Data-driven framework for input/output lookup tables reduction: Application to hypersonic flows in chemical nonequilibrium

Physical Review Fluids, vol. 8

Abstract

Capturing high temperature effects in hypersonic flow simulations relies upon expensive thermochemical gas models. We present here a novel model-agnostic machine-learning technique to extract a reduced thermochemical model of a gas mixture from a library. Combining techniques of dimensionality reduction, spectral clustering, and radial basis functions, an accurate and more efficient alternative to the original model is obtained.

Authors 5

1. Clément Scherding

   Sorbonne Université · Institut Jean Le Rond d'Alembert

   Affiliation as printed

   Institut Jean le Rond d'Alembert, Sorbonne University, 75005 Paris, France

2. Georgios Rigas

   Imperial College London

   Affiliation as printed

   Department of Aeronautics, Imperial College London, London SW7 2AZ, United Kingdom

3. Denis Sipp
   Affiliation as printed

   DAAA, Onera, 92190 Meudon, France

4. Peter J. Schmid

   King Abdullah University of Science and Technology

   Affiliation as printed

   Department of Mechanical Engineering, KAUST, 23955 Thuwal, Saudi Arabia

5. Taraneh Sayadi Aachen Institute for Combustion Technology

   Sorbonne Université · Institut Jean Le Rond d'Alembert · RWTH Aachen University

   Affiliation as printed

   Institut Jean le Rond d'Alembert, Sorbonne University, 75005 Paris, France

   Institute for Combustion Technology, Aachen University, 52062 Aachen, Germany