Título: Algoritmo Genético Híbrido Aplicado à Otimização de um Controlador com Escalonamento de Ganhos
Autores: Moedinger, Luis Henrique; Coelho, Leandro dos Santos
Resumo: This paper presents the optimization of a gain scheduling controller based on Lamarckian evolution. The evolutionary theory advocated by Lamarck focuses on the inheritance of characteristics acquired for self-adaptation to environment. In the domain of the purpose of acquiring adaptive strategies, it is important to make use of the information of experiences through adaptation. The Lamarckian evolution approach presented in this paper combines a local search algorithm (simulated annealing) with genetic algorithms (glabal search). Simulation results deal the control of a continuous stirred tank reactor, that presents open-loop unstable dynamic and nonlinear behaviors. The simulation results show that the application of the Lamarckian evolution strategy effectively improve the parameters optimization of gain scheduling controller.
Código DOI: 10.21528/CBRN2003-057
Artigo em PDF: 6CBRN_057.PDF
Arquivo BibTex: 6CBRN_057.bib