Improved ANN Based Impedance Estimator For Phase To Ground Faults In UHV Transmission Line

The high speed protection of power system for transmission and primary distribution networks are the most important issue in the selective tripping of the power plant. In order to solve this problem high speed automatic reclosure is continuously in development with state of the art technology used. The economic and technical advantages of distance protection are considerably large enough because the main advantage of it is that the range of the fault detection in the line is not depends on the changes in the source impedance.The main factors that effects the effectiveness of the traditional distance relaying schemes in single line to ground, double line to ground and specially in simultaneous open conductor fault are the variation in fault resistance, power flow direction as well as magnitude. In this thesis, the work is presented that will discuss about the aforementioned problems of conventional distance relaying methods in doubly fed transmission system. An accurate digital distance relaying scheme integrated with artificial neural network impedance estimator is developed using the conventional method impedance after removal of the error impedance from it using modified scheme. The modified scheme is immune to the variation in fault location for under reach and overreach problem caused by sequence current components. A series of test conducted on a800kV,400km transmission line for single phase to ground faults as well as simultaneous open conductor fault in PSCAD/EMTP and Matlab/Simulink. Finally comparison has been done with the conventional methods in order to check the accuracy and robustness of the proposed scheme which is found to be97%.