Chapter 1 An integrated framework based on data driven techniques for process supervision

Document Type

Article

Publication Date

12-1-2006

Abstract

An integrated framework for process monitoring and supervision is proposed. Firstly, the data is freed from outliers using mean minimum distance clustering technique. A novel technique for unsupervised pattern classification is proposed. It is applied for simultaneous fault detection and diagnosis. A continuous pilot plant is used to check the efficiency of the proposed strategy. The result shows that the proposed framework can be used for process supervision of real time, non-linear systems. © 2006 Elsevier B.V. All rights reserved.

Publication Source (Journal or Book title)

Computer Aided Chemical Engineering

First Page

1401

Last Page

1406

This document is currently not available here.

Share

COinS