Korean Journal of Chemical Engineering

, Volume 18, Issue 5, pp 623–629 | Cite as

A method of model validation for chaotic chemical reaction systems based on neural network



A chaotic system with measurable state variables fewer than the degrees of freedom of the system is identified with the Artificial Neural Network (ANN) method combined with dynamic training. Instead of using the usual method of Sum of Square Errors (SSE), the identified models are validated with the return maps (embedded trajectories), the largest Lyapunov exponent, and the correlation dimension when there is no exogenous input, and bifurcation diagram when there is an exogenous input. This method is demonstrated for nonisothermal, irreversible, first-order, series reaction A→ B → C in a CSTR.

Key words

Chaos Neural Network Dynamic Training System Identification Model Validation 



dimensionless concentrations of species A


dimensionless concentrations of species B


dimensionless temperature in the reactor


Damk ohler number


dimensionless activation energy


ratio of the two rate constants


ratio of activation energies


dimensionless adiabatic temperature rise


ratio of heat effects


dimensionless heat transfer coefficient


dimensionless coolant bath temperature


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Abarbanel, H. D. I., Brown, R., Sidorowich, J. J. and Tsimring, L. S., “The Analysis of Observed Chaotic Data in Physical Systems,”Rev. Mod. Phys.,65(4), 1331 (1993).CrossRefGoogle Scholar
  2. Adomaitis, R. A., Farber, R. M., Hudson, J. L., Kevrekidis, I. G., Kube, M. and Lapedes, A. S., “Application of Neural Nets to System Identification and Bifurcation Analysis of Real World Experimental Data,” In:Neural Networks: Biological computers or electronic brains, Springer Verlag, Paris, 87 (1990).Google Scholar
  3. Aguirre, L. A.and Billings, S. A., “Validating Identified Nonlinear Models with Chaotic Dynamics,”Int. J. Bifurcation and Chaos,4(1), 109 (1994).CrossRefGoogle Scholar
  4. Bhat, N. and McAvoy, T. J., “Use of Neural Nets for Dynamic Modeling and Control of Chemical Process Systems,”Comp. Chem. Eng.,14(4/5), 573 (1990).CrossRefGoogle Scholar
  5. Casdagli, M., “Nonlinear Prediction of Chaotic Time Series,”Physica D,35, 335 (1989).CrossRefGoogle Scholar
  6. Chang, K. S., Kim, J. Y. and Rhee, H. K., “Intricate CSTR Dynamic,”Korean J. Chem. Eng.,6, 69 (1989).CrossRefGoogle Scholar
  7. Chang, K. S., Kim, H. J. and Lee, J. S., “Process Systems Engineering and Chaos,”Chemical Industry and Technology,15, 2 (1997).Google Scholar
  8. Doedel, E. J. and Heinemann, R. F., “Numerical Computation of Periodic Solution Branches and Oscillatory Dynamics of the Stirred Tank Reactor with A→ B→ C Reactions,”Chem. Eng. Sci.,38(9), 1493 (1983).CrossRefGoogle Scholar
  9. Doedel, E. J., “AUTO: Software for Continuation and Bifurcation Problems in Ordinary Differential Equations,” AUTO 86 User Manual, CALTECH (1986).Google Scholar
  10. Elnashaie, S. S. E. H. and Abashar, M. E., “Chaotic Behavior of Periodically Forced Fluidized-Bed Catalytic Reactors with Consecutive Exothermic Chemical Reactions,”Chem. Eng. Sci.,49(15), 2483 (1994).CrossRefGoogle Scholar
  11. Elnashaie, S.S.E. H., Abashar, M. E. and Teymour, F. A., “Chaotic Behavior of Fludized-Bed Catalytic Reactors with Consecutive Exothermic Chemical Reactions,”Chem. Eng. Sci.,50(1), 49(1995).CrossRefGoogle Scholar
  12. Farmer, J. D., Ott, E. and Yorke, J. A., “The Dimensions of Chaotic Attractors,”Physica 7D, 153 (1983).Google Scholar
  13. Farr, W. W. and Aris, R., “Yet who would have thought the old man to have had so much blood in him?”reflections on the multiplicity of steady states of the stirred tank reactor,Chem. Eng. Sci.,41(6), 1385 (1986).CrossRefGoogle Scholar
  14. Giona, M., Lentini, F. and Cimagalli, V., “Functional Reconstruction and Local Prediction of Chaotic Time Series,”Phys. Rev. A,44, 3496 (1991).CrossRefGoogle Scholar
  15. Grassberger, P. and Procaccia, I., “Measuring the Strangeness of Strange Attractors,”Physica D,9, 189 (1983).CrossRefGoogle Scholar
  16. Grassberger, P., Schreiber, T. and Schaffrath, C., “Nonlinear Time Sequence Analysis,”Int. J. Bifurcation and Chaos,1(3), 521 (1991).CrossRefGoogle Scholar
  17. Hamer, J. W., Akramov, T. A. and Ray, W. H., “The Dynamic Behavior of Continuous Polymerization Reactors — II. Nonisothermal Solution Homopolymerization and Copolymerization in a CSTR,”Chem. Eng. Sci.,36(12), 1897 (1981)CrossRefGoogle Scholar
  18. Hénon, M., “On the Numerical Computation of Poincaré Maps,”Physica 5D, 412 (1982).Google Scholar
  19. Himmelblau, D. M., “Application of Artificial Neural Networks in Chemical Engineering,”Korean J. Chem. Eng.,17, 696 (2000).CrossRefGoogle Scholar
  20. Hussain, M. A., Kittisupakorn, P. and Kershenbaum, L., “The Use of a Partially Simulated Exothermic Reactor to Test Nonlinear Algorithms,”Korean J. Chem. Eng.,17, 373 (2000).CrossRefGoogle Scholar
  21. Jeong, E. Y., Oh, S. C. and Yeo, Y. K., “Application of Traveling Salesman Problem (TSP) for Decision of Optimal Production Sequence,”Korean J. Chem. Eng.,14, 416 (1997).CrossRefGoogle Scholar
  22. Jorgensen, D. V. and Aris, R., “On the Dynamics of a Stirred Tank with Consecutive Reactions,”Chem. Eng. Sci.,38(1), 45 (1983).CrossRefGoogle Scholar
  23. Kahlert, C., Rossler, O. E. and Varma, A., “Chaos in a Continuous Stirred Tank Reactor with Two Consecutive First-Order Reactions, One Exo-, One Endothermic,”Springer Ser. Chem. Phys.,18, 355 (1981).Google Scholar
  24. Kang, Y., Woo, K. J., Ko, M. H., Cho, Y. J. and Kim, S. D., “Particle Flow Behavior in Three-Phase Fluidized Beds,”Korean J. Chem. Eng.,16, 784 (1999).CrossRefGoogle Scholar
  25. Kim, H. J., Lee, J. S., Han, C. and Chang, K. S., “Chaos and Fractals in Process Systems Engineering,” Proceedings of the fortyfirst annual meeting of the ISSS, Seoul (1997).Google Scholar
  26. Kim, H. J., “Identification and Validation of Neural Network Models for Chaotic Chemical Reaction Systems,” M. S. Thesis, Pohang University of Science and Technology, Korea (1998).Google Scholar
  27. Kim, H. J. and Chang, K. S., “Hybrid Neural Network Approach in Description and Prediction of Dynamic Behavior of Chaotic Chemical Reaction Systems,”Korean J. Chem. Eng.,17, 696 (2000).CrossRefGoogle Scholar
  28. Kim, S. H. and Han, G. Y., “An Analysis of Pressure Drop Fluctuation in a Circulating Fluidized Bed’,’Korean J. Chem. Eng.,16, 677 (1999).CrossRefGoogle Scholar
  29. Liu, J., Min, K., Han, C. and Chang, K. S., “Robust Nonlinear PLS Based on Neural Networks and Application to Composition Estimator for High-Purity Distillation Columns,”Korean J. Chem. Eng.,17, 184 (2000).CrossRefGoogle Scholar
  30. Lynch, D. T., “Chaotic Behavior of Reaction Systems: Parallel Cubic Autocatalators,”Chem. Eng. Sci.,47(2), 347 (1992).CrossRefGoogle Scholar
  31. Lynch, D. T., “Chaotic Behavior of Reaction Systems: Mixed Cubic and Quadratic Autocatalysis,”Chem. Eng. Sci.,47(17/18), 4435 (1992).CrossRefGoogle Scholar
  32. Lynch, D. T., “Chaotic Behavior of Reaction Systems: Consecutive Quadratic/Cubic Autocatalysis via Intermediates,”Chem. Eng. Sci.,48(11), 2103 (1993).CrossRefGoogle Scholar
  33. Mankin, J. C. and Hudson, J. L., “Oscillatory and Chaotic Behavior of a Forced Exothermic Chemical Reaction,”Chem. Eng. Sci.,39(12), 1807 (1984).CrossRefGoogle Scholar
  34. Mankin, J. C. and Hudson, J. L., “The Dynamics of Coupled Nonisothermal Continuous Stirred Tank Reactors,”Chem. Eng. Sci.,41(10), 2651 (1986).CrossRefGoogle Scholar
  35. Packard, N. H., Crutchfield, J. P., Farmer, J. D. and Shaw, R. S., “Geometry from a Time Series,”Phys. Rev. Lett.,45(9), 712 (1980).CrossRefGoogle Scholar
  36. Park, J., Kim, J., Cho, S. H., Han, K. H., Yi, C. K. and Jin, G. T., “Development of Sorbent Manufacturing Technology by Agitation Fluidized Bed Granulator (AFBG),”Korean J. Chem. Eng.,16, 659 (1999).CrossRefGoogle Scholar
  37. Parker, T. S. and Chua, L. O., “Practical Numerical Algorithms for Chaotic Systems,” Springer-Verlag (1989).Google Scholar
  38. Pinto, J. C. and Ray, W. H., “The Dynamic Behavior of Continuous Solution Polymerization Reactors-VU. Experimental Study of a Copolymerization Reactor,”Chem. Eng. Sci.,50(4), 715 (1995).CrossRefGoogle Scholar
  39. Pinto, J. C. and Ray, W. H., “The Dynamic Behavior of Continuous Solution Polymerization Reactors-VIII. A Full Bifurcation Analysis of a Lab-Scale Copolymerization Reactor,”Chem. Eng. Sci.,50(6), 1041 (1995).CrossRefGoogle Scholar
  40. Pinto, J. C. and Ray, W. H., “The Dynamic Behavior of Continuous Solution Polymerization Reactors-IX. Effects of Inhibition,”Chem. Eng. Sci.,51(1), 63 (1996).CrossRefGoogle Scholar
  41. Principe, J. G., Rathie, A. and Kuo, J. M., “Prediction of Chaotic Time Series with Neural Networks and the Issue of Dynamic Modeling,”Int. J. Bifurcation and Chaos,2(4), 989 (1992).CrossRefGoogle Scholar
  42. Roux, J. C., Simoyi, R. H. and Swinney, H. L., “Observation of a Strange Attractor,”Physica 8D, 257 (1983).Google Scholar
  43. Sauer, T., Yorke, J. A. and Casdagli, M., “Embedology,”J. Stat. Phys.,65(3/4), 579 (1991).CrossRefGoogle Scholar
  44. Sauer, T., and Yorke, J. A., “How Many Delay Coordinates Do You Need?,”Int. J. Bifurcation and Chaos,3(3), 737 (1993).CrossRefGoogle Scholar
  45. Schmidt, A. D. and Ray, W. H., “The Dynamic Behavior of Continuous Polymerization Reactors -I. Isothermal Solution Polymerization in a CSTR,”Chem. Eng. Sci.,36, 1401 (1981).CrossRefGoogle Scholar
  46. Schmidt, A. D., Clinch, A. B., and Ray, W. H., “The Dynamic Behavior of Continuous Polymerization Reactors — III. An Experimental Study of Multiple Steady States in Solution Polymerization,”Chem. Eng. Sci.,39(3), 419 (1984).CrossRefGoogle Scholar
  47. Seydel, R., “From Equilibrium to Chaos: Practical Bifurcation and Stability Analysis,” Elsevier, New York (1988).Google Scholar
  48. Sohn, S. H., Oh, S. C. and Yeo, Y. K., “Prediction of Air Pollutants by Using an Artificial Neural Network,”Korean J. Chem. Eng.,16, 382 (2000).CrossRefGoogle Scholar
  49. Takens, F., “Detecting Strange Attractors in Turbulence,” in Lecture Notes in Mathematics, vol. 898 eds. Rand, D. A. and Young, L. S., Dynamical Systems and Turbulence, Springer Verlag, Berlin, 366 (1981).Google Scholar
  50. Teymour, F. andRay, W. H., “The Dynamic Behavior of Continuous Solution Polymerization Reactors-IV. Dynamic Stability and Bifurcation Analysis of an Experimental Reactor,”Chem. Eng. Sci.,44(9), 1967 (1989).CrossRefGoogle Scholar
  51. Teymour, F. and Ray, W. H., “The Dynamic Behavior of Continuous Polymerization Reactors-V. Experimental Investigation of Limit-Cycle Behavior for Vinyl Acetate Polymerization,”Chem. Eng. Sci.,47(15/16), 4121 (1992).CrossRefGoogle Scholar
  52. Teymour, F. and Ray, W. H., “The Dynamic Behavior of Continuous Polymerization Reactors-VI. Complex Dynamics in Full-Scale Reactors,”Chem. Eng. Sci.,47(15/16), 4133 (1992).CrossRefGoogle Scholar
  53. Wang, Y. and Hudson, J. L., “Effect of Electrode Surface Area on Chaotic Attractor Dimensions,”AIChE J.,37(12), 1833 (1991).CrossRefGoogle Scholar
  54. Wolf, A., Swift, J. B., Swinney, H. L. and Vastano, J. A., “Determining Lyapunov Exponents from a Time Series,”Physica 16D, 285 (1985).Google Scholar

Copyright information

© Korean Institute of Chemical Engineering 2001

Authors and Affiliations

  1. 1.Department of Chemical Engineering and Automation Research CenterPohang University of Science and TechnologyPohangKorea

Personalised recommendations