IMC design based on SVM model of the batch reactor. (28th November 2011)

• Record Type: Journal Article
• Authors: Sujatha, S.; Pappa, N.
• Is Part Of: International journal of engineering systems modelling and simulation. Volume 3:Number 3/4(2011)
• Page Start: 140
• Page End: 147
• Publication Date: 2011-11-28
• Subjects: support vector machine -- SVM -- internal model control -- IMC -- batch reactor; Engineering systems -- Computer simulation -- Periodicals; Engineering systems -- Mathematical models -- Periodicals; 620.0042
• Languages: English
• ISSNs: 1755-9758

Abstract

Currently, SVM is an active field in artificial intelligent technology and has been applied to pattern recognition, regression and signal processing applications. It refers to kernel-based methods; follow the simple, but powerful idea of non-linearity mapping input data into high-dimensional feature space. The batch reactors are the important unit of many industries; mostly, it is used in chemical and pharmaceutical industries. In this paper, the support vector machine is employed to identify the batch reactor. The simulation results show that support vector machine provides a new and effective method for modelling a non-linear process and has promising application in industrial process. A non-linear control strategy for a batch reactor process with input-output form is proposed. This strategy is termed as internal model control (IMC). IMC is found to be well suited for a system when there is no significant rate of change of the set point.