On the Optimality of a Simplified Multicharacteristic Component Inspection Model

Abstract

Inspection for multicharacteristic components is an important means to assure product quality. A component is inspected with respect to its characteristics of which non-conformance of one would result in the rejection of the component. Based on a cost-minimization model developed recently by Raoul et al., this paper develops a simplified version of the model to capture the cost implication of false rejection, false acceptance and inspection of the components. The simplified model is computationally more efficient than the earlier one. Optimality of the sequencing of characteristics to be inspected is explored. Based on the simplified model, the optimal number of cycles for inspection can be readily determined. A stopping rule is developed for the search of the optimal number of cycles. Sufficient conditions for performing one cycle of inspection or no multicharacteristic inspection at all are given. Finally, the results are extended to the case where the probabilities of defectives are random.