GAS ANALYSIS SYSTEM BASED ON ARTIFICIAL NEURAL NETWORKS

B. Baraboi, M. Cretu, C. Fosalau, C. Donciu

Abstract

The paper presents the design and implementation of an automated system for the analysis of gas mixtures. Using low-cost, non-selective gas sensors in combination with signal processing algorithm based on artificial neural networks, the prototype system is able to correctly classify three combustible gases (methane, isobutane, and hydrogen) and to indicate when the total gas concentration in the air exceeds a preset alarm point. The system is designed using LabVIEW and virtual instrumentation concept and is capable of performing online analysis of gas mixtures.

Keywords

gas recognition, gas sensors, artificial neural networks, LabVIEW

Download

IMEKO-TC4-2001-113.pdf

DOI

-

IMEKO TC

TC4 - Measurement of Electrical Quantities

Back to the proceedings