Under The Process Capability Index For Non-normal Condition For Theoretical Analysis And Simulation Studies

During the process capability analysis and the monitoring on the process, it is always consume that the process is normal. But, there are lots of non-normal processes in the practice, so the research on the non-normal process capability is an important to analyze the process. The process capability indices(PCIs) indicate the extent to which a process can satisfy a specification, the research on the process capability indices is of great theoretical and practical values.In my dissertation, effective process capability indices are proposed according to the characteristics of the non-normal processes. And the Bootstrap method is used to obtain the intervals of the PCIs. This is very important to enhance the quality and strengthen market competitiveness.The main content of this paper is as follows: first, on the basis of analyzing the process capability, a new method is proposed to get the process capability indices under non-normality and the process capability index under the section curve quality loss function. Then, the standard bootstrap confidence interval and the percentile bootstrap confidence interval are used to obtain the confidence intervals of the process capability indices. Furthermore, the non-normal process capability indices are applied to the Exponential distribution, the Weibull distribution and the tailed-normal distribution and the confidence intervals are obtained by the two kinds of Bootstrap methods. From the results of the simulation we can see that the methods proposed in this paper effectively calculate the process capability of the non-normal distributions.