Fault detection and isolation in wind turbines using support vector machines and observers
| Autor: | Peter Fogh Odgaard, Nida Sheibat-Othman, Mohamed Abdelmoula Benlahrache, Sami Othman |
|---|---|
| Přispěvatelé: | Laboratoire d'automatique et de génie des procédés (LAGEP), Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-École Supérieure Chimie Physique Électronique de Lyon-Centre National de la Recherche Scientifique (CNRS), Department of Electronic Systems - Aalborg University, Aalborg University [Denmark] (AAU) |
| Jazyk: | angličtina |
| Rok vydání: | 2013 |
| Předmět: |
0209 industrial biotechnology
Engineering Wind power Observer (quantum physics) business.industry 020209 energy 02 engineering and technology Turbine Fault detection and isolation [SPI.AUTO]Engineering Sciences [physics]/Automatic Support vector machine ACTI PES 020901 industrial engineering & automation Control theory 0202 electrical engineering electronic engineering information engineering Benchmark (computing) SNLEP [SPI.GPROC]Engineering Sciences [physics]/Chemical and Process Engineering business ComputingMilieux_MISCELLANEOUS |
| Zdroj: | Sheibat-Othman, N, Othman, S, Benlahrache, M & Odgaard, P F 2013, ' Fault detection and isolation in wind turbines using support vector machines and observers ', Proceedings of the American Control Conference, pp. 4459-4464 . < http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6580527&refinements%3D4280000137%26sortType%3Dasc_p_Sequence%26filter%3DAND%28p_IS_Number%3A6579790%29 > 2013 American Control Conference (ACC) 2013 American Control Conference (ACC), Jun 2013, Washington, France. ⟨10.1109/ACC.2013.6580527⟩ The 2013 American Control Conference (ACC) The 2013 American Control Conference (ACC), Jun 2013, Washington, United States Scopus-Elsevier ACC |
| DOI: | 10.1109/ACC.2013.6580527⟩ |
| Popis: | In this work, the benchmark FAST that simulates a closed-loop three-bladed wind turbine is used for fault detection and isolation. Two methods were employed to isolate faults of different types at different locations: Support vector machines (SVM) and a Kalman-like observer. SVM could isolate most faults with the used data and characteristic vectors, except for high varying dynamics. In this case, the use of an observer, which is model-based, was found necessary. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|