Abstract
Ultrasonic motor (USM) has many advantages such as small, light, high torque at low speed, and so on. However, USM contains non-linear elements caused by various frictions, changes of temperature, fluctuation of load-mass, and so on. Therefore, it is difficult to accomplish satisfactory control performance in USM by using conventional control method such as PI control. In this paper, we propose a practical design method of neural networks (NN) controller for USM. In this design method, learning of NN is started from using input-output data of PI control for USM to construct NN controller. Once NN controller has been constructed, self-learning of NN is adopted to improve the control performance of USM. The effectiveness of proposed design method is confirmed by experiments using the existent USM.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: TRANSACTIONS OF THE JAPAN SOCIETY OF MECHANICAL ENGINEERS Series C
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
