R.A. Batashov1

1 Plekhanov Russian University of Economics (Moscow, Russia)
1 rusbatashov@gmail.com

In this research, the integration of machine learning models into operational calculations of capacitive level gauges is considered. The purpose of the work is to develop a mathematical algorithm, modeling measurement processes based on machine learning equations, to calculate the volume of petroleum products in a tank according to the principle of operation of the information and measuring system of a capacitive discrete-continuous level gauge. The study analyzes the principles of measurement using various methods: continuous and discrete level measurement, and also developed a combined approach for measuring the level of petroleum products.
A comparative analysis of the technical characteristics of various measurement methods has been carried out. Based on this analysis, a machine learning model was created using random forest and neural network algorithms. The results of the work were carefully analyzed and interpreted, which made it possible to draw sound technical conclusions. Thus, the introduction of information technology and machine learning into measurement processes opens up new opportunities to improve the accuracy and reliability of data in the oil and gas industry.

Batashov R.A. The research of the model of artificial neural networks in the processing and analysis of data from measuring equipment. Information-measuring and Control Systems. 2025. V. 23. № 1. P. 33−40. DOI: https://doi.org/10.18127/j20700814-202501-04 (in Russian)

1. Gutnikov V.S. Integral'naya elektronika v izmeritel'nyh ustrojstvah: uchebnik dlya vuzov. L.: Energiya. 1980. 240 s.
2. Grohol'skij A.L., Gorbov M.M., Strunskij M.G, Fedotov V.K. Emkostnye pervichnye izmeritel'nye preobrazovateli diametra neizoliro­vannogo mikroprovoda. Izmereniya, kontrol', avtomatizaciya: Nauch.-tekhn. sb. obzorov / CNII TEN priborostroeniya. M.: Akademiya. 1978. 256 s.
3. Cheredov A.I. Preobrazovateli dlya elektricheskogo izmereniya parametrov emkostnyh datchikov. Diss. na soiskanie uchenoj stepeni k.t.n. L.: Energiya. 1984. 233 s.
4. Buhgol'c V.P., Tisevich E.G. Emkostnye preobrazovateli v sistemah avtomaticheskogo kontrolya i upravleniya. M.: Energiya. 1972. 80 s.
5. Pat. 2239164 Rossijskaya Federaciya, MPK 21V 47/00. Emkostnoj urovnemer so shtangoj / A.G. Godnev, V.M. Suslov; zayavitel' i patentoobladatel' A.G. Godnev: opubl. v B.I. 2002. № 30.
6. Mirkes E.M., Gorban' A.N., Dunin-Barkovskij V.L., Kirdin A.N. i dr. Logicheski prozrachnye nejronnye seti i proizvodstvo yavnyh znanij iz dannyh. Nejroinformatika. Novosibirsk: Nauka. Sibirskoe predpriyatie RAN. 1998. 296 s.
7. Blohin N.V., Makrushin S.V. Postroenie vektornogo predstavleniya otraslej ekonomiki s pomoshch'yu grafovyh nejronnyh setej. Informacionno-izmeritel'nye i upravlyayushchie sistemy. 2023. T. 21. № 5. S. 7−15. DOI: https://doi.org/10.18127/j20700814-202305-02