Premium
Diagnosis of Impurity Levels in a Copolymerization Process
Author(s) -
Lou Shijin,
Duever Thomas A.,
Budman Hector M.
Publication year - 2005
Publication title -
macromolecular theory and simulations
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.37
H-Index - 56
eISSN - 1521-3919
pISSN - 1022-1344
DOI - 10.1002/mats.200400074
Subject(s) - observability , computer science , fault (geology) , design of experiments , fuzzy logic , artificial intelligence , boundary (topology) , algorithm , machine learning , mathematics , statistics , mathematical analysis , seismology , geology
Abstract Summary: This work investigates a fault diagnosis problem in the copolymerization process of styrene and methyl methacrylate (STY/MMA). Two topics are discussed in this paper: the system observability and optimal experimental design (OED) to reduce fault misclassification. Lack of observability has been found to be one of the major causes of misclassification in fault diagnosis, which is not remediable by any means other than including the right measurements necessary for the observability. In this work, the system observability has been studied through simulation analysis. Then, two new experimental design methods are proposed to train the projection pursuit regression (PPR) algorithm for fault diagnosis purpose. The new design methods, referred to as Gaussian probability design and Fuzzy boundary design, are compared to a conventional factorial design, to evaluate their performance for the problem under study. The Gaussian probability design is based on the calculation of the probability of an experimental data point near a class boundary belonging to a specific class. The Fuzzy boundary design is based on a bootstrapping technique used in part for the learning process in developing neural network models. It investigates the insufficiency of training data based on the identification of class boundaries by a group of models, such as PPR models. Both Gaussian probability design and Fuzzy boundary design methods automatically search for the sparseness of the training data, and provide guidelines to include pairs of training data on two sides of a class boundary in the areas where the data density is the lowest. The proposed design methods outperform a conventional factorial design by reducing the fault misclassification more effectively with the same amount of additional training data.Testing data in the process measurement space of temperature vs. conversion.