Monitoring Profiles Based On Partial Linear Models

Quality of a process is characterized by the functional relationship between a response variable and one or more explanatory variables, such functional relationship is usually described by profile, monitoring such profiles is one of the hot research direction in the field of SPC. According to the advantage of semi-parametric models,we propose a novel scheme to monitor partial linear profiles based on multivariate exponentially weighted moving average procedure. The proposed scheme not only provides a more effective SPC solution to solve partial linear profiles than nonparametric profiles, but also resolves the latent problem in popular parametric monitoring methods of being unable to detect certain types if changes due to a misspecified, out-of-control model. Our simulation results compare our method with former in ARLs. In addition, a systematic diagnostic approach is provided to locate the change point of the process and identify the type of change in the profile. Finally, a power load example is used to illustrate the implementation of the proposed monitoring and diagnostic approach.