DocumentCode :
2148931
Title :
Adaptive detection of generator out-of-step conditions in power systems using an artificial neural network
Author :
Abdelaziz, A.Y. ; Irving, M.R. ; Mansour, M.M. ; El-Arabaty, A.M. ; Nosseir, A.I.
Author_Institution :
Dept. of Electr. Power & Machines, Ain Shams Univ., Cairo, Egypt
Volume :
1
fYear :
1996
fDate :
2-5 Sept. 1996
Firstpage :
166
Abstract :
Application of artificial neural networks (ANN) to power systems has resulted in an overall improvement of solutions in many implementations. This paper presents a new approach for adaptive out-of-step detection of synchronous generators based on neural networks. The paper describes the ANN architecture adopted as well as the selection of the input features for training the ANN. A feedforward model of the neural network based on the stochastic backpropagation training algorithm has been used to predict the out-of-step condition. Due to power network configuration changes, the performance of the protective relays can vary. Consequently, an adaptive out-of-step prediction strategy is suggested in this paper. The capabilities of the proposed strategy have been tested through computer simulation for a typical case study. The results reveal an acceptable classification performance.
Keywords :
backpropagation; digital simulation; feedforward neural nets; power system protection; power system stability; relay protection; synchronous generators; adaptive detection; adaptive out-of-step prediction strategy; artificial neural network; feedforward model; power network configuration changes; power systems; protective relays; stochastic backpropagation training algorithm; synchronous generators;
fLanguage :
English
Publisher :
iet
Conference_Titel :
Control '96, UKACC International Conference on (Conf. Publ. No. 427)
ISSN :
0537-9989
Print_ISBN :
0-85296-668-7
Type :
conf
DOI :
10.1049/cp:19960546
Filename :
651372
Link To Document :
بازگشت