Search Results

Now showing 1 - 6 of 6

Some of the metrics are blocked by your
consent settings
Improvement to reduce training time of back-propagation neural networks for discrimination between external short circuit and internal winding fault
(2014-11-05)
Bunjongjit, S.
;
Ngaopitakkul, A.
;
Pothisarn, C.
;
Jettanasen, C.
This paper proposes the improvement technique to reduce training time of back-propagation neural network. The decision algorithm based on the hybrid of discrete wavelet transform (DWT) and back-propagation neural network (BPNN) has been proposed to classify between external fault and internal fault in power transformer. The DWT is employed to decompose high frequency component of post-fault differential current signals and used as an input pattern for the training process of a neural network in a decision algorithm with a use of the BPNN. The proposed technique is compared with conventional training process of BPNN in terms of average accuracy and training time process. The obtained results show that the proposed technique can reduce of training process duration time and is very effective in classifying between external fault and internal fault in power transformer with satisfactory accuracy.
Some of the metrics are blocked by your
consent settings
A discrete wavelet transform and fuzzy logic algorithm for identifying the location of fault in underground distribution system
(2013-01-01)
Bunjongjit, S.
;
Ngaopitakkul, A.
;
Pothisarn, C.
This paper proposes the hybrid decision algorithm of discrete wavelet transform (DWT) and fuzzy logic in order to identify the location of fault in underground distribution cable. The high frequency component obtained from DWT with the mother wavelet daubechies4 (db4) is used as an index for the occurrence of faults. The first peak time of DWT, obtained from positive sequence that can detected the occurrence of faults are considered as an input pattern of decision algorithm. The obtained average accuracy results have shown that the proposed decision algorithm is able to identify the location of fault with satisfactory accuracy. © 2013 IEEE.
Some of the metrics are blocked by your
consent settings
Analysis of characteristics using wavelet transform for simultaneous faults in electrical power system
(2012-12-12)
Pothisarn, C.
;
Ngaopitakkul, A.
This paper presents an analysis of characteristics for simultaneous fault signals in a 500-kV electrical power transmission system using wavelet transform. Such fault signals can occur in the transmission system, and have an effect to the operation of distance relays installed in the system. The fault analysis is performed using PSCAD/EMTDC. The Discrete Wavelet Transform (DWT) is used in order to detect the high frequency components. In addition, characteristics of fault current at various fault inception angles, fault locations and faulty phases are detailed. It has been found that when applying the previous decision algorithm give a wrong conclusion of fault types and fault location. © 2012 IEEE.
Some of the metrics are blocked by your
consent settings
Analysis of characteristics of simultaneous faults in electrical power systems using wavelet transform
(2008-12-01)
Ngaopitakkul, A.
;
Pongchaisrikul, W.
;
Kunakorn, A.
This paper presents an algorithm used in the analysis of simultaneous fault characteristics. The system under investigations is the 500-kV transmission network in Thailand. The analysis is performed using PSCAD/EMTDC and MATLAB/Simulink. Wavelet transform is used in order to detect high frequency components of the fault current signals. The characteristics of the fault current with various fault inception angles, fault locations and faulty phases are observed. It is found that the technique proposed in this paper gives satisfactory results in the simultaneous fault classification. © 2008 IEEE.
Some of the metrics are blocked by your
consent settings
Identification of fault types for a three-bus transmission network using Discrete Wavelet Transform and probabilistic neural networks
(2007-12-01)
Patcharoen, T.
;
Ngaopitakkul, A.
;
Kunakorn, A.
This paper proposes a new algorithm for detecting faults in an electric power transmission network system. The Discrete Wavelet Transform (DWT) and probabilistic neural network (PNN) are used in order to detect the high frequency components and to identify fault types on a three-bus transmission network with a loop structure. Simulations and the training process for the neural network are performed using PSCAD/EMTDC and MATLAB. It is found that the proposed algorithm gives satisfactory results, and will be very useful in the development of a modern protection scheme for electrical power transmission network systems. © 2007 RPS.
Some of the metrics are blocked by your
consent settings
Discrimination between external short circuits and internal faults in transformer windings using discrete wavelet transforms
(2005-12-01)
Ngaopitakkul, A.
;
Kunakorn, A.
;
Ngamroo, I.
In this paper, a technique for separation between internal faults in a two-winding three-phase transformer and external short circuits is presented. The fault detection algorithm is constructed on the basis of coefficient comparison from signals decomposed from Discrete Wavelet Transform. Computer simulations are performed using ATP/EMTP as well as MATLAB/Simulink. Various cases and fault types are studied to verify the validity of the algorithm. It is found that the proposed method gives a satisfactory accuracy, and will be particularly useful in a development of a modern differential relay for a transformer protection scheme. © 2005 IEEE.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results