Control of a two-link flexible manipulator using neural networks

Minoru Sasaki; Haruki Murasawa; Satoshi Ito

doi:10.1117/12.784510

9 January 2008 Control of a two-link flexible manipulator using neural networks

Minoru Sasaki, Haruki Murasawa, Satoshi Ito

Proceedings Volume 6794, ICMIT 2007: Mechatronics, MEMS, and Smart Materials; 67942Y (2008) https://doi.org/10.1117/12.784510
Event: ICMIT 2007: Mechatronics, MEMS, and Smart Materials, 2007, Gifu, Japan

Abstract

In this paper, control of a two-link flexible manipulator using neural networks is presented. The neural networks are trained so as to make the error between the root strain and the desired root strain and the error between the joint angles and the desired joint angles almost zero. In the process, the neural networks learn the inverse dynamics of the system. Also we compared the learning algorithms between conventional back propagation method and adaptive learning method. The numerical results and experimental results show that this NN control system can suppress the vibrations of the flexible manipulator within a short time in comparison with no feedback. Numerical and experimental results for the vibration control of a two-link flexible manipulator are presented and verify that the proposed NN control system is effective at controlling flexible dynamical systems.

Citation Download Citation

Minoru Sasaki, Haruki Murasawa, and Satoshi Ito "Control of a two-link flexible manipulator using neural networks", Proc. SPIE 6794, ICMIT 2007: Mechatronics, MEMS, and Smart Materials, 67942Y (9 January 2008); https://doi.org/10.1117/12.784510

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available