Paul SAVES - Admis au titre de docteur

paul.saves@free.fr
Compte LinkedIn https://www.linkedin.com/in/paul-saves-3aa9a9113/

Doctorat Mathématiques et Applications

Thèse soutenue le 19 janvier 2024 - Institut Supérieur de l'Aéronautique et de l'Espace

Ecole doctorale : EDMITT - Ecole Doctorale Mathématiques, Informatique et Télécommunications de Toulouse

Sujet : Optimisation multi-disciplinaire en grande dimension pour l’éco-conception avion en avant-projet

Mots-clés de la thèse : Optimisation de concepts multidisciplinaires,Optimisation sur modèles de substitution,Processus gaussien,Variables mixtes catégorielles,Variables hiérarchiques,Conception d'avions écologiques,

Direction de thèse : Nathalie BARTOLI

Co-direction de thèse : Youssef DIOUANE

Unité de recherche : ISAE-ONERA MOIS MOdélisation et Ingénierie des Systèmes

Master - M2R Recherche opérationnelle

obtenu en septembre 2020 - ENAC Toulouse

Production scientifique

- Nathalie Bartoli (ONERA/DTIS), Youssef Diouane (ISAE-Supaero/DISC), Joseph Morlier (ISAE-SUPAERO/DMSM), Thierry Lefebvre (ONERA/DTIS) 2021. High dimensional multidisciplinary design optimization with Gaussian process for eco-design aircraft MASCOT-NUM21 PdD day, 0, https://www.gdr-mascotnum.fr/media/mascot21_poster-saves.pdf
- P. Saves 2020. On adapting the Super-Efficient Global Optimization solver tohandle mixed-variables, with applications in aircraft design. AGILE 4.0, 10.5281/zenodo.4672290, https://www.agile4.eu/cloud/index.php/s/XFxGFZitiqqZ8rm
- Nathalie Bartoli, ONERA, France, nathalie.bartoli@onera.fr Youssef Diouane, Institut Supérieur de l'Aéronautique et de l'Espace, France, youssef.diouane@isae.fr Thierry Lefebvre, ONERA, France, thierry.lefebvre@onera.fr Joseph Morlier, Institut Supérieur de l'Aéronautique et de l'Espace, France, joseph.morlier@isae.fr Paul Saves, ONERA, France, paul.saves@free.fr 2021. Présentation de la Toolbox SMT. SurDay : L'I.A. pour les modèles de substitution , 0, https://sites.google.com/view/surday2021/programme
- Paul Saves, Nathalie Bartoli, Youssef Diouane, Thierry Lefebvre, Joseph Morlier, Christophe David, Eric Van, Sébastien Defoort 2021. Constrained Bayesian optimization over mixed categorical variables, with application to aircraft design ECCOMAS Aerobest 2021, 1, https://hal.archives-ouvertes.fr/hal-03346341/document
- Paul Saves, Eric Nguyen Van, Nathalie Bartoli, Thierry Lefebvre, Christophe David, Sébastien Defoort, Youssef Diouane, Joseph Morlier 2022. Bayesian optimization for mixed variables using an adaptive dimension reduction process: applications to aircraft design AIAA SCITECH 2022 Forum, 0082, https://hal.archives-ouvertes.fr/hal-03514915/document
- Paul Saves, Nathalie Bartoli, Youssef Diouane, Joseph Morlier, Thierry Lefebvre 2021. Enhanced Kriging models within a Bayesian optimization framework to handle both continuous and categorical inputs SIAM CSE21, 1, https://hal.archives-ouvertes.fr/hal-03402296
- Saves, Paul, ISAE-Supaero & ONERA (présentateur) Diouane, Youssef, Polytechnique Montréal Bartoli, Nathalie, ONERA, DTIS, Université de Toulouse, Toulouse, France Lefebvre, Thierry, ONERA Morlier, Joseph, ISAE-Supaero 2022. Towards a unified Gaussian process kernel-based correlation matrix representation for mixed-categorical variables JOPT 2022 - HEC Montreal, JOPT 2022 - HEC Montreal, https://symposia.gerad.ca/jopt2022/fr/schedule?slot_id=2023
- Robin Grapin, Youssef Diouane, Joseph Morlier, Nathalie Bartoli, Thierry Lefebvre, Paul Saves, Jasper H Bussemaker 2022. Constrained Multi-Objective Bayesian Optimization with Application to Aircraft Design AIAA AVIATION 2022 Forum, 4053, https://arc.aiaa.org/doi/abs/10.2514/6.2022-4053
- Paul Saves, Youssef Diouane, Nathalie Bartoli, Thierry Lefebvre, Joseph Morlier 2022. A general square exponential kernel to handle mixed-categorical variables for Gaussian process AIAA AVIATION 2022 Forum, 3870, https://hal.archives-ouvertes.fr/hal-03700850/document
- Paul Saves, Nathalie Bartoli, Youssef Diouane, Joseph Morlier, Thierry Lefebvre, Eric Nguyen Van, Christophe David, Sebastien Defoort 2022. New advances in Multidisciplinary Design Optimization with Gaussian Process for Eco-design Aircraft 3rd European MDO Workshop -Toward Green Aviation, 3, https://www.researchgate.net/publication/363739124_New_advances_in_Multidisciplinary_Design_Optimization_with_Gaussian_Process_for_Eco-design_Aircraft
- Paul Saves, Eric Nguyen Van, Nathalie Bartoli, Thierry Lefebvre, Christophe David, Sébastien Defoort, Youssef Diouane, Joseph Morlier 2023. MDO Best Paper, 2023 Presentation. Bayesian optimization for mixed variables using an adaptive dimension reduction process: applications to aircraft design. https://arc.aiaa.org/doi/10.2514/6.2022-0082 AIAA SCITECH 2023, 0, https://www.researchgate.net/publication/367531372_MDO_Best_Paper_2023_Presentation_Bayesian_optimization_for_mixed_variables_using_an_adaptive_dimension_reduction_process_applications_to_aircraft_design_httpsarcaiaaorgdoi10251462022-0082
- P. Saves, Y. Diouane, N. Bartoli, T. Lefebvre, J. Morlier 2023. A mixed-categorical correlation kernel for Gaussian process Neurocomputing, 126472, https://doi.org/10.1016/j.neucom.2023.126472
- P Saves, Y Diouane, N Bartoli, T Lefebvre, J Morlier 2023. A new mixed-categorical correlation kernel for Gaussian process gdr mascot-num, 1, https://mascotnum2023.sciencesconf.org/data/mascotnum2023_Saves.pdf
- Paul Saves, Remi Lafage, Nathalie Bartoli, Youssef Diouane, Jasper Bussemaker, Thierry Lefebvre, John T. Hwang, Joseph Morlier, Joaquim R. R. A. Martins 2024. SMT 2.0: A Surrogate Modeling Toolbox with a focus on Hierarchical and Mixed Variables Gaussian Processes Advances in Engineering Software, Volume 188, https://www.sciencedirect.com/science/article/pii/S096599782300162X
- Remy Priem , Nathalie Bartoli , Youssef Diouane , Sylvain Dubreuil and Paul Saves 2023. High-dimensional efficient global optimization using both random and supervised embeddings AIAA AVIATION 2023 FORUM, 4448, https://arc.aiaa.org/doi/10.2514/6.2023-4448
- Paul Saves, Youssef Diouane, Nathalie Bartoli, Thierry Lefebvre, Joseph Morlier 2024. High-dimensional mixed-categorical Gaussian processes with application to multidisciplinary design optimization for a green aircraft ArXiV preprint, 2311.06130, https://arxiv.org/abs/2311.06130

Langues Vivantes : Espagnol C2 - Maternel - Français C2 - Maternel - Anglais C2 - Maternel - Russe A2 - Élémentaire

Dernière mise à jour le 22 novembre 2023