Search In this Thesis
   Search In this Thesis  
العنوان
Design of a neuro-fuzzy controller for an electro-mechnical system /
المؤلف
Omar, Basma Abdel-Mawgoud Abo Elala.
هيئة الاعداد
باحث / بسمه عبد الموجود أبو العلا عمر
مشرف / فايز فهمي جمعه عريض
مشرف / أميرة يس هيكل
الموضوع
Adaptive control systems. Fuzzy systems. Electric machinery.
تاريخ النشر
2012.
عدد الصفحات
149 p. :
اللغة
الإنجليزية
الدرجة
ماجستير
التخصص
Computer Networks and Communications
تاريخ الإجازة
01/01/2012
مكان الإجازة
جامعة المنصورة - كلية الهندسة - Department of Computers Engineering and Systems
الفهرس
Only 14 pages are availabe for public view

from 149

from 149

Abstract

In this thesis an Adaptive Neuro Fuzzy Inference System (ANFIS) controller using error and derivative of error inputs is proposed for the speed control of a separately excited dc motor (SEDCM) using chopper circuit.
The aim of this study is to simulate a speed control system that can predict the dynamic behaviors of a DC motor fed by chopper circuit which suffer from internal and external disturbance. To test the validity of the proposed controller, it is tested against speed and load variation and compared to other conventional and intelligent controllers. Moreover, step parameter variation is also studied, where the armature winding resistance is changed and the results are discussed.
The performance of the proposed system has been compared with conventional one, where the conventional PI controller (speed controller) in the Chopper-Fed DC Motor Drive is replaced by the adaptive Neuro-Fuzzy controller to improve the dynamic behavior of the model. Also compared with fuzzy self-tuning PID controller, Neural Network (NN) speed controller, and PSO based fuzzy PI controller.
Computer Simulation is conducted to demonstrate the performance of the proposed controller and results show that the proposed design succeeded over the conventional PI controller where it enhances dynamic responses and reduce ripples. Moreover, results of comparing the proposed ANFIS controller with other related work is improved. The entire system is modeled using MATLAB 2009 toolbox.