Title :
Power quality disturbance waveform recognition using wavelet-based neural classifier. II. Application
Author :
Santoso, Surya ; Powers, Edward J. ; Grady, W. Mack ; Parsons, Antony C.
Author_Institution :
Dept. of Electr. & Comput. Eng., Texas Univ., Austin, TX, USA
fDate :
1/1/2000 12:00:00 AM
Abstract :
For pt.I see ibid., vol.15, no.1, p.222-8 (2000). A wavelet-based neural classifier is constructed and thoroughly tested under various conditions, The classifier is able to provide a degree of belief for the identified waveform. The degree of belief gives an indication about the goodness of the decision made. It is also equipped with an acceptance threshold so that it can reject ambiguous disturbance waveforms. The classifier is able to achieve the accuracy rate of more than 90% by rejecting less than 10% of the waveforms as ambiguous
Keywords :
belief maintenance; inference mechanisms; neural nets; pattern recognition; power supply quality; power system analysis computing; power system faults; waveform analysis; Dempster-Shafer theory of evidence; acceptance threshold; ambiguous disturbance waveforms rejection; degree of belief; power quality disturbance waveform recognition; wavelet-based neural classifier; Capacitors; Decision making; Frequency; Helium; Neural networks; Power quality; Power system reliability; Testing; Voting; Wavelet domain;
Journal_Title :
Power Delivery, IEEE Transactions on
