Copyright (c) 2013 AJC
This work is licensed under a Creative Commons Attribution 4.0 International License.
Soft-Sensing Research on Ethylene Polymerization Based on PCA-SVR Algorithm
Corresponding Author(s) : J. Liang
Asian Journal of Chemistry,
Vol. 25 No. 9 (2013): Vol 25 Issue 9
Abstract
The important indices indicating product specifications and grades, melt index and density, can not be measured easily in gas phase ethylene polymerization reaction. Thus, a soft-sensing algorithm is proposed which mainly adopts the technique of support vector regression (SVR) to build prediction model. In this model, two important parameters, C and g are estimated through particle swarm optimization (PSO). Meanwhile, principal component analysis (PCA) is employed to extract features and by this preprocessing step the prediction accuracy can be improved to varying degree. The experiment results demonstrate that, compared with traditional neural network (NN) and single SVR methods, the proposed PCA-PSO-SVR model can achieve best results and is, hence, suitable for soft-sensing in similar processes.
Keywords
Download Citation
Endnote/Zotero/Mendeley (RIS)BibTeX
- M. Yang, B. Hu, Z.S. Fei, P.Y. Zheng and J. Liang, Chin. J. Sci. Instrum., 31, 481 (2010).
- L. Fortuna, S. Graziani and M.G. Xibilia, Control Eng. Practice, 13, 499 (2005).
- P. Ramasubramanian and A. Kannan, Soft Comput., 10, 699 (2006).
- J.B. Li and X.G. Liu, J. Appl. Polym. Sci., 119, 3093 (2011).
- Y.L. Wang, Y.D. Hu, G.D. Li and Q.S. Wei, Asian J. Chem., 19, 4512 (2007).
- L.J. Cao and F.E.H. Tay, IEEE Trans. Neural Networ., 14, 1506 (2003).
- J. Shi and X.G. Liu, J. Appl. Polym. Sci., 101, 285 (2006).
- E. Fataei, S.M. Monavari, A.H. Hasani, A.R. Karbasi and S.A. Mirbagheri, Asian J. Chem., 22, 2991 (2010).
- C.W. Hsu, C.C. Chang and C.J. Lin, A Practical Guide to Support Vector Classification, National Taiwan University, Taipei (2008).
- S. Yerel, Asian J. Chem., 21, 4054 (2009).
- J. Kennedy and R. Eberhart, In Proceedings of IEEE International Conference on Neural Networks: Particle Swarm Optimization, Perth, Australia, p. 1942 (1995).
- M. Clerc and J. Kennedy, IEEE Trans. Evolut. Comput., 6, 58 (2002).
- Y. Shi and R.C. Eberhart, In Proceedings of IEEE International Conference on Evolutionary Computation: A Modified Particle Swarm Optimizer, San Diego, p. 69 (1998).
- K.B. McAuley and J.F. MacGregor, AIChE J., 38, 1564 (1992).
- X. Bao and L.K. Dai, Asian J. Chem., 22, 4511 (2010).
References
M. Yang, B. Hu, Z.S. Fei, P.Y. Zheng and J. Liang, Chin. J. Sci. Instrum., 31, 481 (2010).
L. Fortuna, S. Graziani and M.G. Xibilia, Control Eng. Practice, 13, 499 (2005).
P. Ramasubramanian and A. Kannan, Soft Comput., 10, 699 (2006).
J.B. Li and X.G. Liu, J. Appl. Polym. Sci., 119, 3093 (2011).
Y.L. Wang, Y.D. Hu, G.D. Li and Q.S. Wei, Asian J. Chem., 19, 4512 (2007).
L.J. Cao and F.E.H. Tay, IEEE Trans. Neural Networ., 14, 1506 (2003).
J. Shi and X.G. Liu, J. Appl. Polym. Sci., 101, 285 (2006).
E. Fataei, S.M. Monavari, A.H. Hasani, A.R. Karbasi and S.A. Mirbagheri, Asian J. Chem., 22, 2991 (2010).
C.W. Hsu, C.C. Chang and C.J. Lin, A Practical Guide to Support Vector Classification, National Taiwan University, Taipei (2008).
S. Yerel, Asian J. Chem., 21, 4054 (2009).
J. Kennedy and R. Eberhart, In Proceedings of IEEE International Conference on Neural Networks: Particle Swarm Optimization, Perth, Australia, p. 1942 (1995).
M. Clerc and J. Kennedy, IEEE Trans. Evolut. Comput., 6, 58 (2002).
Y. Shi and R.C. Eberhart, In Proceedings of IEEE International Conference on Evolutionary Computation: A Modified Particle Swarm Optimizer, San Diego, p. 69 (1998).
K.B. McAuley and J.F. MacGregor, AIChE J., 38, 1564 (1992).
X. Bao and L.K. Dai, Asian J. Chem., 22, 4511 (2010).