Announcement for Downloading full text filePlease respect the Copyright Act.
All digital full text dissertation and theses from this website are authorized the copyright owners. These copyrighted full-text dissertation and theses can be only used for academic, research and non-commercial purposes. Users of this website can search, read, and print for personal usage. In respect of the Copyright Act of the Republic of China, please do not reproduce, distribute, change, or edit the content of these dissertations and theses without any permission. Please do not create any work based upon a pre-existing work by reproduction, Adaptation, Distribution or other means.
URN etd-0731106-111550 Statistics This thesis had been viewed 3228 times. Download 1373 times. Author Wei-Feng Huang Author's Email Address email@example.com Department Electrical Engineering Year 2005 Semester 2 Degree Master Type of Document Master's Thesis Language English Page Count 43 Title FUZZY NEURAL NETWORK DESIGN WITH SWITCHING STRATEGY FOR PERMANENT-MAGNET SYNCHRONOUS MOTOR SPEED CONTROLLER Keyword fuzzy neural network switching strategy switching strategy fuzzy neural network Abstract In this thesis, a self-constructing fuzzy neural network controller (SCFNNC) design with switching strategy for permanent-magnet synchronous motor is proposed to track periodic reference input command. The SCFNN system is a straightforward implementation of fuzzy inference system with four layered neural network structure. This system combines the advantages of the neural networks and fuzzy logic theorem. The exact output result of the system cannot be determined due to the uncertainties of the plant dynamic such as parameter variations and external disturbance. To overcome the drawback and to increase the on-line learning rate of the weights, the switching strategy is proposed to choice a suitable parameter of error term. First, the switching condition is defined by speed error. Next, we will judge whether the switching condition is satisfied through proposed switching regulator. Finally, the switching regulator is back-propagated to the SCFNN and adjusted the link weights and other parameter. Several simulations are provided to compare the effectiveness with the SCFNN and proposed SCFNN using switching strategy. The simulation results for periodic reference trajectories show that the dynamic behavior of the proposed control system is robust with regard to plant parameter variations and external load disturbance. Advisor Committee Hung-Ching Lu - advisor
Cheng-Hung Tsai - co-chair
Ta-Hsiung Hung - co-chair
Files Date of Defense 2006-06-14 Date of Submission 2006-07-31