Chemical Vapor Identification by Plasma Treated Thick Film Tin Oxide Gas Sensor Array and Pattern Recognition

Abstract

Present study deals the class recognition potential of a four element plasma treated thick film tin oxide gas sensor array exposed with volatile organic compounds (VOCs). Methanol, Ethanol and Acetone are selected as target VOCs and exposed on sensor array at different concentration in range from 100-1000 ppm. Sensor array consist of four tin oxide sensors doped with 1-4 % PbO concentrations were fabricated by thick film technology and then treated with oxygen plasma for 5-10 minute durations. Sensor signal is analyzed by principal component analysis (PCA) for visual classification of VOCs. Further output of PCA is used as input for classification of VOCs by four pattern classification techniques as: linear discriminant analysis (LDA), k-nearest neighbor (KNN), back propagation neural network (BPNN) and support vector machine (SVM). All the four classifier results 100 % correct classification rate of VOCs by response analysis of sensor array treated with plasma for 5 minute.

Keywords

• Tin oxide sensor
• Plasma treatment
• Pattern recognition methods
• Chemical vapor identification