Neural networks and fuzzy logic in electrical engineering

Control system packages have become essential ingredients of both undergraduate and graduate courses in the control area. This work describes our experience with the use of MATLAB/sup TM/ with its fuzzy logic and neural networks toolboxes in electrical engineering control courses. While some of the methods in the area of intelligent systems and control have significant benefits to offer, engineers are often reluctant to utilize new intelligent control techniques for several reasons. Two fuzzy logic controllers for a gas turbine have been developed using speed and mechanical power deviations. A neural network has been designed to tune the gains of the fuzzy logic controllers based on the operating conditions of the electric power plant. Student feedback indicates that theoretical developments in lectures on control systems were only appreciated after the laboratory exercises.