부분최소자승법을 이용한 공정변수의 예측에 관한 연구

Abstract

In this era of emerging technologies, model based monitoring and control methods have greatly facilitated the online prediction of quality variables of complex chemical processes. In chemical industries, efficient model based monitoring and control of process variables are essential industrial practices for reducing the amount of off-specification products and consequently for reducing the operation cost. Offline analytical measurement of the product quality variables often takes long time to control the process efficiently and this delay prevents the operator to make quick decisions in nonlinear and dynamic processes. Several soft Sensors have been developed through phenomenological, empirical and hybrid modeling and many techniques have been proposed for online adaptation of model parameters incorporated in various chemical processes. In this work a soft sensor based on an empirical model has been developed for the successful predictions of melt index (MI) in grade-changing polymerization of High Density Polyethylene (HDPE) process. In order to capture the nonlinearity and grade-changing characteristics of the polymerization process efficiently, a recursive partial least squares (PLS) update as well as a model bias update is applied to the process data successfully. Two schemes have been proposed: scheme-I and scheme-II. Scheme-I makes use of an arbitrary threshold value which selects one of the two update methods according to the process requirement at a certain updating instance so as to minimize the relative root mean squared error (RMSE). On the other hand, with the aim of preventing excessive PLS update, scheme-II minimizes the number of PLS update runs (NPR) while maintaining, increasing or sometimes reducing the RMSE obtained from scheme-I. Proposed schemes are compared with other strategies to exhibit their superiority.