https://repository.sustech.edu/handle/123456789/1341 2026-04-08T03:55:17Z https://repository.sustech.edu/handle/123456789/14711 Neuro-Fuzzy Controller Design for a Dc Motor Drive Mustafa, Ghazally Y.; Ali, A. Taifour; Bashier, Eisa; Elrahman, Mirghani Fateh This paper presents a neuro-fuzzy controller design for speed control of DC motor. The most commonly used controller for the speed control of dc motor is the conventional Proportional-Integral-Derivative (PID) controller. The PID controller has some disadvantages like: high overshoot, sensitivity to controller gains and slow response. Fuzzy control and neuro-fuzzy control are proposed in this study. The performances of the two controllers are compared with PID controller performance. In this paper, neural networks are used in a novel way to solve the problem of tuning a fuzzy logic controller. The neuro fuzzy controller uses neural network learning techniques to tune membership functions. For the speed control of dc motor drives, it is observed that neuro-fuzzy controller gives a better response compared to other controllers Article 2013-02-01T00:00:00Z https://repository.sustech.edu/handle/123456789/14709 Comparison of some Classical PID and Fuzzy Logic Controllers Tayeb, Eisa Bashier M.; Ali, A. Taifour Abstract— The proportional-integral-derivative (PID) controller is tuned to find its parameters values. Generally most of the tuning methods depend mainly on the experimental approach of open-loop unit step response. The controller parameters can be found if the system truly can be approximated by First Order Plus-Dead Time (FOPDT). The performance of most of them deteriorates as the ratio of approximated equivalent delay L to the overall time constant T changes. On the other hand fuzzy PID controller is not tuned through the same conventional tuning procedures. It’s constructed as a set of control rules and the control signal is directly deduced fr om the knowledge base and the fuzzy inference. Fuzzy controller parameters tuned by starting from the equivalent values obtained for optimum controller. The performances of different PID tuning techniques are simulated for different order systems and compared wi th fuzzy-PD+I controller. MATLAB simulation results show that Fuzzy PD+I have better performances over other conventional PID controllers. Article 2012-09-01T00:00:00Z https://repository.sustech.edu/handle/123456789/14708 Control of Induction Motor Drive using Artificial Neural Network Ali, Taifour; Abbas, Abdelaziz Y. M.; Osman, Ekram Hassabo Abaid The induction motor drive is a dynamic nonlinear system with uncertainty in the machine parameters. The aim of this study is to improve tracking performance of the induction motor drive. A method for controlling induction motor drive is presented with conventional Proportional-Integral (PI) controller and Artificial Neural Networks (ANNs) controller. MATLAB/SIMULINK software is used to develop a three phase induction motor model. Also the performances of the two controllers have been verified. The ANN is trained so that the speed of the drive tracks the reference speed. It is found that with the use of the ANN controller the performance and dynamics of the induction motor are enhanced as compared with that of a conventional PI controller. Article 2013-11-04T00:00:00Z https://repository.sustech.edu/handle/123456789/14707 FUZZY CONTROL DESIGN FOR A TWIN ROTOR MULTI-INPUT MULTI-OUTPUT SYSTEM (TRMS) Elrahman, Mirghani Fateh; Imam, Ahmed; Taifor, Awadalla This paper presents the designing of fuzzy logic controller for a twin rotor multi-input-multioutput system (TRMS). The control objective is to make the beam of the TRMS move quickly and accurately to the desired positions, i.e., the pitch and the travel angles. Developing controller for this type of system is challenging due to the coupling effects between two axes and also due to its highly nonlinear characteristics. In this investigation accurate dynamic models of the system for both vertical and horizontal movements are developed so as to get very similar responses to that of the real plant. These models are then used as test-beds to develop a set of fuzzy controllers. The performance of the controllers in tracking movements in both vertical and horizontal planes is found to be very satisfactory. A comparative performance study of this fuzzy control approach with respect to a single PID approach is also presented in this study Article 2009-09-01T00:00:00Z