Korean Journal of Chemical Engineering

, Volume 17, Issue 4, pp 373–392 | Cite as

Applications of artificial neural networks in chemical engineering

Featured Review


A growing literature within the field of chemical engineering describing the use of artificial neural networks (ANN) has evolved for a diverse range of engineering applications such as fault detection, signal processing, process modeling, and control. Because ANN are nets of basis functions, they can provide good empirical models of complex nonlinear processes useful for a wide variety of purposes. This article describes certain types of neural networks that have proved to be effective in practical applications, mentions the advantages and disadvantages of using them, and presents four detailed chemical engineering applications. In the competitive field of modeling, ANN have secured a niche that now, after one decade, seems secure.

Key words

Artificial Neural Networks Control Data Rectification Fault Detection Modeling 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Barton, R., “Analysis and Rectification of Data from Dynamic Chemical Processes via Artificial Neural Networks,” Ph.D. Dissertation, Univ. of Texas, Austin, TX (1996).Google Scholar
  2. Billings, S. A. and Voon, W. S. F., “Correlation Based Model Validity Tests for Nonlinear Models,”Intl. J. Control,44, 235 (1986).CrossRefGoogle Scholar
  3. Baum, E. B. and Haussler, D., “What Size Net Gives Valid Generalization?,”Neural Comput.,1, 151 (1988).CrossRefGoogle Scholar
  4. Chen, S., Billings, S. A., Cowan, C. F. N. and Grant, P.M., “Nonlinear System Identification using Radial Basic Functions,”Intl. J. Systems Sci.,21, 2513 (1990).CrossRefGoogle Scholar
  5. Cybenko, G., “Approximation by Superpositions of a Sigmoidal Function,”Math. Control Signal Syst.,2, 303 (1987).CrossRefGoogle Scholar
  6. Draper, N., “Straight Line Regression when Both Variables are Subjects to Error,” Proceed. 1991 Kansas State Univ. Conf. Appld. Statistics in Agriculture, 1 (1991).Google Scholar
  7. Elman, J. L., “Finding Structure in Time,”Cognitive Science,14, 179 (1990).CrossRefGoogle Scholar
  8. Fiesler, E., “Handbook of Neural Computation,” Oxford Univ. Press, N.Y. (1996).Google Scholar
  9. Franke, R., “Convergence Properties of Radial Basis Functions,”Constr. Approx.,4, 243 (1988).CrossRefGoogle Scholar
  10. Fine, T. L., “Feed Forward Neural Network Methodology,” Springer, N.Y. (1999).Google Scholar
  11. Fukuoka, Y., Matsuki, H., Minamitani, H. and Iskida, A., “A Modified Backpropagation Method to Avoid False Local Minima,”Neural Networks,11, 1059 (1998).CrossRefGoogle Scholar
  12. Geman, S., Bienonstock, E. and Doursat, R., “Neural Networks and the Bias/Variance Dilema,”Neural Computation 4, 1 (1992).Google Scholar
  13. Hertz, J.A., Krogh, A. S. and Palmer, R.G., “Introduction to the Theory of Neural Computation,” Addison Wesley (1991).Google Scholar
  14. Jang, S. S., Joseph, B. and Mukai, H., “Comparison of Two Approaches to One-line Parameters and State Estimation of Nonlinear Systems,”Ind. Engng. Chem. Process Dev.,25, 809 (1986).CrossRefGoogle Scholar
  15. Kamruzzaman, J., Kumagai, Y. and Hikitu, H., “Study on Minimal Net Size, Convergence Behavior and Generalization Ability of Heterogeneous Backpropagation Network,”Artificial Neural Networks,2, 203 (1992).Google Scholar
  16. Karjala, T.W., “Dynamic Data Rectification via Recurrent Neural Networks,” Ph.D. Dissertation, Univ. of Texas, Austin, TX (1995).Google Scholar
  17. Kay, J.W. and Titterington, D.M., “Statistics and Neural Networks,” Oxford Univ. Press, Oxford (2000).Google Scholar
  18. Kim, I.W., Liebman, M. J. and Edgar, T. F., “Robust Error in Variables Estimation using Nonlinear Programming,”AIChE Journal,36, 405 (1990).Google Scholar
  19. Kulawski, G. J. and Brdys, N. A., “Stable Adaptive Control with Recurrent Networks,”Automatica,36, 5 (2000).CrossRefGoogle Scholar
  20. Lee, C. C., Chung, P. C., Tsai, J.-R. and Chang, C. I., “Robust Radial Basic Function Networks,”IEEE Trans. SMC-Part B, Cybernetics,29, 674 (1999).Google Scholar
  21. Lee, T. C., “Structure Level Adaptation for Artificial Neural Networks,” Kluwer Acad. Publ. (1991).Google Scholar
  22. Lippmann, R. P., “An Introduction to Computing with Neural Nets,”IEEE ASSP Magn,4, 4 (1987).Google Scholar
  23. Ljung, L., “System Identification, Theory for the User,” Prentice Hall (1987).Google Scholar
  24. Ljung, L. and Sjoberg, J., “A System Identification Perspective on Neural Nets,”Proceed. 1992 IEEE Workshop on Neural Nets for Signal Processing, IEEE (1992).Google Scholar
  25. MacMurray, J. C., “Modeling and Control of a Packed Distillation Column using Artificial Neural Networks,” M.S. Thesis, Univ. of Texas, Austin, TX (1993).Google Scholar
  26. Moody, J., “Prediction Risk and Architecture Selection for Neural Networks,” in From Statistics to Neural Networks, eds. V. Cherkassky, J. H. Friedman, and H. Wechsler, Springer Verlag, Berlin, 147 (1994).Google Scholar
  27. Patwardhan, A. A., “Modeling and Control of a Packed Distillation Column,” Ph.D. Dissertation, Univ. of Texas, Austin, TX (1991).Google Scholar
  28. Psichogious, D. and Unger, L., “A Hybrid Neural Network First Principles Approach to Process Modeling,”AIChE Journal,38, 1499 (1992).CrossRefGoogle Scholar
  29. Reed, R., “Pruning Algorithms-A Survey,”IEEE Trans. Neural Net.,4, 740 (1993).CrossRefGoogle Scholar
  30. Rumerhart, D. E. and McClelland, J. L., “Parallel Distributed Processing,” MIT Press,1 (1986).Google Scholar
  31. Seinfeld, J. H., “Optimal Stochastic Control of Nonlinear Systems,”AIChE J.,16, 1016 (1970).CrossRefGoogle Scholar
  32. Sjoberg, J. and Ljung, L., “Overtraining, Regularization, and Searching for a Minimum in Neural Networks,” in Proceed. IFAC Symp. Adaptive Systems in Control and Signal Processing, IFAC, 669 (1992).Google Scholar
  33. Soderstrom, T., “Identification of Stochastic Linear Systems in Presence of Input Noise,”Automatica,17, 713 (1981).CrossRefGoogle Scholar
  34. Suewatanakal, W., “A Comparison of Fault Detection and Classification using ANN with Traditional Methods,” Ph.D. Dissertation, Univ. of Texas, Austin, TX (1993).Google Scholar
  35. van de Laar, P. and Heskes, T., “Pruning Using Parameter and Neuronal Matrices,”Neural Computation,11, 977 (1999).CrossRefGoogle Scholar
  36. Werbos, P. J., “Backpropagation through Time: What it Does and How to Do It,”Proceed. IEEE,78, 1550 (1990).CrossRefGoogle Scholar

Copyright information

© Korean Institute of Chemical Engineering 2000

Authors and Affiliations

  1. 1.Department of Chemical EngineeringThe University of Texas AustinTexasUSA

Personalised recommendations