A testing procedure for the lifetime performance index of products with Weibull distribution under progressively first-failure-censoring
碩士 === 淡江大學 === 統計學系碩士班 === 104 === Since the consumers’ demand for the quality of products is getting higher and higher, to upgrade the process capability to reach a pre-specified target has become a very important topic in manufacturing industry. In practice, process capability...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | zh-TW |
| Published: |
2016
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/9c25t3 |
| Summary: | 碩士 === 淡江大學 === 統計學系碩士班 === 104 === Since the consumers’ demand for the quality of products is getting higher and higher, to upgrade the process capability to reach a pre-specified target has become a very important topic in manufacturing industry. In practice, process capability indices (PCIs) have played an important role to evaluate the process capability of the producing processes for any products. In this research, we focus on the index of CL for the lifetime of products with Weibull distribution.
Weibull distribution is one of the most commonly used lifetime distribution in many engineering fields. In this study, we construct a confidence interval and a confidence region for two parameters based on the progressive type I censored sample
for Weibull distribution. The unbiased estimator of the lifetime performance index CL is found and it is used as the test statistic to develop a hypothesis testing procedure to determine if the process is capable or not. The Monte Carlo simulation is done to compare the powers under various censored schemes and a comparison conclusion is made. Finally, we give two practical examples to illustrate the use of this testing algorithmic procedure.
|
|---|