Browse > Article

Real-Time Fault Diagnosis for Tin Oxide Gas Sensors Using Thermal Modulation and an ART-2 Neural Network  

Lee, In-Soo (Kyungpook National University, School of Electronics and Electrical Engineering)
Cho, Jung-Hwan (University of Massachusetts Lowell, Department of Civil and Environment Engineering)
Abstract
We present a new method of on-line fault diagnosis for tin oxide gas sensors using the responses extracted from thermal modulation of the sensor's micro hot plate and an ART-2 NN (adaptive resonance theory 2 neural network) that employs uneven vigilance parameters. We diagnosed faults in tin oxide gas sensors exposed to oil vapor and to high humidity. The diagnosis used the resistance pattern extracted from the tin oxide gas sensor under dynamic operating temperatures and was normalized to enhance the classification ability of the proposed method. The normalized values of the sensor resistance are then used as the input pattern for the ART-2 NN fault classification. The performance was then evaluated using $H_2S$ gas at 1 ppm. This method is proven to be helpful to diagnose faults typically generated by oil vapor or high humidity.
Keywords
fault diagnosis; gas sensor fault; oil vapor; humidity; thermal modulation; ART-2 neural network;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 M. Pardo, G. Faglia, G. Sberveglieri, M. Corte, F. Masulli, and M. Riani, "Monitoring reliability of sensors in an array by neural networks", Sensors and Actuators B, Vol. 67, pp. 128-133, Aug. 2000.   DOI
2 J. Wagner and R. Shoureshi, "A failure isolation strategy for thermofluid system diagnostics", ASME J. Engineering for Industry, Vol. 115, pp. 459-465, 1993.   DOI
3 R. Isermann, "Process fault detection based on modeling and estimation methods-a survey", Automatica, Vol. 20, No. 4, pp. 387-404, April 1984.   DOI
4 M. M. Polycarpou and A. T. Vemuri, "Learning methodology for failure detection and accommodation", IEEE Control Systems Magazine, Vol. 15, No. 3, pp. 16-24, June 1995.   DOI
5 T. Sorsa, H. N. Koivo, and H. Koivisto, "Neural networks in process fault diagnosis", IEEE Trans. Sysem, Man and Cybernetics, Vol. 21, No. 4, pp. 815- 825, July 1991.   DOI
6 A. Srinivasan and C. Batur, "Hopfield/ART-1 neural network-based fault detection and isolation", IEEE Trans. Neural Networks, Vol. 5, No. 6, pp. 890-899, June 1994.   DOI
7 In Soo Lee and Jung Hwan Cho, "Fault diagnosis of nonlinear systems based on decision tree approach and neural network", Journal of Korean Institute of Information Technology, Vol. 10, No. 5, pp. 41-48, May 2012.
8 F. Parret, Ph. Menini, A. Martinez, K. Soulantica, A. Maisonnat, and B. Chaudret, "Improvement micromachined SnO2 gas sensors selectivity by optimized dynamic temperature operating mode", Sensors and Actuators B, Vol. 118, pp. 276-282, Oct. 2006.   DOI
9 Yamazoe N, Fuchigami J, Kishikawa M, and Seiyama T, "Interactions of tin oxide surface with O2, H2O, and H2", Surf Sci, Vol. 86, pp. 335, 1979.   DOI
10 A. Port, M. Gregorkiewitz, N. Machetti, S. Rocchi, B. Serrano, L. Tondi, N. Ulivieri, V. Vignoli, G. Faglia, and E. Comini, "Selectivity enhancement of SnO sensors by means of operating temperature modulation", Thin Solid Films, Vol. 418, pp. 2-8, 2002.   DOI
11 C. H. Shim, D. S. Lee, S. I. Hwang, M. B. Lee, and D. D. Lee, "Gas sensing characteristics SnO2 thin film fabricated by thermal oxidation of Sn/Pt double layer", Sensors and Actuators B, Vol. 81, pp. 176-181, Jan. 2002.   DOI
12 B. U. Moon, J. M Lee, C. H. Shim, M. B. Lee, J. H. Lee, D. D. Lee, and J. H. Lee, "Silicon bridge type micro-gas sensor array", Sensors and Actuators B, Vol. 108, pp. 271-277, Aug. 2005.   DOI
13 In Soo Lee, Pil Jae Shin, and Gi Joon Geon, "Diagnosis of a linear system using ART2 neural networks", Journal of Control, Automation and System Engineering, Vol. 3, pp. 244-251, June 1997.
14 S. Y. Kung, "Digital Neural Networks", Prentice Hall, 1993.