Ecological Systems and Devices Annotation << Back -PREDICTION OF NITROGEN OXIDES IN FLUE GASES OF THE BURNER UNIT V.N. Kovalnogov, S.V. Busygin, D.A. Generalov, V.N. Klyachkin Based on the known results of operation and testing of the burner device, it is necessary to build a mathematical model to predict the content of nitrogen oxides depending on the value of the performance indicators (load, air consumption, methane and biogas, fuel and oxidizer compositions, and others). This is the task of constructing a regression dependence, but standard methods of regression analysis do not always provide the necessary forecasting accuracy. In this case, special methods of machine learning by precedents – "with a teacher" – may be more effective: neural networks, compositional methods, the method of support vectors and others. The purpose of the study is to develop an algorithm for building a mathematical model that provides the necessary accuracy of forecasting. It is shown that in this example, the "random forest" method showed the best accuracy. Keywords: regression model, machine learning, decision tree busting, random forest, support vector method. DOI: 10.25791/esip.5.2023.1370 Pp. 32-38.