The offshore wind sector is continually expanding, increasing the need to advance the application of remote smart sensors and automated analysis to monitor the structural integrity of offshore wind turbines. This internship combines smart-sensing technology developed by industry host Eleven-I with recent academic developments in structural health analysis via two components: (i) a critical review and synthesis of smart conditional monitoring techniques in offshore wind turbines, and (ii) the application of machine learning in conditional monitoring of turbine blade damage detection.
The second component builds upon a recently developed machine learning protocol to estimate monopile fatigue based on metocean data, through exploration of this protocol to evaluate blade damage detection. This utilises a data-driven approach based on a unique test dataset of accelerometer time-series corresponding with controlled blade damage.
The research literature synthesis will be then adapted to public outreach material with aims to communicate the science to the public and inspire the next generation researchers for the sector. This internship will provide the principal investigator with exposure and knowledge of an industry setting, and support seed fund for future grant applications to continue working on engineering and technology developments that support the offshore renewable energy sector.