EVALUATION OF THE EFFECTIVENESS OF MACHINE LEARNING CLASSIFIERS FOR GAS TYPE AND CONCENTRATION RECOGNITION

The paper highlights the artificial intelligence (AI) classification methods in machine learning for recognizing the gas type and its concentration in a mixture. The applicability of classifiers is assessed. During the study, theoretical values of hydrogen, hydrocarbons, and their mixtures with a hydrogen fraction of 20, 50 and 80% were calculated, and the AI classifiers were evaluated using experimental data obtained from a catalytic sensor. The presented classifiers made it possible to determine the type of gas with an accuracy of up to 87.5%.