학술논문

AI techniques applied to diagnosis of vibrations failures in wind turbines
Document Type
Periodical
Source
IEEE Latin America Transactions IEEE Latin Am. Trans. Latin America Transactions, IEEE (Revista IEEE America Latina). 18(08):1478-1486 Aug, 2020
Subject
Power, Energy and Industry Applications
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Engineered Materials, Dielectrics and Plasmas
Fields, Waves and Electromagnetics
General Topics for Engineers
Monitoring
Wind turbines
Deep learning
Irrigation
Silicon compounds
Support vector machines
Machine learning
fault detection
fault diagnosis
condition monitoring
Language
ISSN
1548-0992
Abstract
Supervision and fault diagnosis in wind turbines using automatic learning techniques allow early detection of the degeneration of the components, as well as the detection and diagnosis of sudden failures. This contribution evaluates different machine learning methodologies to predict, detect and diagnose electrical and mechanical failures of wind turbines. An integrated monitoring and diagnostic system is proposed using automatic learning algorithms adapted to the different components and faults of the wind turbine