The article concentrated on the relevant issue of ensuring the reliability of turbine flow transducers (TFT), used to determine the volumetric flow rate as part of crude quality control systems (CQCS). As the author notes, the reliability, especially its numerical indicators, shall be considered separately for each homogeneous group of equipment, including measuring instruments, which have their own functional and technological features. Separate attention is given to crucial factors that must be considered when determining the metrological reliability of not only TFT but also of any other measuring instruments that are subject to the measurement of metrological performances over time and methods for monitoring the metrologically sound order of TFT. The research included an analysis of the application of the predictive analytics method in mechanical engineering for monitoring of the technical and metrological state of equipment. Software has been developed using Python and an algorithm for determining the volumetric flow rate in the system for collecting and processing information in the CQCS depending on the values of the Reynolds number, which makes it possible to early detect the occurrence of a metrological failure of the TFT. The data on the results of verification and metrological performances control of 60 TFT running on oil with different rheological properties over the past 5 years were analyzed. The conducted research showed that the application of the algorithm will allow to: reduce the risk of emergency situations and termination of accounting operations in the CQCS; reduce the duration of forced downtime of the CQCS or reduce them completely to zero; obtain reliable data on the performance of the TFT, which makes it possible to predict the residual life of parts and assemblies (the operating time before the limit state), etc.
References
1. Aralov O.V., Buyanov I.V., Analysis of methods and approaches to reliability assessment in the prediction of main pipeline transport equipment failures (In Russ.), Nauka i tehnologii truboprovodnogo transporta nefti i nefteproduktov = Science & Technologies: Oil and Oil Products Pipeline Transportation, 2017, V. 7, no. 6, pp. 104–114.
2. Otkhman N.Z., Polukhin V.I., Improvement of metrological reliability in design of data-measuring systems (In Russ.), Vestnik TGTU, 2011, no. 2, pp. 365-370.
3. Efremov L.V., Estimation of instrument metrological reliability from group testing data (In Russ.), Priborostroenie, 2012, no. 6.
4. Gusenitsa Ya.N., Sherstobitov S.A., Malakhov A.V., Method of substantiation of calibration intervals of measuring instruments (In Russ.), Naukoemkie tekhnologii v kosmicheskikh issledovaniyakh Zemli, 2016, no. S1.
5. Avci C., Tekinerdogan B., Athanasiadis I.N., Software architectures for big data: a systematic literature review, Big Data Analytics, 2020, V. 5, no. 5, DOI:10.1186/s41044-020-00045-1
6. Chun-Wei Tsai, Chin-Feng Lai, Han-Chieh Chao, Vasilakos A.V., Big data analytics: a survey, Journal of Big Data 2, 2015, no. 1, DOI:10.1186/s40537-015-0030-3
7. Hasan M., Genetic algorithm and its application to big data analysis, International Journal of Scientific & Engineering Research, 2014, V. 5, no. 1, pp. 1991–1996.
8. Tolk A., The next generation of modeling & simulation: Integrating big data and deep learning, Proceedings of Summer Simulation Multiconference, 2015 At: Chicago, IL. 2015.
9. Ribeiro A., Silva A., da Silva A., Data modeling and data analytics: A survey from a big data perspective, Journal of Software Engineering and Applications, 2015, no. 8, pp. 617–634, DOI:10.4236/jsea.2015.812058
10. Khasanov A.R., Impact of predictive analytics on the activities of companies (In Russ.), SRRM, 2018, no. 3 (108), DOI:10.17747/2078-8886-2018-3-108-113
11. Dobrynin S.L., Burkovskiy V.L., Monitoring and predictive analytics of technological equipment on the based of industrial internet of things (In Russ.), Voronezhskiy gosudarstvennyy tekhnicheskiy universitet, 2020, V. 16, no. 5, pp. 7–12, DOI 10.36622/VSTU.2020.16.5.001.
12. D'yakov N.A., Golunova A.S., Process control systems based on predictive analytics: Design (In Russ.), Elektrotekhnicheskie sistemy i kompleksy, 2021, no. 1 (50), pp. 58–64, DOI: https://doi.org/10.18503/2311-8318-2021-1(50)-58-64
13. Livanov M., Russia's first complex of predictive analytics for power and industrial equipment (In Russ.), Ekspozitsiya neft' i gaz, 2016, no. 3 (49), pp. 82–83.
14. Gorelik A., The enterprise big data lake: Delivering the promise of big data and data science, O’Reilly Media, 2019, 224 p.
15. Aralov O.V., Buyanov I.V., Savanin A.S., Iordanskiy E.I., Research of methods for oil kinematic viscosity calculation in the oil-trunk pipeline (In Russ.), Nauka i tekhnologii truboprovodnogo transporta nefti i nefteproduktov = Science & Technologies: Oil and Oil Products Pipeline Transportation, 2017, V. 7, no. 5, pp. 97–105.
