Design and implementation of an automatic condition-monitoring expert system for ball-bearing fault detection

A. Hajnayeb; S.E. Khadem; M.H. Moradi

doi:10.1108/00368790810858395

Login

Welcome:
Guest

Search for:

Browse:

Product Information:

Resources:

Industrial Lubrication and Tribology

ISSN: 0036-8792

Online from: 1948

Subject Area: Mechanical & Materials Engineering

Content: Latest Issue | Latest Issue RSS | Previous Issues

Options: To add Favourites and Table of Contents Alerts please take a Emerald profile

Design and implementation of an automatic condition-monitoring expert system for ball-bearing fault detection

Document Information:
Title:	Design and implementation of an automatic condition-monitoring expert system for ball-bearing fault detection
Author(s):	A. Hajnayeb, (Department of Mechanical Engineering, Tarbiat Modarres University, Tehran, Iran), S.E. Khadem, (Department of Mechanical Engineering, Tarbiat Modarres University, Tehran, Iran), M.H. Moradi, (Biomedical Engineering Department, Amirkabir University, Tehran, Iran)
Citation:	A. Hajnayeb, S.E. Khadem, M.H. Moradi, (2008) "Design and implementation of an automatic condition-monitoring expert system for ball-bearing fault detection", Industrial Lubrication and Tribology, Vol. 60 Iss: 2, pp.93 - 100
Keywords:	Condition monitoring, Neural nets, Vibration
Article type:	Research paper
DOI:	10.1108/00368790810858395 (Permanent URL)
Publisher:	Emerald Group Publishing Limited
Abstract:	Purpose – This paper aims to improve the performance and speed of artificial neural network (ANN)-ball-bearing fault detection expert systems by eliminating unimportant inputs and changing the ANN structure. Design/methodology/approach – An algorithm is used to select the best subset of features to boost the success of detecting healthy and faulty ball. Some of the important parameters of the ANN are also optimized to make the classifier achieve the maximum performance. Findings – It was found that better accuracy can be obtained for ANN with fewer inputs. Research limitations/implications – The method can be used for other machinery condition-monitoring systems which are based on ANN. Practical implications – The results are useful for bearing fault detection systems designers and quality check centers in bearing manufacturing companies. Originality/value – The algorithm used in this research is faster than in previous studies. Changing ANN parameters improved the results. The system was examined using experimental data of ball-bearings.