Title :
Evolving a neural controller for a ball-and-beam system
Author :
Wang, Qing ; Mi, Man ; Ma, Guangfu ; Spronck, Peter
Author_Institution :
Harbin Inst. of Technol., China
Abstract :
This work presents an evolutionary controller design method for a ball-and-beam system. The method consists of a population of feedforward neural network controllers that evolve towards an optimal controller through the use of a genetic algorithm. The optimal controller is then applied to several different initial positions from which it has to balance the system. From the simulation results, we can conclude that the evolved neural controller can balance the system effectively.
Keywords :
control system synthesis; feedforward neural nets; genetic algorithms; neurocontrollers; nonlinear control systems; optimal control; ball-and-beam system; evolutionary controller design method; feedforward neural network controllers; genetic algorithm; optimal controller; Artificial neural networks; Backpropagation algorithms; Control systems; Design methodology; Equations; Feedforward neural networks; Genetic algorithms; Neural networks; Nonlinear control systems; Optimal control;
Conference_Titel :
Machine Learning and Cybernetics, 2004. Proceedings of 2004 International Conference on
Print_ISBN :
0-7803-8403-2
DOI :
10.1109/ICMLC.2004.1382286
