An Artificial Intelligence Based Approach for High Impedance Faults Analysis in Distribution Networks

An Artificial Intelligence Based Approach for High Impedance Faults Analysis in Distribution Networks

M. S. Abdel Aziz (Shaker Consultancy Group, Egypt), M. A. Moustafa Hassan (Cairo University, Egypt) and E. A. El-Zahab (Cairo University, Egypt)
Copyright: © 2012 |Pages: 16
DOI: 10.4018/ijsda.2012040104
OnDemand PDF Download:
List Price: $37.50


This paper presents a new approach for high impedance faults analysis (detection, classification and location) in distribution networks using Adaptive Neuro Fuzzy Inference System. The proposed scheme was trained by data from simulation of a distribution system under various faults conditions and tested for different system conditions. Details of the design process and the results of performance using the proposed method are discussed. The results show the proposed technique effectiveness in detecting, classifying, and locating high impedance faults. The 3rd harmonics, magnitude and angle, for the 3 phase currents give superior results for fault detection as well as for fault location in High Impedance faults. The fundamental components magnitude and angle for the 3 phase currents give superior results for classification phase of High Impedance faults over other types of data inputs.
Article Preview

1. Introduction

Detection and discovery of High Impedance Faults (HIF) in electrical distribution networks are a challenge for protection engineers. This is due to the behavior of this kind of faults and their relatively low fault current levels with respect to feeder load current. High Impedance Faults in Power networks represent safety hazards, utility liability problems and possibility of equipment damage due to arcing and resistance fires. Different schemes and algorithms have been proposed by different researchers to cope with the problems associated with HIF. These detection techniques were categorized into four classes:

  • a)

    Time domain: The time domain detection algorithms, arc detection algorithms are based on the arc current waveform as stated in Sultan et al. (1994) and include electromechanical relay and artificial neural network based relaying (Calhoun et al., 1982).

  • b)

    Frequency domain: The detection algorithm of the frequency domain applies Fourier transform to extract the features of the harmonic components. The identification approach based on frequency domain involved 3rd harmonic current (Sharaf & Wang, 2003), statistical pattern recognition approach (Sedighi et al., 2005), energy technique (Aucoin & Russell, 1982), randomness technique (Russell & Chinchali, 1989), half cycle asymmetry (Kwon et al., 1991) and amplitude ratio technique.

  • c)

    Wavelet transform: Wavelet transform can be employed to examine the transient phenomena of HIFs signals in both the time and frequency domains (Aucoin & Jones, 1996; Eldin et al., 2007; Saleh, 2009; Shaaban, 2010; Aucoin, 1987).

  • d)

    Adaptive Neuro Fuzzy Inference System (ANFIS) mixed with some digital signal processing techniques (Jang, 1993).

Also some of the existing detection schemes conventional over current, ground relays dominate one harmonic detection and high frequency based ripple detection in the range of 2-10 kHz (Snider & Shan, 1997; Wester, 1998; Elkalashy et al., 2008). These schemes utilize the frequency spectra generated by the nonlinearity of the ground path associated with arcing, soil fusing and temporal variations in the equivalent fault impedance (Jeerings, 1989; Benner & Russell, 1997; Shebl et al., 2010). ANFIS proposed scheme offer one of the best alternatives to the HIF problem (Chan & Yibin, 1998; Yu & Khan, 1994). Design of (ANFIS) unit based approach for an accurate HIF detection algorithm is presented in the paper.

Before, ANFIS was applied using Wavelet (Reddy et al., 2007), where Wavelet is a heavy computational algorithm. In this proposed technique, the Discrete Fourier Transform (DFT) is used before ANFIS and its time of computation will be less than ANFIS with Wavelet. This proposed approach was not applied before.

The rest of the paper is organized as follows. Section 2 contains the distribution system under protection. Section 3 describes the Adaptive Neuro Fuzzy Inference System method. Section 4 clarifies the simulation environment. Section 5 presents the results and discussion.

2. The Distribution System Under Protection

A single line diagram for the protected distribution feeder is illustrated in Figure 1 (Uriarte, 2003). It consists of a 13.8 kV distribution feeder of ~33 km in length. It is formed by three sections of equal length and equal segment impedance. Each segment carries one load behind its appropriate and ideal step down transformers. The loads are of different types and behind different kinds of transformer banks. The high impedance faults are simulated using ATP package based on Prikler and Høidalen (2002).

Complete Article List

Search this Journal:
Open Access Articles: Forthcoming
Volume 7: 4 Issues (2018): 1 Released, 3 Forthcoming
Volume 6: 4 Issues (2017)
Volume 5: 4 Issues (2016)
Volume 4: 4 Issues (2015)
Volume 3: 4 Issues (2014)
Volume 2: 4 Issues (2013)
Volume 1: 4 Issues (2012)
View Complete Journal Contents Listing