Nonlinear Constrained Principal Component Analysis in the Quality Control Framework
Many problems in industrial quality control involve n measurements on p process variables X n,p . Generally, we need to know how the quality characteristics of a product behavior as process variables change. Nevertheless, there may be two problems: the linear hypothesis is not always respected and q quality variables Y n,q are not measured frequently because of high costs. B-spline transformation remove nonlinear hypothesis while principal component analysis with linear constraints (CPCA) onto subspace spanned by column X matrix. Linking Y n,q q and X n,p variables gives us information on the Y n,q without expensive measurements and off-line analysis. Finally, there are few uncorrelated latent variables which contain the information about the Y n,q and may be monitored by multivariate control charts. The purpose of this paper is to show how the conjoint employment of different statistical methods, such as B-splines, Constrained PCA and multivariate control charts allow a better control on product or service quality by monitoring directly the process variables. The proposed approach is illustrated by the discussion of a real problem in an industrial process.
KeywordsPrincipal Component Analysis Process Variable Quality Characteristic Multivariate Linear Model Robust Principal Component Analysis
Unable to display preview. Download preview PDF.
- ABECASSIS, J., DURAND, J.F., MEOT, J.M., and VASSEUR, P. (1992): Etude non linéaire de l’influence des conditions de séchage sur la qualité des pâtes alimentaires par l’analysis en composantes principales par rapport à des variables instrumentales. Agro-Industrie et Methodes Statistiques, 3èmes Journees Europeennes.Google Scholar
- D’AMBRA, L., and LAURO, N. (1982): Analisi in componenti principali in rapporto ad un sottospazio di riferimento. Italian Journal of Applied Statistics, 1.Google Scholar
- EUBANK, R.L. (1988): Smoothing splines and non parametric regression. Markel Dekker and Bosel, N.Y.Google Scholar
- GROVE, D.M., WOODS, D.C., and LEWIS, S.M. (2004): Multifactor B-Spline Mixed Mod-els in Designed Experiments for the Engine Mapping Problem. Journal of Quality Tech-nology, 36, 4, 380-391.Google Scholar
- IZERNMAN, A.J. (1975): Reduced-rank regression for the multivariate linear model. Journal of Multivariate Analysis, 5.Google Scholar