Radial Basis Function Neural Network with Discrete Wavelet Transform for Power System Fault Analysis

Abstract

The fault detection and classification of all types of faults can be done by implementing Radial basis function neural network with discrete wavelet transform can be proposed in these paper. The Radial Basis Function Neural Network is commonly used artificial neural network due to  their approximation and faster learning speed. The critical aspect that ensuring the power system stability and Reliability of electrical grids is power system fault analysis. It is regularly hard for conventional fault detection strategies to deal with the complexity and nonlinearity present in power system. Artificial intelligence strategies have proven ability in improving fault efficiency and accuracy in recent times. The Integration of RBFNN and DWT in power system fault analysis represents a synergistic approach and these integrated framework offers improved fault detection and classification capabilities. These application offers a potential solution for fault analysis in power system. These networks can adapt quickly to changing operating conditions, making them suitable for real-time fault analysis in dynamic power systems. In these paper the concept of RBFNN with  Discrete Wavelet Transforms are verified with MATLAB Simulink. The simulation results are obtained from proposed system for all types of faults in power system.