Share Email Print
cover

Proceedings Paper

Cross sensitivity reduction of gas sensors using genetic algorithm neural network
Author(s): Junhua Liu; Yong Zhang; Yonghuai Zhang; Ming Chen
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

12 Infrared absorption method in analyzing gas components is a traditional spectrum analyzing method of gas. Nevertheless, the distribution of the absorption spectrum of a certain kind of gas intercrosses with another's, which means that the absorption peaks of two kinds of gases are near very close. So, when those kinds of gases aforementioned are mixed together, the spectrum analysis will have the cross sensitivity. In this paper, the genetic neural network algorithm is adopted to recognize the patterns of the mixed gases with three components in the simulation recognition. The genetic algorithm decreases the cross sensitivity of the gas sensor. Especially the staged-sectional method is used to increase the recognition accuracy of various over-limit value.

Paper Details

Date Published: 13 February 2001
PDF: 9 pages
Proc. SPIE 4201, Optical Methods for Industrial Processes, (13 February 2001); doi: 10.1117/12.417392
Show Author Affiliations
Junhua Liu, Shanghai Jiao Tong Univ. (China)
Yong Zhang, Shanghai Jiao Tong Univ. (China)
Yonghuai Zhang, Shanghai Jiao Tong Univ. (China)
Ming Chen, Shanghai Jiao Tong Univ. (China)


Published in SPIE Proceedings Vol. 4201:
Optical Methods for Industrial Processes
Stuart Farquharson, Editor(s)

© SPIE. Terms of Use
Back to Top