Self-Tuning PID Control

  • Mohammad Teshnehlab
  • Keigo Watanabe
Part of the International Series on Microprocessor-Based and Intelligent Systems Engineering book series (ISCA, volume 19)


Recently, there has been much emphasis on increasing the learning capability and structural flexibility of neural networks (NNs). Optimization or self-tuning is often required for designs, planning of actions, motions and tasks In most cases, the ordinary control theory can not be easily applied, specially for real-time application which is affected by uncertain parameters and environment factors. An effective method to overcome this problem is to find the optimal or suboptimal solution by defining cost function and using NNs with parallel learning, and on-line processing, together with flexibility in structure, to operate in a way to minimize the cost function. Self-tuning control algorithms lack an intelligent ability to choose time varying parameters. It has been shown that the application of optimal approaches makes effective utilization of NNs for sensory, recognitory, and forecasting capabilities necessary in the robotic control. There are many examples of applications of optimization problems in literature [1]–[3]. From this chapter, we describe several learning models for NNs as controllers.


Momentum Coefficient IEEE Control System Magazine Main Tank Plus Integral Plus Derivative 
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]
    T. Shibata and T. Fukuda, “Neuromorphic control for robotic manipulators, position, force and impact control,” Proc. of Fifth IEEE International Symposium on Intelligent Control, Philadelphia, USA, pp. 310–315, 1990.Google Scholar
  2. [2]
    P. P. Chu, “Using a Semi-asynchronous hopfield network to obtain optimal converge in logic minimization,” Proc. of IJCNN’91-Seattle, Vol. 1, pp. 141146, 1991.Google Scholar
  3. [3]
    G. Fanner, “An algorithm-structured neural net for the shortest-path problem,” Proc. of IJCNN’91-Seattle, Vol. 1, pp. 153–158, 1991.Google Scholar
  4. [4]
    D. Psaltis, A. Sideris, and A.A. Yamamura, “A Multilayered neural network controller,” IEEE Control Systems Magazine, pp. 17–20, April 1988.Google Scholar
  5. [5]
    K. J. Astrom, T. Hagglund, “Automatic tuning of PID controllers,” ISA, Research triangle park, NC, USA, 1988.Google Scholar
  6. [6]
    K. J. Astrom, C. C. Hang and P. Person, “Heuristics for assessment of PID control with Ziegler-Nichols tuning,” Report, Coden: LUTFD2/TFRT-7404, Department of automatic control, Lund institute of technology, Lund, Sweden, 1988.Google Scholar
  7. [7]
    K. J. Astrom, C. C. Hang, P. Person and Persson, “Towards intelligent PID control,” Automatica, Vol. 28, No. 1, pp. 1–9, 1992.CrossRefGoogle Scholar
  8. [8]
    N. V. Bhat, P. A. Minderman, Jr. T. McAvoy, and N. S. Wang, “Modeling chemical process systems via neural computation,” IEEE Control Systems Magazine, pp. 24–30, April 1990.Google Scholar
  9. [9]
    T. McAvoy, N. Wang, S. Naidu, and N Bhat, “Use of neural nets for interpreting biosensor data,” Proc. Joint Conf. Neural Networks, Washington DC, pp. 1227–1233, June 1989.Google Scholar
  10. [10]
    K. Marzuki and S. Omatu, “Neural network controller for a temperature control system,” IEEE Control Systems Magazine, pp. 58–64, June 1992.Google Scholar
  11. [11]
    J. G. Ziegler and B. Nichols, “Optimal setting for automatic controllers,” Trans. ASME, Vol. 64, pp. 759–768, 1942.Google Scholar
  12. [12]
    M. Kawato, Y. Uno, M. Isobe and R. Suzuki, “A Hierarchical model for voluntary movement and its application to robotics,” Proc. of IEEE Inter. Conf. on Network, Vol. IV, pp. 573–582, 1987.Google Scholar
  13. [13]
    D. W. Clark and P. J. Gawthrop, “Self-tuning controller,” Proc. Inst. Elec. Eng., Vol. 122, No. 9, pp. 929–934, 1975.CrossRefGoogle Scholar
  14. [14]
    D. W. Clark and P. J. Gawthrop, “Self-tuning control,” Proc. Inst. Elec. Eng., Vol. 126, No. 6, pp. 633–639, 1979.CrossRefGoogle Scholar
  15. [15]
    T. W. Kraus and T. J. Myron, “Self-tuning PID controller uses pattern recognition approach,” Control Eng., pp. 106–111, June 1984.Google Scholar
  16. [16]
    C. C. Hang, C. C. Lim, and S. H. Soon, “A new PID auto-tuner design based on correlation technique,” Proc. 2nd Multinational Instrumentation Conf., Peoples Republic of China, 1986.Google Scholar
  17. [17]
    T. Hagglund and K. J. Astrom, “Automatic tuning of PID controllers based on dominant pole design,” Proc. of IFAC Conference on Adaptive Control pf Chemical Processes, Frankfurt, Germany, 1985.Google Scholar
  18. [18]
    D. E. Rumelhart, G. E. Hinton and R. J. Williams, “Learning internal representations by error propagation,” in Parallel Distributed Processing: Explorations in the Microstructure of Cognition, D. E. Rumelhart, and J. L. McClelland, Eds., Cambridge, MA: MIT Press, Vol. 1, pp. 318–362, 1986.Google Scholar
  19. [19]
    W. Pitts and W. S. McCulloch, “How we know universals: the perception of auditory and visual forms,” Bulletin of Mathematical Biophysics, Vol. 9, pp. 127–147, 1947.CrossRefGoogle Scholar
  20. [20]
    R. W. Swiniarski, “Neuromorphic self-tuning PID controller uses pattern recognition approach,” Proceeding of the 7th Internal Conference of Systems Engineering, pp. 18–20, July 1990.Google Scholar
  21. [21]
    M. Teshnehlab and K. Watanabe, “Neural networks-based self-tuning controller using the learning of SFs,” IEEE/ Nagoya University World Wisemen Women Workshop (WWW), pp. 31–38, Oct. 1993.Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 1999

Authors and Affiliations

  • Mohammad Teshnehlab
    • 1
  • Keigo Watanabe
    • 2
  1. 1.Faculty of Electrical EngineeringK.N. Toosi UniversityTehranIran
  2. 2.Department of Mechanical EngineeringSaga UniversityJapan

Personalised recommendations