Moscow State University. M.V. Lomonosov (Department of Socio-Cultural Design and Development of Territories, professor)
Moskva, Moscow, Russian Federation
This article considers the application of machine learning methods in process modeling systems to predict the state of equipment in various industries. The relevance of the topic is due to the need to improve the efficiency of production operations in an increasingly competitive and rapidly changing market environment. The paper presents a review of modern technological process modeling systems and describes their application areas. Special attention is paid, to such forecasting methods as linear regression, recurrent neural networks of long-term memory and autoregressive integrated moving average model. In the practical part, data analysis as well as an experiment for predicting temperature values using the above-mentioned methods was carried out. The results showed that for the data used, the LSTM and ARIMA models provide higher prediction accuracy.
process modeling systems, modeling, prediction, import substitution, refinery, oil and gas industry, machine learning, linear regression, LSTM, ARIMA, process optimization, technological processes
1. Shmeleva A.S., Suloeva S.B., Rostova O.V. Metody i instrumenty gibkogo upravleniya cifrovymi innovacionnymi proektami: monografiya. – SPb: Politeh-Press, 2023. – 240 s.
2. Anisimov V.G. Analiz i ocenivanie effektivnosti investicionnyh proektov v usloviyah neopredelennosti / V.G. Anisimov [i dr.].- Moskva: Voennaya akademiya General'nogo shtaba Vooruzhennyh sil Rossiyskoy Federacii; 2006. 288 s. EDN: https://elibrary.ru/SWBIZP.
3. Il'in I.V. Matematicheskie metody i instrumental'nye sredstva ocenivaniya effektivnosti investiciy v innovacionnye proekty / I.V. Il'in [i dr.]. - Sankt-Peterburg, 2018.- 289 s. EDN: https://elibrary.ru/XMMDTV.
4. Anisimov V.G. Strategicheskoe upravlenie innovacionnoy deyatel'nost'yu: analiz, planirovanie, modelirovanie, prinyatiya resheniy, organizaciya, ocenka / V.G. Anisimov [i dr.].- Sankt-Peterburg, 2017.- 312 s. EDN: https://elibrary.ru/ZCXSIN.
5. Anisiforov A.B., Rostova O.V., Balabneva O.A. Osnovy cifrovoy transformacii biznesa: ucheb. posobie. – SPb: Politeh-Press, 2023. – 96 s. DOI: https://doi.org/10.18720/SPBPU/2/id23-636; EDN: https://elibrary.ru/NQGNMK
6. Sistemy imitacionnogo modelirovaniya: vybiraem podhodyaschuyu / [Elektronnyy resurs]. URL: https://habr.com/ru/companies/lanit/articles/351870 / (data obrascheniya: 05. 01. 2025).
7. Shirokova S.V., Rostova O.V., Bolsunovskaya M.V., Dmitrieva L.A., Almataev T.O. Audit informacionnoy bezopasnosti proizvodstvennoy kompanii // Informacionnye i upravlyayuschie sistemy. – 2023. – № 1 (122). – S. 41-50. DOI: https://doi.org/10.31799/1684-8853-2023-1-41-50; EDN: https://elibrary.ru/MFUKDX
8. Saurenko T.N. Modeli ocenki ekologo-ekonomicheskih posledstviy tehnogennyh avariy na promyshlennyh ob'ektah / T.N. Saurenko [i dr.] // Ekonomicheskie strategii EAES: problemy i innovacii: sbornik materialov IV Mezhdunarodnoy nauchno-prakticheskoy konferencii.- Moskva, 2021. S. 126-140. EDN: https://elibrary.ru/DLKSHN.
9. Saurenko T.N.Matematicheskie modeli prognozirovaniya ekologicheskoy ugrozy tehnogennyh avariy i katastrof v sostave integrirovannyh sistem bezopasnosti regiona / T.N. Saurenko [i dr.] // Tehnologii grazhdanskoy bezopasnosti. 2019. T. 16. № 3 (61). S. 62-67. EDN: https://elibrary.ru/DUUIRX. DOI:https://doi.org/10.54234/CST.19968493.2019.16.3.61.11.62.
10. Zegzhda P.D. Metodicheskiy podhod k postroeniyu modeley prognozirovaniya pokazateley svoystv sistem informacionnoy bezopasnosti / P.D. Zegzhda [i dr.] // Problemy informacionnoy bezopasnosti. Komp'yuternye sistemy. 2019. № 4. S. 45-49. EDN: https://elibrary.ru/QLDDDQ.
11. Anisimov V.G., Anisimov E.G., Veselko A.A., Pak A.Yu.Ocenka effektivnosti tehnologicheskih processov na predpriyatiyah mashinostroitel'noy otrasli ekonomiki// Zhurnal tehnicheskih issledovaniy. 2022. T. 8. № 1. S. 30-35. EDN: https://elibrary.ru/GBDHEU.
12. Mal'kov M. V., Oleynik A. G., Fedorov A. M. Modelirovanie tehnologicheskih processov: metody i opyt. Trudy Kol'skogo nauchnogo centra RAN, – 2010, t.13, – №4. – C. 1-9.
13. Komp'yuternoe modelirovanie tehnologicheskih processov / [Elektronnyy resurs]. URL: http://tstu-isman.tstu.ru/pdf/lecture3.pdf / (data obrascheniya: 05. 01. 2025).
14. Rostova O.V., Shirokova S.V., Usikov R.F. Upravlenie sistemami informacionno-tehnologicheskoy podderzhki na predpriyatii po proizvodstvu slozhnyh tehnicheskih kompleksov // Voprosy oboronnoy tehniki. Seriya 16: Tehnicheskie sredstva protivodeystviya terrorizmu. – 2020. – № 3-4 (141-142). – S. 9-18. EDN: https://elibrary.ru/EQVFGP
15. Tebekin A.V. Sposob formirovaniya kompleksnyh pokazateley kachestva innovacionnyh proektov i programm / A.V. Tebekin [i dr.] // Zhurnal issledovaniy po upravleniyu.
16. T. 4. № 11. S. 30-38. EDN: https://elibrary.ru/YQGWDB.
17. Anisimov V.G., Anisimov E.G., Lihacheva O.A. Model' dlya ocenivaniya vliyaniya raspredeleniya resursov na kachestvo obrazovatel'nogo processa // Vestnik Rossiyskoy tamozhennoy akademii. 2012. № 4. S. 060-066. EDN: https://elibrary.ru/PJBTZP.
18. Anisimov V.G., Lihacheva O.A., Sergeev I.V. Ocenka kachestva obrazovatel'nogo processa c ispol'zovaniem matematicheskoy modeli// Vestnik universiteta. 2012. № 18. S. 152-155. EDN: https://elibrary.ru/OGPAXA.
19. Sazykin A.M. Prognozirovanie sformirovannosti voenno-professional'nyh kompetenciy/ A.M. Sazykin [i dr.]// Izvestiya Rossiyskoy akademii raketnyh i artilleriyskih nauk. 2024. № 2 (132). S. 32-36. EDN: https://elibrary.ru/ARHNUG. DOI:https://doi.org/10.53816/20753608_2024_2_32.
20. Anisimov V.G., Anisimov E.G., Bosov D.B. Matematicheskie modeli i metody upravleniya innovacionnymi proektami.- Moskva, 2009. 188 s. EDN: https://elibrary.ru/TMDMSP.
21. Tebekin A.V. Model' prognoza stoimosti i srokov modernizacii promyshlennyh predpriyatiy / A.V. Tebekin [i dr.] // Zhurnal issledovaniy po upravleniyu. 2019. T. 5. № 3. S. 31-37. EDN: https://elibrary.ru/XBWMXL.
22. Avdeev M.M. Informacionno-statisticheskie metody v upravlenii mikroekonomicheskimi sistemami / M.M. Avdeev [i dr.]. - Sankt-Peterburg; Tula. 2001. 139 s. EDN: https://elibrary.ru/TMDNNJ.
23. Vidy i tipy mashinnogo obucheniya / [Elektronnyy resurs]. URL: https://sky.pro/wiki/python/vidy-i-tipy-mashinnogo-obucheniya (data obrascheniya: 25. 01. 2025).
24. Vedernikov Yu.V. Modeli i algoritmy intellektualizacii avtomatizirovannogo upravleniya diversifikaciey deyatel'nosti promyshlennogo predpriyatiya / Yu.V. Vedernikov, A.Yu. Gar'kushev [i dr.] // Voprosy oboronnoy tehniki. Seriya 16: Tehnicheskie sredstva protivodeystviya terrorizmu. 2014. № 5-6 (71-72). S. 61-72. EDN: https://elibrary.ru/SFKMTZ. DOI: https://doi.org/10.1109/MITS.2014.2355083
25. Skorohod A. V. Obzor algoritmov s chastichnym privlecheniem uchitelya. – Petrozavodsk: MCNP «Novaya nauka», 2021. – S. 239-243. EDN: https://elibrary.ru/VLAWYZ
26. Lineynaya regressiya / [Elektronnyy resurs] // https://habr.com/ru/articles/804135 / (data obrascheniya: 06. 01. 2025).
27. Rekurrentnaya neyronnaya set' (RNN): vidy, obuchenie, primery / [Elektronnyy resurs]. URL: https://neurohive.io/ru/osnovy-data-science/rekurrentnye-nejronnye-seti (data obrascheniya: 06. 01. 2025).
28. Tregub A. V., Tregub I. V. Metodika postroeniya modeli ARIMA dlya prognozirovaniya dinamiki vremennyh ryadov // Lesnoy vestnik. – 2011. – № 5. – C. 179-183.
29. Prognozirovanie vremennyh ryadov metodom ARIMA / [Elektronnyy resurs]. URL: https://elar.urfu.ru/bitstream/10995/52487/1/978-5-9908685-0-2_2017_72.pdf (data obrascheniya: 22. 01. 2025).
30. Agbessi A. P., Salami A. A., Agbosse K. S., Birregah B. Peak Electrical Energy Consumption Prediction by ARIMA, LSTM, GRU, ARIMA-LSTM and ARIMA-GRU [Elektronnyy resurs]. URL: https://www.mdpi.com/1996-1073/16/12/4739 (data obrascheniya: 06. 01. 2025). DOI: https://doi.org/10.3390/en16124739
31. Gazofrakcioniruyuschaya ustanovka (GFU) / [Elektronnyy resurs]. URL: https://neftegaz.ru/tech-library/neftekhimiya/142166-gazofraktsioniruyushchaya-ustanovka-gfu/ (data obrascheniya: 16. 01. 2025).
32. Shmeleva A.S., Suloeva S.B., Rostova O.V. Informacionnaya podderzhka upravleniya innovacionno-investicionnoy deyatel'nost'yu predpriyatiya neftegazovoy otrasli // Zhurnal issledovaniy po upravleniyu. – 2021. – T. 7. – № 6. – S. 57-67. EDN: https://elibrary.ru/ZGCCKX
33. Modelirovanie tehnologicheskih processov / [Elektronnyy resurs]. URL: https://ntik.ru/services/digital/solutions/proxima (data obrascheniya: 14. 01. 2025).
34. Ragas A.A.M.A., Chupin A.L., Bolsunovskaya M. V., Shirokova S. V., Senotrusova, S. V. Accelerating Sustainable and Economic Development via Scientific Project Risk Management Model of Industrial Facilities / /Sustainability (Switzerland), 2023. DOI: https://doi.org/10.3390/su151712942
