Title :
Design an Intelligent Neural-Fuzzy Controller for Hybrid Motorcycle
Author :
Liu, Yao-Lun ; Tong, Chia-Chang ; Jwo, Wu-Shun ; Lin, Shuen-Jeng
Author_Institution :
Chien-kuo Technol. Univ., Changhua
Abstract :
The main propose of this article is to design an intelligent neural-fuzzy controller for hybrid motorcycle. A self-tuning PID tracking controller based on RBF neural network with Fuzzy current limiter is proposed to maneuver the motor and save some energy in hybrid mode. The outer motor control loop is designed to track down the speed fluctuations by Neural-PID controller. Besides, one inner loop is designed to limit the armature current whenever the power demand is diminished according to a set of Fuzzy rules. The proposed structure is put into tests by Matlab programming. Simulations confirm this RBF-PID controller with Fuzzy current limiter can save 23.5% energy for a tracking task.
Keywords :
current limiters; fuzzy control; mathematics computing; motorcycles; neurocontrollers; production engineering computing; radial basis function networks; self-adjusting systems; three-term control; Matlab programming; RBF neural network; fuzzy current limiter; fuzzy rules; hybrid motorcycle; intelligent neural-fuzzy controller; motor control loop; self-tuning PID tracking controller; Current limiters; Fluctuations; Fuzzy control; Fuzzy neural networks; Motor drives; Motorcycles; Neural networks; Power demand; Three-term control; Tracking loops; Fuzzy; Hybrid Vehicle; Radial Basis Function (RBF) Neural Network; Self-tuning PID Controller;
Conference_Titel :
Fuzzy Information Processing Society, 2007. NAFIPS '07. Annual Meeting of the North American
Conference_Location :
San Diego, CA
Print_ISBN :
1-4244-1213-7
Electronic_ISBN :
1-4244-1214-5
DOI :
10.1109/NAFIPS.2007.383852
