Development of smart gas sensor system to classify binary gas mixtures

Solvents are used in a large number of industries especially in cleaning and cosmetic. Solvents are known to be harmful to human health. Classification of solvent in a product is important to determine the level of hazard that can people faced. In this study, three different solvents, methanol, acetone, and chloroform, are used to obtain binary gas mixtures in a laboratory environment. A gas sensor system that has 9 QCM sensors is used to obtain binary gas mixtures data. The developed system uses artificial neural network trained by artificial bee colony algorithm. This hybrid algorithm is used to classify binary gas mixtures. Too many scenarios are tested and it is observed that classifying binary gas mixtures by ANN-ABC hybrid method gives successful results and increased the classification performance of test data by 71.43%.