Fault Classification Accuracy Measurement for a Distribution System with Artificial Neural Network without using Signal Processing Technique
S.V.Khond1, G. A.Dhomane2

1S. V. Khond*, Dept of Electrical Engg, Government College of Engineering, Chandrapur, Gondwana University, Gadchiroli, M.S., India.
2G.A.Dhomane, Dept of Electrical Engg, Government College of Engineering, Amravati, M.S., India.
Manuscript received on December 17, 2019. | Revised Manuscript received on December 24, 2019. | Manuscript published on January 10, 2020. | PP: 1523-1527 | Volume-9 Issue-3, January 2020. | Retrieval Number: C8558019320/2020©BEIESP | DOI: 10.35940/ijitee.C8558.019320
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Faults occurring on electrical distribution network are unpredictable and needs to be cleared at the earliest so as to reduce power outage time. Hence fault detection and their classification plays important role. In this research paper the fault classification accuracy was measured for an electrical power distribution network with artificial neural network without using any signal processing method. Although many digital signal processing methods are developed to enhance electrical fault classification accuracy, it is essential to measure it for comparison when no signal processing method is used. Fault classification was considered as a pattern recognition application of neural networks. Two layer feed forward back propagation neural network was used as classifier. IEEE 13 bus distribution feeder was simulated in MATLAB with Simulink for collecting the input data. The simulation results show that the faults can be classified satisfactorily. L-G, L-L and L-L-L faults were simulated for measuring the accuracy of fault classification. 
Keywords: Electrical Power Distribution, Fault Classification, Artificial Neural Networks, Signals Processing Technique.
Scope of the Article: Classification