This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
|
||||||||
|
Paper Details
Paper Title
Fault Detection and Classification in Transmission Line by using Support Vector Machine Technique
Authors
  Amit Madhukarrao Tayade,  Nitin J. Phadkule
Abstract
Detection and classification of faults in transmission line is of great importance in power system because 80-85% faults occur on transmission line. Detection of faults provides whether system is stable or faulty whereas classification of faults indicates which type of fault is occurred. Both detection and classification suggests accurate and appropriate protection scheme to be implemented. There are numerous techniques used for classifying the faults, but lack of accuracy and processing speed demands new techniques and methods to be invented. In case of new inventions Machine Learning is the latest technique which is taking attention of many researchers. Machine learning includes many algorithms for classification of faults like Naïve Bayes, Support vector machine (SVM), Bagging, Boosting, etc. Also deep learning and neural network techniques are being investigated for most accurate and fast protection scheme. This paper presents the fault detection and classification in transmission line with the help of support vector machine technique. Support vector machine requires less data for training and has fast operation which gives accurate and satisfactory results.
Keywords- fault detection, fault classification, transmission line, distribution line, machine learning, Support Vector Machine (SVM).
Publication Details
Unique Identification Number - IJEDR1902069Page Number(s) - 367-375Pubished in - Volume 7 | Issue 2 | May 2019DOI (Digital Object Identifier) -    Publisher - IJEDR (ISSN - 2321-9939)
Cite this Article
  Amit Madhukarrao Tayade,  Nitin J. Phadkule,   "Fault Detection and Classification in Transmission Line by using Support Vector Machine Technique", International Journal of Engineering Development and Research (IJEDR), ISSN:2321-9939, Volume.7, Issue 2, pp.367-375, May 2019, Available at :http://www.ijedr.org/papers/IJEDR1902069.pdf
Article Preview
|
|
||||||
|