The European Union’s energy and environmental policies are aimed at promoting and developing offshore wind platforms. This means that the Spanish electricity system will depend more and more on this type of electricity generation systems. The wind turbines for this case are larger, more complex, and require high demands for safety, reliability, availability and maintainability. In this project, this problem is addressed, with the final aim being the comprehensive and optimal management of this type of wind turbine parks.

The project starts with the intention of continuing and completing the National WindSeaEnergy project (DPI2012-31579), where more than 300 scientific references were analyzed in high impact journals, observing that there are great deficiencies in mathematical models that allow analyzing the signals that are they are monitoring to determine the state of the structures, as well as the optimal management of wind turbines and wind farms.

OptiWindSeaPower intends to continue and complete this study initiated in the field of the rotating elements of the wind turbine, and of the maintenance management thereof, making a more exhaustive study in the monitoring systems and methods of signal processing for the structural elements of said teams. The necessary data from WindSeaEnergy will be taken as a reference, as well as the European OPTIMUS, NIMO, WINPRO and the National IcingBlades projects. For this purpose, the design and development of a test bench of an ultrasound-based monitoring system will be required to determine the structural state of the wind turbines to complete this set of signals. A life cycle cost model for the predictive maintenance system will be developed. It is proposed to use mathematical models based on the analysis in time, frequency and time / frequency, as well as Transformed Wavellets, Neural Networks / Artificial Intelligence, methods based on the extraction of signal characteristics and derivatives of the System Transfer Function . The multivariate analysis will be done through Logical Decision Trees, which will be analyzed using Binary Decision Diagrams, and the important measures created by heuristic methods. This will allow controlling and optimizing the status of a wind turbine integrally. For the optimal management of the offshore wind farm, it will be considered as a Markovian decision problem, and the Restless Bandit indexes will be analyzed in order to determine the structure of the «Whittle» indices in different contexts. Finally, new indexes of significance based on costs will be created and the problem of optimization and its resolution will be formulated through metaheuristic methods to determine the optimal investment policy in the management of this type of parks.

The work team consists of members of the UCLM (6), the University College of Financial Studies of Madrid (3), and 5 of the universities of Drexel (USA), Birmingham (England), Monterrey (USA), King Fasial University (Saudi Arabia), Kyungpook National University (South Korea), with a clear multidisciplinary character, consisting of members specialized in Industrial Engineering, Economics, Statistics and Operations Research, and Energy.