Intership M2 in Mechanics (H-F)

Hybrid AI-reliability approach for modeling and dimensioning Wind Turbine Gearboxes

Keywords : Reliability-Based Design Optimization, Wind Turbine Gearbox

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 2025 and 2030, reaching 732 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., 2021] 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., 2020] 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 scientic/technical prdouction

The main outcome expected by the end of the internship is:

·        Conference Paper: Presenting the proposed method and results to an international conference.

Lab presentation

CESI LINEACT (UR 7527), Laboratory for Digital Innovation for Businesses and Learning to Support the Competitiveness of Territories, anticipates and accompanies the technological mutations of sectors and services related to industry and construction. The historical proximity of CESI with companies is a determining element for our research activities. It has led us to focus our efforts on applied research close to companies and in partnership with them. A human-centered approach coupled with the use of technologies, as well as territorial networking and links with training, have enabled the construction of cross-cutting research; it puts humans, their needs and their uses, at the center of its issues and addresses the technological angle through these contributions.

Its research is organized according to two interdisciplinary scientific teams and several application areas.

• Team 1 "Learning and Innovating" mainly concerns Cognitive Sciences, Social Sciences and Management Sciences, Training Techniques and those of Innovation. The main scientific objectives are the understanding of the effects of the environment, and more particularly of situations instrumented by technical objects (platforms, prototyping workshops, immersive systems...) on learning, creativity and innovation processes.

• Team 2 "Engineering and Digital Tools" mainly concerns Digital Sciences and Engineering. The main scientific objectives focus on modeling, simulation, optimization and data analysis of cyber physical systems. Research work also focuses on decision support tools and on the study of human-system interactions in particular through digital twins coupled with virtual or augmented environments.

These two teams develop and cross their research in application areas such as

• Industry 5.0,

• Construction 4.0 and Sustainable City,

• Digital Services.

Links to the research axes of the research team involved

CESI Lineact Research Thematic: mechanics, materials and processes.

Bibliography

Trabelsi, H., Guizani, A., Barkallah, M., Hammadi, M., Haddrich, A., & Haddar, M. (2021). Consideration of the uncertainty in dimensioning of a gearbox of a wind turbine. Journal of Theoretical and Applied Mechanics, 59(1), 67-79.

Ghorbel, A., Graja, O., Hentati, T., Abdennadher, M., Walha, L., & Haddar, M. (2020). The effect of the brake location and gear defects on the dynamic behavior of a wind turbine. Arabian Journal for Science and Engineering, 45(5), 4437-4451.

Kamel, A., Dammak, K., El Hami, A., Ben Jdidia, M., Hammami, L., & Haddar, M. (2022). A modified hybrid method for a reliability-based design optimization applied to an offshore wind turbine. Mechanics of Advanced Materials and Structures, 29(9), 1229-1242.

Karmi, B., Saouab, A., Guerine, A., Bouaziz, S., Hami, A. E., Haddar, M., & Dammak, K. (2024). Reliability based design optimization of a two-stage wind turbine gearbox. Mechanics & Industry, 25, 16.

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

Contacts and Application

Expected documents to candidate:

· A curriculum vitae (CV) detailing academic background, technical skills, and relevant experiences

· A motivation letter (maximum one page) expressing interest in the internship and alignment with the research topic

· Academic transcripts (relevé de notes) from the current and previous years of study

· Any reference letters or supporting documents that may strengthen the application

And must be submitted as a single PDF file.