Artificial neural network approach for humidity-influenced methane sensor response processing

Guido Huyberechts; Przemyslaw M. Szecowka; J. Roggen; Benedykt W. Licznerski

doi:10.1117/12.238160

8 April 1996 Artificial neural network approach for humidity-influenced methane sensor response processing

Guido Huyberechts, Przemyslaw M. Szecowka, J. Roggen, Benedykt W. Licznerski

Proceedings Volume 2780, Metal/Nonmetal Microsystems: Physics, Technology, and Applications; (1996) https://doi.org/10.1117/12.238160
Event: Metal/Nonmetal Microsystems: Physics, Technology, and Applications, 1995, Polanica Zdroj, Poland

Abstract

The problem of methane sensor application in the domestic environment is presented. Tin dioxide thick film technology sensor conductance changes depending on methane concentration. Simple calibration cannot be approached because the conductance is also strongly influenced by humidity. Nevertheless, despite changing humidity accurate methane concentration determination is possible using a two-sensor system. It includes methane sensor and very selective humidity sensor. Artificial neural network is used for reasoning about methane concentration based on responses of these sensors. Feedforward type network is simulated, trained with backpropagation method and tested. The network's accuracy is compared with simple calibration of the sensor.

Citation Download Citation

Guido Huyberechts, Przemyslaw M. Szecowka, J. Roggen, and Benedykt W. Licznerski "Artificial neural network approach for humidity-influenced methane sensor response processing", Proc. SPIE 2780, Metal/Nonmetal Microsystems: Physics, Technology, and Applications, (8 April 1996); https://doi.org/10.1117/12.238160

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