Sylvain Girard¶

I lead the “Reliability & Uncertainty” team at Phimeca Engineering Paris.

We use data science and numerical simulation to help designing, operating and maintaining industrial system safely and efficiently.

My main research interest are

Uncertainty modelling, in particular of spatio-temporal phenomena. Applications include pollution diagnosis and forecast, and health monitoring of industrial systems.
Dimension reduction and function approximations.
System scale modelling (also known as 0D/1D in some engineering comunities).

News¶

Francesco Cancelliere joins in September 2021 us as Marie Skłodowska-Curie Fellow within GREYDIENT project: “Machine learning and physical modelling interactions for vehicle batteries optimisation”.
IMdR “Uncertainty and Industry” workshop, 6 May 2021: “Computer experiment with dynamical models” (Replay available on demand by email).
Maéva Caillat joined our team on december 2020. Welcome Maéva!
The ThermoSysPro website is online. ThermoSysPro is a Modelica library for modeling electricity generation plants. Have a look at the (brand new) online scientific documentation.
Phimeca Engineering and Principia will chair a special session for the 31st ESREL conference (19-23 September 2021) entitled: “Health monitoring and predictive maintenance of offshore systems”.
Phimeca publish her new website. Get ready for the 20th birthday party!
Antoine Lesieur will take on the MADiPA postdoc in March 2021 (Modèles Auto-associatifs pour la Dispersion de Polluants dans l’Atmosphère – Phimeca & Inria).
AFFIDA project on offshore wind turbine predictive maintenance is funded by the European Regional Development Fund.

2020/12/08 – Périllat, Raphaël\(^*\), S. G. & I. Korsakissok λμ22, [🗎 get paper], “Solutions rapides pour la prévision des risques de pollution atmosphérique”.
2020/11/26 – Gerrer, Claire-Eleuthèriane\(^*\) & S. G. NAFEMS’20 on numerical simulation [🗎 get slides], “Health monitoring using statistical learning and digital twins”.
2020/03/02 – Rencontres INRIA LJLL en calcul scientifique [🗎 get slides], “Réduction de dimension avec des modèles auto-associatifs”.