A New Hybrid Approach using Time-Domain Reflectometry Combined with Wavelet and Neural Network for Fault Identification in Wiring Network

The modern power electric network is subject to insure more and more complicated functions; the main functions are transfer of energy and information. The faults in wiring cables constitute one of worst problems of power electric network. In practice, the combination of Time Domain Reflectometry (TDR) and wavelet transform is generally used to detect and localize the faults in electric network. Classically, the identification process based on the decomposition of fault signal on details and approximations using Discrete Wavelet Transform (DWT) build some errors both at fault position and in fault nature. For solving this problem a new and improved method which combines the time domain reflectometry, wavelet transform and neural network is proposed in this paper. First, the response of the transmission line is obtained using the Finite Difference Time Domain method (FDTD) applied to transmission line equations, then, the obtained results are analyzed with DWT. Finally, Neural Network method (NN) is applied to solve the inverse problem for reducing the error of fault location affecting the branches of electric network.