1 January 2007 Using neural networks to model an electromagnetic-actuated microactuator
Author Affiliations +
J. of Micro/Nanolithography, MEMS, and MOEMS, 6(1), 013011 (2007). doi:10.1117/1.2712864
Abstract
We present the use of artificial neural networks (ANNs) to model an electromagnetic microelectromechanical system (MEMS) microactuator. It is inherently complex and time consuming to model/predict the response of an electromagnetic microactuator numerically by finite element analysis, particularly when it is actuated by a pulse of current in media with different properties (e.g., air, water, and diluted methanol). ANNs are used to model the maximum displacement (dmax) of the microactuator for a range of burst frequencies (fb) and input currents (Icoil), as well as different mechanical designs and actuation media. The prediction errors of the ANN model in normal and pressurized air are <13 and <2%, respectively. The prediction error for the same response in water or 50% diluted methanol in water is <10%.
Jemmy Sutanto, Ronald Setia, Adam Papania, Gary Stephen May, Peter J. Hesketh, Yves H. Berthelot, "Using neural networks to model an electromagnetic-actuated microactuator," Journal of Micro/Nanolithography, MEMS, and MOEMS 6(1), 013011 (1 January 2007). http://dx.doi.org/10.1117/1.2712864
JOURNAL ARTICLE
10 PAGES


SHARE
KEYWORDS
Microactuators

Neural networks

Electromagnetism

Data modeling

Microelectromechanical systems

Microfluidics

Neurons

Back to Top