Control Chart For Monitoring The Coefficient Of Variation

In traditional quality control applications,control charts are often used to detect the mean or variance of a process.In some cases,the mean or variance of a process is not a constant,and their ratio-coefficient of variation is a constant when the process is controlled,Therefore,test the coefficient of variation is more reasonable,more in line with actual needs.According to the dimension of the variable,the coefficient of variation can be divided into one variable coefficient of variation and multiple coefficient of variation.In this paper,the coefficient of variation is studied in two directions: univariate and multiple coefficient of variation.First of all,the article will be the traditional Cumulative Sum(CUSUM)control chart and exponentially weighted moving average(EWMA)control chart,to construct a new control unity coefficient of variation control chart-mixed CUSUM-EWMA control chart,and compared with some of the existing methods.The results show that the proposed control chart has better ability to detect the small and medium shift of the coefficient of variation.Secondly,In the detection problem of multiple coefficient of variation equality,the definition of multivariate coefficient of variation is introduced,and the EWMA control chart is proposed according to the definition.The simulation results show that this paper the proposed multiple control graphs have a good performance for detecting the problem of multiple CV equivalence.