Title :
A new method for overcurrent relay (O/C) using neural network and fuzzy logic
Author :
Abyane, Hossien Askarian ; Faez, Karim ; Karegar, Hossien Kazemi
Author_Institution :
Dept. of Electr. Eng., Amirkabir Univ. of Technol., Tehran, Iran
Abstract :
For coordination of O/C relays, it is necessary to model the relay characteristics and calculate the time dial setting (TDS) of the relays. The O/C relays´ characteristics are normally modeled by a polynomial using a curve fitting technique. A new method for calculating the TDS and t (operating time of O/C relays) based on a neural network and fuzzy logic is used. In this method, fuzzy logic uses the same information as the neural network. Also the variation of t with the TDS is not assumed linear, therefore t is calculated with a high accuracy. In addition, in the method used for determination of the TDS, we do not need to use numerical analysis and mathematical equations, so the calculation speed as well as the accuracy is increased.
Keywords :
curve fitting; fuzzy logic; neural nets; overcurrent protection; polynomials; power system analysis computing; relay protection; accuracy; curve fitting; fuzzy logic; neural network; overcurrent relay coordination; polynomial; power system protection; relay characteristics; time dial setting; Circuit faults; Computer errors; Computer networks; Fuzzy logic; Neural networks; Power system faults; Power system protection; Power system relaying; Protective relaying; Relays;
Conference_Titel :
TENCON '97. IEEE Region 10 Annual Conference. Speech and Image Technologies for Computing and Telecommunications., Proceedings of IEEE
Conference_Location :
Brisbane, Qld., Australia
Print_ISBN :
0-7803-4365-4
DOI :
10.1109/TENCON.1997.647342