Skip to Main content Skip to Navigation
Conference papers

RANS closure approximation by artificialneural networks

Abstract : Turbulence modelling remains a challenge for the simulation of turbomachinery flows. Reynolds Averaged Navier-Stokes (RANS) equations will still be used for high-Reynolds number flows for several years and so there is interest in improving their prediction capability. Machine learning techniques offer several strategies which could be exploited for this purpose. In this work, an approach to improve the Spalart-Allmaras model is investigated. In particular , the model is used to predict the flow around the T106c low pressure gas turbine cascade. As a first step, an Artificial Neural Network (ANN) is trained on the data generated by the original model. Then, an optimisation procedure is applied in order to find the weights of the network which minimise the error between the predicted results and the available experimental data. The new model is tested at different Reynolds numbers on the T106c cascade and on a wind turbine airfoil in post-stall conditions. Significant improvements are observed in the condition chosen for the optimisation. Future work will be devoted to the generalisation of the approach by including multiple working conditions optimisations and adding new physical variables as inputs of the ANN.
Complete list of metadata

Cited literature [31 references]  Display  Hide  Download
Contributor : Andrea Ferrero Connect in order to contact the contributor
Submitted on : Tuesday, December 10, 2019 - 7:11:44 PM
Last modification on : Wednesday, February 2, 2022 - 3:54:43 PM
Long-term archiving on: : Wednesday, March 11, 2020 - 9:48:11 PM


Files produced by the author(s)


  • HAL Id : hal-02403432, version 1



Andrea Ferrero, Angelo Iollo, Francesco Larocca. RANS closure approximation by artificialneural networks. ETC 2019 - 13th European Turbomachinery Conference on Turbomachinery Fluid Dynamics and Thermodynamics, Apr 2019, Lausanne, Switzerland. ⟨hal-02403432⟩



Record views


Files downloads