Design, fabrication, and real-time neural network control of a three-degrees-of-freedom nanopositioner

Author

Ku, Sang-Soon ; Pinsopon, Unnat ; Cetinkunt, Sabri ; Nakajima, Shin-ichi

Author_Institution

Dept. of Mech. Eng., Illinois Univ., Chicago, IL, USA

Volume

5

Issue

3

fYear

2000

fDate

9/1/2000 12:00:00 AM

Firstpage

273

Lastpage

280

Abstract

A nanometric precision three-degrees-of-freedom positioner is designed and fabricated. Actuation is based on piezoelectric stacks. Capacitive gap sensors with less than 1.0-nm resolution are used for position feedback. In order to design a proper closed-loop controller, the open-loop characteristics of the nanopositioner (static stiffness, hysteresis, drift, frequency response, and the coupling effects) are experimentally investigated. A cerebellar model articulation controller neural network control algorithm was applied in order to provide real-time learning and better tracking capability compared to a standard proportional-integral-derivative control algorithm

Keywords

cerebellar model arithmetic computers; closed loop systems; control system synthesis; frequency response; micropositioning; nanotechnology; neurocontrollers; piezoelectric actuators; 3 DOF nanopositioner; capacitive gap sensors; cerebellar model articulation controller neural network control algorithm; coupling effects; drift; hysteresis; open-loop characteristics; piezoelectric stacks; position feedback; proportional-integral-derivative control algorithm; real-time learning; real-time neural network control; static stiffness; three-degrees-of-freedom nanopositioner; tracking capability; Capacitive sensors; Fabrication; Hysteresis; Nanopositioning; Neural networks; Neurofeedback; Open loop systems; Pi control; Proportional control; Sensor phenomena and characterization;

fLanguage

English

Journal_Title

Mechatronics, IEEE/ASME Transactions on

Publisher

ieee

ISSN

1083-4435

Type

jour

DOI

10.1109/3516.868919

Filename

868919