GA-neural network based position control of Traveling Wave Ultrasonic Motor

Author(s):  
Mohammad Jahani ◽  
Hamed Mojallali
2011 ◽  
Vol 2-3 ◽  
pp. 12-17
Author(s):  
Sheng Lin Mu ◽  
Kanya Tanaka

In this paper, we propose a novel scheme of IMC-PID control combined with a tribes type neural network (NN) for the position control of ultrasonic motor (USM). In this method, the NN controller is employed for tuning the parameter in IMC-PID control. The weights of NN are designed to be updated by the tribes-particle swarm optimization (PSO) algorithm. This method makes it possible to compensate for the characteristic changes and nonlinearity of USM. The parameter-free tribes-PSO requires no information about the USM beforehand; hence its application overcomes the problem of Jacobian estimation in the conventional back propagation (BP) method of NN. The effectiveness of the proposed method is confirmed by experiments.


2007 ◽  
Vol 43 (4) ◽  
pp. 934-941 ◽  
Author(s):  
Frederic Giraud ◽  
Betty Lemaire-Semail ◽  
Julien Aragones ◽  
Jacques P. Robineau ◽  
Jean-Thierry Audren

2011 ◽  
Vol 383-390 ◽  
pp. 1623-1628
Author(s):  
Hui Min Zhang ◽  
Hai Yan Wang ◽  
Jing Zhuo Shi ◽  
Xun Liu

It is very hard for the traveling wave ultrasonic motor to start directly with high speed, because of their special running mechanism and the unique features. To solve this problem and realize the uitrasonic motor’s high-speed start control, speed controller with on-line self-tuning parameters is designed. Neural network is used to realize the online adjustment of controller’s parameters, to agree with the different starting request of different speed references, and make best use of motor’s ability. The experiments indicated that the motor start fast and accurately, the control algorithm is effective and reliable.


Sign in / Sign up

Export Citation Format

Share Document