The Journal of Korean Institute of Information Technology (한국정보기술학회논문지)

Korean Institute of Information Technology (한국정보기술학회)
권호 표지

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)
  • Published : 2013.02.28
⟨ Previous Next ⟩

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.

본 논문에서는 산화주석 박막으로 형성된 가스 센서의 온라인 고장진단을 위하여 센서의 마이크로 열판 열산화 방법으로 추출한 데이터와 여러 경계인수를 갖는 ART-2 신경회로망을 이용한 새로운 방법을 제안하였다. 식용유 증기와 고습에 의해서 발생된 산화주석 가스센서의 고장을 진단하였다. 진단방법은 동적 동작온도에서 산화주석 박막 가스센서로부터 추출한 저항패턴들을 사용하였고 제안한 방법의 분류능력을 증대시키기 위한 정규화하였다. 센서 저항의 정규화 된 값들은 고장분류를 위한 ART-2 신경회로망의 입력 값으로 사용되었다. 고장 진단 성능은 1 ppm의 $H_2S$(황화수소)를 사용하여 확인하였다. 제안된 방법은 식용유 증기와 고습에 의해 발생된 고장진단에 유용한 것으로 확인되었다.

Keywords

References

  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. https://doi.org/10.1016/S0925-4005(00)00402-0
  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. https://doi.org/10.1115/1.2901790
  3. R. Isermann, "Process fault detection based on modeling and estimation methods-a survey", Automatica, Vol. 20, No. 4, pp. 387-404, April 1984. https://doi.org/10.1016/0005-1098(84)90098-0
  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. https://doi.org/10.1109/37.387613
  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. https://doi.org/10.1109/21.108299
  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. https://doi.org/10.1109/72.329685
  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. https://doi.org/10.1016/j.snb.2006.04.055
  9. 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. https://doi.org/10.1016/S0040-6090(02)00575-8
  10. 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. https://doi.org/10.1016/S0925-4005(01)00949-2
  11. 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. https://doi.org/10.1016/j.snb.2005.01.042
  12. 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. https://doi.org/10.1016/0039-6028(79)90411-4
  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.