A combined adaptive approach for detection and isolation of wind turbine faults

Abstract

This paper presents an approach for development of a diagnostic system on the base of a combination of different methods for fault detection, isolation and identification. The important place is given to algorithms of diagnostics by means of support vector machine (SVM) and fault detection estimator together with bank of fault isolation estimators (FDE-FIE). The idea of this approach is illustrated on a practical example of the diagnostic task solution for benchmark model of the wind turbine.