Predicting the Deflections of Micromachined Electrostatic Actuators Using Artificial Neural Network (ANN)

Sensors & Transducers

Ishak Hj. Abd. AZID¹  Mohd. Ismahadi SYONO²  Hing Wah LEE² 

[1] Department of Mechanical Engineering, University of Science Malaysia, Engineering Campus, 14300 Nibong Tebal, Seberang Perai Selatan, Pulau Pinang, Malaysia;Microfludics and BioMEMS, MIMOS Berhad, Kuala Lumpur, Malaysia;

关键词: MEMS;    Electrostatic;    Neural network;    Micromachined structure;   

DOI  :  

来源: DOAJ

【 摘 要 】

In this study, a general purpose Artificial Neural Network (ANN) model based on the feed-forward back-propagation (FFBP) algorithm has been used to predict the deflections of a micromachined structures actuated electrostatically under different loadings and geometrical parameters. A limited range of simulation results obtained via CoventorWare™ numerical software will be used initially to train the neural network via back-propagation algorithm. The micromachined structures considered in the analyses are diaphragm, fixed-fixed beams and cantilevers. ANN simulation results are compared with results obtained via CoventorWare™ simulations and existing analytical work for validation purpose. The proposed ANN model accurately predicts the deflections of the micromachined structures with great reduction of simulation efforts, establishing the method superiority. This method can be extended for applications in other sensors particularly for modeling sensors applying electrostatic actuation which are difficult in nature due to the inherent non-linearity of the electro-mechanical coupling response.

【 授权许可】

Unknown