Abstract
Recognition of power quality events by analyzing the voltage and current waveform disturbances is a very important task for the power system monitoring. This paper presents a new approach for the recognition of power quality disturbances using wavelet transform and neural networks. The proposed method employs the wavelet transform using multiresolution signal decomposition techniques working together with multiple neural networks using a learning vector quantization network as a powerful classifier. Various transient events are tested, such as voltage sag, voltage swell, interruption, notching, impulsive transient, and harmonic distortion. The results show that the classifier can efficiently detect and classify different types of power quality disturbance.
Additional information
Notes on contributors
Suriya Kaewarsa
Suriya Kaewarsa received a B.Eng. degree in electrical engineering from Rajamangala Institute of Technology, Main Campus and an M.Eng.degree in electrical engineering from King Mongkut’s University of Technology Thonburi, Thailand, in 2001 and 2003, respectively. He is currently pursuing a PhD degree in electrical engineering at Suranaree University of Technology, Thailand. His research interests include power systems, advanced signal processing applications in power quality analysis, and power electronics.
Kitti Attakitmongcol
Kitti Attakitmongcol received an B.Eng. degree in electronics engineering from King Mongkut’s Institute of Technology Ladkrabang, Thailand, an M.S. and PhD degree in electrical engineering from Vanderblit University, Nashville, USA, in 1996 and 1999, respectively. He is an assistant professor in the School of Electrical Engineering, Suranaree University of Technology. His research interests include digital signal processing, wavelet, and multiwavelet transforms.