Bobis, James P.
M.S. (Master of Science)
Department of Electrical Engineering
Electronic controllers; Neural networks (Computer science); Nonlinear systems; Fuzzy systems
Physical systems are inherently nonlinear. Nonlinear system can be described by nonlinear differential equations. Some common nonlinear system behaviors are multiple equilibrium points, limit cycles, bifurcation, chaos. For nonlinear control, the research task involved constructing a controller so that the closed loop system meets the desired characteristics. This paper shows the construction process for a neural-fuzzy robust adaptive position controller using MATLAB. For this project's controller, the fuzzy approach is used in order to convert human knowledge into control knowledge. The fuzzy membership functions and rules were implemented with both a backpropagation feedforward neural network and a logical network. A novel devised adaptive algorithm is used to adjust the centroid parameter. To demonstrate the robustness (which is the ability to control different nonlinear models) of this controller, two first order and two second order nonlinear plants, a chaotic system, and a pendulum model are used to implement the simulation. The results show that the controller cancels the nonlinear terms in the system and causes the system to converge to step inputs.
Yao, Xudong, "A robust fuzzy-neural controller for nonlinear systems" (1996). Graduate Research Theses & Dissertations. 542.
viii, 84 pages
Northern Illinois University
Rights Statement 2
NIU theses are protected by copyright. They may be viewed from Huskie Commons for any purpose, but reproduction or distribution in any format is prohibited without the written permission of the authors.