摘要
在统计过程控制(SPC)技术中要求质量特征服从正态分布。而在实际生产中,许多稳定的过程不一定满足正态分布的假设。许多学者和质量工程师纷纷提出将非正态数据转变成正态数据的方法,以便使用SPC技术对这些数据进行分析,从而得出合理有效的结论。解决这个问题的一种方法是使用Johnson分布系统对这些非正态数据进行转换。文章提出了一套系统的处理非正态数据并计算其过程能力指数的方法,结合使用Johnson分布系统百分比拟合法,并给出具体的步骤和做法,最后应用该方法对实际案例进行研究,并计算其过程能力指数,与实际相比照,证实了该方法的有效性和实用性。文章用相应的matlab和m initab分析软件来辅助实现这个方法,具有可操作性,可以用于指导生产实践。
Quality characteristics analyzed in statistical process control （SPC） are often required to be normally distributed. However, non-normal data in most stable processes is not uncommon. Many professors and quality engineers develop the methods that can transform the non-normal data to normality in order to use the SPC to get a rational conclusion. One approach to solve this problem is to transform the non-normal data using the Johnson system of distributions. A systematic method that uses the percentile matching is proposed. The detailed procedures are given. Finally, this method is applied to a practical case study and the process capability can be calculated. Matlab and minitab are used in this method, which can be used to guide the practice.
出处
《组合机床与自动化加工技术》
2007年第8期104-107,共4页
Modular Machine Tool & Automatic Manufacturing Technique
基金
国家自然科学基金资助项目(70372044)
新世纪优秀人才资助计划(NCET-04-0240)
