The Study of Sample Size Determination for Lower Confidence Limits for Estimating Multiple Product Characteristics Process Capability Indices

• Main Authors: Shu-Yu Wu, 吳書宇
• Other Authors: Tong-Yuan Koo
• Format: Others
• Language: zh-TW
• Published: 2002
• Online Access: http://ndltd.ncl.edu.tw/handle/60773212374484460054

碩士 === 國立雲林科技大學 === 工業工程與管理研究所碩士班 === 90 === The conventional process capability indices, such as Cp, Cpk, Cpm, have been proved as a useful tool to evaluate the process performance. Because the product complexity has been increased recently, the process capability analysis for process with multiple product characteristics becomes important. Some multivariate process capability indices have been developed for this purpose under the assumption of multivariate normal distribution. However, all these process capability indices are point estimators and will be affected by sampling errors. In order to resolve this problem, researchers have proposed the confidence interval for those process capability indices. In this paper, the sample number will be calculated under the condition of certain a risk, the fixed ratio of lower confidence interval and the value of the process indices MCp or the process indices MCpm. The tables of sample number for numerous a risk, the fixed ratio of lower confidence interval and the value of the process indices MCp or the process indices MCpm, and number of product characteristics are generated for the use of practicioners.