• DocumentCode
    806348
  • Title

    Micro gas sensor array with neural network for recognizing combustible leakage gases

  • Author

    Lee, Dae-Sik ; Ban, Sang-Woo ; Lee, Minho ; Lee, Duk-Dong

  • Author_Institution
    Bio-MEMS Group, Electron. & Telecommun. Res. Inst., Daejon, South Korea
  • Volume
    5
  • Issue
    3
  • fYear
    2005
  • fDate
    6/1/2005 12:00:00 AM
  • Firstpage
    530
  • Lastpage
    536
  • Abstract
    A micro gas sensor array, consisting of four porous tin oxide thin films added with noble metal catalysts on a micro-hotplate, was designed and fabricated. The micro-hotplate was designed to obtain a uniform thermal distribution along with a low-power consumption and fast thermal response. The sensing properties of the sensors toward certain combustible gases, i.e., propane, butane, LPG, and carbon monoxide, were evaluated. A multilayer neural network was then used to classify the gas species. The results demonstrated that the proposed micro sensor array, plus multilayer neural network employing a backpropagation learning algorithm, was very effective in recognizing specific kinds and concentration levels of combustible gas below their respective threshold limit values.
  • Keywords
    backpropagation; chemical variables measurement; gas sensors; microsensors; neural nets; LPG; backpropagation learning algorithm; butane; carbon monoxide; combustible gases; combustible leakage gas recognition; combustible leakage gases; low-power consumption; metal catalysts; micro gas sensor array; micro sensor array; microhotplate; multilayer neural network; porous tin oxide thin films; propane; sensing properties; thermal distribution; thermal response; Biomembranes; Gas detectors; Gases; Lithography; Multi-layer neural network; Neural networks; Sensor arrays; Silicon; Sputter etching; Tin; Combustible leakage gas recognition; micro gas sensors; neural network;
  • fLanguage
    English
  • Journal_Title
    Sensors Journal, IEEE
  • Publisher
    ieee
  • ISSN
    1530-437X
  • Type

    jour

  • DOI
    10.1109/JSEN.2005.845186
  • Filename
    1430707