Master Thesis Internship: Machine learning surrogates for stress intensity factor solutions in aircraft crack growth analysis

Background

Structural integrity of aircraft structures is traditionally assessed using damage tolerance methodologies, where crack growth is predicted based on stress intensity factor (SIF) solutions. These SIF solutions are often obtained from high-fidelity finite element (FE) analyses and stored in large databases, such as geometry-specific K-solution libraries used in tools like AFGROW and NASGRO.

While these databases provide accurate and validated solutions, they only include solutions for simple or standardized geometries & loading conditions and they are computationally expensive to extend to more complex geometries or loading conditions.

At the same time, more detailed crack growth analysis for new design tools or digital twin applications require faster and more flexible K solutions to support them. Recent advances in machine learning (ML) and surrogate modelling offer the possibility to replace or augment analytical or FE-based K-solution databases with fast, compact, and continuously differentiable models that retain the underlying physics.

This thesis explores whether (physics-informed) ML models can be trained on existing FEM-derived K-solutions to provide accurate, conservative, and computationally efficient predictions suitable for crack growth analysis in an aircraft damage tolerance context.

Assignment

The objective of this thesis is to develop and evaluate a machine-learning-based surrogate model for stress intensity factor solutions that is applicable for any geometry and loading condition.

Expected results

At the end of the project, the student is expected to deliver:

• A validated ML-based surrogate model capable of predicting stress intensity factors for a defined class of crack geometries;

• Quantitative comparison of surrogate accuracy versus FEM-based solutions applied to crack growth calculations;

• Demonstration of significant computational speed-up relative to FEM analysis;

• Clear discussion of applicability, limitations, and implications for aircraft structural integrity.

Duration

6 months

Profile

The ideal master student for this thesis has:

• A background in aerospace engineering, mechanical engineering, civil engineering, applied mathematics or applied physics;

• Experience with numerical modelling in Python;

• Affinity with data-driven modelling;

• Interest in fracture mechanics;

• Affinity with uncertainty quantification is a plus.

The assignment is well suited for students who enjoy bridging fundamental modelling with real-world engineering applications.

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.

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 1000 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.

The assignment will be managed by the Aerospace Vehicles Integrity & Life Cycle Support (AVIL) department. This department provides operational, inspection and maintenance advice to manufacturers and users of aerospace structures and components of (alternative) propulsion sources. It focuses on many facets of MRO, including predictive maintenance, and carries out materials research and conducts engineering failure analysis.

Interested?

Send your application, together with your motivation letter and CV via the “apply” button. We will contact you as soon as possible. Questions? You can contact Emiel Amsterdam (emiel.amsterdam@nlr.nl)

A VOG screening is part of the interview process.