The Control Of Inverse Time-Overcurrent Relay By Ann (Artificial Neural Networks) For Automation Of A System

Absmcr: Overcurrent reIuys cat7 be used to protect practically any power system element. If the operating time o fa reiny depends on the current magriitude being smallest where is the in the relay and quantity Ip is when the current is the greatest. Such a churacteristic is known as the pickup setting of relay. Equation 1 known as an inverse time characlerislic and the r e l q is known as an time overcurrenS It is ,lot describes an ideal relay operating characteristic. possible to show the inverse time-overcuj-rent relay operating characteristic with a determined function, In this paper the characteristic of inverse time-overcurrent relay (t=f(I)) is obtained by means of nrtgicial neural networks (ANN). ANN is successfully used in a lot of areas such as fault detection, control and signal processing. One of the major paradigms of A-vN is feed$opward For this paper, it is used feed-forward network and error backpropagation algorithm. I d I < Ip no fault is zone, do not trip (1)