Neural network modeling of valve stiction dynamics

被引：0
作者：
Zabiri, H. [1 ]
Sarnyudia, Y. [2 ]
Zainudin, W. N. W. M. [1 ]
机构：
[1] Univ Teknol PETRONAS, Tronoh 31750, Perak, Malaysia
[2] Curtin Univ Technol, Sarawak Campus, Malaysia
来源：
WCECS 2007: WORLD CONGRESS ON ENGINEERING AND COMPUTER SCIENCE | 2007年
关键词：
control valve stiction; neural network; modeling;
D O I：
暂无
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
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. In this paper, we present a new approach in control instability valve stiction modeling using Recurrent Neural-Network with NARX structure. It is shown that the performance of the developed model is comparable to other models reported in literature.
引用
收藏
页码：108 / +
页数：2
相关论文
共 12 条
[1]  
CATFOLIS T, 1996, P 8 INT C TOOL ART I
[2]  
CHOUDHURY MAA, CONTROL ENG PRACTICE, V13, P641
[3]  
CHOUDHURY MAA, 2005, IFAC WORLD C PRAH
[4]   Diagnosis of poor control-loop performance using higher-order statistics [J].
Choudhury, MAAS ;
Shah, SL ;
Thornhill, NF .
AUTOMATICA, 2004, 40 (10) :1719-1728
[5]  
Hagan M., 1996, Neural network design
[6]  
Kano M., 2004, P IFAC DYCOPS CAMBR
[7]  
KARIWALA V, 2004, P IEEE APC 2004 VANC
[8]  
LIN T, 1996, IEEE T NEURAL NETWOR, V7
[9]  
MULLER F, 1994, P SUMM COMP, P742
[10]  
RADHAKRISHNAN VR, 2006, INT C COMP PROC CONT
12