Modified kernel Hebbian algorithm with application to modeling of hydro-dearomatization process

Huagong Xuebao/Journal of Chemical Industry and Engineering (China)

Volumn 58, Issue 6, 2007, Pages 1518-1522

  Wang, Haiqing ^a   Song, Zhihuan ^a   Li, Ping ^a  

^a STATE KEY LABORATORY OF INDUSTRIAL CONTROL TECHNOLOGY   (China)

Author keywords

Hebbian algorithm; Hydro dearomatization; Product quality modeling; Statistical learning theory

Indexed keywords

ALGORITHMS; CHEMICAL MODIFICATION; DIESEL FUELS; HYDROGENATION; MATHEMATICAL MODELS; QUALITY CONTROL;

HEBBIAN ALGORITHM; HYDRO-DEAROMATIZATION; PRODUCT QUALITY MODELING; STATISTICAL LEARNING THEORY;

AROMATIC COMPOUNDS;

EID: 34347209749     PISSN: 04381157     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Article

References (10)

1. Lin Shixiong. Petroleum Refinery Engineering. 3rd ed. Beijing: Petrochemical Engineering Publishing Company, 2000.
2. Duan Aijun, Wan Guofu, Zhao Zhen. Research advances in catalytic hydro-dearomatization of diesel fuel. Modern Chemical Industry, 2005, 25(3): 14-18.
3. Komulainen T, Sourander M, Jamsa-Jounela S-L. An online application of dynamic PES to a dearomatization process. Comput. Chem. Engng., 2004, 28(11): 2611-2619.
4. Liikala T. The use of fault detection in model predictive control of a refinery process unit[D]. Finland: Helsinki University of Technology, 2005.
5. Wang Haiqing, Song Zhihuan, Li Ping. Fault detection behavior and performance analysis of PCA-based process monitoring methods. Ind. Eng. Chem. Res., 2002, 41: 2455-2464.
6. Yeh T M. Huang C T. Estimate of process compositions and plantwide control from multiple secondary measurements using artificial neural networks. Comput. Chem. Engng., 2003, 27: 55-72.
7. Scholkopf B, Smola A J. Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. MA. The MIT Press, 2002.
8. Shawe-Taylor J, Cristianini N. Kernel Methods for Pattern Analysis. UK: Cambridge University Press, 2004.
9. Kim K I, Franz M, Scholkopf B. Iterative kernel principal component analysis for image modeling. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(9): 1351-1366.
10. Sanger T D. Optimal unsupervised learning in a single-layer linear feedforward neural netowork. Neural Networks, 1989, 12: 459-473.