Research Article Application of Hilbert{Huang transform and support vector machine for detection and classication of voltage sag sources

Abstract: Power quality disturbances, including voltage sag, swell, harmonics, icker, and notch, are one of the main concerns for industries and electrical equipment. Among these disturbances, voltage sag, due to its irrecoverable economic eects on industries, is particularly important. In this paper, the detection and classication of voltage sag sources containing motor starting, short circuit, transformer energizing, and the reacceleration of motors after fault clearance using the Hilbert{Huang transform (HHT) and support vector machine (SVM) are studied. A voltage sag waveform includes several oscillating modes; for separating these oscillating modes, which are called intrinsic mode functions (IMFs), empirical mode decomposition is used. Next, by applying the HHT to these IMFs, some required features of each IMF are extracted. Finally, these features are given to the SVM for classication. The results of this classication method as compared with other methods show the high eciency of the proposed method