Integrated Greedy-Tabu-Search Method for the Economic Statistical Design of Shewhart Charts

Shewhart charts, also known as control charts, are important Statistical Process Control (SPC) techniques used for prompt detection of failures in a manufacturing process and minimization of production costs. Techniques have been used to find the chart’s parameters that best comply with economic and statistical requirements. In this paper a method that integrates a Greedy and a Tabu-Search (TS) algorithm is presented to estimate these parameters for X̄ control charts which are used for controlling process mean. When tested with different cost models and statistical restrictions with general failure distribution, and constant and variable sampling intervals, the performance of the proposed method was more accurate when compared to TS alone and a Genetic Algorithm.