Recognition of fault transients using a probabilistic neural-network classifier

Proceedings of the 3rd International Conference on Intelligent Systems and Image Processing 2015

Leelajindakrairerk

2015

This paper is focused on the behavior of current waveform when the single line to ground fault occurs on the pilumped equivalent circuit experimental test bench of distribution system. The experimental test bench can be divided into the distribution system either overhead line or underground cable. The parameter of experimental test bench is calculated based on per-unit method by using the data from the 115 kV distribution system in Thailand. The various case studies are performed by changing the type of distribution system, the location of fault, the inception angle of fault including varying the load. The obtained results show that, during the fault occurrence, the current waveform has a sudden change and increases more than 10 times in comparison with normal condition. Finally, the results from the experimental test bench will be beneficial in the behavioral study of the fault current in case of both overhead line and underground cable and will be development of the short-circuit protection system in the distribution system.

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Study of Characteristics of Fault in Overhead and Underground Cable Distribution System Using Experimental Test Bench

Yindeesap

Proceedings of the 3rd International Conference on Intelligent Systems and Image Processing 2015

Leelajindakrairerk

2015

“…In the literature for fault detection, several decision algorithms 1–42 have been developed to be employed in the protective relay for preventing maloperation of the protective equipment under different nonfault conditions, including magnetizing inrush current, ratio mismatch, through‐fault current, etc. There are many techniques 1–42 for detecting faults, such as artificial neural networks (ANNs) 12,30,39,40, transient‐based protection 13,18–20, finite element 14, fuzzy logic 35, hybrid systems 14,32, and so on. An algorithm for protecting a transformer with three windings using the increments of flux linkages (IFLs) has been proposed by Kang et al 2.…”

Section: Introductionmentioning

confidence: 99%

A discrete wavelet transform approach to discriminating among inrush current, external fault, and internal fault in power transformer using low-frequency components differential current only

IEEJ Trans Elec Electron Eng

Jettanasen

2014

This paper proposes an algorithm based on discrete wavelet transform (DWT) for discriminating among inrush current, internal fault, and external fault in power transformers. Fault conditions are simulated using the Alternative Transients Program/Electromagnetic Transients Program (ATP/EMTP). Daubechies4 (db4) is employed as the mother wavelet to decompose low‐frequency components from fault signals. The ratio between per unit (p.u.) differential current and p.u. time is suggested as an index. The numerator of the ratio is the difference between the maximum differential current and the minimum differential current in terms of p.u. with a base value selected at the transformer‐rated current. The ratio is calculated for all three phases, and from a trial and error process the indices for the separation among the internal fault condition, the external fault condition, and inrush condition are defined. The results obtained from the proposed technique show good accuracy for discriminating faults in the considered system. In addition, the proposed algorithm uses data of the differential current with a time of quarter cycle under the analysis. © 2014 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

“…Most of them offer different solutions and techniques based on, for example, artificial neural networks (ANNs), fuzzy logic, finite element analysis, transient‐based protection, hybrid systems, etc. [1–7]. In recent years, there has been much progress in the development of algorithms for detecting faults in transformers using transients‐based techniques [8].…”

Section: Introductionmentioning

confidence: 99%

A novel probabilistic neural network‐based algorithm for classifying internal fault in transformer windings

Jettanasen

IEEJ Transactions Elec Engng

2013

The major function of protective devices in a power system is to detect the occurrence of faults and to isolate the faulty sections from the rest of the system. Much progress has been made in the development algorithms for detecting faults in power transformers, which depend on transients‐based techniques. This paper presents an algorithm based on a combination of discrete wavelet transforms and probabilistic neural networks (PNNs) for classifying internal faults in a two‐winding three‐phase transformer. Fault conditions of the transformer are simulated using alternative transients program/electromagnetic transients program (ATP/EMTP) in order to obtain current signals. The mother wavelet Daubechies4 is employed to decompose the high‐frequency components from these signals. All three phases of the differential current signals are used in the fault detection decision algorithm. The variations of first‐scale high‐frequency component that detects fault are used as an input for the training pattern. The training process for the neural network and fault diagnosis decision is implemented using toolboxes on MATLAB/Simulink. Various cases and fault types based on the Thailand electricity transmission and distribution systems are studied to verify the validity of the algorithm. Backpropagation neural network is also compared with the PNN in this paper. It is found that the proposed method gives satisfactory accuracy with less training time, and will be particularly useful in the development of a modern differential relay for a transformer protection scheme. © 2013 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.