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

• Published in: IEEE/ASME transactions on mechatronics Vol. 5; no. 3; pp. 273 - 280
• Main Authors: Sang-Soon Ku, Pinsopon, U., Cetinkunt, S., Nakajima, S.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.09.2000; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Applied sciences; Capacitive sensors; Cerebellar model articulation controller; Computer science; control theory; systems; Control system synthesis; Control theory; Control theory. Systems; Degrees of freedom (mechanics); Exact sciences and technology; Fabrication; Feedback control; Hysteresis; Learning systems; Mathematical models; Mechanical engineering. Machine design; Mechatronics; Nanocomposites; Nanomaterials; Nanopositioning; Nanostructure; Neural networks; Neurofeedback; Open loop systems; Pi control; Position control; Precision engineering, watch making; Proportional control; Real time; Sensor phenomena and characterization; Piezoelectric sensor; Capacitive transducer; Position control; Precision engineering; High precision; Feedback regulation; Neural network; Real time; Nanometer scale; Positioner; Feedback; Piezoelectric actuators; Miniaturization; System with three degrees of freedom; Motion control
• ISSN: 1083-4435; 1941-014X
• DOI: 10.1109/3516.868919

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.