«Automation and Informatization of the fuel and energy complex»

Evaluation of the possibility of building composite and nonlinear forecast models of key quality indicators of bitumen on the example of the bitumen production installation (BPI)

UDC: 681.5:665.637
DOI: 10.33285/2782-604X-2023-5(598)-26-33

Authors:

¹ National University of Oil and Gas "Gubkin University", Moscow, Russia

Keywords: additive property, oxidized bitumen, road bitumen, low-temperature properties, blending of oil products, compounded raw materials, viscosity, quality control, mathematical models, prediction of bitumen properties

Annotation:

The article deals with the problem of producing bitumen with specified quality characteristics using a bitumen production installation (BPI) by adding vacuum gasoil (VGO) to the initial product (tar). Reducing the VGO overconsumption will provide an additional economic effect. The construction of bitumen quality predictive models will allow obtaining operational data on its quality and reduce the VGO consumption. The bitumen production process is essentially non-linear and the quality of bitumen is highly dependent on the raw material quality. The article considers the hypothesis of improving the accuracy of predictive models of BPI quality key indicators by building composite (at the input of the models there used the data on the BPI raw material quality) and nonlinear models of the bitumen quality indicators. The article discusses conceptual approaches, the methodology and standard algorithms for calculating the key quality indicators of mixed raw material flows of BPI (tar softening temperature, tar viscosity) and bitumen (softening temperature, penetration at 25 °C) is completed and tested.

Bibliography:

1. Grudnikov I.B. Teoriya i praktika bitumnogo dela. – Ufa: Neftegazovoe delo, 2013. – 420 s.
2. Bitumnye vyazhushchie materialy: ucheb. posobie / A.I. Abdullin, T.F. Ganieva, M.R. Idrisov [i dr.]; pod red. E.A. Emel'yanychevoy. – SPb.: Prospekt Nauki, 2017. – 208 s.
3. Gun R.B. Neftyanye bitumy. – M.: Khimiya, 1973. – 432 s.
4. Murashkina A.V., Meshcheryakova E.A., Likhterova N.M. Vliyanie tekhnologicheskikh parametrov protsessa okisleniya gudronov na pokazateli kachestva bitumov // Vestn. MITKhT im. M.V. Lomonosova. – 2010. – T. 5, № 4. – S. 63–69.
5. Vliyanie gruppovogo khimicheskogo sostava smesi zapadnosibirskikh neftey na kachestvo dorozhnogo bituma / V.E. Somov, G.D. Zalishchevskiy, A.G. Brusnin [i dr.] // Khimiya i tekhnologiya topliv i masel. – 2016. – № 5(597). – S. 40–44.
6. Regulirovanie reologicheskikh svoystv dispersnykh sistem dlya obespecheniya sovremennykh trebovaniy k neftyanym dorozhnym bitumam / P.M. Tyukilina, A.A. Gureev, A.A. Andreev, R.E. Solov'ev // Khimiya i tekhnologiya topliv i masel. – 2019. – № 2(612). – S. 20–25.
7. Issledovanie vliyaniya gruppovogo sostava gudrona na kachestvo promyshlennykh okislitel'nykh bitumov / N.Yu. Belokon', V.G. Kompaneets, I.V. Kolpakova, T.K. Stupina // Neftepererabotka i neftekhimiya. – 2001. – № 1. – S. 19–23.
8. Matematicheskoe modelirovanie sostava syr'ya dlya proizvodstva neftyanykh dorozhnykh bitumov iz "sukhikh" gudronov / P.M. Tyukilina, A.A. Andreev, N.A. Sheykina [i dr.] // Mir nefteproduktov. Vestn. neftyanykh kompaniy. – 2017. – № 1. – S. 39–44.
9. Gureev A.A. Neftyanye vyazhushchie materialy. – M.: Nedra, 2018. – 239 s.
10. Sharikov Yu.V., Titov O.V. Modelirovanie i upravlenie protsessami okisleniya bitumov v kolonnykh okislitel'nykh apparatakh nepreryvnogo deystviya // Mezhdunar. nauch.-issled. zhurn. – 2014. – № 4-2(23). – S. 81–84.
11. Ispol'zovanie metoda analiza mnogomernykh dannykh pri razrabotke tekhnologii proizvodstva vysokokachestvennykh dorozhnykh bitumov // P.M. Tyukilina, V.N. Mel'nikov, V.A. Tyshchenko [i dr.] // Khimiya i tekhnologiya topliv i masel. – 2015. – № 5(591). – S. 15–20.
12. Lebedeva A.Yu. Sozdanie tsifrovoy modeli okislitel'nogo apparata ustanovki proizvodstva bituma // Novye idei v naukakh o Zemle: materialy XIV Mezhdunar. nauch.-prakt. konf., M., 02–05 apr. 2019 g.: v 7 t. T. 4. – M.: RGGU im. S. Ordzhonikidze, 2019. – S. 446–448.
13. Pearson R.K. Outliers in process modeling and identification // IEEE Transactions on Control Systems Technology. – 2002. – Vol. 10, Issue 1. – P. 55–63. – DOI: 10.1109/87.974338
14. A systematic approach for soft sensor development / Bao Lin, B. Recke, J.K.H. Knudsen, S.B. Jørgensen // Computers Aided Chemical Engineering. – 2007. – Vol. 31, Issue 5. – P. 419–425. – DOI: 10.1016/j.compchemeng. 2006.05.030
15. Scheffer J. Dealing with missing data // Research Letters in the Information and Mathematical Sciences. – 2002. – Vol. 3, No. 1. – P. 153–160.
16. Guyon I., Elisseeff A. An introduction to variable and feature selection // J. of Machine Learning Research. – 2003. – Vol. 3, No. 7-8. – P. 1157–1182.
17. Recursive PCA for adaptive process monitoring / Weihua Li, H.H. Yue, S. Valle-Cervantes, S. Joe Qin // J. of Process Control. – 2000. – Vol. 10, Issue 5. – P. 471–486. – DOI: 10.1016/S0959-1524(00)00022-6
18. Otchet po adaptatsii nelineynykh zakonov smesheniya temnykh nefteproduktov / Honeywell. – Omsk., 2017.