Author(s): Pinna, Danielle ; Toso, Rodrigo ; Semaan, Gustavo ; Sá, Fernando de ; Pereira, Ana I. ; Ferreira, Ângela P. ; Soares, Jorge ; Brandão, Diego
Date: 2024
Persistent ID: http://hdl.handle.net/10198/30377
Origin: Biblioteca Digital do IPB
Subject(s): Wind turbine; Machine learning; Fault classification
The last few years have been marked by the insertion of renewable technologies in the global energy matrix, such as wind and solar energy, which are considered clean energies with low environmental impact. Wind turbines, responsible for the energy conversion process, are complex equipment that are expensive and susceptible to numerous failures. Monitoring turbine components can help detect failures before they occur, reducing equipment maintenance costs. This work compares the training time of different techniques for tuning hyperparameters in supervised machine-learning models for fault detection in wind turbines. Results show the importance of data optimization during model training.
