Marie-Curie (MSCA) PhD position: Enhancing the dependability of mission-critical system through an advanced data-driven anomaly detection methodology for electromagnetic disturbances (iSense – DC9)

At the M-Group at KU Leuven Bruges Campus, we are driving innovation in interconnected, intelligent mechatronic systems. A dedicated part of our team focuses on electromagnetic risk management, addressing the latest challenges in electromagnetic interference and advancing the future of this rapidly evolving field.
Website unit

Project

The iSense Doctoral Network is on a mission to train a new generation of experts to address the complex and ever-evolving electromagnetic environment. The focus? Tackling the problem of electromagnetic interference (EMI) through groundbreaking research and innovation. You’ll contribute to the development of next-gen EMI sensors, early-warning detection tools, and new modeling and testing strategies—ensuring the future of technology is interference-free.

In this PhD position (DC9), you will focus on identifying anomalies—unexpected deviations from normal behavior—in electromagnetic disturbances that occur during the operation of mission- and safety-critical systems. To tackle this, the objective is to design a machine learning-based anomaly detection methodology. The focus will be on semi-supervisedlearning techniques to build models of normal electromagnetic behavior, while exploring how these models can be integrated with the innovative concept of an EMI footprint. Detecting these anomalies is particularly challenging due to the diverse nature of electromagnetic disturbances, requiring research in how the resulting data-driven methodology can be made sufficiently robust in real-world environments. 

Your mission:

In this exciting role, you will:

• Develop a tailored, semi-supervised anomaly detection methodology specifically designed to identify potential EMI.
• Enhance the accuracy and robustness of anomaly detection in EMI environments, minimizing false alarms and improving system reliability.
• Explore the integration of the EMI footprint concept into the anomaly detection framework to further refine detection capabilities.

Expected results:

• A cutting-edge, semi-supervised framework for real-time anomaly detection in EMI data, designed to be highly effective and practical.
• Machine-learning models with enhanced accuracy for identifying EMI, significantly reducing false alarms and improving overall detection performance.

Profile

We are seeking a highly motivated, enthusiastic, passionate, and communicative researcher who holds a Master of Science degree in electrical engineering and/or computer science, with outstanding academic achievements. Candidates should demonstrate a strong affinity for EMC, machine learning and artificial intelligence.

Offer

This is more than just a PhD position—it’s an opportunity to be part of an internationally recognized network of researchers through the MSCA iSense Doctoral Network (www.dn-isense.eu). As a PhD candidate, you will be based at KU Leuven’s Bruges Campus, with exciting secondments at the TU Sofia and Barco.

We offer:

• A fully funded 3-year PhD scholarship (extendable to 4 years)
• Specialized doctoral training to boost your expertise.
• Opportunities to collaborate in groundbreaking interdisciplinary research and participate in international conferences.
• Access to state-of-the-art infrastructure and a range of university benefits (health insurance, etc.).
• A dynamic, passionate team of fellow PhD students and test engineers.

https://dn-isense.eu

Interested?

For more information please contact Prof. Mathias Verbeke, tel.: +32 50 66 47 76, mail: mathias.verbeke@kuleuven.be or Prof. dr. ir. Davy Pissoort, tel.: +32 50 66 48 49, mail: davy.pissoort@kuleuven.be.

KU Leuven strives for an inclusive, respectful and socially safe environment. We embrace diversity among individuals and groups as an asset. Open dialogue and differences in perspective are essential for an ambitious research and educational environment. In our commitment to equal opportunity, we recognize the consequences of historical inequalities. We do not accept any form of discrimination based on, but not limited to, gender identity and expression, sexual orientation, age, ethnic or national background, skin colour, religious and philosophical diversity, neurodivergence, employment disability, health, or socioeconomic status. For questions about accessibility or support offered, we are happy to assist you at this email address.