Proposta de GPC auto-tuning usando algoritmo genético

• Ano de defesa: 2018
• Autor(a) principal: Piontkovsky Filho, Ademir José
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal do Espírito Santo; BR; Mestrado em Engenharia Elétrica; Centro Tecnológico; UFES; Programa de Pós-Graduação em Engenharia Elétrica
• Palavras-chave em Português: 621.3; Sistemas lineares variantes no tempo; Controle preditivo; Algorítmos genéticos; Sistemas de controle ajustável; Controlador de auto-ajuste; Engenharia Elétrica
• Link de acesso: http://repositorio.ufes.br/handle/10/9564

This dissertation proposes an automatic tuning technique for Generalized Predictive Controller (GPC) with control horizon equal to one to be applied in any plant, with the intention of designing adaptive GPC in auto-tuning mode. The tuning algorithm is initialized through a pre-analysis of the set of tuning parameters that guarantee the stability of the plant in closed loop. Such a region of stability is used by the Genetic Algorithm (GA) to search for the parameters that provide the best overshoot and settling time of the step response. In the preanalysis, one must choose the value of the prediction horizon parameter (hp) andthe desired interval of the λ and δ parameters when evaluating the Root Locus of the characteristic equation of the closed-loop system generated through a graphical interface. Through simulations of auto-tuning mode Adaptive GPC using the GA for stable, unstable, minimum and non-minimal phase plants, it is shown that the proposed algorithm makes AG convergence faster. It is shown in this dissertation that in some plants the stability region of the closed-loop system with the GPC controller does not change when increasing the value of hc, which allows in this case to apply the proposed automatic tuning techniques to the GPC with horizon of control greater than 1. In addition, a tuning rule is proposed for GPC auto-tunning, generated through an offline tuning using genetic algorithm and the graphic interface, for a first-order plant.