Diagnóstico OWC basado en aprendizaje automático utilizando datos reales medidos de plantas de energía undimotriz
- Fares Mzoughi
- Izaskun Garrido Hernandez
- Jon Lecube Garagarza
- Aitor J. Garrido Hernández
- Aitor J. Garrido Hernández (ed. lit.)
- Matilde Santos Peñas (ed. lit.)
- Izaskun Garrido Hernandez (ed. lit.)
Publisher: Servicio Editorial = Argitalpen Zerbitzua ; Universidad del País Vasco = Euskal Herriko Unibertsitatea
ISBN: 978-84-09-58971-5
Year of publication: 2024
Pages: 13-18
Congress: Jornada Internacional de Energía Eólica y Marina (5. 2023. null)
Type: Conference paper
Abstract
This paper presents an innovative classificationoriented diagnosis method for power take-off (PTO) systems in wave energy converter (WEC) farms. The proposed approach underwent testing at the Mutriku Multiple Oscillating Water Column (OWC)-based wave power plant with the aim of reducing the Levelized Cost of Energy (LCoE) through the application of predictive maintenance strategies. The methodology involves utilizing Linear Discriminant Analysis (LDA) to identify the most crucial features derived from the measured data. Subsequently, the Support Vector Machine (SVM) is employed as a classification technique to categorize the condition of the OWC system.