Title: IMC design based on SVM model of the batch reactor

Authors: S. Sujatha; N. Pappa

Addresses: Department of Instrumentation Engineering, Madras Institute of Technology, Anna University, Chennai-600044, Tamilnadu, India. ' Department of Instrumentation Engineering, Madras Institute of Technology, Anna University, Chennai-600044, Tamilnadu, India

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.

Keywords: support vector machines; SVM; internal model control; IMC; batch reactors; simulation; modelling; nonlinear processes; nonlinear control.

DOI: 10.1504/IJESMS.2011.043840

International Journal of Engineering Systems Modelling and Simulation, 2011 Vol.3 No.3/4, pp.140 - 147

Published online: 21 Mar 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article