Nicolás Gorostidi defenderá su tesis el lunes 15 de septiembre

La defensa tendrá lugar en la Sala Adela Moyua, en la Facultad de Ciencia y Tecnología del Campus de Leioa de la UPV/EHU, a las 11:00 horas.

Nicolás Gorostidi es doctorando en matemáticas y estadística, con una investigación centrada en la aplicación de técnicas de deep learning al seguimiento del estado estructural de los sistemas de amarre de aerogeneradores eólicos flotantes marinos. Su trabajo combina matemáticas aplicadas, mecánica computacional y modelización estadística para desarrollar estrategias de mantenimiento predictivo en sistemas eólicos marinos. Asimismo, posee un Máster en Dinámica de Fluidos Computacional por la Cranfield University y un Grado en Ingeniería Mecánica por la Universidad de Oviedo. Fuera del ámbito académico, es pianista de jazz, corredor de maratones y aficionado a la repostería.

Su tesis, titulada “Structural Health Monitoring of Floating Offshore Wind Turbine Mooring Lines using Deep Learning”, está dirigida por el Prof. David Pardo (BCAM, Ikerbasque y UPV/EHU) y el Dr. Vincenzo Nava (Politecnico di Torino). La defensa está programada para el 15 de septiembre de 2025, a las 11:00 horas, en la Sala Adela Moyua de la Facultad de Ciencia y Tecnología de la UPV/EHU (Campus de Leioa).

En nombre de todas las personas que formamos parte de BCAM, queremos desearle lo mejor para su futuro, tanto en lo profesional como en lo personal.

Abstract

Floating offshore wind energy has strong potential as a clean energy source, but high operational costs and harsh environmental conditions limit its widespread deployment. Maintenance is often slowed by difficult weather, and conventional monitoring techniques provide unreliable assessments of turbine structural integrity. Structural health monitoring (SHM), an inverse problem from a mathematical perspective, offers a promising solution, using sensor data to infer system properties. This dissertation focuses on applying deep learning to SHM for floating turbines, specifically to detect degradation in mooring systems.

To address this problem, we develop deep learning models to identify two types of mooring damage: biological fouling and anchor displacements. Due to limited real-world data, we simulate turbine behavior using OpenFAST and extract meaningful statistical features from the platform’s responses to various operational conditions. Deterministic models, including multi-layer perceptrons and autoencoders, are trained to detect anomalies and estimate damage severity, providing early warnings for potential mooring failure, and enabling predictive maintenance strategies before performance losses occur.

We explore common sources of underlying uncertainty arising from structural design, measurement error, and long-term operation. We implement methods to alleviate the effects of these uncertainties, and quantify the individual and collective impact of each source of uncertainty in our predictions.

A probabilistic autoencoder is then implemented to quantify damage as a probability distribution, capturing cases with multiple plausible solutions. By comparing deterministic and probabilistic approaches, we demonstrate how uncertainty influences model predictions and quantify the confidence of our model’s estimations.