Logo

Quantification analysis for NLPCA-based stiction diagnostic tool

H., Zabiri and M., Ramasamy and I. S. Y., Teh (2009) Quantification analysis for NLPCA-based stiction diagnostic tool. In: Proceedings - International Conference on Advanced Computer Control, ICACC 2009 , 22 January 2009 through 24 January 2009, Singapore.

[img] PDF - Published Version
Restricted to Registered users only

259Kb

Official URL: http://www.scopus.com/record/display.url?origin=re...

Abstract

A significant number of control loops in process plants perform poorly due to control valve stiction. Stiction in control valves is the most common and long standing problem in industry, resulting in oscillations in process variables which subsequently lowers product quality and productivity. Developing a method to detect valve stiction in the early phase is imperative to avoid major disruptions to the plant operations. In this paper, nonlinear principal component analysis (NLPCA)-based stiction diagnostic tool is presented. Results from simulated case studies show that with proper quantification analysis, NLPCA shows a very promising capability for stiction diagnosis.

Item Type:Conference or Workshop Item (Paper)
Uncontrolled Keywords:Control loops; Control valves; Diagnostic tools; In controls; In process; Nonlinear principal component analysis; Plant operations; Product qualities; Quantification analysis; Standing problems Component; Control valve stiction, neural network, modeling
Subjects:T Technology > TP Chemical technology
Departments / MOR / COE:Departments > Chemical Engineering
ID Code:3738
Deposited By: Haslinda Zabiri
Deposited On:28 Dec 2010 07:03
Last Modified:19 Jan 2017 08:25

Repository Staff Only: item control page

Document Downloads

More statistics for this item...