Genetic control of a ball-beam system

M. A. Marra, B. E. Boling, B. L. Walcott

Research output: Contribution to conferencePaperpeer-review

10 Scopus citations


This study presents a method of adaptive system control based on genetic algorithms. The method consists of a population of controllers evolving towards an optimum controller through the use of probabilistic genetic operators. A brief overview of genetic algorithms is first given. The remainder of the paper identifies the problems associated with genetic algorithms controllers, and addresses the key issue of stability. A theoretical analysis of the genetic algorithm controller shows the population converges to stable controllers. The controller is then employed to optimize the regulation of a ball-beam system. The dynamics of the ball-beam and the results of computer simulations of the control system are given in support of the developed theory. The genetic algorithm controller is shown to optimize the regulation of the ball-beam system in with respect to an LQR performance index.

Original languageEnglish
Number of pages6
StatePublished - 1996
EventProceedings of the 1996 IEEE International Conference on Control Applications - Dearborn, MI, USA
Duration: Sep 15 1996Sep 18 1996


ConferenceProceedings of the 1996 IEEE International Conference on Control Applications
CityDearborn, MI, USA

ASJC Scopus subject areas

  • Control and Systems Engineering


Dive into the research topics of 'Genetic control of a ball-beam system'. Together they form a unique fingerprint.

Cite this