Determination of an efficient variables sampling system based on the Taguchi process capability index
提出一种基于田口过程能力指数的变量抽样系统，用于在双规格限且质量特性服从正态分布时，通过非线性规划最小化平均样本量并同时满足生产方与使用方风险，比现有抽样方案更高效。
Process capability indices are the important tools used in most of the manufacturing industries to check whether the manufactured products meet their quality specifications or not. These indices are the numerical measures used to judge the precision, accuracy, and performance of the manufacturing process. Acceptance sampling plan is another important tool used to check the quality of procured products. So, the sampling plan with combination of process capability indices will be a powerful tool for improving and maintaining the quality of products. In this paper, we propose a variables sampling system based on one of the most efficient process capability indices called Taguchi capability index. The proposed system can be applied when the quality characteristic under investigation has double specification limits and follows a normal distribution. Advantages of the proposed sampling system over the existing sampling plans are also discussed. Tables are also constructed to determine the optimal parameters by formulating the problem as a non-linear programming in which the average sample number is minimised by satisfying the producer and consumer risks simultaneously. A sensitivity analysis is provided in order to show the efficiency of the proposed sampling system.