| Article ID: | iaor19991728 |
| Country: | United Kingdom |
| Volume: | 25 |
| Issue: | 9 |
| Start Page Number: | 691 |
| End Page Number: | 705 |
| Publication Date: | Sep 1998 |
| Journal: | Computers and Operations Research |
| Authors: | Monga Amit, Zuo Ming J. |
| Keywords: | maintenance, repair & replacement, artificial intelligence, optimization |
In this paper we present a study on reliability based design of a series-parallel system considering burn-in, warranty and maintenance. The system failure rate function incorporates three different phases of a product life cycle, namely, infant mortality period, the useful period and the wear-out period. The system life cycle cost includes costs of burn-in, warranty, installation, preventive maintenance and minimal repair. Genetic algorithms are used to obtain optimal values of system design, burn-in period, preventive maintenance intervals and replacement time. Three distinct cases representing different failure characteristics are studied to investigate the changes in system design and burn-in period for different lengths of warranty.