A fast faulted phase detection relay for high voltage transmission lines using the fir neural networks

This paper presents a new approach to on line faulted phase detection relay for high-speed protection of high voltage transmission lines using artific ial neural networks. The phase detector shows its effectiveness using one r elay connected to a transmission line of a transmission circuit, which is c omposed of three phase 400 kV transmission lines. The type of the neural ne twork used in this approach is the Finite Impulse Response Artificial Neura l Network (FIRANN). The FIRANN is trained using temporal backpropagation tr aining algorithm. The training patterns are obtained by simulating differen t fault types, fault locations and loads for a certain power network using the ATP (Alternative Transient Program) version of the EMTP (Electro-Magnet ic Transient Program). Also, dynamic are faults and current transformer sat uration had been taken into account. This type of neural networks shows a v ery great insensibility against lost and bad data and post-fault and pre-fa ult noise. (C) 1999 Elsevier Science Ltd. All rights reserved.