KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Settings

Author: search.filters.author.Pothisarn, ChaichanSubject: search.filters.subject.Back-propagation neural network

Search Results

Now showing 1 - 3 of 3
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Selection of proper activation functions in back-propagation neural networks algorithm for transformer internal fault locations
    (2012-12-01)
    Jettanasen, Chaiyan
    ;
    Pothisarn, Chaichan
    ;
    Bunjongjit, Sulee
    ;
    Ngaopitakkul, Atthapol
    ;
    Suechoey, Boonlert
    This paper presents an analysis on the selection of an appropriate activation function used in neural networks for locating the internal fault in a two-winding three-phase transformer. A decision algorithm based on a combination of Discrete Wavelet Transforms and neural networks is developed. Fault conditions of the transformer are simulated using ATP/EMTP in order to obtain current signals. The training process for the neural network and fault diagnosis decision are implemented using toolboxes on MATLAB/Simulink. Various activation functions in hidden layers and output layers are compared in order to find out and to select the best activation function for indicating the position of internal faults of the winding transformer for the winding to ground faults. It is found that the use of Hyperbolic tangent-function for the hidden layers, and Linear activation function for the output layer gives the most satisfactory accuracy in these particular case studies. © 2012 IEEE.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Application of back-propagation neural network for transformer differential protection schemes part 1 discrimination between external short circuit and internal winding fault
    (2012-12-01)
    Ngaopitakkul, Atthapol
    ;
    Jettanasen, Chaiyan
    ;
    Klomjit, Jittiphong
    ;
    Pothisarn, Chaichan
    ;
    Seewirote, Buncha
    This paper proposes an algorithm based on a combination of discrete wavelet transform (DWT) and back-propagation neural network (BPNN) for discriminating between external fault and internal winding fault of three-phase two-winding transformer. The DWT is employed for extracting the high frequency component contained in the post-fault differential current waveforms, and the coefficients of the first scale from the DWT that can detect fault are investigated as an input for the training pattern. Various cases studies based on Thailand electricity transmission and distribution systems have been investigated so that the algorithm can be implemented. Results show that the proposed technique is highly satisfactory. © 2012 IEEE.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Application of back-propagation neural network for transformer differential protection schemes part 2 identification the phase with fault appearance in power transformer
    (2012-12-01)
    Ngaopitakkul, Atthapol
    ;
    Pothisarn, Chaichan
    ;
    Bunjongjit, Sulee
    ;
    Klomjit, Jittiphong
    ;
    Suechoey, Boonlert
    In this paper, a decision algorithm for identifying the phase with fault appearance of a two-winding three-phase transformer has been proposed. A decision algorithm based on a combination of Discrete Wavelet Transforms and back-propagation neural networks (BPNN) is developed. Daubechies4 (db4) is employed as mother wavelet in order to decompose high frequency components from fault signals. The maximum coefficients of DWT at cycle of phase A, B, C and zero sequence for post-fault differential current are used as input patterns for training process, and the results obtained from the decision algorithm are investigated. Various cases and fault types are studied to verify the validity of the algorithm. The result is found that the proposed decision algorithm can give more satisfactory results. © 2012 IEEE.