An EWMA –Based Method for Monitoring Polytomous Logistic Profiles (Case Study: Alloy Fasteners' Manufacturing Process)

In certain statistical process control applications, quality of a process or product can be characterized by a function commonly referred to as profile. Some of the potential applications of profile monitoring are cases where quality characteristic of interest is modeled using dichotomous or polytomous variables. Polytomous variables, especially multinomial variables, have various applications. In this paper, we proposed three methods for monitoring a profile when the process output is a multinomial response variable. Multinomial logistic regression (MLR) provides the basis for our profile model. Two methods including Multivariate exponentially weighted moving average (MEWMA) statistics, and Likelihood ratio test (LRT) statistics are proposed to monitor MLR profiles in phase II. Performances of these three methods are evaluated by average run length criterion (ARL). A real case study from alloy fasteners manufacturing process is used to illustrate the implementation of the proposed approach. Results indicate satisfactory performance for the proposed method.

Keywords:

Average run length (ARL) , Multivariate Exponentially weighted moving average (MEWMA) control chart , Multinomial regression , Profile monitoring , Alloy fasteners