Demodulation of Fabry-Perot pressure sensors based on radial basis function network

Jing Wu; Ming Wang; Xiajuan Dai

doi:10.1117/12.808072

2 February 2009 Demodulation of Fabry-Perot pressure sensors based on radial basis function network

Jing Wu, Ming Wang, Xiajuan Dai

Proceedings Volume 7157, 2008 International Conference on Optical Instruments and Technology: Advanced Sensor Technologies and Applications; 71570L (2009) https://doi.org/10.1117/12.808072
Event: International Conference of Optical Instrument and Technology, 2008, Beijing, China

Abstract

In this paper, we present a demodulation of Fabry-Perot pressure sensor method based on radial basis function network(RBF). RBF network is a kind of three layers frontal feedback neural network with single connotative layer. It is proved that RBF is able to approach random continuous function with random precision. The cavity length variation is simulated from 473 to 483 µm with the step of 0.5 µm and the simulation result shows that the relative error of this new method is less than 0.02% and the maximum absolute error is less than 0.1 µm. The MEMS Fabry-Perot pressure sensor is also demodulated by the experiment. In the experiment, we change the pressure from 0 to 2 MPa with the step of 0.1 MPa. The experimental result shows that its linearity of the cavity length versus pressure achieves 0.98858 and the standard deviation between measured pressures and real pressures is less than 0.05 Mpa. By the experiment we can see that, this RBF network method can obtain upper precision and can reach the practice demand. This new method adapts to the practice demand with its higher resolution and less calculation time.

Citation Download Citation

Jing Wu, Ming Wang, and Xiajuan Dai "Demodulation of Fabry-Perot pressure sensors based on radial basis function network", Proc. SPIE 7157, 2008 International Conference on Optical Instruments and Technology: Advanced Sensor Technologies and Applications, 71570L (2 February 2009); https://doi.org/10.1117/12.808072

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available