Design of a Gas Detection System Based on BP Neural Network

Abstract:

On the basis of the brief overview of principles of the gas detection system, this paper has analyzed the characteristics, structure and identification theory to explain the method of gas detection based on an artificial neural network. And it has analyzed and researched gas detection system based on neural network and thus solved the problems such as cross-sensitiveness in present gas sensor. The results show that the gas sensor array "cross-sensitive" issue can be effectively solved through the combination of the pattern recognition of artificial neural network and the gas sensor array technology, which accordingly realizes qualitative identification for different gases and has broad application prospects.

• Periodical: Applied Mechanics and Materials (Volumes 55-57)
• Pages: 1819-1823
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.55-57.1819
• Online since: May 2011
• Authors: Yin Long Wang, Ke Cheng Lin, Xi Wu Wang, Zhi Guang Geng, Qi Gen Zhong
• Keywords: Gas Detection, Neural Network (NN), Sensor Array

References

[1] Kim B W, Kim S M. GA-optimized back-propagation neural network with multi-parameterized gradients and applications to predicting plasma etch data[J]. Chemo metrics and Intelligent Laboratory Systems, 2005, 79, p.123.

DOI: 10.1016/j.chemolab.2005.06.002

[2] Kim K J. Artificial neural networks with evolutionary instance selection for financial forecasting[J]. Expert Systems with Applications, 2006, 30, p.519.

DOI: 10.1016/j.eswa.2005.10.007

[3] Marzia Z, Cosimo D, Pietro S, et al. Drift counteraction with multiple self-organizing maps for an electronic nose[J]. Sensors and Actuators B, 2004, 98, p.305.

DOI: 10.1016/j.snb.2003.10.029

[4] Bicego M. Odor classification using similarity-based representation [J]. Sensors and Actuators B, 2005, 110, p.225.

DOI: 10.1016/j.snb.2005.01.034