G.A. Optimisation of PID Controllers — Optimal Fitness Functions

  • D. Drabble
  • P. V. S. Ponnapalli
  • M. Thomson
Part of the Advances in Soft Computing book series (AINSC, volume 9)


Genetic Algorithms (GAs) have been in many cases successfully applied to a wide variety of optimisation problems. The work described here focuses on the application of genetic algorithms to the optimisation of linear & non-linear PID controllers. The techniques used here are based around the formulation of a suitable objective function, which, as part of the GA evaluates the fitness of a given PID parameter set. The proposed objective function is based directly on performance criteria specified in terms of the rise time, settling time and peak overshoot of a physical system. The functions are evaluated via a set of trials on a range of systems with varying dynamics and the success rate determined by comparison with sets of target step response characteristics. The results show that the objective function is more robust than ISE based methods in the optimisation of multiple step response objectives, having a low deviation from the target across the range of parameters (rise time, settling time & peak overshoot).


Step Response Integral Square Error Proposed Objective Function Peak Overshoot Suitable Objective Function 
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.
    Vlachos, C., Williams, D., & Gomm, J.B.: Genetic approach to decentralised PI controller tuning for multivariable processes. IEE Proc. — Control Theory Appl., Vol. 146, No. 1 (1999), pp. 58–64.CrossRefGoogle Scholar
  2. 2.
    Porter, B., Jones, A.H.: Genetic tuning of digital PID controllers. Electronics Letters, Vol. 28, No. 9 (1992), pp. 843–844.CrossRefGoogle Scholar
  3. 3.
    Muffler, A., Li, Y., Ng, K.C., Murray-Smith, D.J., & Sharman, K.C.: Neurocontrollers designed by a genetic algorithm. GALESIA ‘95, IEE Conf. Pub. 414 (1995), pp. 536–542.Google Scholar
  4. 4.
    Krohling, R. — Design of PID Controller for Disturbance Rejection: A Genetic Optimization Approach. IEE Intl. Conf. GALESIA (1997), pp.498–503..Google Scholar
  5. 5.
    Chipperfield, A.J., Fleming, P.J. (Eds.) — MATLAB Toolboxes and applications for control. Peter Peregrinus Ltd. (1993), pp. 139–144.Google Scholar
  6. 6.
    Goldberg, D.: Genetic Algorithms in Search, Optimisation and Machine Learning. (1989) Addison-Wesley Publishing, Inc.MATHGoogle Scholar
  7. 7.
    Kawabe, T., Tagami, T., & Katayama, T.: A genetic algorithm based minimax optimal design of robust I-PD controller. UKACC Intnl. Conf. On Control (1996), IEE Pub. 427, pp. 436–441.Google Scholar
  8. 8.
    Astrom, K.J.,Hägglund, T.: Automatic tuning of PID controllers. Research Triangle Park, N.C.: Instrument Society of America (1988).Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • D. Drabble
    • 1
  • P. V. S. Ponnapalli
    • 1
  • M. Thomson
    • 1
  1. 1.Control Systems Research Group, Department of Engineering & TechnologyManchester Metropolitan UniversityManchesterUK

Personalised recommendations