The adaptive fuzzy - support vector machine for fault detection and isolation in wind turbine

Authors

  • Yassine Fadili Laboratory of Electronics, Signal-Systems and Information Science (LESSI). Department of Physics, Faculty of Sciences Dhar El Mehraz. University Sidi Mohammed Ben Abdellah, Fez, Morocco
  • Ismail Boumhidi Laboratory of Electronics, Signal-Systems and Information Science (LESSI). Department of Physics, Faculty of Sciences Dhar El Mehraz. University Sidi Mohammed Ben Abdellah, Fez, Morocco

Abstract

This paper concerns the problem of fault diagnosis in wind turbines. Motived by SupportVector Machines (SVM) method and Fuzzy Logic algorithm, a novel procedure is derived to provide for the wind turbine diagnosis. Since, the conventional SVM classifier with fixed parameters cannot bring performance of high accuracy and fast reflex. In this work, the proposed FDI strategy has raised the problem of congeal the parameters of classifiers after learning, this novel strategy based on the evaluating of error of classification to adjust the parameters of classifier w and b in real time using the fuzzy logic. This principal allow for achieve a new classifier online, which is able to process the new data comes from measuring sensors. The Different parts of the process were investigated, including actuators, sensors and process faults. With duplicated sensors, have detected sensor faults in blade pitch positions, generator and rotor speeds rapidly, but under specific constraints on the fault. all Process faults mainly concerned friction in the wind turbine, which might cause it damage. The fault could be detected under constraints of high magnitude error. the comparing Our results with the conventional SVM classifier indicate the value of our method

Keywords: Fault Detection and Isolation (FDI), wind turbine, classification, SupportVector Machine (SVM), Fuzzy logic

Cite As

Y. Fadili, I. Boumhidi, "The adaptive fuzzy - support vector machine for fault detection and isolation
in wind turbine", Engineering Intelligent Systems, vol. 26 no. 1, pp. 35-43, 2018.




Downloads

Published

2018-03-01

Issue

Vol. 26 No. 1 (2018): International Journal of Engineering Intelligent Systems

Section

General Submission

License

The submission of a paper implies that, if accepted for publication, it will not be published elsewhere in the same form, in any language, without the prior consent of the publisher. Before publication, authors are requested to assign copyright to CRL Publishing Ltd. This allows CRL to sanction photocopying, and to authorize the reprinting of issues or volumes according to demand. Authors' traditional rights will not be jeopardized by assigning Copyright in this way, as they retain the right to reuse the material following publication, and to veto third-party publication.