DocumentCode :
3514833
Title :
A novel approach for modeling cracking furnace severity
Author :
Zhuang, Xiaofeng ; Yu, Jinshou
Author_Institution :
Res. Inst. of Autom., East China Univ., Shanghai, China
Volume :
1
fYear :
2004
fDate :
15-19 June 2004
Firstpage :
250
Abstract :
Due to the strong nonlinear and dynamic behavior of the naphtha cracking furnace, the ordinary feed forward neural network was not suitable to model its severity index. Principal component analysis (PCA) method and dynamic neural network structure were therefore employed at this situation. The model was built on the industrial process data instead of simulation data, and the process operation condition selected for modeling cross over the normal operation range. Comparison with the models based on other algorithms was conducted. The relative parameters that affect the furnace severity were analyzed. The results show that the model based on this approach is suitable in a wide range of operation conditions, and can be used to supervise the process dynamic.
Keywords :
chemical industry; cracks; furnaces; principal component analysis; recurrent neural nets; PCA method; dynamic neural network structure; furnace severity index; industrial process data; naphtha cracking furnace modeling; principal component analysis; Automation; Coils; Feeds; Furnaces; Hydrocarbons; Laboratories; Neural networks; Principal component analysis; Robustness; Temperature;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Control and Automation, 2004. WCICA 2004. Fifth World Congress on
Print_ISBN :
0-7803-8273-0
Type :
conf
DOI :
10.1109/WCICA.2004.1340567
Filename :
1340567
Link To Document :
بازگشت