Matches in SemOpenAlex for { <https://semopenalex.org/work/W3178290420> ?p ?o ?g. }
- W3178290420 endingPage "110567" @default.
- W3178290420 startingPage "110567" @default.
- W3178290420 abstract "A deep-learning based approach is developed for efficient evaluation of thermophysical properties in numerical simulation of complex real-fluid flows. The work enables a significant improvement of computational efficiency by replacing direct calculation of the equation of state with a deep feedforward neural network with appropriate boundary information (DFNN-BC). The proposed method can be coupled to a flow solver in a robust manner. Depending on the numerical formulation of the flow solver, the neural network takes in either the primitive or conservative variables, including the chemical composition of the system, and calculates all relevant fluid properties for the subsequent routines in the solver. Two test problems are employed to validate the proposed methodology. The first uses a preconditioning scheme with dual-time integration for the simulation of swirl rocket injector flow dynamics under supercritical conditions. The second uses a conservative-variable based formulation for the simulation of laminar counterflow diffusion flames for cryogenic combustion. A parametric analysis is performed to optimize the numbers of hidden layers and neurons per hidden layer. The computational accuracy, efficiency, and memory requirements of the neural network are examined. The DFNN-BC model accelerates the evaluation of real-fluid properties by a factor of 2.43 and 3.7 for the two test problems, respectively, and the overall flowfield simulation by 1.5 and 2.3, respectively. In addition, the memory usage is reduced by up to five orders of magnitude in comparison with the table look-up method." @default.
- W3178290420 created "2021-07-19" @default.
- W3178290420 creator A5030732775 @default.
- W3178290420 creator A5046326510 @default.
- W3178290420 creator A5057455678 @default.
- W3178290420 creator A5063853260 @default.
- W3178290420 date "2021-11-01" @default.
- W3178290420 modified "2023-10-12" @default.
- W3178290420 title "Deep-learning accelerated calculation of real-fluid properties in numerical simulation of complex flowfields" @default.
- W3178290420 cites W1044946043 @default.
- W3178290420 cites W1969188355 @default.
- W3178290420 cites W1973085334 @default.
- W3178290420 cites W1978595606 @default.
- W3178290420 cites W1998876093 @default.
- W3178290420 cites W2024444207 @default.
- W3178290420 cites W2034133890 @default.
- W3178290420 cites W2037471094 @default.
- W3178290420 cites W2057929076 @default.
- W3178290420 cites W2064881871 @default.
- W3178290420 cites W2066486563 @default.
- W3178290420 cites W2070182252 @default.
- W3178290420 cites W2075886908 @default.
- W3178290420 cites W2094028479 @default.
- W3178290420 cites W2094818470 @default.
- W3178290420 cites W2096262497 @default.
- W3178290420 cites W2117129266 @default.
- W3178290420 cites W2129146828 @default.
- W3178290420 cites W2129288307 @default.
- W3178290420 cites W2145789064 @default.
- W3178290420 cites W2187033240 @default.
- W3178290420 cites W2534240011 @default.
- W3178290420 cites W2585298970 @default.
- W3178290420 cites W2602295025 @default.
- W3178290420 cites W2804701454 @default.
- W3178290420 cites W2808873106 @default.
- W3178290420 cites W2884038422 @default.
- W3178290420 cites W2884127945 @default.
- W3178290420 cites W2888642407 @default.
- W3178290420 cites W2895786603 @default.
- W3178290420 cites W2899283552 @default.
- W3178290420 cites W2940953274 @default.
- W3178290420 cites W2950068888 @default.
- W3178290420 cites W2972729858 @default.
- W3178290420 cites W3108167715 @default.
- W3178290420 cites W4235892290 @default.
- W3178290420 cites W47285034 @default.
- W3178290420 doi "https://doi.org/10.1016/j.jcp.2021.110567" @default.
- W3178290420 hasPublicationYear "2021" @default.
- W3178290420 type Work @default.
- W3178290420 sameAs 3178290420 @default.
- W3178290420 citedByCount "13" @default.
- W3178290420 countsByYear W31782904202022 @default.
- W3178290420 countsByYear W31782904202023 @default.
- W3178290420 crossrefType "journal-article" @default.
- W3178290420 hasAuthorship W3178290420A5030732775 @default.
- W3178290420 hasAuthorship W3178290420A5046326510 @default.
- W3178290420 hasAuthorship W3178290420A5057455678 @default.
- W3178290420 hasAuthorship W3178290420A5063853260 @default.
- W3178290420 hasBestOaLocation W31782904201 @default.
- W3178290420 hasConcept C105795698 @default.
- W3178290420 hasConcept C11413529 @default.
- W3178290420 hasConcept C117251300 @default.
- W3178290420 hasConcept C121332964 @default.
- W3178290420 hasConcept C154945302 @default.
- W3178290420 hasConcept C1633027 @default.
- W3178290420 hasConcept C199360897 @default.
- W3178290420 hasConcept C2778770139 @default.
- W3178290420 hasConcept C28826006 @default.
- W3178290420 hasConcept C33923547 @default.
- W3178290420 hasConcept C41008148 @default.
- W3178290420 hasConcept C44154836 @default.
- W3178290420 hasConcept C459310 @default.
- W3178290420 hasConcept C500300565 @default.
- W3178290420 hasConcept C50644808 @default.
- W3178290420 hasConcept C57879066 @default.
- W3178290420 hasConcept C76563973 @default.
- W3178290420 hasConcept C90278072 @default.
- W3178290420 hasConceptScore W3178290420C105795698 @default.
- W3178290420 hasConceptScore W3178290420C11413529 @default.
- W3178290420 hasConceptScore W3178290420C117251300 @default.
- W3178290420 hasConceptScore W3178290420C121332964 @default.
- W3178290420 hasConceptScore W3178290420C154945302 @default.
- W3178290420 hasConceptScore W3178290420C1633027 @default.
- W3178290420 hasConceptScore W3178290420C199360897 @default.
- W3178290420 hasConceptScore W3178290420C2778770139 @default.
- W3178290420 hasConceptScore W3178290420C28826006 @default.
- W3178290420 hasConceptScore W3178290420C33923547 @default.
- W3178290420 hasConceptScore W3178290420C41008148 @default.
- W3178290420 hasConceptScore W3178290420C44154836 @default.
- W3178290420 hasConceptScore W3178290420C459310 @default.
- W3178290420 hasConceptScore W3178290420C500300565 @default.
- W3178290420 hasConceptScore W3178290420C50644808 @default.
- W3178290420 hasConceptScore W3178290420C57879066 @default.
- W3178290420 hasConceptScore W3178290420C76563973 @default.
- W3178290420 hasConceptScore W3178290420C90278072 @default.
- W3178290420 hasLocation W31782904201 @default.
- W3178290420 hasOpenAccess W3178290420 @default.
- W3178290420 hasPrimaryLocation W31782904201 @default.