KMITL

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

Browse

Search Results

Now showing 1 - 10 of 15

Some of the metrics are blocked by your
consent settings
Classification of Fault Type on Loop-Configuration Transmission System Using Support Vector Machine
(2017-11-15)
Sreewirote, Bancha
;
Ngaopitakkul, Atthapol
This paper proposed to applied Support vector machine (SVM) algorithm for classified the fault type on the 500 kV transmission systems with connected in loop configuration. The fault signal was simulated using ATPDraw/EMTP program at frequency 200 kHz. The fault detection was analyzing the high frequency component by discrete wavelet transform (DWT). For the first stage, the coefficient of DWT was used for the fault detection. After the fault can be detected, the fault classification will be identified using SVM algorithm. The maximum coefficient from wavelet transform was used as input pattern of SVM to classify the type of fault. The input pattern of SVM consists of 4 input; maximum coefficient of DWT in all phase current and zero sequence current. For the SVM process, the fault classification used the five model of SVM because each model is working in parallel to avoid mistake (or error). In addition, the same input in five model were simultaneously used while the output of each models is differently according to specification of model. The overall result of 2160 case studies data can be summarized that the fault classification using SVM algorithm is highly satisfactory.
Some of the metrics are blocked by your
consent settings
Fault classification on the hybrid transmission line system between overhead line and underground cable
(2017-08-30)
Klomjit, Jittiphong
;
Ngaopitakkul, Atthapol
This paper illustrates fault classification on hybrid transmission line. Current signals were analyzed by coefficients of discrete wavelet transform (DWT). Daubechies4 (db4) is employed as mother wavelet to decompose high frequency components from fault signals. In this paper, ATP/EMTP is used to simulate fault signal from current signals. Hybrid system between overhead line and underground cable of 115 kV from Provincial Electricity Authority (PEA-Thailand) system in case single circuit single conductor with overhead and underground was used as simulation case study. Various factors such as location of fault, fault type and fault angle have been taken into consideration. DWT is then applied on phase current and zero sequence signals using MATLAB software in order to obtain coefficient in scale 1 for further analysis. This value is mainly used to design algorithm for fault classification. Result obtained from the study is satisfactory.
Some of the metrics are blocked by your
consent settings
Study of Multi-distributed Generation Behavior when Fault Occurrence in Distribution System Using Wavelet Transform
(2016-12-28)
Ananwattanaporn, Santipont
;
Ngaopitakkul, Atthapol
In the last decade the number of power generation using renewable energy has been rapidly increased due to the energy and environmental issue. This trend in renewable energy has shifting power generation system from Centralized Generation (CG) to Distributed Generation (DG). With the new power generation on conventional distribution system, Analysis on disturbance must be done to ensure safety and reliability of the system. This paper aim to analyze behavior of transient signal when disturbance occur in distribution system with distributed generation. System under study is 22kV distribution system consist of wind power generation unit. Simulation was done by using PSCAD/EMTP program. The Discrete Wavelet Transform (DWT) is applied for decomposition of fault signal. To evaluate wavelet characteristic when fault occur in the system, Comparison in case of distribution system with and without wind power generation were done. Result indicated that with distributed generation, fault level is increasing and cause a changing in wavelet signal characteristic.
Some of the metrics are blocked by your
consent settings
Image watermarking using joined wavelet and time domain
(2014-10-14)
Padungdit, Akarapol
;
Suggree, Sippawit
;
Tuwanut, Panwit
This paper presents Image Watermarking Using Joined Wavelet and Time Domain. This method proposed has advantages above a single domain watermarking which are time domain or frequency domain. The advantages are that the output watermarked image is more robust and the result watermark after attacked from both geometric attacks and frequency attacks is better than the single watermarking method.
Some of the metrics are blocked by your
consent settings
An application of discrete wavelet transform and support vector machines algorithm for fault locations in underground cable
(2012-12-12)
Apisit, C.
;
Pothisarn, C.
;
Ngaopitakkul, A.
This paper proposes a technique using discrete wavelet transform (DWT) and support vector machines (SVM) for fault location in underground distribution cable. The ATP/EMTP is used to simulate fault signals. The mother wavelet daubechies4 (db4) is employed to decompose high frequency component from these signals. The maximum coefficient obtained from positive sequence current in first scale capable of detecting fault of each bus is used as input pattern for the training pattern. It is shown that the proposed technique gives satisfactory results, and will be very useful in the development of a power system protection scheme. © 2012 IEEE.
Some of the metrics are blocked by your
consent settings
An application of discrete wavelet transform and support vector machines algorithm for classification of fault types on underground cable
(2012-12-12)
Ngaopitakkul, A.
;
Pothisarn, C.
;
Bunjongjit, S.
;
Suechoey, B.
This paper proposes a new technique using discrete wavelet transform (DWT) and support vector machines (SVM) to classify the fault types in underground distribution systems. The DWT is used to detect the high frequency components from fault signals. Positive sequence current signals are used in fault detection decision algorithm. The variations of first scale high frequency component that detects fault are used as an input for the SVM. Various cases studies based on Thailand electricity underground distribution systems have been investigated so that the algorithm can be implemented. SVM is also compared with the coefficients DWT comparison technique. The proposed method gives satisfactory accuracy, and will be very useful in the development of a modern protection scheme for electrical power transmission and distribution systems. © 2012 IEEE.
Some of the metrics are blocked by your
consent settings
Differential protection schemes for classification of fault detection between external fault and internal winding fault in transformer using probabilistic neural network
(2012-12-01)
Jettanasen, C.
;
Klomjit, J.
;
Positharn, C.
;
Bunjongjit, S.
;
Ngaopitakkul, A.
This paper proposes an algorithm based on a combination of discrete wavelet transform (DWT) and probabilistic neural network (PNN) for discriminating between external fault and internal winding fault in power transformer. The coefficients of the first scale from the DWT that can detect fault are investigated. The maximum coefficients details (cD1) from DWT in first scale at 1/4 cycle of phase A, B, C and zero sequence for post-fault differential current waveforms have been used as an input for the training process of the PNN in a decision algorithm. Various cases studies based on Thailand electricity transmission and distribution systems have been investigated so that the algorithm can be implemented. The results show that the proposed algorithm is capable of performing the fault detection with satisfactory accuracy. © 2012 IEEE.
Some of the metrics are blocked by your
consent settings
Discrete wavelet transform and probabilistic neural network algorithm for fault location in underground cable
(2012-12-01)
Apisit, C.
;
Positharn, C.
;
Ngaopitakkul, A.
This paper proposes an algorithm based on a combination of discrete wavelet transform (DWT) and probabilistic neural network (PNN) for locating fault on underground cable. Simulations and the training process for the PNN are performed using ATP/EMTP and MATLAB. The mother wavelet daubechies4 (db4) is employed to decompose high frequency component from fault signals. The first peak time in first scale of each bus, that can detect fault, is used as input pattern for the training pattern. Various cases studies based on Thailand electricity distribution underground systems have been investigated so that the algorithm can be implemented. The results show that the proposed algorithm is capable of performing the fault location with satisfactory accuracy. © 2012 IEEE.
Some of the metrics are blocked by your
consent settings
Improvement of algorithm to reduce training time of back-propagation neural network for transformer interturn fault location
(2012-10-29)
Ngaopitakkul, A.
;
Pothisarn, C.
;
Klomjit, J.
;
Bunjongjit, S.
;
Suechoey, B.
This paper presents an algorithm based on a combination of Discrete Wavelet Transforms and back-propagation neural networks for location of interturn faults in a two-winding three-phase transformer. 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 by MATLAB. In addition, the choice of initial number of neurons for the first hidden layer to decrease duration time of train process is taken into account. A comparison between the proposed technique and conventional training is presented. The result is shown that the proposed technique is very effective in reduce training time and gives a satisfactory accuracy. © 2012 IEEE.
Some of the metrics are blocked by your
consent settings
Discrete wavelet transform and support vector machines algorithm for classification of fault types on transmission line
(2012-01-01)
Kunadumrongrath, K.
;
Ngaopitakkul, A.
This paper proposes a new technique using discrete wavelet transform (DWT) and support vector machines (SVM) to classify the fault types on transmission systems. The DWT is used to detect the high frequency components from fault signals. Positive sequence current signals are used in fault detection decision algorithm. The variations of first scale high frequency component that detects fault are used as an input for the SVM. Various cases studies based on Thailand electricity transmission systems have been investigated so that the algorithm can be implemented. SVM is also compared with the comparison of the coefficients DWT technique as well as back-propagation neural network algorithm. The proposed method gives satisfactory accuracy, and will be very useful in the development of a modern protection scheme for electrical power transmission systems.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results