Copenhagen, Capital Region of Denmark, Denmark
Technical leader with 14+ years of experience across renewable energy and industrial engineering. Specialized in fleet-level performance modelling, technical risk assessment, and decision support for large, complex systems. Known for translating advanced analysis into clear guidance for engineers, asset managers, and senior decision-makers, and for mentoring others in technically demanding environments.
//Technical leadership for fleet-level performance modelling, uncertainty, and decision support// -Owned development and governance of Ørsted’s wind energy yield and performance modelling frameworks used for project bidding, budgeting, and long-term asset decisions. -Provided technical guidance to asset managers and senior stakeholders on turbine and fleet performance, uncertainty, and technical risk. -Acted as technical authority on model assumptions, data quality, and interpretation, supporting consistent decision-making across projects. -Lead responsible for massive automated power prediction pipeline, where advanced algorithms hind/forecast WTG-based power for entire offshore portfolio on nightly basis.
//Wind turbine performance testing, calibration, and validation across development stages// -Led measurement and analysis campaigns assessing prototype turbine performance (IEC 61400-12-1), coordinating across test, instrumentation, and analysis teams. -Developed software translating complex international technical standards into deployable logic, enabling new service business opportunities. Successfully applied tool in proto use case with major WTG manufacturer. -Through own initiative, developed Python-based robust automated alarm system to monitor measurements critical to ongoing campaign, significantly decreasing down time and relieving analysts of manual monitoring effort. -Through own initiative, developed automated reporting tool linking MATLAB based calculations programmatically to Python-based reporting logic, significantly decreasing manual effort required to iterate versions of accredited & deeply technical WTG analyses. -Supervised machine learning-based MSc theses (focus in time series based surrogate modelling) and contributed to PhD-level teaching in data science via course in automation using Python. -Collaborated with industry partners on AI-driven turbine blade defect forecasting.
Topic: Applied Machine Learning Techniques for Performance Analysis in Large Wind Farms Performed in collaboration with DTU Risø -Work published in journal "Energies - Artificial Intelligence & Smart Energy Section": https://www.mdpi.com/1996-1073/14/13/3756
-Developed and applied method and Python-based tool for structural health monitoring & diagnosis of offshore wind farms via modal analysis of in-situ measurement devices.
-Developed robust & streamlined wake loss model using novel methods -Developed floating WTG models to inform high level business case assumptions driven by MATLAB-based load wind & wave forcing load simulations (also my own development).