VALVE STICTION DETECTION USING NLPCA

H., Zabiri and A. , Maulud and M. , Ramasamy and T. D. T. , Thao (2007) VALVE STICTION DETECTION USING NLPCA. In: PETRONAS APC Forum, 17-18 December 2007 , Kuala Lumpur, Malaysia.

[thumbnail of HaslindaZabiri_APCForum2007.pdf] PDF
HaslindaZabiri_APCForum2007.pdf - Published Version
Restricted to Registered users only

Download (696kB) | Request a copy

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), which is widely known for its capability in unravelling nonlinear correlations in process data, is extended to investigate control valve stiction problems. Results from simulated case studies show that NLPCA is a promising tool for valve stiction diagnosis.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Stiction detection, nonlinear principal component analysis
Subjects: T Technology > TP Chemical technology
Departments / MOR / COE: Departments > Chemical Engineering
Depositing User: Haslinda Zabiri
Date Deposited: 28 Dec 2010 07:05
Last Modified: 19 Jan 2017 08:27
URI: http://scholars.utp.edu.my/id/eprint/3757

Actions (login required)

View Item
View Item