基于田口质量损失函数的控制图优化设计

Design Optimization of Control Charts Based on Taguchi's Quality Loss Function

由于在生产实际中存在大量非正态过程,传统控制图将失去其有效性。针对实际生产过程中质量特性不服从正态分布的情况,以Burr分布作为非正态数据的近似分布,结合均值随机漂移和田口质量损失函数,给出X-图的经济统计最优设计方法;根据过程输出数据,提出最优样本容量及控制限的选择。数值计算的结果显示该方法可靠;通过灵敏度分析,研究了各参数对最优设计的影响。

Data or measurements are usually thought to be normally distributed when control charts are designed, however, it is not true in some processes. Based on Taguchi＇s loss function, this paper uses the Burr distribution as the appropriate one for various non-normal distributions to determine the control limits and the sampling plan. An example illustrates the reliability of the method and from the results of the sen-sitivity analyses, the effects of parameters on the optimal design can be found.