Selective Assembly to Minimize Clearance Variation by Shifting the Process Mean When Two Components Have Dissimilar Variances

Abstract

Selective assembly is an effective approach for improving a quality of a product assembled from two types of components, when the quality characteristic is the clearance between the mating components. In this paper, optimal selective assembly is discussed when the two component dimensions are normally distributed with unequal variances, and the component with the smaller variance is manufactured at two shifted means. We give conditions for the mean shift which minimizes the variance of the clearance, and show its uniqueness. It is also shown that the optimal mean shift increases when the difference between the two variances of the two component dimensions becomes larger. Finally, some numerical results are given to show that the method studied in this paper gives much improvement over the previous method (not shifting), especially for the case when the two variances are much different.