«Automation and Informatization of the fuel and energy complex»

Application of decision tree algorithms for automating wet gas flow measurement and accounting processes

UDC: 62-52
DOI: -

Authors:

¹ Orenburg State University, Orenburg, Russia
² Baishev University, Aktobe, Kazakhstan

Keywords: machine learning, decision-making trees, natural gas, gas quantity accounting, gas flow rate, wet gas

Annotation:

In modern conditions of industrial production problem, particularly in the oil and gas sector, is ensuring accurate monitoring and accounting of wet gas flow rate and volume. Measurement errors when measuring this parameter, can lead to significant economic losses, as well as reduced reliability and efficiency of technological processes. Therefore, the development and implementation of intelligent methods used for automating wet gas measurement systems are of particular relevance. The author of the article presents an approach to solving this problem based on machine learning algorithms, specifically decision-making tree methods. The author considers the possibilities of applying these algorithms for processing technological process parameters and building models that provide high-accuracy forecasting. The proposed approach allows increasing the level of automation of accounting wet gas quantity systems, minimize the human factor impact and optimize the processes of wet gas measurement and control.

Bibliography:

1. Economides M.J., Wood D.A. The state of natural gas // Journal of Natural Gas Science and Engineering. – 2009. – Vol. 1, Issue 1-2. – P. 1–13. – DOI: 10.1016/j.jngse.2009.03.005
2. Yorucu V., Bahramian P. Price modelling of natural gas for the EU-12 countries: Evidence from panel cointegration // Journal of Natural Gas Science and Engineering. – 2015. – Vol. 24. – P. 464–472. – DOI: 10.1016/j.jngse.2015.04.006
3. Unaccounted for gas in natural gas transmission networks: Prediction model and analysis of the solutions / F. Arpino, M. Dell’Isola, G. Ficco, P. Vigo // Journal of Natural Gas Science and Engineering. – 2014. – Vol. 17. – P. 58–70. – DOI: 10.1016/j.jngse.2014.01.003
4. Istomin V.A. Problema obespecheniya pokazateley kachestva prirodnogo gaza i ravnovesiya uglevodorodnykh sistem s vodnymi fazami. – M.: IRTs Gazprom, 1999. – 78 s.
5. Daev Zh.A. Avtomatizirovannaya sistema kontrolya svedeniya balansa gaza na osnove metodov nechetkoy logiki // Vestnik MGTU "Stankin". – 2018. – № 3(46). – S. 131–135.
6. Opyt primeneniya neyrosetevogo podkhoda s doobucheniem seti na ogranichennom ob"eme vyborki dlya resheniya zadachi klassifikatsii ob"ektov okruzheniya magistral'nogo gazoprovoda / O.O. Prutsakov, K.N. Zhuchkov, D.V. Tret'yakov [i dr.] // Avtomatizatsiya i informatizatsiya TEK. – 2021. – № 12(581). – S. 14–20. – DOI: 10.33285/0132-2222-2021-12(581)-14-20
7. Burkov A. Mashinnoe obuchenie bez lishnikh slov. – SPb.: Piter, 2020. – 192 s.
8. Teoriya i praktika mashinnogo obucheniya: uchebnoe posobie / V.V. Voronina, A.V. Mikheev, N.G. Yarushkina, K.V. Svyatov. – Ul'yanovsk: UlGTU, 2017. – 290 s.
9. Komartsova L.G., Maksimov A.V. Neyrokomp'yutery. – 2-e izd., pererab. i dop. – M.: MGTU im. N.E. Baumana, 2004. – 400 s.
10. Flood susceptibility modelling using novel hybrid approach of reduced-error pruning trees with bagging and random subspace ensembles / Chen Wei, Hong Haoyuan, Li Shaojun [et al.] // Journal of Hydrology. – 2019. – Vol. 575. – P. 864–873. – DOI: 10.1016/j.jhydrol.2019.05.089
11. Cutler A., Cutler D.R., Stevens J.R. Random Forests // Ensemble Machine Learning. Methods and Applications. Chapter 5. – Springer New York, 2012. – P. 157–175.
12. Data Mining: Practical Machine Learning Tools and Techniques / I.H. Witten, E. Frank, M.A. Hall, C.J. Pal. – 2nd Edition. – San Francisco: Morgan Kaufmann Publishers, 2005. – P. 354–362.
13. Quinlan J.R. Learning with Continuous Classes // 5th Australian Joint Conference on Artificial Intelligence, Hobart, Nov. 16–18, 1992. – P. 343–348.
14. Quinlan J.R. Simplifying Decision Trees // International Journal of Man-Machine Studies. – 1987. – Vol. 27, Issue 3. – P. 221–234. – DOI: 10.1016/S0020-7373(87)80053-6
15. Lakshmi Devasena C. Proficiency comparison of LADTree and REPTree classifiers for credit risk forecast // International Journal on Computational Sciences & Applications. – 2015. – Vol. 5, Issue 1. – P. 39–50. – DOI: 10.48550/arXiv.1503.06608
16. Mohamed W.N.H.W., Salleh M.N.M., Omar A.H. A Comparative Study of Reduced Error Pruning Method in Decision Tree Algorithms // 2012 IEEE International Conference on Control System, Computing and Engineering, Penang, Malaysia, Nov. 23–25, 2012. – P. 392–397.