DocumentCode
383282
Title
Hybrid intelligent systems for industrial data analysis
Author
Kordon, Arthur K.
Author_Institution
Dow Chem. Co., Freeport, TX, USA
Volume
1
fYear
2002
fDate
2002
Firstpage
10
Abstract
A novel approach for industrial data analysis based on integration of three key computational intelligence approaches (genetic programming, analytical neural networks, and support vector machines) is proposed. The developed empirical models have good generalization capabilities, explicit input/output relationships,. self-assessment capabilities, and low implementation and maintenance cost. The proposed approach has been implemented in several industrial applications in The Dow Chemical Company.
Keywords
genetic algorithms; intelligent control; learning automata; neural nets; analytical neural networks; computational intelligence approaches; explicit input/output relationships; genetic programming; hybrid intelligent systems; industrial data analysis; inferential sensors; neural networks; self-assessment capabilities; support vector machines; Chemical industry; Computational intelligence; Computer industry; Costs; Data analysis; Genetic programming; Hybrid intelligent systems; Industrial relations; Neural networks; Support vector machines;
fLanguage
English
Publisher
ieee
Conference_Titel
Intelligent Systems, 2002. Proceedings. 2002 First International IEEE Symposium
Print_ISBN
0-7803-7134-8
Type
conf
DOI
10.1109/IS.2002.1044221
Filename
1044221
Link To Document