Selective methane detection under varying moisture conditions using static and dynamic sensor signals

Abstract This paper reports the development of a methane analyser, which meets some of the requirements of a reliable domestic methane detector. The equipment is based on a five-element array that includes four tin oxide gas sensors and a humidity sensor. The pattern recognition engine is based on multilayer perceptron (MLP) neural networks trained with the back-propagation algorithm. Both static and dynamic signals from the sensors are fed into the neural networks to identify and quantify methane and ethanol. The system identifies and quantifies unknown samples of these contaminants, even when the ambient relative humidity varies broadly (from 25% to 80%). As a result, the equipment detects methane, rejects false alarms caused by ethanol and complies with some aspects of the European directive for domestic methane detectors.

[1]  Raúl Rojas,et al.  Statistics and Neural Networks , 1996 .

[2]  Julian W. Gardner,et al.  A brief history of electronic noses , 1994 .

[3]  P. Gubian,et al.  Identification and quantification of methane and ethyl alcohol in an environment at variable humidity by an hybrid array , 1997 .

[4]  B. Romanowicz,et al.  Domestic gas detection system using two SnO2 integrated sensors , 1994 .

[5]  Przemyslaw M. Szecowka,et al.  Simultaneous quantification of carbon monoxide and methane in humid air using a sensor array and an artificial neural network , 1997 .

[6]  Patrick Mielle,et al.  Managing dynamic thermal exchanges in commercial semiconduting gas sensors , 1996 .

[7]  E. Llobet,et al.  Analysis of the conductance transient in thick-film tin oxide gas sensors , 1996 .

[8]  Sergio Pizzini,et al.  A family of tin oxide-based sensors with improved selectivity to methane , 1992 .

[9]  S. Birlasekaran,et al.  Ambient temperature dependent heating power control for motorola micro CO gas sensor , 1998 .

[10]  Udo Weimar,et al.  A modified multilayer perceptron model for gas mixture analysis , 1993 .

[11]  Maximilian Fleischer,et al.  Sensitive, selective and stable CH4 detection using semiconducting Ga2O3 thin films , 1995 .

[12]  J. Brezmes,et al.  Qualitative and quantitative analysis of volatile organic compounds using transient and steady-state responses of a thick-film tin oxide gas sensor array , 1997 .

[13]  Philippe Dondon,et al.  Development of a reliable methane detector , 1997 .

[14]  Muriel Loesch,et al.  Comparison between two Figaro sensors (TGS 813 and TGS 842) for the detection of methane, in terms of selectivity and long-term stability , 1995 .

[15]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .