Machine learning is revolutionizing computational mechanics, enhancing the solution of complex mechanical problems through artificial intelligence. This approach leverages advanced algorithms to improve traditional numerical methods, offering innovative solutions for various mechanical engineering challenges.

Research Area and Project description:
A PhD position is available for a research project at the intersection of computational mechanics, nonlinear solid mechanics, artificial neural networks (ANNs), and forming process modelling. The project aims to integrate ANNs with the finite element method (FEM) to develop an advanced hybrid sub-structuring technique.

The primary objective is to use ANNs to enhance FEM performance in nonlinear mechanics through dimension reduction and efficient computation, while maintaining accuracy. This research will focus on developing a hybrid sub-structuring approach with intelligent macro-elements, offering a versatile framework for various scenarios.

Key areas of investigation include optimizing ANNs integration with FEM, addressing existing constraints, and exploring applications in simulating forming processes. A notable example includes models with strong local-global interactions, requiring fine mesh resolutions in areas with local elastic deformations (e.g., forming tools) and nonlinear phenomena like frictional contact (e.g., tool-workpiece).

The Challenge:
Designing and training ANNs to enhance FEM requires a deep understanding of both machine learning and computational mechanics. The integration process is complex, demanding fundamental knowledge of finite element formulation, advanced programming and modelling skills.

The ideal candidate for this PhD position will possess the following qualifications:

• MSc degree in Computational Mechanics, Mechanical Engineering, Applied Physics, Data Science, or a related field with excellent grades.
• Special interest in numerical modelling techniques (especially FEM).
• Knowledge of nonlinear solid mechanics, computational methods and machine learning.
• Strong programming skills.
• High degree of responsibility and independence.
• Strong verbal and written communication skills.
• Proficiency in English (IELTS minimum score 6.5 or TOEFL-iBT minimum score 90).

We provide a dynamic and inclusive environment where teamwork and collaboration are highly valued. Throughout the project, you will have ample opportunity to enhance your skills and expertise through continuous learning and development. In this role, you will engage in fundamental research with significant potential for industrial applications, making meaningful contributions to both academic and industry advancements.

Our offer includes:

• Excellent working conditions in an exciting scientific environment, and a green and lively campus.
• A full-time 4-year PhD position.
• Excellent mentorship and facilities.
• A professional and personal development program within Graduate School Twente.
• A starting salary of € 2770,- gross per month in the first year and increasing to € 3539,- gross per month in the fourth year.
• A holiday allowance of 8% of the gross annual salary and a year-end bonus of 8.3%.
• A minimum of 29 holidays per year in case of full-time employment.
• Full status as an employee at the University of Twente, including pension and health care benefits.

The intended start date is before the end of 2024.