Title: Operator-based nonlinear fault detection and fault tolerant control for microreactor using one-class SVM
Authors: Yoshiki Ogihara; Mingcong Deng
Addresses: Department of Electrical and Electronic Engineering, The Graduate School of Engineering, Tokyo University of Agriculture and Technology, 2-24-16 Nakacho, Koganei, Tokyo, Japan ' Department of Electrical and Electronic Engineering, Tokyo University of Agriculture and Technology, 2-24-16 Nakacho, Koganei, Tokyo, Japan
Abstract: This paper proposes a method of nonlinear fault detection scheme using one-class support vector machine (SVM) and operator-based fault tolerant control system for a microreactor with Peltier device. This method requires only one-shot training data for the normal condition of the plant. The data is used to learn for the SVM, it realises nonlinear fault detection without the known fault condition of the plant. Also, the control system that consists of the nonlinear model of the microreactor system and operator-based controller designed by the model is introduced as the fault tolerant control system using compensation operator to remove the sensor fault. The usefulness of the method is shown by an experiment of the temperature sensor fault case for the temperature control system of the microreactor system.
Keywords: nonlinear control; fault detection; fault tolerant control; one-class classification; support vector machine; SVM.
International Journal of Advanced Mechatronic Systems, 2020 Vol.8 No.2/3, pp.109 - 115
Received: 22 Mar 2020
Accepted: 08 May 2020
Published online: 19 Nov 2020 *