LOCATION AND EVALUATION OF BEARINGS DEFECTS BY VIBRATION ANALYSIS AND NEURAL NETWORKS

Authors

  • M. E. Boukhobza Signals, Systems and Data Laboratory, Electronics department, USTO
  • Z. Derouiche Signals, Systems and Data Laboratory, Electronics department, USTO
  • Z. Ahmed Foitih Power Electronic and Automation Laboratory, Electronics department, USTO

DOI:

https://doi.org/10.5755/j01.mech.19.4.5051

Keywords:

maintenance, vibration, temporal indicators, Bearing, Artificial Neural Network (ANN)

Abstract

The quality of maintenance has an important influence on firm performance. Detection and monitoring of the progression of the defects of machines can reduce maintenance costs by minimizing the number of unplanned shutdowns and ensuing economic losses.

The state of a machine depends largely on the condition of rotating elements that compose it and especially bearings.

The vibration measurements are used as indicators of the health status of machines and timeliness of maintenance. The objective of this work is to establish a system based on artificial neural networks to know precisely the position of an incipient defect on the bearing elements and quantify its severity, using indicators from vibration signals.

DOI: http://dx.doi.org/10.5755/j01.mech.19.4.5051

Downloads

Published

2013-08-29

Issue

Vol. 19 No. 4 (2013)

Section

DYNAMICS OF MECHANICAL SYSTEMS