Abstract
This paper presents an analysis on the selection of an appropriate activation function used in neural networks for fault diagnosis decision algorithm in transformer and transmission line protection scheme. A decision algorithm based on a combination of discrete wavelet transform (DWT) and back-propagation neural networks (BPNN) is developed. The discrete wavelet transform is employed for extracting the high frequency component contained in the fault signals. The training process for the neural network and fault diagnosis decision are implemented using toolboxes on MATLAB/Simulink. The activation functions in each hidden layers and output layer have been varied to find out and to select the best activation function for fault diagnosis decision algorithm. 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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
O.A.S. Youssef, Discrimination between faults and magnetizing inrush currents in transformers based on wavelet transforms. Electr. Power Syst. Res. 63(2), 87–94
M.E. Hamedani Golshan, M. Saghaian-nejad, A. Saha, H. Samet, A new method for recognizing internal faults from inrush current conditions in digital differential protection of power transformers. Electr. Power Syst. Res. 71(1), 61–71
A.A. Yusuff, A.A. Jimoh, J.L. Munda, Determinant-based feature extraction for fault detection and classification for power transmission lines. IET Gener. Transm. Distrib. 5(12), 1259–1267
F.E. Perez, R. Aguilar, E. Orduna, G. Guidi, High-speed non-unit transmission line protection using single-phase measurements and an adaptive wavelet: zone detection and fault classification. IET Gener. Transm. Distrib. 6(7), 593–604
P. Chiradeja, A. Ngaopitakkul, Identification of fault types for single circuit transmission line using discrete wavelet transform and artificial neural networks, in Proceedings of the International Multiconference of Engineers and Computer Scientists 2009, IMECS2009, 18–20 Mar 2009, Hong Kong. Lecture Notes in Engineering and Computer Science, pp. 1520–1525
D. Barbosa, U. Chemin Netto, D.V. Coury, M. Oleskovicz, Power transformer differential protection based on clarke’s transform and fuzzy systems. IEEE Trans. Power Deliv. 26(2), 1212–1220
N. Perera, A.D. Rajapakse, Development and hardware implementation of a fault transients recognition system. IEEE Trans. Power Deliv. 27(1), 40–412
S. Seyedtabaii, Improvement in the performance of neural network-based power transmission line fault classifiers. IET Gener. Transm. Distrib. 6(8), 731–737
A. Ngaopitakkul, C. Jettanasen, Combination of discrete wavelet transform and probabilistic neural network algorithm for detecting fault location on transmission system. Int. J. Innovative Comput. Inf. Control 7(4), 1861–1874
J. Upendar, C.P. Gupta, G.K. Singh, Fault classification scheme based on the adaptive resonance theory neural network for protection of transmission lines. Electr. Power Compon. Syst. 38(4), 424–444
A. Abu-Siada, S. Islam, A novel online technique to detect power transformer winding faults. IEEE Trans. Power Deliv. 27(2), 849–857
Z. Gajic, Use of standard 87T differential protection for special three-phase power transformers part I: theory. IEEE Trans. Power Deliv. 27(3), 1035–1040
M. Moscoso, S. Hosseini, G.J. Lloyd, K. Liu, Operation and design of a protection relay for transformer condition monitoring, in Proceedings of 11th International Conference on Developments in Power System Protection, DPSP2012, pp. 1–6
A. Ashrafian, M. Rostami, G.B. Gharehpetian, Hyperbolic S-transform-based method for classification of external faults, incipient faults, inrush currents and internal faults in power transformers. IET Gener. Transm. Distrib. 6(10), 940–950
O.A.S. Youssef, A wavelet-base technique for discrimination between faults and magnetizing inrush currents in transformers. IEEE Trans. Power Deliv. 18(1), 170–176
A. Ngaopitakkul, C. Pothisarn, Selection of proper activation functions in back-propagation neural networks algorithm for fault classification in underground cable. IAENG Trans. Eng. Technol. 7(1), 308–319
N. Suttisinthong, B. Seewirote, A. Ngaopitakkul, C. Pothisarn, Selection of proper activation functions in back-propagation neural network algorithm for single-circuit transmission line, in Proceedings of the International MultiConference of Engineers and Computer Scientists 2014, IMECS2014, 12–14 Mar 2014, Hong Kong. Lecture Notes in Engineering and Computer Science, pp. 758–762
A. Ngaopitakkul, A. Kunakorn, Internal fault classification in transformer windings using combination of discrete wavelet transforms and back-propagation neural networks. Int. J. Control Autom. Syst. (IJCAS) 4(3), 365–371
Acknowledgment
The authors wish to gratefully acknowledge financial support for this research from the King Mongkut’s Institute of Technology Ladkrabang Research fund, Thailand. The authors would like also to thank for partially supported by the Faculty of Engineering, Rajamangala University of Technology Rattanakosin Research fund.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer Science+Business Media Dordrecht
About this chapter
Cite this chapter
Ngaopitakkul, A., Bunjongjit, S. (2015). Selection of Proper Activation Functions in Back-Propagation Neural Network Algorithm for Transformer and Transmission System Protection. In: Yang, GC., Ao, SI., Huang, X., Castillo, O. (eds) Transactions on Engineering Technologies. Springer, Dordrecht. https://doi.org/10.1007/978-94-017-9588-3_22
Download citation
DOI: https://doi.org/10.1007/978-94-017-9588-3_22
Published:
Publisher Name: Springer, Dordrecht
Print ISBN: 978-94-017-9587-6
Online ISBN: 978-94-017-9588-3
eBook Packages: EngineeringEngineering (R0)