DocumentCode :
2041843
Title :
Application of cascade correlation neural network in modelling of overcurrent relay characteristics
Author :
Meshkin, Matin ; Faez, Karim ; Abyaneh, Hossein Askarian ; Kanan, H. Rashidy
Author_Institution :
Electr. Eng. Dept., Amirkabir Univ. of Technol., Tehran, Iran
fYear :
2006
fDate :
20-22 March 2006
Firstpage :
1
Lastpage :
6
Abstract :
Modelling of Overcurrent (OC) relays with inverse time relay characteristics is a vital job for coordination of these relays. There are many publications in which the OC relay characteristics have been modelled. In this paper a new model based on cascade correlation neural network is proposed. The cascade correlation neural network is used to calculate operating times of OC relays for various Time Dial Settings (TDS) or Time Multiplier Settings (TMS). This method can cover nonlinearity of the characteristic and its accuracy is much higher than the polynomial and the other neural networks models such as perceptron and backpropagation neural networks models. The method is tested on three types of OC relays and the results obtained shows, the accuracy of the new method is higher and therefore it is more useful than the others. The model is validated by comparing the results obtained from the new method with nonlinear analytical, perceptron and backpropagation neural networks models.
Keywords :
backpropagation; multilayer perceptrons; overcurrent protection; power engineering computing; relay protection; OC relays; backpropagation neural networks models; cascade correlation neural network; inverse time relay characteristics; nonlinear analytical model; overcurrent relay characteristics modelling; perceptron model; time dial settings; time multiplier settings; Analytical models; Artificial neural networks; Backpropagation; Correlation; Mathematical model; Relays; Training; Cascade Correlation; Neural Network; Overcurrent Relay; Relay Coordination; Relay Modelling;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
GCC Conference (GCC), 2006 IEEE
Conference_Location :
Manama
Print_ISBN :
978-0-7803-9590-9
Electronic_ISBN :
978-0-7803-9591-6
Type :
conf
DOI :
10.1109/IEEEGCC.2006.5686187
Filename :
5686187
Link To Document :
بازگشت