Modelling of Industrial Processes using Natural Computation

  • A. P. de Weijer
Conference paper


The relatively new field of natural computation has already many useful applications. In this paper the use of multivariate statistics and natural computation to probe process-structure-property relationships is demonstrated. An application of multivariate statistics and natural computation to the relationships between process conditions, physical structure and the (thermo-)mechanical properties of poly(ethylene terephthalate) yarns illustrates their usefulness.


Genetic Algorithm Artificial Neural Network Physical Structure Ethylene Terephthalate Natural Computation 
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]
    A. Baines, F.P. Bradbury, and C.W. Suckling. Research in the chemical industry. Elsevier, New York, 1969.Google Scholar
  2. [2]
    C.B. Lucasius. Towards Genetic Algorithm Methodology in Chemometrics. PhD thesis, University of Nijmegen, Nijmegen, 1994.Google Scholar
  3. [3]
    J.R.M. Smits. Exploring the Possibilities of Applying Artificial Neural Networks on Problems in Analytical Chemistry. PhD thesis, University of Nijmegen, Nijmegen, 1993.Google Scholar
  4. [4]
    A.P. de Weijer. Process - Structure - Property Relationships Obtained with Natural Computation PhD thesis, University of Nijmegen, Nijmegen, in press.Google Scholar
  5. [5]
    E.V. Thomas. A primer on multivariate calibration. Anal. Chem., 66: 795A - 804A, 1994.CrossRefGoogle Scholar
  6. [6]
    A.K. Dewdney. 200% of Nothing. Wiley, New York, 1993.MATHGoogle Scholar
  7. [7]
    P.W. Atkins. Physical Chemistry. Oxford University Press, London, 1984.Google Scholar
  8. [8]
    A.P. de Weijer, L. Buydens, G. Kateman, and H.M. Heuvel. Neural networks used as a soft-modelling technique for quantitative description of the relation between physical structure and mechanical properties of poly(ethylene terephthalate) yarns. Chemom. Intell. Lab. Syst., 16: 77–86, 1992.CrossRefGoogle Scholar
  9. [91.
    A.P. de Weijer, C. Lucasius, L. Buydens, G. Kateman, and H.M. Heuvel. Using genetic algorithms for an artificial neural network inversion Chemom. Intell. Lab. Syst., 20: 45–55, 1993.CrossRefGoogle Scholar
  10. [10]
    J. Zupan and J. Gasteiger. Neural networks: a new method for solving chemical problems or just a passing phase. Anal.Chim.Acta, 248: 1–30, 1991.CrossRefGoogle Scholar
  11. [11]
    M.G. Northolt, A. Roos, and J.H. Kampschreur. Birefringence, compliance, and viscoelasticity of poly(ethylene terephthalate) fibers. J. Pol. Sci. Pol. Phys., 27: 1107–1120, 1989.CrossRefGoogle Scholar
  12. [12]
    D.W. van Krevelen. Properties of polymers. Elsevier, Amserdam, 1990.Google Scholar
  13. [13]
    D. Rummelhart, G. Hinton, and R. Williams. Learning representations by back-propagating errors. Nature, 323: 533–536, 1986.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Limited 1995

Authors and Affiliations

  • A. P. de Weijer
    • 1
  1. 1.Akzo Nobel Central ResearchArnhemThe Netherlands

Personalised recommendations