Record Details

A fast training neural network and its updation for incipient fault detection and diagnosis

DSpace at IIT Bombay

View Archive Info
 
 
Field Value
 
Title A fast training neural network and its updation for incipient fault detection and diagnosis
 
Creator RENGASWAMY, R
VENKATASUBRAMANIAN, V
 
Subject neural network
fault detection and diagnosis
bayes classifier
 
Description Fast incipient fault diagnosis is becoming one of the key requirements for safe and optimal process operations. There has been considerable work done in this area with a variety of approaches being proposed for incipient fault detection and diagnosis (FDD). Incipient FDD problem is particularly difficult in the case of chemical processes as these processes are usually characterized by complex operations, high dimensionality and inherent nonlinearity. Neural networks have been shown to solve FDD problems in chemical processes as they develop inherently non-linear input-output maps and are well suited for high dimensionality problems. In this work, to enhance the neural network framework, we address the following three issues, (i) speed of training; (ii) introduction of time explicitly into the classifier design; and (iii) online updation using a mirror-like process model. (C) 2000 Elsevier Science Ltd. All rights reserved.
 
Publisher PERGAMON-ELSEVIER SCIENCE LTD
 
Date 2011-10-22T03:22:47Z
2011-12-15T09:10:41Z
2011-10-22T03:22:47Z
2011-12-15T09:10:41Z
2000
 
Type Article; Proceedings Paper
 
Identifier COMPUTERS & CHEMICAL ENGINEERING,24,431-437
0098-1354
http://dx.doi.org/10.1016/S0098-1354(00)00434-8
http://dspace.library.iitb.ac.in/xmlui/handle/10054/14808
http://hdl.handle.net/100/1598
 
Source 7th International Symposium on Process Systems Engineering,KEYSTONE, COLORADO,JUL 16-21, 2000
 
Language English