Polynomial Control Chart Based On Likelihood Ratio Test

With the automation of industrial applications such as highly sensitive sensors and other applications,information services industry in the field of high-performance computer technology development.Online large-scale?high-dimensional?complex data collection can be achieved quickly.In many cases,the quality of the product we are concerned with is not simply the mean or variance(or distribution)of a certain or a few indicators,but rather the relationship between some independent variables and response variables characterized or measured,this relationship is often referred to as a profile relationship.In many cases,this curve can be described by the polynomial regression relationship.In this paper,we propose a Phase II polynomial control chart based on likelihood ratio test,which measures the performance of the control graph by the average run length(ARL),and compara with Orthogonal Polynomial Method(OTH)control charts,Multivariant Cumulative Sum(MCUSUM)control charts,Multivariant Exponentially Weighted Moving Average(MEWMA)control charts,T~2 control charts.The results show that the proposed method performs satisfactorily.