Low cost microcontroller based fault detector, classifier, zone identifier and locator for transmission lines using wavelet transform and artificial neural network: A hardware co-simulation approach

A low cost, fast and reliable microcontroller based protection scheme using wavelet transform and artificial neural network has been proposed and its effectiveness evaluated in real time. The proposed scheme, based on the hardware co-simulation approach performs all the functions of transmission line protection i.e. fault detection/classification, fault zone/section identification and location estimation. The fault detection/classification and zone identification algorithms use fundamental frequency current component to estimate a fault index. The fault location estimation module uses wavelet transform coefficients in hybridization with a parallel artificial neural network structure. For hardware implementation, a 8-bit ATmega microcontroller is used and interfaced with the simulated power system model using Integrated Development Environment (IDE). The scheme is tested on a power system model of 400 kV, 50 Hz three phase double circuit line with source at both the ends. Laboratory tests have been performed in real time for 20,000 fault cases including evolving faults with varying fault resistance, fault inception angle, fault distance, direction of power flow angle and its magnitude. The tests confirm the suitability and reliability of proposed scheme even with Current Transformer (CT) saturation. The implementation of the proposed approach on a low cost microcontroller with the lesser execution time, makes the prototype ideal for implementation on a digital platform (digital relay), thus leading to financial viability and sustainability of the protection scheme. (C) 2016 Elsevier Ltd. All rights reserved.