Improvement of oil heating unit calculation methods using digital modeling and machine learning

THE RELEVANCE. The issues of efficient use of fuel and energy resources in the Russian industry remain extremely important, which is confirmed by the adoption of a number of legislative and regulatory documents at the federal and regional levels. Historically, the structure of energy complexes of enterprises, including production using oil systems, was formed in conditions of low energy prices, which led to insufficient energy efficiency of technological processes. In this regard, the modernization of existing components, in particular, oil heating systems, using modern methods of technological modeling, becomes an urgent task. THE PURPOSE. The study of oil heating unit in order to optimize its thermal regime, reduce energy losses and develop measures to improve energy efficiency using technological modeling tools is the purpose of this study. METHODS. To achieve the set objectives the following methods were used: system analysis of thermal and technological processes, mathematical and computer modeling of heat exchange in the oil heating unit, methods of energy-technological combination to identify energy saving reserves. RESULTS. Within the framework of the research there were carried out: analysis of heat losses in the oil heating unit, modeling of heat flows taking into account changes in viscosity and heat capacity of oil, evaluation of efficiency of heat exchange equipment and identification of “bottlenecks”. Proposed solutions: introduction of an additional heat exchanger for waste gas heat recovery, optimization of heating modes by means of automation of temperature parameters control, use of recuperative schemes to increase system efficiency. CONCLUSION. Implementation of the proposed measures will result in savings of up to 6.55 million rubles per year. Application of technological modeling tools in modernization of oil heating unit allows to optimize thermal processes, reduce energy losses and increase economic efficiency of production. Implementation of the proposed solutions will provide significant energy savings with a relatively short payback period. The implementation of this project will contribute to the digital transformation of heat transfer processes and energy efficiency in the petrochemical industry through the application of artificial intelligence and machine learning technologies. This corresponds to the key directions of the Strategy for Scientific and Technological Development of the Russian Federation, including the transition to intelligent production systems, big data processing and the introduction of automated control methods. Thus, the proposed approach opens up new opportunities for the digitalization of petrochemical industries, increasing their efficiency, environmental friendliness and competitiveness in accordance with the priorities of scientific and technological development of the Russian Federation.

1. Manuiko G.V., Aminova G.A., Diakonov G.S., Akhmetov I.G., Bronskaya VV. Kinetic heterogeneity of neodymium catalytic system modified by methylalumoxane // Theoretical bases of chemical technology. 2015. Т. 49. № 3. P. 261.

2. Shatunov D.N., Kamaeva K.A., Malygin A.V., Klinov A.V. Influence of segmental partitions design on the heat exchange process in a gas-oil heat exchanger // Herald of technological university. 2024. T. 27. № 8. P. 98-103.

3. Bronskaya V.V., Zinnurova O.V., Firsin A.A., Shipin A.V. Digital modeling of gas fractionation unit using machine learning methods // Modern high technologies. – 2024. – № 11 – P. 10-16. - DOI 10.17513/snt.40204.

4. Haritonova O., Bronskaya V., Zinnurova O., Firsin A. Modeling of a delayed coking plant in the MatLab program // Vestnik of Astrakhan State Technical University. Series: Management, computer science and informatics. 2024. no. 2. pp. 29-37. DOI: https://doi.org/10.24143/2072-9502-2024-2-29-37.

5. Haibullina A., Khairullin A., Balzamov D., Ilyin V., Bronskaya V., Khairullina L. Local heat transfer dynamics in the in-line tube bundle under asymmetrical pulsating flow // Energies. 2022. Т. 15. № 15. P. 5571.

6. Balzamov D.S., Konakhina I.A. System of energy-technological combination of high-temperature dehydrogenation section of isoamylenes into isoprene // Bulletin of Kazan State Power Engineering University. - 2010. - № 1(4). - P. 16-25.

7. Balzamov D.S., Bronskaya V.V. Increasing the efficiency of thermal energy use at the thermal technology section of ethylene production. Power engineering: research, equipment, technology. 2025; 27 (1): 103-115. doi: 10.30724/1998-9903-2025-27-1-103-115.

8. Artyushkin I.V., Maksimov A.E. Development of an automatic control system for thermochemical dehydration of oil emulsions based on an artificial neural network // Bulletin of Samara State Technical University. Series: Technical Sciences. 2017. № 1 (53). P. 7-15.

9. Malygin A.V., Emel’yanov I.I., Semin R.V., Fazlyev A.R., Ziyatdinov N.N., Klinov A.V. Modeling of membrane separation of liquid mixture in Aspen HYSYS. Tonk. Khim. Tekhnol. - Fine Chem. Technol. 2025;20(1):75–88. https://doi.org/10.32362/2410-6593-2025-20-1-75-88.

10. Chen X., Wang N. Modeling a Delayed Coking Process with GRNN and Double-Chain Based DNA Genetic Algorithm // International Journal of Chemical Reactor Engineering. 2010. Vol. 8, Is. 1. DOI: 10.2202/1542-6580.2192.

11. Hayrullin A., Haibullina A., Sinyavin A., Ilyin V. Experimental study of the in-line tube bundle thermal performance in pulsating flow // International Journal of Heat and Mass Transfer. – 2024. – Vol. 232. – P. 125916. – DOI 10.1016/j.ijheatmasstransfer.2024.125916.

12. Denikeeva A.U. Modeling of the process of gasoil production using an artificial neural network // Priority scientific directions: from theory to practice. 2016. № 26-1. P. 219-223.

13. Hayrullin A., Sinyavin A., Haibullina A. [et al.] Heat Transfer in Annular Channels with the Inner Rotating Cylinder and the Radial Array of Cylinders // Energies. – 2024. – Vol. 17, №. 23. – P. 6047. – DOI 10.3390/en17236047.

14. Mukhametzyanova A.G., Bronskaya V.V., Kharitonova O.S. Neural network modeling of flow hydrodynamics in column apparatuses with nozzle elements // Herald of technological university. 2021. Т. 24, № 12. P. 139-141.

15. Frolov I.N., Firsin A.A., Okhotnikova E.S., Yusupova T.N., Ziganshin M.A. Тhe study of bitumen by differential scanning calorimetry: the interpretation of thermal effects // Petroleum Science and Technology. 2019. Т. 37, № 4. P. 417–424.

16. Laptev A.G., Lapteva E.A., Solovieva O.V., Klochkova V.A. Methods of Mathematical Modeling of Desorption of Poorly Soluble Gases in Packed Devices // Theoretical Foundations of Chemical Engineering. – 2024. – Vol. 58, No. 4. – P. 1027-1035. – DOI 10.1134/S0040579525600147.

17. Bakhtadze N.N., Lototsky V.A. Knowledge-based models of nonlinear systems based on inductive learning // Intelligent Systems Reference Library. 2016. Vol. 98. P. 85–104.

18. Tun M.S., Lakshminarayanan S., Emoto G. Data Selection and Regression Method and Its Application to Softsensing Using Multirate Industrial Data // Journal of Chemical Engineering of Japan. 2008. Vol. 41, Is. 5. P. 374–383.

19. Shaimukhametov D.R., Mustafina S.A., Shaimukhametova D.V. Direct modeling of the process of dehydrogenation of methylbutene into isoprene on the basis of artificial neural networks // Herald of technological university. 2017. Т. 20, № 24. P. 123-126.

20. Burlutsky E., Balzamov D., Bronskaya V. [et al.] Influence of Temperature on the Thermal Properties of the Core Material - the Coefficient of Temperature Conductivity, Specific Heat Capacity, Thermal Conductivity // International Journal of Technology. – 2023. – Vol. 14, №. 2. – P. 443. – DOI 10.14716/ijtech.v14i2.6009

21. Haibullina A.I., Zinnatullin N.X., Ilyin V.K. Improving heat exchanger efficiency using the pulsed method of cleaning. Power engineering: research, equipment, technology. 2021;23(1):59-67. (In Russ.) https://doi.org/10.30724/1998-9903-2021-23-1-59-67