Using the ANN Classifier to Recognize the Disturbance Patterns for a Multivariate System

Abstract

The importance of recognition of control chart patterns (CCPs) has been addressed in recent years. Most of those studies focused on determination of CCPS for a statistical process control (SPC) application alone. In addition, the use of engineering process control (EPC) is able to greatly improve the SPC process. However, even though many studies have reported an increased use of SPC-EPC mechanism, there has been very little research discussed on the effectiveness of recognition of CCPs for the SPC-EPC system. The purpose of the present study is thus to ascertain the effectiveness of proposing a useful classifier to recognize the CCPs for a multivariate SPC-EPC system. Because of its effective performance on classification, the present study applies the artificial neural network (ANN) technique to serve as the classifier in order to recognize the CCPs for a multivariate SPC-EPC system. The performance of the proposed ANN classifier is evaluated through a series of computer simulations.