Melt Index Predict by Radial Basis Function Network Based on Principal Component Analysis

  • Xinggao Liu
  • Zhengbing Yan
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4224)


Melt index is considered important quality variable determining product specifications. Reliable prediction of melt index (MI) is crucial in quality control of practical propylene polymerization processes. In this paper, a radial basis function network (RBF) model based on principal component analysis (PCA) and genetic algorithm (GA) is developed to infer the MI of polypropylene from other process variables. Considering that the genetic algorithm need long time to converge, chaotic series are explored to get more effective computation rate. The PCA-RBF model is also developed as a basis of comparison research. Brief outlines of the modeling procedure are presented, followed by the procedures for training and validating the model. The research results confirm the effectiveness of the presented methods.


Root Mean Square Error Radial Basis Function Receptive Field Radial Basis Function Network Back Propagation Neural Network 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bafna, S.S., Beall, A.M.: A design of experiments study on the factors affecting variability in the melt index measurement. J. Appl. Polym. Sci. 65(2), 277–288 (1997)CrossRefGoogle Scholar
  2. 2.
    Chan, W.-M., Nascimento, C.A.O.: Use of neural networks for modeling of olefin polymerization in high pressure tubular reactors. J. Appl. Polym. Sci. 53(10), 1277–1289 (2003)CrossRefGoogle Scholar
  3. 3.
    Kong, W., Yang, J.: Prediction of polypropylene melt index based on RBF networks. J. Chem. Ind. Eng (Chinese) 54(8), 1160–1163 (2003)Google Scholar
  4. 4.
    Shi, J., Liu, X.: Melt index prediction by neural soft-sensor based on multi-scale analysis and principal component analysis. Chinese J. Chem. Eng. 13(6), 849–852 (2005)Google Scholar
  5. 5.
    Moody, J., Darken, C.: Learning with localized receptive fields. In: Touretzky, D., Hinton, G., Sejnowski, T. (eds.) Proc. 1988 Connectionist Models Summer School, Carnegie Mellon University. Morgan Kaufmann Publishers, San Francisco (1988)Google Scholar
  6. 6.
    Moody, J., Darken, C.: Fast learning in networks of locally-tuned processing units. Neural Comp. 1, 281–294 (1989)CrossRefGoogle Scholar
  7. 7.
    Zheng, C., Jiao, L.: Automatic parameters selection for SVM based on GA. In: Proceedings of the 5th world congress on intelligent control and automation, Hangzhou, P.R. China (2004)Google Scholar
  8. 8.
    Lin, C.T., Jou, C.P.: Controlling chaos by GA-based reinforcement learning neural network. IEEE T. Neural Networ. 10(4), 846–859 (1999)CrossRefGoogle Scholar
  9. 9.
    Chen, S., Cowan, C.F.N., Grant, P.M.: Orthogonal least squares learning algorithm for radial basis function networks. IEEE T. Neural Networ. 2(2), 302–309 (1991)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Xinggao Liu
    • 1
  • Zhengbing Yan
    • 1
  1. 1.National Laboratory of Industrial Control Technology, Department of Control Science and EngineeringZhejiang UniversityHangzhouP.R. China

Personalised recommendations