Adaptive wavelet networks for power-quality detection and discrimination in a power system

• Published in: IEEE transactions on power delivery Vol. 21; no. 3; pp. 1106 - 1113
• Main Authors: Lin, C.-H., Wang, C.-H.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.07.2006; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptive probabilistic network; Adaptive systems; adaptive wavelet network (AWN); Applied sciences; Discrimination; Disturbances; Disturbances. Regulation. Protection; Electric potential; Electrical engineering. Electrical power engineering; Electrical power engineering; Exact sciences and technology; Feature extraction; Miscellaneous; Morlet wavelet; Networks; Operation. Load control. Reliability; Performance analysis; Power electronics, power supplies; Power networks and lines; Power quality; Power system analysis computing; Power system modeling; Power systems; Probability theory; Testing; Voltage; Voltage fluctuations; Wavelet; Wavelet analysis; Probabilistic approach; adaptive wavelet network (AWN); Power system harmonics; Power system stability; Harmonic analysis; Processing time; Power electronics; Pattern recognition; Adaptive probabilistic network; Tuning; Learning; Model matching; Electrical network; Wavelet transformation; Morlet wavelet; power quality; Voltage stability; Feature extraction; Energy quality; Voltage dip; Harmonic distortion; Service quality; Comparative study; Electric fault
• ISSN: 0885-8977; 1937-4208
• DOI: 10.1109/TPWRD.2006.874105

This paper proposes a model of power-quality detection for power system disturbances using adaptive wavelet networks (AWNs). An AWN is a two-subnetwork architecture, consisting of the wavelet layer and adaptive probabilistic network. Morlet wavelets are used to extract the features from various disturbances, and an adaptive probabilistic network analyzes the meaningful features and performs discrimination tasks. AWN models are suitable for application in a dynamic environment, with add-in and delete-off features using automatic target adjustment and parameter tuning. The proposed AWN has been tested for the power-quality problems, including those caused by harmonics, voltage sag, voltage swell, and voltage interruption. Compared with conventional wavelet networks, the test results showed accurate discrimination, fast learning, good robustness, and faster processing time for detecting disturbing events.