%0 Unpublished work %T Data-driven framework for input/output lookup tables reduction -- with application to hypersonic flows in chemical non-equilibrium %+ Institut des Sciences du Calcul et des Données (ISCD) %+ Imperial College London %+ DAAA, ONERA, Université Paris Saclay [Meudon] %+ Department of Mathematics [Imperial College London] %+ Institut Jean Le Rond d'Alembert (DALEMBERT) %A Scherding, Clément %A Rigas, Georgios %A Sipp, Denis %A Schmid, Peter J. %A Sayadi, Taraneh %Z 24 pages, 16 figures, 2 tables %8 2022-11-15 %D 2022 %Z 2210.04269 %Z Engineering Sciences [physics]Preprints, Working Papers, ... %X In this paper, we present a novel model-agnostic machine learning technique to extract a reduced thermochemical model for reacting hypersonic flows simulation. A first simulation gathers all relevant thermodynamic states and the corresponding gas properties via a given model. The states are embedded in a low-dimensional space and clustered to identify regions with different levels of thermochemical (non)-equilibrium. Then, a surrogate surface from the reduced cluster-space to the output space is generated using radial-basis-function networks. The method is validated and benchmarked on a simulation of a hypersonic flat-plate boundary layer with finite-rate chemistry. The gas properties of the reactive air mixture are initially modeled using the open-source Mutation++ library. Substituting Mutation++ with the light-weight, machine-learned alternative improves the performance of the solver by 50% while maintaining overall accuracy. %G English %2 https://hal.science/hal-03852556/document %2 https://hal.science/hal-03852556/file/2210.04269.pdf %L hal-03852556 %U https://hal.science/hal-03852556 %~ ONERA %~ CNRS %~ IJLRDA %~ UNIV-PARIS-SACLAY %~ SORBONNE-UNIVERSITE %~ SORBONNE-UNIV %~ SU-SCIENCES %~ FED-3 %~ ISCD %~ UNIVERSITE-PARIS-SACLAY %~ SU-TI %~ ALLIANCE-SU %~ TEST3-HALCNRS