A Novel Neural Network Model of Capacitive MEMS Accelerometers

Author

Bahadorimehr, A.R. ; Hamidon, M.N. ; Hezarjaribi, Y.

Author_Institution

Electr. & Electron. Dept., Univ. Putra Malaysia, Serdang

fYear

2008

fDate

25-27 Nov. 2008

Firstpage

174

Lastpage

178

Abstract

This paper presents a nonlinear model for a capacitive Micro-electromechanical accelerometer (MEMA). System parameters of the accelerometer are developed using the effect of cubic term of the folded-flexure spring. To solving this equation we use FEA method. The neural network (NN) uses Levenberg-Marquardt (LM) method for training the system to have more accurate response. The designed NN can identify and predict the displacement of movable mass of accelerometer. The simulation results are very promising.

Keywords

accelerometers; capacitive sensors; computerised instrumentation; finite element analysis; learning (artificial intelligence); microsensors; neural nets; FEA method; Levenberg-Marquardt method; capacitive MEMS accelerometer; folded-flexure spring; microelectromechanical accelerometer; neural network model; nonlinear model; Acceleration; Accelerometers; Circuits; Damping; Electrostatics; Fingers; Micromechanical devices; Neural networks; Nonlinear equations; Springs;

fLanguage

English

Publisher

ieee

Conference_Titel

Semiconductor Electronics, 2008. ICSE 2008. IEEE International Conference on

Conference_Location

Johor Bahru

Print_ISBN

978-1-4244-3873-0

Electronic_ISBN

978-1-4244-2561-7

Type

conf

DOI

10.1109/SMELEC.2008.4770302

Filename

4770302