Article ID: | iaor20162981 |
Volume: | 18 |
Issue: | 4 |
Start Page Number: | 537 |
End Page Number: | 555 |
Publication Date: | Jul 2016 |
Journal: | International Journal of Productivity and Quality Management |
Authors: | Niaki Seyed Taghi Akhavan, Noorossana Rassoul, Ershadi Mohammad Javad |
Keywords: | design, quality & reliability, statistics: inference |
Employing profiles using variable sample size (VSS) may improve its effectiveness and hence is investigated in this paper. Besides, the implementation cost of a profile is an important factor in determining the main parameters. In this paper, the Lorenzen‐Vance function is first extended to model implementation cost of VSS linear profiles. Then, the resulted economic model is solved using a genetic algorithm (GA). The average run length criterion when process is in control, ARL0 and the average run length measure when process goes out of control, ARL1, is used to evaluate statistical properties of the designed profile. Moreover, a sensitivity analysis on the main parameters of the Lorenzen‐Vance function shows that the developed economic model is robust with respect to fixed and variable cost of constructing the profile, while it is very sensitive to the time of constructing the profile.