Wyniki wyszukiwania - BazTech

Ograniczanie wyników

1 Przegląd Elektrotechniczny

1 2011

Znaleziono wyników: 1

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Chaotic characteristics of time series of partial discharges in oilpaper insulation and their applications in pattern recognition

Yongfen L., Junhao L., Ping H., Shengchang J., Yanming L.

Przegląd Elektrotechniczny

2011

R. 87, nr 7

219-224

In order to recognize partial discharges (PD), five kinds of typical defects in oil-paper insulation are built and measured with current pulse method, and chaos method is used to research the time series of PD signals. The results revealed that the PD is of obvious chaotic characteristic, and the PD process is chaotic one. The PD patterns can be qualitatively analyzed and recognized by using the chaotic time series of PD and their chaotic attractors. Phase space reconstruction parameters and post-reconstruction chaotic characteristic quantities can be selected to quantify the PD's chaotic characteristics. Verification and comparison on pattern recognition effects of PRPD and CAPD were performed respectively by adopting the neural network of radial basis function (RBF), and the result showed that the effects of both were good and had their own advantages. Besides, statistical operators in PRPD mode and chaotic characteristic quantities in CAPD mode were comprehensively selected as the input vectors of neural network, and the average recognition rate can reach 95%, this result showed that the recognition on PD was improved by a relatively large scale.

Przeprowadzono badania pięciu typowych przypadków defektów izolacji papierowo-olejowej. Sygnały wyładowań niezupełnych przetworzono w szeregi czasowe. Stwierdzono że process ma character chaotyczny. Wykorzystano teorię przebiegów chaotycznych do analizy sygnału i klasyfikacji wad.