[STAGE MASTER 2]

Description : Wind turbines play a vital role in the global energy transition, forming the cornerstone of renewable electricity generation. Wind power harnesses an inexhaustible resource to produce clean energy, significantly reducing carbon emissions and dependence on fossil fuels. Recent forecasts predict that cumulative onshore wind capacity will increase by 45% between and , reaching GW. In this context of rapid expansion and increasing technological complexity, optimizing key wind turbine components has become a major challenge, making it necessary to move beyond traditional design approaches. In a collaborative engineering context, traditional design methodologies, based on a sequential "design/simulation/return to initial stage in case of failure" loop, are becoming increasingly inadequate in the face of the growing complexity of mechanical systems like wind turbine gearboxes. These systems are subject to parametric uncertainties (e.g., material properties, gear mesh stiffness, wind loads) and complex dynamic excitations (aerodynamic torques, braking forces), requiring a robust design approach. New approaches integrating artificial intelligence (AI) and machine learning (ML) are emerging as powerful tools to optimize the design process and improve decision-making in the face of uncertainty. This work is part of this dynamic. It aims to develop an innovative design approach, based on AI and ML, to support decision-making and optimal design of mechanical systems. Specifically, this work aims to develop an innovative design approach, based on AI and ML, to support the robust design and optimization of wind turbine gearbox systems. The proposed approach will build upon the foundational work of [Trabelsi et al., ] for the precise finite element modeling of gearbox systems under uncertainty, incorporating interval computation methods to handle design variables like gear dimensions and material properties. To handle uncertainties effectively, we will draw inspiration from [Ghorbel et al., ] by modeling gear defects (e.g., profile errors, assembly defects) and their impact on dynamic behavior, validated by Monte Carlo simulations or chaos polynomials to ensure the robustness and reliability of the resulting solutions. Fast and reliable AI-based meta-models (e.g., Gaussian Processes, Bayesian Neural Networks) will be developed to replace costly simulations within optimization loops, ensuring robust and reliable solutions for vibration minimization and fault tolerance in wind turbine gearboxes. Objectives : Conduct a literature review on the modeling and simulation of wind turbine gearboxes, with an emphasis on uncertainty management, gear defects, and reliability approaches. Develop a numerical model of the wind turbine gearbox system. This model will combine the physical equations of the system (e.g., gear mesh stiffness, braking torque, wind-induced loads) and the variability in input parameters to study the effect of uncertainties on output responses (e.g., vibration levels, dynamic stability). Implement a Reliability-Based Design Optimization (RBDO) process for gearbox sizing. The optimization will aim to minimize vibrations and gear failures while guaranteeing operational stability under variable wind conditions. Develop a software prototype integrating the modeling, uncertainty propagation, and optimization method. This prototype will apply the proposed methodology to the wind turbine gearbox case study and quantify its benefits compared to a deterministic design. Expected scientific/technical production : The main outcome expected by the end of the internship is: Conference Paper: Presenting the proposed method and results to an international conference. References: Ghorbel, A., Graja, O., Hentati, T., Abdennadher, M., Walha, L., & Haddar, M. . The effect of the brake location and gear defects on the dynamic behavior of a wind turbine. Arabian Journal for Science and Engineering, 45, -. Kamel, A., Dammak, K., El Hami, A., Ben Jdidia, M., Hammami, L., & Haddar, M. . A modified hybrid method for a reliability-based design optimization applied to an offshore wind turbine. Mechanics of Advanced Materials and Structures, 29, -. Karmi, B., Saouab, A., Guerine, A., Bouaziz, S., Hami, A. E., Haddar, M., & Dammak, K. . Reliability based design optimization of a two-stage wind turbine gearbox. Mechanics & Industry, 25, 16. Profile The Candidate's Profile : The candidate should be a Master’s student (M2) or in the final year of an Engineering School program, with a background in Computational Mechanics. She/He should have some knowledge and experience in a number of the following topics: Finite Element Modeling and Computational Mechanics. Programming experience with interpreted languages such as MATLAB, Python, or similar. Fluent written and verbal communication skills in English are required Starting date Dès que possible