Robust Inferential Sensors Based on Ensemble of Predictors Generated by Genetic Programming

  • Elsa Jordaan
  • Arthur Kordon
  • Leo Chiang
  • Guido Smits
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3242)

Abstract

Inferential sensors are mathematical models used to predict the quality variables of industrial processes. One factor limiting the widespread use of soft sensors in the process industry is their inability to cope with non-constant noise in the data and process variability. A novel approach for inferential sensors design with increased robustness is proposed in the paper. It is based on three techniques. The first technique increases robustness by using explicit nonlinear functions derived by Genetic Programming. The second technique applies multi-objective model selection on a Pareto-front to guarantee the right balance between accuracy and complexity. The third technique uses ensembles of predictors for more consistent estimates and possible self-assessment capabilities. The increased robustness of the proposed sensor is demonstrated on a number of industrial applications.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Kordon, A., Smits, G.: Soft Sensor Development Using Genetic Programming. In: Proceedings of GECCO 2001, San Francisco, pp. 1346-1351 (2001) Google Scholar
  2. 2.
    Kalos, A., Kordon, A., Smits, G., Werkmeister, S.: Hybrid Model Development Methodology for Industrial Soft Sensors. In: Proceedings of the ACC 2003, Denver CO, pp. 5417–5422 (2003)Google Scholar
  3. 3.
    Kordon, A.K, Smits, G.F., Jordaan, E., Rightor, E.: Robust Soft Sensors Based on Integration of Genetic Programming, Analytical Neural Networks, and Support Vector Machines. In: Proceedings of WCCI 2002, Honolulu, pp. 896–901 (2002) Google Scholar
  4. 4.
    Sharkey, A. (ed.): Combining Neural Nets. Ensemble and Modular Multi-Net Systems. Springer, London (1999)MATHGoogle Scholar
  5. 5.
    Vapnik, V.: Statistical Learning Theory. Wiley, New York (1998)MATHGoogle Scholar
  6. 6.
    Deb, K.: Multi-Objective Optimization Using Evolutionary Algorithms. Wiley, Chichester (2001)MATHGoogle Scholar
  7. 7.
    Bleuer, S., Brack, M., Thiele, L., Zitzler, E.: Multi-Objective Genetic Programming. Reducing Bloat bt Using SPEA-2. In: Proceedings of CEC 2001, pp. 536–543 (2001)Google Scholar
  8. 8.
    Koza, J.: Genetic Programming. On the Programming of Computers by. MIT Press, Cambridge (1992)Google Scholar
  9. 9.
    Smits, G., Kotanchek, M.: Pareto-Front Exploitation in Symbolic Regression. In: Riolo, R., Worzel, B. (eds.) Genetic Programming Theory and Practice, Kluwer, Boston (2004) (in press)Google Scholar
  10. 10.
    Lennox, B., Montague, G., Frith, A., Gent, C., Bevan, V.: Industrial Applications of Neural Networks - An Investigation. Journal of Process Control 11, 497–507 (2001)CrossRefGoogle Scholar
  11. 11.
    Kordon, A., Jordaan, E., Chew, L., Smits, G., Bruck, T., Haney, K., Jenings, A.: Biomass Inferential Sensor Based on Ensemble of Models Generated by Genetic Programming. In: Deb, K., et al. (eds.) GECCO 2004. LNCS, vol. 3103, pp. 1078–1089. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  12. 12.
    Liu, Y., Yao, X., Higuchi, T.: Evolutionary Ensembles with Negative Correlation Learning. IEEE Transactions on Evolutionary Computation 4(4), 380–387 (2000)CrossRefGoogle Scholar
  13. 13.
    Imamura, K., Soule, T., Hechendorn, R., Foster, J.: Behavior Diversity and a Probabilistically Optimal GP Ensemble. Genetic Programming and Evolvable Machines 4, 235–253 (2003)CrossRefGoogle Scholar
  14. 14.
    Hodge D., Simon, L., Karim,M.: Data Driven Approaches to Modeling and Analysis of Bioprocesses. Some Industrial Examples. In: Proceedings of the ACC 2003, Denver, pp. 2062- 2076 (2003) Google Scholar
  15. 15.
    Cheruy, A.: Software Sensors in Bioprocess Engineering. Journal of Biotechnology 52, 193–199 (1997)CrossRefGoogle Scholar
  16. 16.
    Soule, T.: Heterogenesity and Specialization in Evolving Teams. In: Goldberg, D., Cantu- Paz, E., Parmee, I., Beyer, H.-G. (eds): Proceedings of GECCO 2000, Las Vegas (2000) Google Scholar
  17. 17.
    Brameier, M., Banszaf, W.: Evolving Teams of Predictors with Linear Genetic Programming. Genetic Programming and Evolvable Machines 2, 381–407 (2001)MATHCrossRefGoogle Scholar
  18. 18.
    Iba, H.: Bagging, Boosting, and Bloating in Genetic Programming. In: Proceedings of GECCO 1999 (1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Elsa Jordaan
    • 1
  • Arthur Kordon
    • 2
  • Leo Chiang
    • 2
  • Guido Smits
    • 1
  1. 1.Dow Benelux B.V.TerneuzenThe Netherlands
  2. 2.Dow ChemicalFreeportUSA

Personalised recommendations