Title :
A recurrent wavelet neural network controller with improved particle swarm optimization for linear synchronous motor drive
Author :
Lin, Faa-Jeng ; Teng, Li-Tao ; Chu, Hen
Author_Institution :
Dept. of Electr. Eng., Nat. Central Univ., Chungli
Abstract :
A recurrent wavelet neural network (RWNN) controller is proposed in this study to control the mover of a permanent magnet linear synchronous motor (PMLSM) servo drive to track periodic reference trajectories. First, the dynamic model of the PMLSM drive system is derived. Next, an RWNN controller is proposed to control the PMLSM. Moreover, the connective weights, translations and dilations of the RWNN are trained online by back-propagation (BP) method. Furthermore, an improved particle swarm optimization (IPSO) is adopted to adapt the learning rates of the RWNN to improve the learning capability. Finally, the control performance of the proposed RWNN controller with IPSO is verified by some experimental results.
Keywords :
backpropagation; control engineering computing; electric machine analysis computing; linear motors; machine control; neurocontrollers; particle swarm optimisation; permanent magnet motors; recurrent neural nets; synchronous motor drives; wavelet transforms; back-propagation method; learning rates; linear synchronous motor drive; particle swarm optimization; periodic reference trajectories tracking; permanent magnet linear synchronous motor servo drive; recurrent wavelet neural network controller; Centralized control; Drives; Friction; Neural networks; Particle swarm optimization; Particle tracking; Recurrent neural networks; Servomechanisms; Synchronous motors; Trajectory;
Conference_Titel :
Electrical Machines and Systems, 2008. ICEMS 2008. International Conference on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-3826-6
Electronic_ISBN :
978-7-5062-9221-4
