Dr Sergio Lopez Dubon
Tidal energy is one of the solutions to produce clean and predictable green energy. Nevertheless, there are still big gaps that need to be close, one of these is the structural design of larger tidal blades under complex fatigue conditions. This can be done through data-driven techniques using the FASTBLADE test facility a product of the collaboration between the University of Edinburgh and Babcock International.
FASTBLADE allows simulating complex ocean loads conditions in a fraction of time (20 years in 3 months), capturing a significant amount of data (around 500 GB per day) from the blades. This ensures that FASTBLADE reaches its full potential by improving the operational inputs (system settings and characterised in-service load data) and outputs (machine response and specimen response) using data-driven techniques.
The main motivation of this project is to improve the FASTBLADE facility data flow, enabling it to obtain more realistic, accurate and cheaper structural testing data. This will allow developers and designers to understand the performance of the tidal blades better and accelerate design developments, ultimately enabling them to become more efficient and competitive.
The main objectives of the project are:
- Develop the load data classification techniques using machine learning to define input parameters for multi-axis and multi-frequency testing regimes.
- Create a Digital Twin of the FASTBLADE facility.
- Apply machine learning techniques to extend the operational range and capabilities of the FASTBLADE System
- Deploy data-driven techniques to understand the tell-tale signs of failure and locate the point of failure within thick composite structures.
- Use Digital Image Correlation System for sensor placement optimization.
- Determine the threshold at which accelerated testing breaks down at full scale.
This TRAIN@Ed project has received funding from the DDI programme and the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No 801215.
For more information visit Edinburgh Research Explorer Profile.