Application to GA-Based Fuzzy Control for Nonlinear Systems with Uncertainty

In this study, we strive to combine the advantages of fuzzy theory, genetic algorithms (GA), H-infinite tracking control schemes, smooth control and adaptive laws to design an adaptive fuzzy sliding model controller for the rapid and efficient stabilization of complex and nonlinear systems. First, we utilize a reference model and a fuzzy model (both involvingrules) to describe and well-approximate an uncertain, nonlinear plant. The FLC rules and the consequent parameter are decided on via GA. A boundary-layer function is introduced into these updated laws to cover modeling errors and to guarantee that the state errors converge into a specified error bound. After this, a H-infinite tracking problem is characterized. We solve an eigenvalue problem (EVP), and derive a modified adaptive neural network controller (MANNC) to simultaneously stabilize and control the system and achieve H-infinite control performance.