Analyzing the Response of a Temperature Modulated Tin-Oxide Gas Sensor Using Local Linear Neuro-Fuzzy Model for Gas Detection

Abstract:

A resistive gas sensor (RGS) under temperature modulation regime is considered as a system for gas detection. Five target gases including Methanol, Ethanol, 2-Propanol, 1-Butanol, and Hydrogen each at 11 concentration levels, were selected for diagnosis using a single commercial gas sensor. For modulating the sensor, a staircase containing five voltage steps each with 20s plateau is applied to micro-heater of the sensor. This, in turn, alters both the temperature and the resistance profiles of the sensing layer which are considered as the input and the output of the defined system, respectively. In this way, five systems corresponding to five steps of the system input can be distinguished. Next, each system under the influence of the examined target gases is modeled with neuro-fuzzy network. Local linear model tree (LOLIMOT) used as learning algorithm of the systems and weights of the trained networks utilized as the features of the sensor in presence of target gas. Mapping these feature vectors using linear discriminant analysis showed successful classification of all target gases.

• Periodical: Key Engineering Materials (Volume 543)
• Pages: 129-132
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.543.129
• Online since: March 2013
• Authors: Seyed Mohsen Hosseini-Golgoo, H. Bozorgi, A. Saberkari, S. Rahbarpour
• Keywords: Gas Detection, Local Linear Model Tree, Neuro-Fuzzy Network, Resistive Gas Sensor, Temperature Modulation

References

[1] N. Barsan, D. Koziej, and U. Weimar, Metal oxide-based gas sensor research: How to? , Sens. Actuators B., vol. 121, no. 1, pp.18-35, (2007).

DOI: 10.1016/j.snb.2006.09.047

[2] F. Hossein-Babaei and M. Orvatinia, A novel approach to hydrogen‏ sensing, IEEE Sensors J., vol. 4, no. 6, p.802–806, (2004).

DOI: 10.1109/jsen.2004.837499

[3] K. Persaud and G. H. Dodd, Analysis of discrimination mechanisms‏ in the mammalian olfactory system using a model nose, Nature, vol. ‏ 299, p.352–355, (1982).

DOI: 10.1038/299352a0

[4] F. Hossein-Babaei and S. M. Hosseini-Golgoo, Analyzing the response of the thermally modoulated gas sensor using a linear system identification technique for gas diagnosis, IEEE Sensors J., vol. 8, no. 11, pp.1837-1847, (2008).

DOI: 10.1109/jsen.2008.2006260

[5] S. M. Hosseini-Golgoo and F. Hossein-Babaei, Assessing the diagnostic information in the response patterns of the temperature modulated tin oxide gas sensor, Meas. Sci. Technol., vol. 22, 2011 (11 pp), doi: 10. 1088/0957-0233/22/3/035201.

DOI: 10.1088/0957-0233/22/3/035201

[6] F. Hossein-Babaei, S. M. Hosseini-Golgoo, and A. Amini, Extracting discriminative information from the Padé-Z transformed responses of a temperature-modulated chemoresistive sensor for gas recognition, Sens. Actuators B., vol. 142, pp.19-27, (2009).

DOI: 10.1016/j.snb.2009.07.039

[7] F. Hossein-Babaei and A. Amini, A Breakthrough in Gas Diagnosis with a Temperature-Modulated Generic Metal Oxide Gas Sensor, Sens. Actuators B., vol. 166-167, no. 1, pp.419-425, (2012).

DOI: 10.1016/j.snb.2012.02.082

[8] R. Kumar, R. R. Das, V. N. Mishra, and R. Dwivedi, A radial basis function neural network classifier for the discrimination of individual odur using responses of thick film tin-oxide sensors, IEEE Sens. J., vol. 9, no. 10, pp.1254-1261, (2009).

DOI: 10.1109/jsen.2009.2030072

[9] R. Kumar, R. R. Das, V. N. Mishra, and R. Dwivedi, A neuro-fuzzy classifier-cum-quantifier for analysis of alchohols and alchoholic beverages using responses of thick-film tin oxide gas sensor array, IEEE Sens. J., vol. 10, no. 9, pp.1461-1468, (2010).

DOI: 10.1109/jsen.2010.2045369

[10] O. Nelles, Nonlinear system identification, Springer, Berlin, pp.341-389, (2001).