 @default.
- W4220974482 hasConcept C2778517922 @default.
- W4220974482 hasConcept C33923547 @default.
- W4220974482 hasConcept C38349280 @default.
- W4220974482 hasConcept C41008148 @default.
- W4220974482 hasConcept C43617362 @default.
- W4220974482 hasConcept C45347329 @default.
- W4220974482 hasConcept C49040817 @default.
- W4220974482 hasConcept C50644808 @default.
- W4220974482 hasConcept C57489055 @default.
- W4220974482 hasConcept C57879066 @default.
- W4220974482 hasConcept C5961521 @default.
- W4220974482 hasConcept C60908668 @default.
- W4220974482 hasConcept C72921944 @default.
- W4220974482 hasConcept C81363708 @default.