A Supervised Learning Method in Monitoring Linear Profile

In some practical situations, the quality of a process or product is characterized by a relationship (profile) between a response variable and one or more explanatory variables. Such profiles can be modeled using linear or nonlinear regression models. In this paper we propose a supervised feed forward neural network to detect and classify drift shifts in linear profiles. The proposed method contains three networks and the efficacy of the model is assessed using average run length criterion.