Adaptive Fuzzy Neural Network And Its Applications, The Rotary Position Servo System

This thesis focuses on the intelligent control strategies based on fuzzy logic and neural networks and its application in motion control. As an important part of the advanced control methods, intelligent control has been well researched and developed in recent years, and a number of approaches to the application of intelligent control have been introduced. This thesis first presents the fundamentals of fuzzy logic, neural networks and learning control, and then introduces the concepts and research achievements of Adaptive Neuro-Fuzzy Inference System (ANFIS). Last, this thesis proposes two strategies: the weighted fuzzy control strategy for multi objects and the neuro-fuzzy control strategy based on Adaptive Neuro-Fuzzy Inference System , and these two strategies are applied on rotating position servosystem.. And the experiment and simulation results prove the validity of these two strategies.Chapter 1 briefly introduces the backgrounds, main contents and new ideas of this thesis. Chapter 2 presents the theories of fuzzy sets and fuzzy logic and control strategies .Chapter 3 introduces the fundamentals and typical instances of neural networks. Meanwhile, the NN-based approaches to the application of intelligent control are presented in this chapter.Chapter 4 browses the brief history ,and introduces the fundamentals of ANFIS. Meanwhile, its brief introduction of research achievements are presented in this chapter.Chapter 5 presents the implemented methods of real time control on MATLAB.Chapter 6 implementing the stable control of rotating position servosystem, presents PID control, fuzzy control and ANFIS control strategies and its method and experimental results.Chapter 7 summarizes the work of this thesis, and then gives the conclusions.