Title :
Optimization of Neural Network Model Structures for Valve Stiction Modeling
Author :
Zabiri, H. ; Mazuki, N.
Author_Institution :
Chem. Eng. Dept., Univ. Teknol. PETRONAS, Tronoh, Malaysia
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. To help understand and study the behavior of sticky valve, several valve stiction models have been proposed in the literature. In this paper, a black box neural network-based modeling approach is proposed to model valve stiction. It is shown that with optimum model structures, performance of the developed NN stiction model is comparable to other established method.
Keywords :
neural nets; optimisation; pneumatic control equipment; stiction; valves; neural network model; optimization; valve stiction; Artificial neural networks; Chemical engineering; Chemical industry; Computer networks; Control systems; Friction; Mathematical model; Neural networks; Signal processing; Valves; Control valve stiction; modeling.; neural network;
Conference_Titel :
Signal Acquisition and Processing, 2009. ICSAP 2009. International Conference on
Conference_Location :
Kuala Lumpur
Print_ISBN :
978-0-7695-3594-4
DOI :
10.1109/ICSAP.2009.42