ANN Based Fault Classification and Location Estimation for Line to Line Faults of Transmission Line
May Nwe Aye#1, Moe Moe San#2
#Department of Electrical Power Engineering, West Yangon Technological University, Myanmar
This study shows an implemented methodology for fault locator and classifier for faults location occurring on transmission line by using Artificial Neural Network (ANN). This method applies the fundamental frequency components of current and voltage at pre-fault and post-fault condition, measured in each phase at a reference end on one of the transmission lines of the system. The neural fault detector and locators have been trained with different sets of data available from a selected power network model and simulating different fault scenarios. To classify the nonlinear relationship between measured signals, ANN can be used by identifying different patterns of the associated signals. Once the neural network is trained adequately, an improved performance is experienced and gives accurate results for the system with different parameters and conditions. The case study is carried out at 230 kV Shwedaung-Taungdwingyi transmission line. The results are described with corresponding tables in this paper. According to the results, the proposed method shows reliable results and will be applicable for fault classification and estimating fault location for line to line faults.
: Transmission line faults, Fault type classification, Fault location estimation, Artificial neural network, Location error