On-Line Batch Process Monitoring Using Multiway Kernel Independent Component Analysis

  • Fei Liu
  • Zhong-Gai Zhao
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3973)


For on-line batch process monitoring, multiway principal component analysis (MPCA) is a useful tool. But the MPCA-based methods suffer two disadvantages: (i) it restricts itself to a linear setting, where high-order statistical information is discarded; (ii) all the measurement variables must follow Gaussian distribution and the objective of MPCA is only to decorrelate variables, but not to make them independent. To improve the ability of batch process monitoring, this paper proposes a monitoring method named multiway kernel independent component analysis (MKICA). By using kernel trick, the new monitoring indices are investigated, which have been mapped into high-dimensional feature space. On the benchmark simulator of fed-batch penicillin production, the presented method has been validated.


Batch Process Kernel Principal Component Analysis Kernel Trick Monitoring Index Nonlinear Principal Component Analysis 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Nomikos, P., MacGregor, J.: Multivariate SPC Chart for Monitoring Batch Processes. Technometrics 37(1), 41–59 (1995)MATHCrossRefGoogle Scholar
  2. 2.
    Nomikos, P., MacGregor, J.: Monitoring Batch Processes Using Multi-way Principal Component Analysis. AIChE J. 40(8), 1361–1375 (1994)CrossRefGoogle Scholar
  3. 3.
    Martin, E.B., Morris, A.J.: Non-parametric Confidence Bounds for Process Performance Monitoring Charts. Journal of Process Control 6(6), 349–358 (1996)CrossRefGoogle Scholar
  4. 4.
    Dong, D., McAvoy, T.J.: Nonlinear Principal Component Analysis Based on Principal Curves and Neural Networks. Computers and Chemical Engineering 20(1), 65–78 (1996)CrossRefGoogle Scholar
  5. 5.
    Schölkopf, B., Smola, A., Müller, K.R.: Nonlinear Component Analysis as a Kernel Eigenvalue Problem. Neural Computation 10(5), 1000–1016 (1998)CrossRefGoogle Scholar
  6. 6.
    Lee, J.M., Yoo, C.K., Lee, I.B.: Fault Detection of Batch Processes Using Multiway Kernel Principal Component Analysis. Computer and Chemical Engineering 28(9), 1837–1847 (2004)CrossRefMathSciNetGoogle Scholar
  7. 7.
    Yoo, C.K., Lee, J.M., et al.: On-line Monitoring of Batch Processes Using Multiway Independent Component Analysis. Chemometrics and Intelligent Laboratory Systems 71(2), 151–163 (2004)CrossRefMathSciNetGoogle Scholar
  8. 8.
    Yang, J., Gao, X., et al.: Kernel ICA: An Alternative Formulation and Its Application to Face Recognition. Pattern Recognition 38(10), 1784–1787 (2005)MATHCrossRefGoogle Scholar
  9. 9.
    Wold, S., Kettanhe, N., Friden, H., Holmberg, A.: Modelling and Diagnostics of Batch Processes and Analogous Kinetic Experiments. Chemometrics and Intelligent Laboratory Systems 44(2), 331–340 (1998)CrossRefGoogle Scholar
  10. 10.
    Cardosom, J.F., Soulomica, A.: Blind Beamforming for Non-Gaussian Signals. IEEE Proc. F. 140(6), 362–370 (1993)Google Scholar
  11. 11.
    Birol, G., Undey, C., Cinar, A.: A Modular Simulation Package for Fed-batch Fermentation: Penicillin Production. Computers and Chemical Engineering 26(11), 1553–1565 (2002)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Fei Liu
    • 1
  • Zhong-Gai Zhao
    • 1
  1. 1.Institute of AutomationSouthern Yangtze UniversityWuxiP.R. China

Personalised recommendations