Share Email Print
cover

Proceedings Paper

Demodulation of Fabry-Perot pressure sensors based on radial basis function network
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper 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.

Paper Details

Date Published: 3 February 2009
PDF: 9 pages
Proc. SPIE 7157, 2008 International Conference on Optical Instruments and Technology: Advanced Sensor Technologies and Applications, 71570L (3 February 2009); doi: 10.1117/12.808072
Show Author Affiliations
Jing Wu, Nanjing Normal Univ. (China)
Ming Wang, Nanjing Normal Univ. (China)
Xiajuan Dai, Nanjing Normal Univ. (China)


Published in SPIE Proceedings Vol. 7157:
2008 International Conference on Optical Instruments and Technology: Advanced Sensor Technologies and Applications

© SPIE. Terms of Use
Back to Top