Design and Training of Artificial Neural Networks for Locating Low Current Faults in Distribution Systems

Coser, J.; Vale, Douglas Terêncio do; Rolim, J.G.

doi:10.1109/isap.2007.4441599

Cited by 16 publications

(13 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Intelligent techniques are among the most popular approaches. In [4][5][6][7], an artificial neural network (ANN) was used for fault localization in the distribution network. In [4,5], the fundamental frequency components of voltage and * Correspondence: mosba86@yahoo.com.my current were employed.…”

Section: Introductionmentioning

confidence: 99%

“…In [4][5][6][7], an artificial neural network (ANN) was used for fault localization in the distribution network. In [4,5], the fundamental frequency components of voltage and * Correspondence: mosba86@yahoo.com.my current were employed. A combination of ANN and support vector machine (SVM) was proposed in [5], whereas in [6,7], the high frequency components were extracted from the faulted waveform to facilitate fault location.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Studies on the application of wavelet families for a high impedance fault location algorithm in a distribution network

Ali¹,

Bakar²,

Tan³

et al. 2016

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Abstract:Detecting high impedance faults in a distribution network is a great challenge and locating one is even more challenging. This paper will present an enhanced high impedance fault location algorithm based on the database technique. This paper is an extension of a faulty section identification algorithm developed previously. However, in this paper, the performance of the previous algorithm is investigated first in terms of different sampling rate and window size. Then these parameters will be used as a standard parameter to study the effectiveness of different types of mother wavelets. Each mother wavelet will be used to extract important features of a voltage signal from a single measurement point in a typical 38-node underground distribution network.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Studies on the application of wavelet families for a high impedance fault location algorithm in a distribution network

Ali¹,

Bakar²,

Tan³

et al. 2016

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

show abstract

“…Knowledge‐based method, such as artificial neural network [16–18], genetic algorithm [19], and hybrid methods [20–22], are also being applied in the area of fault location. These methods require information such as substation and feeder switch status, real‐time feeder measurement, and atmospheric conditions.…”

Section: Introductionmentioning

confidence: 99%

A generalized fault location method based on voltage sags for distribution network

Awalin

Mokhlis

Bakar

et al. 2013

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

An enhanced fault location method based on voltage sag profiles for distribution networks is presented in this paper. In other previous methods, only a single measurement has been used. The proposed method can be used with any number of measurements in the network, making it more general. A new ranking approach that addresses multiple possibilities of the faulted section is proposed. Different case studies with various numbers of measurements are performed on a large 11‐kV network with the main feeder consisting of 42 buses to validate the method. The test results show that there is an improvement in terms of accuracy in detecting the faulted section in the first attempt for each additional measurement. Therefore, by utilizing the average value of each measurement, a better accuracy of fault location can be achieved. © 2013 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

show abstract

“…Recently a new approach by mapping TDR in frequency domain using continuous wavelet transform (CWT) showed reduction in the complexity of TDR-based fault location methods in distribution systems [16], [17]. On the other hand, various approaches have been published describing applications of artificial neural networks (ANNs) to locating faults in distribution lines [4], [5], [13]- [15]. Some of them employ fundamental frequency components (voltage and current) derived from waveforms [4], [5].…”

Section: Introductionmentioning

confidence: 99%

“…On the other hand, various approaches have been published describing applications of artificial neural networks (ANNs) to locating faults in distribution lines [4], [5], [13]- [15]. Some of them employ fundamental frequency components (voltage and current) derived from waveforms [4], [5]. These methods maximize the influence of load conditions and complexity of the fault locating.…”

Section: Introductionmentioning

confidence: 99%

Path Characteristic Frequency-Based Fault Locating in Radial Distribution Systems Using Wavelets and Neural Networks

Pourahmadi-Nakhli

Safavi

2011

IEEE Trans. Power Delivery

139

View full text Add to dashboard Cite

This paper proposes a new algorithm for localizing phase to ground faults in an electric power distribution system. Fault-originated traveling waves propagate along the distribution paths in both directions away from the fault point and are reflected at line terminations, junctions between feeders, laterals, and the fault location. Depending on the paths which traveling waves reciprocate through, the transient signal at each node contains certain path characteristic frequencies (PCFs). Energy spectrum of the transient signal has high density around the path characteristic frequencies. On this basis, the transient voltage is decomposed by a wavelet filter and its energy spectrum is decomposed into different levels. Depending on the bandwidth of the wavelet filter and the path characteristic frequencies, the decomposed signal in each level contains a certain percentage of energy. Then, a neural network-based methodology is proposed as a power distribution line fault locator. Energy percentage in each level is the candidate feature for training the artificial neural network. Simulations and the training process for the neural network are performed respectively using ATP/EMTP and MATLAB. It is shown that the results of the proposed algorithm are quite satisfactory. Index Terms-Artificial neural network, fault location, path characteristic frequency, wavelet transform.

show abstract

Design and Training of Artificial Neural Networks for Locating Low Current Faults in Distribution Systems

Cited by 16 publications

References 13 publications

Studies on the application of wavelet families for a high impedance fault location algorithm in a distribution network

Studies on the application of wavelet families for a high impedance fault location algorithm in a distribution network

A generalized fault location method based on voltage sags for distribution network

Path Characteristic Frequency-Based Fault Locating in Radial Distribution Systems Using Wavelets and Neural Networks

Contact Info

Product

Resources

About