Novel adaptive modified recurrent Legendre neural network control for a PMSM servo-driven electric scooter with V-belt continuously variable transmission system dynamics

2014 ◽  
Vol 37 (10) ◽  
pp. 1181-1196 ◽  
Author(s):  
Chih-Hong Lin
Author(s):  
Chih-Hong Lin

In order to capture nonlinear and dynamic behaviors of the V-belt continuously variable transmission system with lots of unknown nonlinear and time-varying characteristics, an intelligent dynamic control system using modified particle swarm optimization is proposed for controlling a permanent magnet synchronous motor servo-drive V-belt continuously variable transmission system to raise robustness. The intelligent dynamic control system comprised an inspector control system, a recurrent Laguerre-orthogonal-polynomials neural network controller with adaptive law and a recouped controller with estimation law. The adaptive law of parameters in the recurrent Laguerre-orthogonal-polynomials neural network is derived according to Lyapunov stability theorem. To achieve better learning performance and faster convergence, the modified particle swarm optimization is employed to regulate two varied learning rates of the parameters in the recurrent Laguerre-orthogonal-polynomials neural network. At last, comparative studies shown by experimental results are illustrated to demonstrate the control performance of the proposed control scheme.


Sign in / Sign up

Export Citation Format

Share Document