The Research on Detection Method of Multi-Gas Sensor Based on BP Neural Network

Abstract:

In the paper the multi-gas sensor are detected aimed at the problem of cross interference between the eight kinds of toxic and harmful gases. The cross sensitive characteristics between the different gases are determined through the interference degree, and the cross sensitive model with the environment parameters is built. The BP network is designed with the Matlab toolbox and the data are trained. The results show that the forecast accuracy of the gas concentration can be improved effectively, and the average relative error is reduced. So the new method is put forward to solve the cross interference problem of dangerous chemicals gas effectively.

• Periodical: Applied Mechanics and Materials (Volume 274)
• Pages: 587-591
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.274.587
• Online since: January 2013
• Authors: Wen Jie Zhao, Zhen Zhou, Ming Yan Yu, Meng Meng Wang, Yun Bo Shi
• Keywords: BP Neural Network (BPNN), Interference Degree, Multi-Gas Sensor

References

[1] Mohammad Abdel Kareem Jaradat, Reza Langari. A hybrid intelligent system for fault detection and sensor fusion. Applied Soft Computing 9 (2009) 415–422.

DOI: 10.1016/j.asoc.2008.05.001

[2] Karim Salahshoor, Mohsen Mosallaei, Mohammadreza Bayat. Centralized and decentralized process and sensor fault monitoring using data fusion based on adaptive extended Kalman filter algorithm. Measurement 41 (2008) 1059–1076.

DOI: 10.1016/j.measurement.2008.02.009

[3] Huyberechts, G. Szecowka, P. Roggen, J. Licznerski, B.W. Simultaneous quantification of carbon monoxide and methane in humid air using a sensor array and an artificial neural network. Sensors and Actuators, B: Chemical, (1997)123-130.

DOI: 10.1016/s0925-4005(97)00283-9

[4] N.S. Rajput, R.R. Das, V.N. Mishra, K.P. Singh, R. Dwivedi. A fully neural implementation of unitary response model for classification of gases/odors using the responses of thick film gas sensor array. Sensors and Actuators B 155 (2011) 759–767.

DOI: 10.1016/j.snb.2011.01.043

[5] A. Ziyatdinov, S. Marco, A. Chaudry, K. Persaud, P. Caminal, A. Perera. Drift compensation of gas sensor array data by common principal component analysis. Sensors and Actuators B 146 (2010) 460–465.

DOI: 10.1016/j.snb.2009.11.034

[6] Changying Li, Paul Heinemann, Richard Sherry. Neural network and Bayesian network fusion models to fuse electronic nose and surface acoustic wave sensor data for apple defect detection. Sensors and Actuators, B 125 (2007)301-310.

DOI: 10.1016/j.snb.2007.02.027

[7] Hongmei Zhang, Mingxun Chang, JunWang, Sheng Ye. Evaluation of quality indices using an electronic nose by MLR, QPST and BP network. Sensors and Actuators B 134(2008) 332~338.

DOI: 10.1016/j.snb.2008.05.008

[8] Yu, Mingyan; Shi, Yunbo; Zhao, Wenjie; Feng, Qiaohua; Wang, Xuan; Sun Lining. Comparison of neural network algorithms based on gas qualitative analysis. Proceedings of the 6th International Forum on Strategic Technology, IFOST 2011, (2011).

DOI: 10.1109/ifost.2011.6021230