Skip to main content
Log in

Nonlinear decoupling PID control using neural networks and multiple models

  • Published:
Journal of Control Theory and Applications Aims and scope Submit manuscript

Abstract

For a class of complex industrial processes with strong nonlinearity, serious coupling and uncertainty, a nonlinear decoupling proportional-integral-differential (PID) controller is proposed, which consists of a traditional PID controller, a decoupling compensator and a feedforward compensator for the unmodeled dynamics. The parameters of such controller is selected based on the generalized minimum variance control law. The unmodeled dynamics is estimated and compensated by neural networks, a switching mechanism is introduced to improve tracking performance, then a nonlinear decoupling PID control algorithm is proposed. All signals in such switching system are globally bounded and the tracking error is convergent. Simulations show effectiveness of the algorithm.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. F. G. Shinskey. Process Control Systems[M]. 2nd ed. New York: McGraw-Hill Book Company, 1979.

    Google Scholar 

  2. P. E. McDermott, D. A. Mellichamp. A decoupling pole placement self-tuning controller for a class of multivariable process[J]. Optimal Control Applications and Methods, 1986, 7(1): 55–79.

    Google Scholar 

  3. S. J. Lang, X. Y. Gu and T. Y. Chai. A multivariable generalized self-tuning controller with decoupling design[J]. IEEE Trans. on Automatic Control, 1986, 31(5): 474–477.

    Article  Google Scholar 

  4. T. Y. Chai. Direct adaptive decoupling control for general stochastic multivariable systems[J]. Int. J. of Control, 1990, 51(4):885–909.

    Google Scholar 

  5. K. Y. Zhu, X. F. Qin, T. Y. Chai. A new decoupling design of self-tuning multivariable generalized predictive control[J]. Int. J. of Adaptive Control, 1999, 13(3): 183–196.

    Article  MathSciNet  Google Scholar 

  6. T. Y. Chai, L. F. Zhai and H. Yue. Nonlinear multivariable decoupling control using neural networks and application[M]// Advanced Robust and Adaptive Control —Theory and Applications. Beijing: Springer-Tsinghua University Press, 2005: 209–223.

    Google Scholar 

  7. T. Y. Chai, H. Yue, L. F. Zhai. Intelligent decoupling control system of complex industrial process and application[C]// Preprints of the 16th IFAC World Congress. Prague, Czech: Elsevier, 2005, Tu-A09-TO/4.

    Google Scholar 

  8. K. J. Åström, T. Hägglund, C. C. Hang, W. K. Ho. Automatic tuning and adaptation for PID controllers—A Survey[J]. Control Engineering Practice, 1993, 1(4): 699–714.

    Article  Google Scholar 

  9. H. X. Wu, S. P. Shen. Basis of theory and applications on PID control[J]. Control Engineering of China, 2003, 10(1): 37–42.

    Google Scholar 

  10. S. S. Ge, C. C. Hang, T. H. Lee, T. Zhang. Stable Adaptive Neural Network Control[M]. Norwell, Massachusetts: Kluwer, 2001.

    Google Scholar 

  11. L. J. Chen, K.S. Narendra. Nonlinear adaptive control using neural networks and multiple models[J]. Automatica, 2001, 37(8): 1245–1255.

    Article  MathSciNet  Google Scholar 

  12. G. C. Goodwin, P. J. Ramadge, P. E. Caines. Discrete-time multivariable adaptive control[J]. IEEE Trans. on Automatic Control, 1980, 25(3): 449–456.

    Article  MathSciNet  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Additional information

This paper is supported by the National Foundamental Research Program of China (No. 2002CB312201), the State Key Program of National Natural Science of China (No. 60534010), the Funds for Creative Research Groups of China (No. 60521003), and Program for Changjiang Scholars and Innovative Research Team in University (No. IRT0421).

Lianfei ZHAI was born in Pingdingshan, Henan Province, P.R. China in 1981. She received the B.E. in the Department of Automatic Control in 2002, from Zhengzhou University. She is currently a Ph.D. student of Northeastern University. Her research interests include decoupling control and its application, adaptive nonlinear control and neural network control.

Tianyou CHAI is a member of Chinese Engineering Academy. He received doctor degree of Northeastern University in 1985. Now he is the director of State Research Center for Metallurgical Automation Technology, and the professor and Ph.D. supervisor of Northeastern University. His research interests are adaptive control, intelligent control, and integrated automation of industrial processes.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Zhai, L., Chai, T. Nonlinear decoupling PID control using neural networks and multiple models. J. Control Theory Appl. 4, 62–69 (2006). https://doi.org/10.1007/s11768-006-5260-7

Download citation

  • Received:

  • Revised:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11768-006-5260-7

Keywords

Navigation