Existing possibilities of the artificial intelligence technologies, in particular the machine learning methods, in relation to the prediction of dangerous fire factors in a room are considered in the article. The analysis is presented concerning the known solutions to the scientific problem, based on which it is established that the methods for predicting dangerous fire factors in a room have advantages and disadvantages. Therefore, the issue of developing new approaches to solving the assigned task remains relevant. The libraries of the high-level programming language Python that are most widely used for machine learning are described. It is established that due to large computational labor intensity, which increases significantly with increasing the mathematical model inputs, the exact formulas that determine the relationship between its parameters are unknown, this is with the exception of the simplest cases. Mathematical predicting model is developed in the form of a system of linear polynomial equations that describes the existing functional relationship between its parameters characterizing the properties of combustible materials. Data processing results presented in the form of the correlation matrix are analyzed. The received results can be used to simulate the processes that describe the thermogasdynamic picture of a fire in a room. Visualization of the obtained results was carried out using the developed multidimensional interactive model, which greatly simplifies the processing and analysis of data, and, also provides for a better understanding of the properties and structure of the relationships of the analyzed object of study. Machine learning methods are an effective tool for predicting dangerous fire factors in a room in addition to already existing predicting methods.

- Koshmarov Yu.A., Puzach S.V., Andreev V.V., Kozlov Yu.I. Prediction of dangerous fire factors in a room: textbook. Moscow: Akademiya GPS MChS Rossii, 2012. 126 p. (In Russ.).
- Svirin I.S. Review of fire spredaing models in the buildings. Problemy bezopasnosti i chrezvychaynykh situatsiy = Safety and emergencies prombles. 2013. № 6. pp. 114–129. (In Russ.).
- Shumilin V.V. Features of mathematical modeling of dangerous fire factors spreading. Problemy obespecheniya bezopasnosti pri likvidatsii posledstviy chrezvychaynykh situatsiy = Problems of ensuring safety in emergency response. 2014. № 1 (3). pp. 332–334. (In Russ.).
- Korhonen T. Fire dynamics simulator with evacuation: FDS + Evac. Technical Reference and User’s Guide (FDS 6.6.0, Evac 2.5.2, DRAFT). Espoo: VTT Technical Research Centre of Finland, 2018. 115 p.
- Fedosov S.V., Ibragimov A.M., Solovev R.A., Murzin N.V., Tarakanov D.V., Lapshin S.S. Mathematical model of fire development in the room system. Vestnik MGSU = Monthly Journal on Construction and Architecture. 2013. № 4. pp. 121–128. (In Russ.).
- Rudnitskiy V.N., Melnikova E.A., Pustovit M.O. Paralleling and optimization of the calculation of fire development process based on three-dimensional cellular automaton. Vektor nauki TGU = Science Vector of Togliatti State University. 2014. № 1 (27). pp. 22–26. (In Russ.).
- Tsvirkun A.D., Rezchikov A.F., Samartsev A.A., Ivashchenko V.A., Kushnikov V.A., Bogomolov A.S., Filimonyuk L.Yu. Mathematical model of the dynamics of fire development in the rooms. Upravlenie bolshimi sistemami: sb. tr. (Large systems management: proceedings). 2018. № 74. pp. 42–62. (In Russ.).
- Samartsev A.A., Rezchikov A.F., Kushnikov V.A., Ivashchenko V.A., Bogomolov A.S., Filimonyuk L.Y., Dolinina O.N., Kushnikov O.V., Shulga T.E., Tverdoklebov V.A., Fominykh D.S. Fire and heat spreading model based on cellular automata theory. Journal of Physics: Conference Series. 2018. Vol. 1015. pp. 1–5.
- Apiecionek L., Zarzycki H., Czerniak J.M., Dobrosielski W.T., Ewald D. The cellular automata theory with fuzzy numbers in simulation of real fires in buildings. Advances in Intelligent Systems and Computing. Cham: Springer, 2018. Vol. 559. pp. 169–182.
- Mamzin E.A. High-performance cellular automaton with a reconfigurable pattern and their application for modeling of heterogeneous dynamical systems: thesis... Candidate of Physical and Mathematical Sciences. Tolyatti, 2011. 152 p. (In Russ.).
- On the development of artificial intelligence in the Russian Federation: Decree of the President of the Russian Federation of October 10, 2019 № 490. Available at: https://www.garant.ru/products/ipo/prime/doc/72738946/ (accessed: January 30, 2020). (In Russ.).
- Zhu Q., Azar A.T. Complex system modelling and control through intelligent soft computations. Cham: Springer, 2015. 863 p.
- Dzhoshi P. Artificial intelligence with Python examples. Creation of the artificial intelligence applications using Python for iteraction with the outside world. Moscow: Dialektika, 2019. 448 p. (In Russ.).
- Rashka S. Python and machine learning. Moscow: DMK Press, 2017. 418 p. (In Russ.).
- Kirk M. Thoughtful machine learning with Python: a test-driven approach. Sebastopol: O’Reilly Media, 2017. 220 p.
- Plas Dzh.V. Python for complex tasks: data science and machine learning. Saint-Petersburg: Piter, 2019. 576 p. (In Russ.).
- Pedregosa F., Varoquaux G., Gramfort A., Michel V., Thirion B., Grisel O., Blondel M., Prettenhofer P., Weiss R., Dubourg V., Vanderplas J., Passos A., Cournapeau D., Brucher M., Perrot M., Duchesnay E. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research. 2011. № 12. pp. 2825–2830.
- Pegat A. Fuzzy modeling and control. Moscow: Laboratoriya znaniy, 2020. 801 p. (In Russ.).
- Lutts M. Learning Python. 4-e izd. Saint-Petersburg: Simvol-Plyus, 2011. 1280 p. (In Russ.).
- Ferster E., Rents B. Methods of correlation and regression analysis. Moscow: Finansy i statistika, 1983. 304 p. (In Russ.).