Please use this identifier to cite or link to this item: https://doi.org/10.1016/j.sna.2005.02.004
Title: Linearization of the scanning field for 2D torsional micromirror by RBF neural network
Authors: Zhao, Y.
Tay, F.E.H. 
Chau, F.S. 
Zhou, G. 
Keywords: 2D torsional micromirror
Linearization
MEMS
RBF neural network
Issue Date: 31-May-2005
Source: Zhao, Y., Tay, F.E.H., Chau, F.S., Zhou, G. (2005-05-31). Linearization of the scanning field for 2D torsional micromirror by RBF neural network. Sensors and Actuators, A: Physical 121 (1) : 230-236. ScholarBank@NUS Repository. https://doi.org/10.1016/j.sna.2005.02.004
Abstract: We report a radial basis function (RBF) neural network (NN) method to linearize the scanning field of a 2D torsional micromirror, which is distorted by the intrinsic nonlinearity of the electrostatic torques. The 2D micromirror system is modelled and the parameters are identified. The feasibility of the method is shown. The system model is coded in the analog hardware description language (AHDL) for system level simulation in Saber™. The experiment is implemented in National Instrument's LabVIEW™ with a real-time embedded controller and a data acquisition card. The NN algorithm is coded in C language as a Dynamic Link Library (DLL) to make it easily integrated into both Saber™ and LabVIEW™. The experimental results agree well with the simulation ones. The distortion rates are improved from 28% in simulation and 23% in experiment to a negligible level respectively. © 2005 Elsevier B.V. All rights reserved.
Source Title: Sensors and Actuators, A: Physical
URI: http://scholarbank.nus.edu.sg/handle/10635/60648
ISSN: 09244247
DOI: 10.1016/j.sna.2005.02.004
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

8
checked on Jan 17, 2018

WEB OF SCIENCETM
Citations

7
checked on Dec 13, 2017

Page view(s)

27
checked on Jan 22, 2018

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.