An optimization‐based approach for designing attribute acceptance sampling plans

Abstract

PurposeThis purpose of this paper is to present an optimization‐based approach to support the design of attribute sampling plans for lot acceptance purposes, with the fraction of non‐conforming items being modeled by a Poisson probability distribution function.Design/methodology/approachThe paper approach stands upon the minimization of the error of the probability of acceptance equalities in the controlled points of the operating curve (OC) with respect to sample size and acceptance number. It was applied to simple and double sampling plans, including several combinations of quality levels required by the producer and the consumer. Formulation of the design of acceptance sampling plans as an optimization problem, having as a goal the minimization of the squared error at the controlled points of the OC curve, and its subsequent solution employing GAMS.FindingsThe results are in strong agreement with acceptance sampling plans available in the open literature. The papers approach in some scenarios outperforms classical sampling plans and allows one to identify the lack of feasible solutions.Originality/valueAn optimization‐based approach to support the design of acceptance sampling plans for attributes was conceived and tested. It allows for a general treatment of these problems, including the identification of a lack of feasible solutions, as well as making possible the determination of feasible alternatives by relaxing some model constraints.