Autoreclosure in Extra High Voltage Lines using Taguchi's Method and Optimized Neural Networks

This paper presents a method to discriminate the temporary faults from the permanent ones in an extra high voltage (EHV) transmission line so that improper reclosing of the line onto a fault is avoided. The fault identification prior to reclosing is based on optimized artificial neural network associated with standard Error Back-Propagation, Levenberg Marquardt Algorithm and Resilient Back-Propagation training algorithms together with Taguchi's Method. The algorithms are developed using MATLAB (TM) software. A range of faults are simulated on EHV modeled transmission line using SimPowerSytems (TM), and the spectra of the fault data are analyzed using fast Fourier transform which facilitates extraction of distinct features of each type of fault. For both training and testing purposes, the neural network is fed with the normalized energies of the DC component, the fundamental and the first four harmonies of the faulted voltages. The developed algorithm is effectively trained, verified and validated with a set of training, dedicated testing and validation data respectively.