| dc.description.abstract | Fuzzy logic provides human reasoning capabilities to capture uncertainties that cannot be described by precise mathematical models. An adaptive fuzzy system is a fuzzy logic system equipped with a learning algorithm. A"learning system" possesses the capability to improve its performance over time by interacting with its environment, so an adaptive control system has the ability to improve the performance of the closed-loop system by generating command inputs to the plant and utilizing feedback information from the plant. This thesis proposes a fast approach for system modeling by neuro-fuzzy networks (NFNs), which can successfully model the nonlinear system dynamics and its uncertainties. This algorithm can construct a system model by NFN, i.e., fuzzy rules can be generated automatically in the learning process from training data without partitioning the input space and selecting initial parameters a priori. This thesis presents an adaptive fuzzy control method of nonlinear systems using the NFN controller, which can be constructed by the fast learning algorithm proposed in this thesis. In simulation studies, an inverted pendulum system can track the desired trajectory very well and the control system has good robustness to disturbances using the adaptive control method proposed. The inverted pendulum is controlled by the proposed adaptive fuzzy control method, classical PID control method and nonadaptive fuzzy control method respectively; the control results show that the adaptive fuzzy control system has the best performances among the three control systems in terms of transient and steady-state results. | fr |
