Présidents de session
Vendredi après midi: session 7
- CLAIRE VALENTIN (LAGEPP)
Vendredi après midi: session 8
- AHMAD HABLY (LAGEPP)
This project has a dual objective, combining teaching and research on machine learning methods for dynamical systems. It contributes to the teaching curriculum by offering students hands-on exposure to neural network tools for modeling and simulation of complex systems. The lectures introduce Physics-Informed Neural Networks (PINNs), providing Master students with concrete methods to embed...
ETUDIANT 14: Lina Laouzai
The rapid growth of electric vehicles (EVs) has led to an increasing demand for efficient and sustainable recycling of lithium-ion batteries. Disassembly is a critical step in the battery recycling process, influencing both economic viability and environmental impact. Recent research has explored various strategies for optimizing disassembly, including...
This MSc internship offers an opportunity to deepen the understanding of natural convection phenomena in non-Newtonian fluids. It will enable the student to develop advanced skills in numerical modeling and stability analysis while contributing to advancing knowledge in this domain. The results could also pave the way for applications in various sectors, such as geothermal energy, energy...
Composite materials are widely used in engineering because of their interesting mechanical properties. The objective of this internship is to study the mechanical behavior of composite materials using a numerical homogenization approach based on Fast Fourier Transforms (FFT). The work focuses on understanding the theoretical framework of the method and implementing numerical tools to compute...
ETUDIANT 15: Nicolas Becker
L’animation de personnages basée sur la physique a connu des avancées significatives au cours des dernières années. Les méthodes d’optimisation et d’apprentissage par renforcement ont permis de complexifier les mouvements appris [1, 3, 8, 9, 10]. Ces approches visent généralement à produire des mouvements réalistes, proches de ceux des humains, en respectant...
Physics-based character animation has seen significant advances in recent years. Optimization and reinforcement learning methods have made it possible to increase the complexity of learned movements [1, 3, 8, 9, 10]. These approaches generally aim to produce realistic movements, similar to those of humans, while respecting real physical laws based on motion capture data. However, in the field...
