Internship: Artificial Intelligence (AI) physics-informed methods for aerospace structures

Background

Aviation is a highly energy-intensive sector. The International Civil Aviation Organization (ICAO) forecasted that by 2050 international aviation emissions could triple compared to 2015. To address this trend, various technical and operational measures - such as the use of sustainable aviation fuels, improvements in airframes and engines, - are essential to mitigate the growth of emissions, ultimately reducing them in the coming decade and contributing to the EU’s overall climate neutrality target.

This assignment allows to contribute to the development of innovative solutions in aerospace engineering. The focus of this internship will be on exploring the application of Artificial Intelligence (AI) physics-informed methods to enhance the Finite Element Method (FEM) for aerospace applications. The primary objective of this internship is to investigate the potential of AI physics-informed methods to improve the simulation capabilities of aerospace structures currently done with FEM. This includes:

• Reviewing existing literature on AI physics-informed methods and their applications in FEM

• Developing and implementing an AI-driven model(s) for enhancing FEM simulations

• Evaluating the performance of AI-enhanced FEM simulations against traditional methods

• Identifying potential aerospace applications where AI physics-informed FEM can provide significant improvements

Assignment

• Develop and train AI models (e.g., neural networks, PINN, KAN, GDL) that can learn from physical laws and simulate complex aerospace phenomena

• Integrate the developed AI models with FEM software to create a hybrid simulation framework

• Apply the hybrid framework to selected aerospace case studies (e.g., structural analysis)

• Analyse and compare the results from AI-enhanced FEM simulations with those from traditional FEM methods

• Conduct a review of current research in AI physics-informed methods and their application to FEM

• Document the research process, results, and conclusions in a comprehensive report

Result

The foreseen result is a comparison between the current method and the new AI physics informed methods.

Duration

This fulltime (graduate) internship starts preferably as soon as possible and will have a duration of 3-9 months.

Profile

• Master student with interest in finite element methods, solid mechanics, programming and AI.

• Familiarity with AI and machine learning concepts, particularly physics-informed neural networks (PINNs) or similar methods

• Programming skills in languages such as Python, C++, or MATLAB

• Experience with FEM software (e.g., Abaqus, Altair) and AI frameworks (e.g., TensorFlow, PyTorch) is desirable

• English fluent

What we offer

• A challenging graduation project/internship in a high-tech result orientated work environment

• Weekly supervision and availability of the technical staff for support

• An internship allowance

• Working in an actual R&D project as part of the team

• Internship results to be used in the current and future projects

• A diverse and multicultural work environment

About NLR

Royal NLR has been the ambitious research organisation with the will to keep innovating for over 100 years. With that drive, we make the world of transportation safer, more sustainable, more efficient and more effective. We are on the threshold of breakthrough innovations. Plans and ideas start to move when these are fed with the right energy. Over 900 driven professionals work on research and innovation. From aircraft engineers to psychologists and from mathematicians to application experts.

Our colleagues are happy to tell you what it’s like to work at NLR.

This assignment will be managed by the Metal Additive Manufacturing & Computational Mechanics department within the Aerospace Vehicles (AV) division.

The Metal Additive Manufacturing & Computational Mechanics department (+25 employees) contributes to the development of lightweight additively manufactured aircraft components and the sustainability of aviation through the use of high-tech materials and computational mechanics predictive and optimization tools.

We evaluate new Metal Additive Manufacturing technologies and in addition to manufacturing, we also increasingly perform simulations of manufacturing processes and develop digital representations using computational mechanics. With these activities, we strengthen the competitiveness of companies that produce aerospace components and support defense tasks. We conduct much of our research together with universities and companies. Our project teams are multidisciplinary and work in (inter)national partnerships.

Interested:

You can apply on this vacancy, for more information you can reach to Wouter van den Brink: Wouter.van.den.Brink@nlr.nl