Recognizing indoor formaldehyde in binary gas mixtures with a micro gas sensor array and a neural network

Abstract

Low-concentration formaldehyde (HCHO) together with ethanol/toluene/acetone/α-pinene (as an interference gas of HCHO) is detected with a micro gas sensor array, composed of eight tin oxide (SnO2) thin film gas sensors with Au, Cu, Pt or Pd metal catalysts. The characteristics of the multi-dimensional signals from the eight sensors are evaluated. A multilayer neural network with an error backpropagation (BP) learning algorithm, plus the principal component analysis (PCA) technique, is implemented to recognize these indoor volatile organic compounds (VOC). The results show that the micro gas sensor array, plus the multilayer neural network, is very effective in recognizing 0.06 ppm HCHO in single gas component and in binary gas mixtures, toluene/ethanol/α-pinene with small relative error.