The following three webinars are part of the dissemination activities of the MATHEO project, in which the JRL-ORE participates.
MATHEO (Smart Mathematics for Offshore Wind / Matemáticas Inteligentes para Eólica Offshore) is a research project funded by the Basque Government under the Elkartek programme. The project is coordinated by TECNALIA and it involves researchers from BCAM and three departments at the University of the Basque Country: Fluid Mechanics, Geodynamics and Applied mathematics, statistics and operations research.
The project seeks to advance in the physical knowledge and in the mathematical modelling of offshore wind and will deal with the development of virtual sensors for the modelling of the seabed and its interaction with foundations using Smoothed Particle Hydrodynamics SPH approaches, as well as “hybrid” methods for the modelling of nonlinear phenomena occurring at the splash zone of support structures for offshore wind and mixed materials, and Deep Learning techniques for operation and smart re-design of components for these platforms.
This consortium taking part in the project will engage with the Basque offshore wind supply chain to maximise the impact of the project: 10 companies and 2 sectorial clusters have shown interest so far in the project results.
Computational and experimental analysis of the overtopping on structures for offshore renewables
The overtopping effect on offshore structures is described, followed by an explanation of numerical modelling. The team provides details about the analytical and experimental validation of the models.
Lecturers: TECNALIA, Department of Energy Engineering of the UPV/EHU
Modelling and simulation of sediment material for offshore wind energy applications
Description of the seabed complexity in terms of sediment types and SPH modelling; application of the numerical models to the interaction of drag embedded anchors with the seabed for floating wind.
Lecturers: TECNALIA, Department of Geodynamics of the UPV/EHU, BCAM, Department of Energy Engineering of the UPV/EHU
Challenges of applying deep neural networks to the offshore wind energy sector
Description of the fundamentals of neural networks and application of deep learning techniques to the structural health monitoring -SHM- for the O&M cost reduction in offshore wind.
Lecturers: TECNALIA, Department of Applied Mathematics, Statistics and Operations Research of the UPV/EHU, BCAM