Fault Classification in Transmission Line Using Wavelet Features and Fuzzy-KNN

Abstract:

Fault occurred in transmission line can cause many problems such as failure of equipment, instability in power flow, and economical losses. Many of the techniques proposed for fault classification in transmission line have applied steady state component as it is easily affected by the surroundings. Then, protection scheme based on fault generated transient that can offer an accurate result for fault classification in power system should be proposed. This paper presents the fault classification scheme using Fuzzy-KNN (Fuzzy k-Nearest Neighbor) classifier and wavelet features. Two wavelet features were calculated in this study which are Wavelet Mean (μ) and Wavelet Standard Deviation (σ). Then, the Fuzzy-KNN classifier was tested with three datasets categories: Ideal, 30 dB noise, and 20 dB noise datasets. The overall results in accuracy performance show that the Fuzzy-KNN classifier performed better than the KNN (k-Nearest Neighbor) classifier.

• Periodical: Applied Mechanics and Materials (Volume 850)
• Pages: 112-117
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.850.112
• Online since: August 2016
• Authors: Mat Nizam Mahmud*, Mohammad Nizam Ibrahim, Muhammad Khusairi Osman, Zakaria Hussain
• Keywords: Fault Classification, Fuzzy K-Nearest Neighbor, Transmission Lines, Wavelet Features

References

[1] U. Minnaar, C. Gaunt, and F. Nicolls, Characterisation of power system events on South African transmission power lines, Electric power systems research, vol. 88, (2012).

DOI: 10.1016/j.epsr.2012.01.015

[2] K. Silva, B. Souza, and N. Brito, Fault detection and classification in transmission lines based on wavelet transform and ANN, Power Delivery, IEEE Trans. on, vol. 21, (2006).

DOI: 10.1109/tpwrd.2006.876659

[3] M. J. B. Reddy, D. V. Rajesh, and D. Mohanta, Robust transmission line fault classification using wavelet multi-resolution analysis, Computers & Electrical Eng., vol. 39, (2013).

DOI: 10.1016/j.compeleceng.2013.02.013

[4] B. Vyas, R. P. Maheshwari, and B. Das, Evaluation of AI Techniques for Fault Type Identification in Advanced Series Compensated Trans. Lines, IETE J. of Research, (2014).

DOI: 10.1080/02564602.2014.893767

[5] Z. He, S. Lin, Y. Deng, X. Li, and Q. Qian, A rough membership neural network approach for fault classification in transmission lines, Int. J. of Elec Power & Energy Syts, (2014).

DOI: 10.1016/j.ijepes.2014.03.027

[6] S. Muyeen, H. M. Hasanien, and A. Al-Durra, Transient stability enhancement of wind farms connected to a multi-machine power system by using an adaptive ANN-controlled SMES, Energy Conversion and Management, vol. 78, (2014).

DOI: 10.1016/j.enconman.2013.10.039

[7] H. -L. Chen, C. -C. Huang, X. -G. Yu, X. Xu, X. Sun, G. Wang, et al., An efficient diagnosis system for detection of Parkinson's disease using fuzzy k-nearest neighbor approach, Expert systems with applications, vol. 40, (2013).

DOI: 10.1016/j.eswa.2012.07.014

[8] O. Castillo, P. Melin, E. Ramírez, and J. Soria, Hybrid intelligent system for cardiac arrhythmia classification with Fuzzy K-Nearest Neighbors and neural networks combined with a fuzzy system, Expert Systems with Applications, vol. 39, (2012).

DOI: 10.1016/j.eswa.2011.08.156

[9] H. -B. Shen, J. Yang, and K. -C. Chou, Fuzzy KNN for predicting membrane protein types from pseudo-amino acid composition, Journal of theoretical biology, vol. 240, (2006).

DOI: 10.1016/j.jtbi.2005.08.016

[10] S. Ekici, Support vector machines for classification and locating faults on transmission lines, Applied Soft Computing, vol. 12, (2012).

DOI: 10.1016/j.asoc.2012.02.011

[11] J. M. Keller, M. R. Gray, and J. A. Givens, A fuzzy k-nearest neighbor algorithm, Systems, Man and Cybernetics, IEEE Transactions on, (1985).

DOI: 10.1109/tsmc.1985.6313426

[12] I. Saini, D. Singh, and A. Khosla, QRS detection using K-Nearest Neighbor algorithm (KNN) and evaluation on standard ECG databases, J. of advanced research, vol. 4, (2013).

DOI: 10.1016/j.jare.2012.05.007

[13] H. Liu and S. Zhang, Noisy data elimination using mutual k-nearest neighbor for classification mining, Journal of Systems and Software, vol. 85, (2012).

DOI: 10.1016/j.jss.2011.12.019

[14] E. Nasibov and C. Kandemir-Cavas, Efficiency analysis of KNN and minimum distance-based classifiers in enzyme family prediction, Comp. biology and chemistry, (2009).

DOI: 10.1016/j.compbiolchem.2009.09.002