Wyniki wyszukiwania - Biblioteka Nauki

1

A New Hybrid Feature Extraction Method for Partial Discharge Signals Classification

100%

Liao R. , Wang K. , Yang L. , Duan L. , Li J.

Przegląd Elektrotechniczny

|

2012

|

tom R. 88, nr 11a

191-195

EN

In this paper, a new hybrid feature extraction method combining adaptive optimal radially Gaussian kernel (AORGK) time-frequency representation with two dimensional nonnegative matrix factorization (2DNMF) is proposed for partial discharge (PD) classification. Firstly, AORGK is applied to obtain the time-frequency matrices of PD ultra-high-frequency (UHF) signals. Then 2DNMF is employed to compress the AORGK amplitude (AORGKA) matrices to extract various feature vectors with different (d1, d2) combinations, i.e. (5, 5), (5, 10), (10, 5) and (10, 10). Finally, the extracted features are classified by fuzzy k nearest neighbor (FkNN) classifier and back propagation neural network (BPNN). 600 samples sam pled from four typical artificial defect models in Laboratory are adopting for testing of the proposed feature extraction algorithm. It is shown that the successful rate by FkNN and BPNN are all higher than 80%, and FkNN has superior classification accuracies than BPNN under four circumstances of (d1, d2) combinations. In addition, FkNN achieves the highest classification accuracy 93.73% with (10, 5) combination. The results demonstrate that it is feasible to apply the proposed algorithm to PD signal classification.

PL

W artykule przedstawiono nową hybrydową metodę klasyfikacji wyładowań niezupełnych (ang. Partial Discharge), wykorzystującą algorytm AORGK (ang. Adaptive Optimal Radially-Gaussian Kernel) o nieujemnej, matrycowej faktoryzacji dwuwymiarowej (ang. 2-Dimensional Nonnegative Matrix Factorization). W metodzie wykorzystano także algorytm k najbliższych sąsiadów oparty na teorii zbiorów rozmytych (ang. Fuzzy k Nearest Neighbour Classifier) oraz sieci neuronowe (ang. Back Propagation Neural Network).

2

Investigation on Chaotic Characteristic of PD Magnitude Series during Propagation of Electrical tree in XLPE Power Cables

100%

Liao R. , Wang K. , Liu L. , Zhou T. , Zhou Q.

Przegląd Elektrotechniczny

|

2012

|

tom R. 88, nr 5b

213-217

EN

The electrical tree propagation experiments were performed under high voltages with a frequency of 50Hz and amplitudes ranging from 12kV to 21kV at room temperature by utilizing an actual XLPE cable as the test sample, where the concentration of electrical field was simulated by a metal needle tip. The chaotic theory was introduced to analyze the PD magnitude series during the propagation process of electrical tree. Experimental results show that deterministic chaos exists in the propagation of electrical tree in XLPE cables, and the largest Lyapunov exponent and correlation of the strange attractors increase with the decrease of electrical tree fractal dimension. The results may provide a new approach for online diagnosis of electrical tree morphology.

PL

rzedstawiono wynika badania wyładowania w kablu XPLE przy częstotliwości 50 Hz i napięciu 12 – 21 kV. Stwierdzono chaotyczny charakter drzewienia elektrycznego. Zaproponowano opis teoretyczny umożliwiający łatwe rozpoznanie typu wyładowania.

3

A Condition Assessment Model of Oil-immersed Transformers Using Cloud and Matter Element Integrated Method

86%

Liao R. , Zhang Y. , Zheng H. , Yang L. , Wang K. , Akram S.

|

2013

|

tom R. 89, nr 4

142-146

EN

High voltage oil-immersed transformers are the most important components in the power system. If there is a potential fault in the transformer it may cause a power failure even a catastrophe. Therefore, it is important to assess the condition of the transformer accurately and to make some relative maintenance to minimize the risk of premature failure. However, condition assessment of transformers can be considered as a multiple-attribute decision-making (MADM) problem which is full of uncertain, fuzzy and randomness information. Aiming at this intricate problem, this paper presents a cloud and matter element integrated approach for assessing the condition of transformers. An assessing index system is established, which includes dissolved gas analysis (DGA), electrical testing and oil testing. An integrated model based on matter element approach and cloud approach is applied to assess the condition of the transformer. Cases study show that the proposed approach is practical and effective. The assessing result can be regarded as a useful suggestion to condition based maintenance of high voltage oil-immersed transformers.

PL

W artykule przedstawiono metodę oceny stanu technicznego transformatora olejowego, opartą na analizie elementów chmury oraz tzw. Matter-Element Analysis. Opracowany został zintegrowany model oraz wskaźnik szacujący stan transformatora, uwzględniający czynniki takie jak: analiza rozpuszczonych gazów (DGA), testy elektryczne i olejowe. Przeprowadzone badania potwierdziły skuteczność metody.