«Automation and Informatization of the fuel and energy complex»

Building of an upper level aggregation model for simulation calculations of non-stationary operational modes of the gas transportation system of the Unified Gas Supply System

UDC: 681.5:622.279
DOI: -

Authors:

¹ Gazprom, St. Petersburg, Russia
² NIIgazekonomika, Moscow, Russia

Keywords: system analysis, gas transmitting systems, non-stationary modeling, machine learning, Unified Gas Supply System

Annotation:

The authors of the article present approaches to the practical application of the previously described models [1] as well as algorithms developed by the authors for calculating the dynamics of gas flows throughout the gas transmission system (GTS) of the Unified Gas Supply System (UGSS) using machine learning models, obtaining a forecast of boundary conditions estimates at selected points of the GTS. The basis of the presented scientific study is the use of system analysis methods to construct adequate results of calculating the dynamics of gas flows in large gas transmission systems. The study considered the issues of forming an aggregated calculation scheme for the GTS of the UGSS and preparing the required initial data. A calculation method was developed based on a combination of linear optimization algorithms and machine-learning technologies to build high-level models. The expediency of carrying out clarifying calculations for individual fragments of the GTS using models with greater detailing, built on a training sampling based on the results of numerical experiments using physical models is noted.

Bibliography:

1. Prakticheskaya realizatsiya primeneniya neyrosetevykh modeley dlya modelirovaniya slozhnykh gazotransportnykh sistem bol'shoy razmernosti / N.A. Kislenko, S.N. Pankratov, V.V. Dedkova [i dr.] // Avtomatizatsiya i informatizatsiya TEK. – 2024. – № 9(614). – S. 33–41.
2. Algorithms and Theory of Computation Handbook. Optimization Problem. – CRC Press, 1999. – URL: https://www.nist.gov/dads/HTML/optimization.html (data obrashcheniya 24.12.2022).
3. Dutta S. Optimization in Chemical Engineering. – 2016. – URL: https://www.researchgate.net/publication/308725162_Optimization_in_Chemical_Engineering (data obrashcheniya 24.12.2022).
4. Yang Xin-She. Nature-Inspired Optimization Algorithms. – Second Edition. – Academic Press, 2020. – 310 p. – URL: https://www.researchgate.net/publication/344443170_Nature-Inspired_Optimization_Algorithms_Second_Edition (data obrashcheniya 24.12.2022).
5. Kochegurova E.A. Teoriya i metody optimizatsii: ucheb. posobie dlya vuzov. – M.: Yurayt, 2021. – 133 s.
6. Sukharev M.G., Stavrovskiy E.R. Optimizatsiya sistem transporta gaza. – M.: Nedra, 1975. – 277 s.
7. Smirnov V.A., Garlyauskas A.I., Firer A.S. Matematicheskie modeli i ikh primenenie v optimizatsionnykh raschetakh edinoy gazosnabzhayushchey sistemy: temat. nauch.-tekhn. obzor. – M.: VNIIEgazprom, 1971. – 60 s.
8. Gol'shteyn E.G., Yudin D.B. Zadachi lineynogo programmirovaniya transportnogo tipa. – M.: Nauka, 1969. – 382 s.
9. Khu T. Tselochislennoe programmirovanie i potoki v setyakh / per. s angl. P.L. Buzytskogo, E.V. Levnera, B.G. Litvaka; pod red. L.L. Fridmana. – M.: Mir, 1974. – 520 s.
10. Kazak A.S., Oleynikov A.V. Primenenie metodov sistemnogo analiza dlya postroeniya tsifrovykh dvoynikov fragmentov gazotransportnykh sistem na osnove neyrosetevogo modelirovaniya (osnovnye polozheniya metodologii analiza i sinteza) // Avtomatizatsiya i informatizatsiya TEK. – 2024. – № 1(606). – S. 5–12.
11. Issledovanie tselesoobraznosti neyrosetevogo modelirovaniya rezhimov raboty kompressornykh stantsiy / A.V. Oleynikov, A.S. Kazak, A.V. Belinskiy [i dr.] // Avtomatizatsiya i informatizatsiya TEK. – 2024. – № 2(607). – S. 10–19.
12. O novom metode tsifrovogo modelirovaniya nestatsionarnykh rezhimov techeniya gaza v magistral'nykh gazoprovodakh s primeneniem neyronnykh operatorov / A.V. Belinskiy, D.V. Gorlov, I.A. Pyatyshev, A.E. Titov // Gazovaya prom-st'. – 2024. – № 5(865). – S. 54–66.