Journal of the Institute of Electronics Engineers of Korea SC (전자공학회논문지SC)

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지

Concentration estimation of gas mixtures using a tin oxide gas sensor and fuzzy ART

반도체식 가스센서와 퍼지 ART를 이용한 혼합가스의 농도 추정

  • Lee Jeong-Hun (School of Electrical Engineering and Computer Science, Kyungpook National University) ;
  • Cho Jung-Hwan (School of Electrical Engineering and Computer Science, Kyungpook National University) ;
  • Jeon Gi-Joon (School of Electrical Engineering and Computer Science, Kyungpook National University)
  • 이정헌 (경북대학교 전자전기컴퓨터학부) ;
  • 조정환 (경북대학교 전자전기컴퓨터학부) ;
  • 전기준 (경북대학교 전자전기컴퓨터학부)
  • Published : 2006.07.01
Download PDF
⟨ Previous Next ⟩

Abstract

A fuzzy ARTMAP neural network and a fuzzy ART neural network are proposed to identify $H_2S,\;NH_3$, and their mixtures and to estimate their concentrations, respectively. Features are extracted from a tin oxide gas sensor operated in a thermal modulation plan. After dimensions of the features are reduced by a preprocessing scheme, the features are fed into the proposed fuzzy neural networks. By computer simulations, the proposed method is shown to be fast in learning and stable in concentration estimating compared with other methods.

본 논문에서는 혼합가스의 종류를 구분하고 농도를 추정하기 위하여 퍼지 ARTMAP 신경회로망과 퍼지 ART 신경회로망을 각각 사용하였다. 온도변환 구동방식의 반도체식 가스센서를 이용하여 $NH_3,\;H_2S$, 그리고 그들의 혼합가스에 대해서 데이터를 획득하였고, 데이터들을 제안한 패턴인식방법의 입력으로 사용하기 위해서 전 처리 과정을 통해 데이터들의 차원을 줄여주었다. 실험을 통해서 본 논문에서 사용한 방법이 이전의 다른 방법들과 비교하여 학습시간을 줄이면서 좀더 안정된 농도 추정 성능을 보여줌을 확인하였다.

Keywords

References

  1. C. Delhpa, M. Siadat, and M. Lumbreras, 'Indentification on Forance R134a in an air-conditioned atmosphere with a TGS sensor array', IEEE Trans. Instrum. Meas., vol. 50, pp. 1370-1374, 2001 https://doi.org/10.1109/19.963212
  2. C. Delhpa, M. Siadat, and M. Lumbreras, 'Humidity dependence of a TGS gas sensor array in a air-conditioned atmosphere', Sens. Actuator B, vol. 59, pp. 255-259, 1999 https://doi.org/10.1016/S0925-4005(99)00230-0
  3. A. Fort, N. Machetti, S. Rocchi, M. B. Serrano Santos, L. Tondi, N. Ulivieri, V. Vignoli, and G. Sbervaglieri, 'Tin oxide gas sensing: Comparison among different measurement techniques for gas mixture classification', IEEE Trans. Instrum. Meas., vol. 52, pp. 921-926, 2003 https://doi.org/10.1109/TIM.2003.814362
  4. B. Yea, T. Osaki, K. Sgahara, and R. Konoshi, 'The concentration-estimation of inflammable gases with a semiconductor gas senor utilizing neural networks and fuzzy inference', Sens. Actuators B, vol. 41, pp. 121-129, 1997 https://doi.org/10.1016/S0925-4005(97)80284-5
  5. R. Inoescu, and E. Llobet, 'Wavelet transform fast feature extraction from temperature modulated semiconductor gas sensors', Sens. Actuators B, vol. 81, pp. 289-295, 2002 https://doi.org/10.1016/S0925-4005(01)00968-6
  6. E. Llobet, R. Ionescu, S. Al-Khalifa, J. Brezmes, X. Vilanova, X. Correig, N. Barsan, and J. W. Gardner, 'Multicomponent gas mixture analysis using a single tin oxide sensor and dynamic pattern recognition', IEEE Sens. J., vol. 1, pp. 207-213, 2001 https://doi.org/10.1109/JSEN.2001.954833
  7. D. S. Lee, D. D. Lee, S. W. Ban, M. Lee, and Y. T. Kim, 'SnO2 gas sensor array for combustible and explosive gas leakage recognition', IEEE Sens. J., vol. 2, pp. 140-149, 2002 https://doi.org/10.1109/JSEN.2002.800685
  8. G. A. Carpenter, S. Grossberg, and D. B. Rosen, 'Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system', Neural Networks, vol. 4, pp. 759-771, 1991 https://doi.org/10.1016/0893-6080(91)90056-B
  9. G. A. Carpenter, S. Grossberg, N. Markuzon, J. H. Reynolds, and D. B. Rosen, 'Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps', IEEE Trans. on Neural Networks, vol. 3, pp. 698-713, 1992 https://doi.org/10.1109/72.159059
  10. E. Llobet, E. L. Hines, J. W. Gardner, P. N. Bartlett, T. T. Mottram, 'Fuzzy ARTMAP based electronic nose data analysis', Sens. Actuators B, vol. 61, pp. 183-190, 1999 https://doi.org/10.1016/S0925-4005(99)00288-9