This paper proposes a Genetic Programming basedalgorithm that can be used to design optimalcontrollers. The proposed algorithm will be named aMultiple Basis Function Genetic Programming (MBFGP).Herein, the main ideas concerning the initialpopulation, the tree structure, genetic operations, andother proposed non-genetic operations are discussed indetails. An optimisation algorithm called numericconstant mutation is embedded to strengthen the searchfor the optimal solutions. The results of solving theoptimal control for linear as well as nonlinear systemsshow the feasibility and effectiveness of the proposedMBFGP as compared to the optimal solutions which arebased on numerical methods. Furthermore, this algorithmenriches the set of suboptimal state feedbackcontrollers to include controllers that have producttime-state terms.
CITATION STYLE
Maher, R. A., & Mohamed, M. J. (2013). An Enhanced Genetic Programming Algorithm for Optimal Controller Design. Intelligent Control and Automation, 04(01), 94–101. https://doi.org/10.4236/ica.2013.41013
Mendeley helps you to discover research relevant for your work.