DocumentCode :
328369
Title :
Pattern classification of waveforms using LVQ1
Author :
Fujita, Hideki ; Yamamoto, Makoto ; Kobayashi, Shigeki ; Youheng, Xu
Author_Institution :
Chubu Electric Power Co. Inc., Nagoya, Japan
Volume :
1
fYear :
1993
fDate :
25-29 Oct. 1993
Firstpage :
951
Abstract :
This paper describes an application of the artificial neural network (ANN) technique using the learning vector quantization 1 (LVQ1) method, as a preprocessing for analyzing power system load characteristics. The clearer load characteristics are, the more accurate the power system analysis is. However, it is an important problem that it takes a long period of time to determine whether the measured data in power system are suitable for the analysis or not. Therefore the authors have developed a pattern classification technique for solving this problem using the LVQ1 method. Brand-new equipment using this technique has been manufactured and is in test at a substation of the Chubu Electric Power Co., Inc, Japan.
Keywords :
digital simulation; learning (artificial intelligence); neural nets; pattern classification; power system analysis computing; substations; vector quantisation; LVQ1 method; artificial neural network; computer simulation; learning vector quantization; load characteristics analysis; power system; substation; Artificial neural networks; Manufacturing; Pattern classification; Power measurement; Power system analysis computing; Power system measurements; Substations; Testing; Time measurement; Vector quantization;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1993. IJCNN '93-Nagoya. Proceedings of 1993 International Joint Conference on
Print_ISBN :
0-7803-1421-2
Type :
conf
DOI :
10.1109/IJCNN.1993.714068
Filename :
714068
Link To Document :
بازگشت