A new control chart based on discriminant analysis for simple linear profiles monitoring

Abstract

In many processes, quality characteristic is identified by the regression relationship between one or more dependent variables and one or more independent variables called profile. In this paper, a control chart based on discriminant analysis (DA) is proposed to monitor simple linear profiles in Phase II. A chi-square control chart joined with DA chart is also used to improve detecting variance shifts. Performance of the proposed method is evaluated in terms of average run length using Monte-Carlo simulations. Performance of the proposed control chart is compared to the basic methods in simple linear profile monitoring. Results present the desirable performance of the proposed method. The real case in shoes leather industry is also investigated to show the effectiveness of the proposed method. results also confirm an acceptable performance of the real case, because the average run length of the proposed control chart is less than the average run length of the comparable method.