Fault Detection and Classification on a Transmission Line using Wavelet Multi Resolution Analysis and Neural Network

Abstract

Transmission and distribution lines are vital links between generating units and consumers. They are exposed to atmosphere, hence chances of occurrence of fault in transmission line is very high, which has to be immediately taken care of in order to minimize damage caused by it. In this paper discrete wavelet transform of voltage signals at the two ends of the transmission lines have been analyzed. Transient energies of detail information for two consecutive data windows at fault are used for analysis. Four layer feed forward back propagation neural networks are designed to classify and locate the fault at different single line to ground fault conditions. General TermsFault classification and detection, wavelet multi resolution analysis, neural network.

An enhanced ACO and PSO based fault identification and rectification approaches for FACTS devices

“…The fault was classified and identified for single line to ground faults. It was further extended to other faults along with the similar effectiveness . Joorbian et al extended the applicability of ANN to locate the fault in extrahigh voltage transmission lines.…”

“…It was further extended to other faults along with the similar effectiveness. 7 Joorbian et al 25 According to the current grid code of DG interconnection, the DGs were required to disconnect upon fault detection. This scheme has provided the rapid reactive power support for voltage stabilization.…”

Notice of Removal: Morphology based radon processed neural network for transmission line fault detection

“…In [8, 10, and 20] CWT techniques are employed. Authors of [9, 13, and 16] used DWT for fault location .The advantages of different wavelets, development of customized wavelets were discussed in [15][16][17][18].In [22], author's uses fast Fourier Fourier transforms for fault location. We have closely followed the methodology employed in [23] where authors used wavelets and neural network for fault detection and location in HVDC transmission lines.…”

“…Since the above feature difference is in 2 D domain, we use radon transform to transform the 2D feature vector to 1D feature vector by radon transform. This is done by another transformation (15) Where is the Radon operator for angles and .In the present work, they are set for degrees 0 to 360.This is applied to all four signal classes. The radon outputs of four signal classes are shown below (Fig 10: Radon output of normal, and fault signals) These outputs are feature vectors of normal and faulty signals.…”

Fault Detection and Classification in Transmission Line Using Wavelet Transform and ANN

“…In past various approaches are applied for fault identifications such as Neural Networks (NNs) [1]- [21], Fuzzy Neuro approaches [1], combined applications [3,4] and wavelet transforms [5]- [8]. Normally these approaches employ the symmetrical components of the current and voltages as input features of supervised learning model.…”