eprintid: 597
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/00/05/97
datestamp: 2023-11-09 15:48:44
lastmod: 2023-11-09 15:48:44
status_changed: 2023-11-09 15:22:47
type: conference_item
metadata_visibility: show
creators_name: Zabiri, H.
creators_name: Mazuki, N.
title: Robustness study on NARXSP-based stiction model
ispublished: pub
keywords: Component; Control valve stiction, neural network, modeling; Control valves; Equipment wear; In-control; Process industries; Product quality; Series-parallel; Stiction models, Recurrent neural networks; Robustness (control systems); Safety valves; Signal analysis; Signal processing; System stability, Stiction
note: cited By 0; Conference of 2009 International Conference on Signal Acquisition and Processing, ICSAP 2009 ; Conference Date: 3 April 2009 Through 5 April 2009; Conference Code:79615
abstract: Stiction is the most commonly found valve problem in the process industry. Valve stiction may cause oscillations in control loops which increases variability in product quality, accelerates equipment wear and tear, or leads to system instability. In this paper, a series-parallel Recurrent Neural Network (NARXSP)-based stiction model is developed and its robustness against the uncertainty in the stiction parameters is tested under various conditions. It is shown that the NARXSP-based stiction model is robust when the stiction is less than 6 of the valve travel span. © 2009 IEEE.
date: 2009
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-77950009735&doi=10.1109%2fICSAP.2009.43&partnerID=40&md5=66e924ab963b3df54bc2182fff05836a
id_number: 10.1109/ICSAP.2009.43
full_text_status: none
publication: 2009 International Conference on Signal Acquisition and Processing, ICSAP 2009
place_of_pub: Kuala Lumpur
pagerange: 184-188
refereed: TRUE
isbn: 9780769535944
citation:   Zabiri, H. and Mazuki, N.  (2009) Robustness study on NARXSP-based stiction model.  In: UNSPECIFIED.