Design Logic For A Fuzzy Controller

Autor: WANG, CHIEN HSIUNG, 王建雄
Rok vydání: 2002
Druh dokumentu: 學位論文 ; thesis
Popis: 90
A fuzzy controller usually uses a database (referred to as “fuzzy knowledge base”) to characterize its control logic for a given system to control. The control logic is always described piecewisely based on the system characteristics. As compared with conventional controllers such as PD,PI or PID controller, the fuzzy controllers present better results according to the reports given by the previous investigators. The governing factors affecting a fuzzy controller, as reported, includes its designs on fuzzifcation 、membership function、fuzzy knowledge base 、inference engine and defuzzification. Among these factors, the designs of the fuzzy knowledge base and membership function are considered to be the most important factors. Many previous studies claim that their fuzzy knowledge base and membership function are created by trial and error, their resulting fuzzy controllers give relative obvious errors. The attempt of this work is to present a logic concept by which a fuzzy controller is designed. An analysis of the resulting fuzzy controller will also be discussed. Hopefully, the results of this work will be able to provide a clue to the person who is working in this area. keyword:fuzzy control、input and output design、steady-state error、phase-plane trajectory.
Databáze: Networked Digital Library of Theses & Dissertations