AJAS Cover
Frequency: Continuous
ISSN: 1546-9239 (Print)
ISSN: 1554-3641 (Online)
Research Article Open Access

Choice Of Input Data Type Of Artificial Neural Network To Detect Faults In Alternative Current Systems

T. Benslimane, B. Chetate and R. Beguenane

Abstract

This paper present a study on different input data types of ANN used to detect faults such as over-voltage in AC systems (AC network , induction motor). The input data of ANN are AC voltage and current. In no fault condition, voltage and current are sinusoidal. The input data of the ANN may be the instantaneous values of voltage and current, their RMS values or their average values after been rectified. In this paper we presented different characteristics of each one of these data. A digital software C++ simulation program was developed and simulation results were presented.

American Journal of Applied Sciences
Volume 3 No. 8, 2006, 1979-1983

DOI: https://doi.org/10.3844/ajassp.2006.1979.1983

Submitted On: 6 July 2005 Published On: 31 August 2006

How to Cite: Benslimane, T., Chetate, B. & Beguenane, R. (2006). Choice Of Input Data Type Of Artificial Neural Network To Detect Faults In Alternative Current Systems. American Journal of Applied Sciences, 3(8), 1979-1983. https://doi.org/10.3844/ajassp.2006.1979.1983

Open AccessCopyright: © 2006 T. Benslimane, B. Chetate and R. Beguenane. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

  • 3,130 Views
  • 2,496 Downloads
  • 1 Citations

Download

Keywords

  • Diagnosis
  • Learning Data type
  • AC voltage and current
  • instantaneous value
  • RMS value
  • Average value