Fault classification and faulted phase selection for transmission line using morphological edge detection filter

Salehi, Moslem; Namdari, Farhad

doi:10.1049/iet-gtd.2017.0999

Cited by 42 publications

(20 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because of these aforementioned advantages, the proposed and also many literature works carried out the pre‐processing of signal using the DWT analysis for training the classifiers such as ANN, Fuzzy, Modified Fuzzy Q‐learning, Fuzzy‐ARTMAP and ANFIS classifier. The work in presents classification of all the conventional faults such as LG, LL, LLG and LLLG fault by using the classifier such as ANN, ANFIS, Chebyshev Neural Network (Ch‐NN), Decision tree, Fuzzy and Modified Fuzzy Q‐learning, and multi‐layer perceptron (MLP) neural network with its accuracy of classification lies in the range of 92% to 100%. Nevertheless, all these works, presents the identification and location of conventional fault without considering the HIF.…”

Section: Comparison With Literature Workmentioning

confidence: 99%

A novel discrete wavelet transform‐based graphical language classifier for identification of high‐impedance fault in distribution power system

Veerasamy

Wahab

Vinayagam³

et al. 2020

Int Trans Electr Energ Syst

View full text Add to dashboard Cite

Summary This paper proposes a discrete wavelet transform (DWT)‐based Graphical Language classifier algorithm for identification of high‐impedance fault (HIF) in medium voltage (MV) distribution network of 13.8 kV. The proposed method of classifier is developed using virtual instrumentation LabVIEW facility, for detection of various faults such as symmetrical, unsymmetrical, and HIF in the system. Initially, the MV distribution feeder network has been modeled in MATLAB/Simulink, and the DWT analysis has been carried out with the introduction of various faults in the network to extract the features. The extracted features such as SD and energy values from the fault current signals have been applied to the proposed classifier algorithm to identify the type of fault. The effectiveness of the presented method has been tested and compared with the similar conventional fuzzy‐based approach. The results indicate that the proposed classifier algorithm outperforms to give 100% accuracy, while the fuzzy‐based approach misclassifies the double line to ground fault (LLG), three‐phase fault (LLLG), and HIF. Furthermore, the proposed algorithm with LabVIEW facility is more flexible and can be implemented in real time using data acquisition unit for obtaining fault current signal from power system.

show abstract

Section: Comparison With Literature Workmentioning

confidence: 99%

A novel discrete wavelet transform‐based graphical language classifier for identification of high‐impedance fault in distribution power system

Veerasamy

Wahab

Vinayagam³

et al. 2020

Int Trans Electr Energ Syst

View full text Add to dashboard Cite

show abstract

“…In contrast with the wavelet transform in [5, 9, 17, 18], S transform in [8] and time‐time transform [22], the type of computation required in MM includes only addition, subtraction, maximum, and minimum operations without any multiplication and/or division [23–25]. Therefore, the proposed IMG in this study has a much lower computation burden and feasibility of implementation.…”

Section: Comparisonmentioning

confidence: 99%

Fast transient‐based detection of busbar faults employing improved morphological gradient

Lashgari

Shahrtash

2020

IET Generation, Transmission & Distribution

View full text Add to dashboard Cite

“…The goal of training is to make the distribution of G(z) as close as possible to the distribution of real data. The goal of D is to achieve the binary classification of input data [16]. If the input comes from real samples, the output of D is 1; if the input is G(z), the output of D is 0.…”

Section: Gan Network Modelmentioning

confidence: 99%

Edge Detection Algorithm of a Symmetric Difference Kernel SAR Image Based on the GAN Network Model

Zhang

Liu

et al. 2019

Symmetry

View full text Add to dashboard Cite

The symmetrical difference kernel SAR image edge detection algorithm based on the Canny operator can usually achieve effective edge detection of a single view image. When detecting a multi-view SAR image edge, it has the disadvantage of a low detection accuracy. An edge detection algorithm for a symmetric difference nuclear SAR image based on the GAN network model is proposed. Multi-view data of a symmetric difference nuclear SAR image are generated by the GAN network model. According to the results of multi-view data generation, an edge detection model for an arbitrary direction symmetric difference nuclear SAR image is constructed. A non-edge is eliminated by edge post-processing. The Hough transform is used to calculate the edge direction to realize the accurate detection of the edge of the SAR image. The experimental results show that the average classification accuracy of the proposed algorithm is 93.8%, 96.85% of the detection edges coincide with the correct edges, and 97.08% of the detection edges fall into the buffer of three pixel widths, whichshows that the proposed algorithm has a high accuracy of edge detection for kernel SAR images.

show abstract

Fault classification and faulted phase selection for transmission line using morphological edge detection filter

Cited by 42 publications

References 44 publications

A novel discrete wavelet transform‐based graphical language classifier for identification of high‐impedance fault in distribution power system

A novel discrete wavelet transform‐based graphical language classifier for identification of high‐impedance fault in distribution power system

Fast transient‐based detection of busbar faults employing improved morphological gradient

Edge Detection Algorithm of a Symmetric Difference Kernel SAR Image Based on the GAN Network Model

Contact Info

Product

Resources

About