Optimal opportunistic maintenance policy using genetic algorithms, 1: formulation

Dragan A. Savic (School of Engineering, University of Exeter, Exeter, UK)
Godfrey A. Walters (School of Engineering, University of Exeter, Exeter, UK)
Jezdimir Knezevic (School of Engineering, University of Exeter, Exeter, UK)

Journal of Quality in Maintenance Engineering

ISSN: 1355-2511

Publication date: 1 June 1995

Abstract

Describes the development of two genetic algorithm (GA) programs for cost optimization of opportunity‐based maintenance policies. The combinatorial optimization problem is formulated and it is shown that genetic algorithms are particularly suited to this type of problem. The theoretical basis and operations of a standard genetic algorithm (SGA) are presented with an iterative procedure necessary for implementation of the SGA to least‐cost part replacement. However, an SGA used in an iterative manner may limit the global search capability of the evolutionary computing technique and may lead to suboptimal solutions. To avoid this problem, an improved GA which considers more than two groups simultaneously is devised. This model is based on the permutation representation and genetic sequencing operators originally developed for the travelling salesman problem. The same example used with the SGA confirmed that the improved GA can bring additional savings.

Keywords

Citation

Dragan A. Savic, Godfrey A. Walters and Jezdimir Knezevic (1995) "Optimal opportunistic maintenance policy using genetic algorithms, 1: formulation", Journal of Quality in Maintenance Engineering, Vol. 1 No. 2, pp. 34-49

Download as .RIS

DOI

: https://doi.org/10.1108/13552519510089574

Publisher

:

MCB UP Ltd

Copyright © 1995, MCB UP Limited

Please note you might not have access to this content

You may be able to access this content by login via Shibboleth, Open Athens or with your Emerald account.
If you would like to contact us about accessing this content, click the button and fill out the form.
To rent this content from Deepdyve, please click the button.