Improved inspection scheme with a loss-based capability index

Abstract

Acceptance sampling is a practical quality tool for lot sentencing and is used primarily for incoming or outgoing inspections. The repetitive group sampling plan (RGSP) has been developed and shown to be superior to the traditional single sampling plan. However, RGSP’s lot disposition does not consider the valuable information from preceding lots, which may reduce its discriminatory power and sampling efficiency. Therefore, we propose a modified RGSP for variables inspection using the loss-based capability index. It uses not only the current sample information but also the results of preceding lots to sentence the current lot. The proposed plan’s operating characteristic (OC) function is derived using the estimated index’s exact sampling distribution. An optimization model is formulated to solve the plan parameters by minimizing the average sample number (ASN) required for inspection. The proposed plan’s advantages over the traditional sampling plans in terms of the OC curve and the ASN are addressed. Moreover, plan parameters are tabulated under various conditions and an application example is presented to illustrate its applicability.