RANS closure approximation by artificialneural networks
| hal.structure.identifier | Politecnico di Torino = Polytechnic of Turin [Polito] | |
| dc.contributor.author | FERRERO, Andrea | |
| hal.structure.identifier | Modeling Enablers for Multi-PHysics and InteractionS [MEMPHIS] | |
| dc.contributor.author | IOLLO, Angelo | |
| hal.structure.identifier | Politecnico di Torino = Polytechnic of Turin [Polito] | |
| dc.contributor.author | LAROCCA, Francesco | |
| dc.date.accessioned | 2024-04-04T02:58:29Z | |
| dc.date.available | 2024-04-04T02:58:29Z | |
| dc.date.conference | 2019-04-08 | |
| dc.identifier.uri | https://oskar-bordeaux.fr/handle/20.500.12278/192662 | |
| dc.description.abstractEn | 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. | |
| dc.language.iso | en | |
| dc.subject.en | RANS | |
| dc.subject.en | Machine learning | |
| dc.subject.en | Turbomachinery | |
| dc.title.en | RANS closure approximation by artificialneural networks | |
| dc.type | Communication dans un congrès | |
| dc.subject.hal | Sciences de l'ingénieur [physics]/Mécanique [physics.med-ph]/Mécanique des fluides [physics.class-ph] | |
| bordeaux.hal.laboratories | Institut de Mathématiques de Bordeaux (IMB) - UMR 5251 | * |
| bordeaux.institution | Université de Bordeaux | |
| bordeaux.institution | Bordeaux INP | |
| bordeaux.institution | CNRS | |
| bordeaux.conference.title | ETC 2019 - 13th European Turbomachinery Conference on Turbomachinery Fluid Dynamics and Thermodynamics | |
| bordeaux.country | CH | |
| bordeaux.conference.city | Lausanne | |
| bordeaux.peerReviewed | oui | |
| hal.identifier | hal-02403432 | |
| hal.version | 1 | |
| hal.invited | non | |
| hal.proceedings | oui | |
| hal.conference.end | 2019-04-12 | |
| hal.popular | non | |
| hal.audience | Internationale | |
| hal.origin.link | https://hal.archives-ouvertes.fr//hal-02403432v1 | |
| bordeaux.COinS | ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.au=FERRERO,%20Andrea&IOLLO,%20Angelo&LAROCCA,%20Francesco&rft.genre=unknown |
Files in this item
| Files | Size | Format | View |
|---|---|---|---|
|
There are no files associated with this item. |
|||