En poursuivant votre navigation sur ce site, vous acceptez le dépôt de cookies dans votre navigateur. (En savoir plus)
Portail > Offres > Offre UPR3251-FRALUS-001 - Contrôle expérimental d'écoulements turbulents cisaillés par apprentissage automatique (H/F).

Machine learning control of experimental turbulent shear flows

This offer is available in the following languages:
Français - Anglais

Assurez-vous que votre profil candidat soit correctement renseigné avant de postuler. Les informations de votre profil complètent celles associées à chaque candidature. Afin d’augmenter votre visibilité sur notre Portail Emploi et ainsi permettre aux recruteurs de consulter votre profil candidat, vous avez la possibilité de déposer votre CV dans notre CVThèque en un clic !

Faites connaître cette offre !

General information

Reference : UPR3251-FRALUS-001
Workplace : ORSAY
Date of publication : Monday, December 24, 2018
Type of Contract : FTC Scientist
Contract Period : 12 months
Expected date of employment : 1 March 2019
Proportion of work : Full time
Remuneration : between 2600€ and 3007 € gross monthly depending on experience
Desired level of education : PhD
Experience required : Indifferent

Missions

The Postdoc will be at the heart of the experimental efforts of the ANR FLOwCON project. He will have to implement the control methods developed in the other tasks of the ANR. These methods will be based on Genetic Programming or reinforced learning.

Activities

His role will be to conduct experimental demonstrations of control by Machine Learning, in 3 experimental situations:
- Fluidic PinBall wake stabilization (at LIMSI, http://berndnoack.com/FlowControl.php)
- open cavity flow stabilization (at LIMSI)
- Reattachment of the turbulent boundary layer on wing profile (PRISM).

Skills

The successful candidate should demonstrate a strong background in experimental flow control ideally with experience in feedback laws. Experience in flow velocimetry and visualization is appreciated. Good notions of signal analysis, control theory and machine learning are certainly a plus. The candidate should also have strong skills in communication and excellent writing capabilities.

Work Context

FLOwCON is an ANR project funded by DGA (French Direction Générale de l'Armement) and devoted to the development and the demonstration of machine learning methods for the closed loop control of turbulent fluid flows such as the one shown in the figure below. This project is lead by a consortium of turbulence control researchers of France at LIMSI, PRISME and PPRIME in collaboration with a world-wide network of leading scholars in machine learning, nonlinear dynamics, control theory, simulations and experiments

Constraints and risks

Use of laser sources.

We talk about it on Twitter!