Efficient fault detection and diagnosis of wind energy converter systems

Fault detection and diagnosis for modern wind turbines converter (WTC) systems have been received an important measure for improving the operation of these systems, in such a way to increase their reliability, availability and required safety. Therefore, this paper deals with the problem of fault detection and diagnosis (FDD) in WTC systems. The developed FDD approach uses feature extraction and selection, and fault classification tools for monitoring WTC system under different operating conditions. The developed FDD approach is addressed such that, the principal component analysis (PCA) technique is used for feature extraction purposes and the machine learning (ML) classifiers are applied for fault diagnosis. In the proposed FDD approach, an efficient features in PCA subspace that extract and select the most informative features from WTC data are provided. Besides, their statistical characteristics are also included. The ML classifiers are applied to the extracted and selected features to perform the fault diagnosis problem. The effectiveness and higher classification accuracy of the developed approach are demonstrated using simulated data extracted from different operating conditions of the wind turbine.