Fault Diagnosis of a Variable-Speed Wind Turbine via Support Vector Machines

Irandoost, Hamid (2018) Fault Diagnosis of a Variable-Speed Wind Turbine via Support Vector Machines. [Laurea magistrale], Università di Bologna, Corso di Studio in Ingegneria dell'automazione [LM-DM270]
Documenti full-text disponibili:
[img] Documento PDF (Thesis)
Disponibile con Licenza: Salvo eventuali più ampie autorizzazioni dell'autore, la tesi può essere liberamente consultata e può essere effettuato il salvataggio e la stampa di una copia per fini strettamente personali di studio, di ricerca e di insegnamento, con espresso divieto di qualunque utilizzo direttamente o indirettamente commerciale. Ogni altro diritto sul materiale è riservato

Download (4MB)


In recent years, wind energy is considered as the most practical substitute energy to replace the fossil fuels. Wind turbines are massive and installed in locations, where a non-planned maintenance is very costly. Therefore, a fault-tolerant control system that is able to maintain the wind turbine connected after the occurrence of certain faults can avoid major economic losses. To keep the wind turbine operational or at least safe, in severe cases, a reliable fault diagnosis methodology has to be exploited. It must detect, in the required time, any deviation of the system behaviour from its ordinary case, identify the location and type of the fault and reconfigure the control system to accommodate the so-called discrepancy. To achieve the above goals, a vast number of methods have been suggested by many researchers all around the world. In this thesis, the promising classification framework of the Support Vector Machines is applied to fault detection for variable speed turbines, highlighting its features. In this regard, different fault scenarios are imposed on a benchmark model of a horizontal-axis wind turbine to check the functionality of the mentioned fault detector and the control reconfiguration module.

Tipologia del documento
Tesi di laurea (Laurea magistrale)
Autore della tesi
Irandoost, Hamid
Relatore della tesi
Correlatore della tesi
Corso di studio
Curriculum: Automation engineering
Ordinamento Cds
Parole chiave
Support Vector Machines,Fault Detection,Wind Turbine,Classification,Optimal Hyperplane,Linearly Separable Dataset,Nonlinearly Separable dataset
Data di discussione della Tesi
16 Marzo 2018

Altri metadati

Statistica sui download

Gestione del documento: Visualizza il documento