Transmission line fault location estimation by Fourier & wavelet transforms using ANN

Abstract

Nowadays, power supply has become a business commodity. The quality and reliability of power needs to be maintained in order to obtain optimum performance. Therefore, it is extremely important that transmission line faults from various sources be identified accurately, reliably and be corrected as soon as possible. In this paper, a comparative study of the performance of Fourier transform and wavelet transform based methods combined with Neural Network (NN) for location estimation of faults on high voltage transmission lines is presented. A new location method is proposed for decreasing training time and dimensions of NN. The proposed algorithms are based on Fourier transform analysis of fundamental frequency of current and voltage signals in the event of a short circuit on a transmission line. Similar analysis is performed on transient current and voltage signals using multi-resolution Daubchies-9 wavelet transform, and comparative characteristics of the two methods are discussed.

Overcoming the Limits of the Charge Transient Fault Location Algorithm by the Artificial Neural Network

“…The second algorithm presented in this paper is based on the Artificial Neural Network (ANN) theory. The importance of ANN-based algorithms is growing in the scientific community, as well as for power system analysis and fault location, as witnessed by several papers [12][13][14][15][16][17][18][19][20][21]. A certain number of ANN-based algorithms have been developed in recent years.…”

A single ended directional fault section identifier and fault locator for double circuit transmission lines using combined wavelet and ANN approach

“…The wavelet transform has capabilities of providing accurate location and classification of electrical transients in power system as depicted by Dasgupta et al [6]. Continuous wavelet transforms (CWT) for a given function f(t) can be calculated by (1) CWTðf ; a; bÞ…”

“…ANN, Fuzzy logic and hybrid techniques using combined wavelet, SVM, ANN and/or fuzzy logic has been applied for protection of transmission lines by Reddy and Mohanta [19], Al-Shaher et al [3], Abdollahi et al [1], Gayatri and Kumarappan [10], Kalam et al [16], Yusuff et al [25], Dasgupta et al [6], Saravanan et al [21], Ekici [8] and Wang et al [24]. But these techniques are non-directional.…”

Selection of suitable features for fault classification in transmission line

“…In the first stage, suitable features are extracted using signal processing tool from the input three phase voltage and/or current signals. Then, the second stage presenting extracted features to the classifiers for several purposes such as detection, classification, estimation of location and identification of zone [1,3,5].…”