Antonios Kapenis
PhD
Design of automatic maintenance recommendation system for wind turbine components
Host organization
Technical University of Denmark - DTU
Project Description
My PhD project, part of the EU-funded IntelliWind network, focuses on designing an automatic maintenance recommendation system for wind turbine components. My main tasks include developing a monitoring system to analyze sensor signals and estimate component structural responses. I will also create a prognostics module to predict the likelihood of component failures based on real-time loading conditions. Finally, I will design an automatic work-order system that recommends which components to maintain across an entire wind farm portfolio. The goal is to reduce downtime, improve reliability, and make maintenance planning smarter and more cost-effective through data-driven decision-making and automation.
​
Supervisors
Professor Athanasios Kolios
Nikolay Dimitrov Senior Researcher
​
Background
I am a PhD student from Greece. I completed both my undergraduate and master's studies in the School of Mechanical Engineering at the Technical University of Crete, Chania, with a specialization in Production and Management Engineering. My research journey began with my diploma thesis on "Predictive Maintenance and Fault Detection on Onshore Windfarms Using Digital Twins." For my thesis, I created a digital twin of a real wind farm in Greece, developed algorithms for power output prediction and fault detection, and used real-time operational data to monitor wind turbines and simulate their performance.
Motivation
I am very excited to continue my research journey and broaden my knowledge, especially in the field of wind energy. The most important thing for me is the opportunity to work with other researchers and exchange ideas with new colleagues. My diploma thesis is highly relevant to my PhD project, which makes me confident about my journey. The skills I gained from my thesis in predictive maintenance using digital twins, fault detection, and forecasting using real operational data will contribute significantly to my PhD's objectives. Furthermore the IntelliWind project provides an ideal blend of academic and industrial training, which is a rare setting and will allow me to balance different interests and points of view.
