izmertechИзмерительная техникаIzmeritel`naya Tekhnika0368-10252949-5237ФГУП "ВНИИФТРИ"10.32446/0368-1025it.2024-9-19-26izmertech-2200Research ArticleИЗМЕРЕНИЯ В ИНФОРМАЦИОННЫХ ТЕХНОЛОГИЯХMEASUREMENTS IN INFORMATION TECHNOLOGIESМоделирование коэффициента истечения расходомеров переменного перепада давлений: аппроксимация радиальнобазисными нейронными сетямиModeling of the discharge coefcient of diferential pressure fowmeters: approximation by using radial-basis function neural networkshttps://orcid.org/0000-0002-7685-2862ДаевЖ. А.DayevZh. А.

Жанат Ариккулович Даев, профессор, доктор технических наук, автоматизированные системы управления, системы измерения, расходометрия

Актобе

Zhanat А. Dayev

Aktobe

zhand@yandex.ruБаишев УниверситетКазахстанBaishev UniversityKazakhstan202402112024091926Copyright © ФГУП "ВНИИФТРИ", 20242024ФГУП "ВНИИФТРИ"ФГУП "ВНИИФТРИ"https://www.izmt.ru/jour/about/submissions#copyrightNoticehttps://www.izmt.ru/jour/article/view/2200

Рассмотрен способ моделирования коэффициента истечения расходомеров переменного перепада давлений. Отмечена актуальность моделирования данного коэффициента методами машинного обучения, в частности нейронными сетями. Предложено использовать радиально-базисные нейронные сети для аппроксимации значений коэффициента истечения измерительных преобразователей типа стандартной диафрагмы. Разработана структура радиально-базисной нейронной сети, которая вычисляет коэффициенты истечения диафрагмы с угловым способом отбора давлений. Оценена погрешность аппроксимации значений коэффициента истечения радиально-базисными сетями и даны рекомендации по построению радиально-базисных сетей для решения задач моделирования характеристик расходомеров переменного перепада давлений. Обсуждены основные достоинства и недостатки применения подобных сетей для моделирования коэффициентов истечения диафрагм расходомеров переменного перепада давлений. По итогам исследования подтверждена эффективность использования радиально-базисных сетей для аппроксимации значений коэффициента истечения. Полученные результаты можно использовать для повышения точности измерений расхода газа и жидкостей с помощью расходомеров переменного перепада давлений.

The discharge coefficient of flow transducers of liquids and gases of differential pressure flowmeters plays an important role in flow rate measurement. The problem of modeling and calculating the discharge coefficient of differential pressure flowmeters directly affects the accuracy of flow rate measurement of these devices. The results of modeling the discharge coefficient of the differential pressure flowmeter in the form of radial-basis neural networks are presented. The described structure of the neural network calculates the values of the discharge coefficient with an angular pressure tapping method. The article evaluates the error of approximation of the discharge coefficient by radial-basis function networks and provides recommendations for building such networks to solve problems of modeling the characteristics of differential pressure flowmeters. The article discusses the main advantages and disadvantages of using such networks as discharge coefficients of the differential pressure flowmeters. The research showed that the use of such networks is justified by their properties to approximate the discharge coefficient and their efficiency in measuring gas and liquid flow rates.

расход газарадиально-базисные функциинейронные сетисистема измерения расходарасходомерgas flow rateradial basis functionneural networksflow measurement systemflowmeterАвтор заявляет, что во время подготовки данной рукописи не было получено никаких средств, грантов или другой поддержки.The author declares that no funds, grants, or other support were received during the preparation of this manuscript.ReferencesКремлевский П. П. Расходомеры и счётчики количества: Справочник. Машиностроение, Ленинград (1989).Kremlevsky P.P. Rashodomery i schetchiki kolichestva: Spravochnik [Flow meters and counters of substances: Handbook] Leningrad, Mashinostroenie Publ., 1989, 701 p. (In Russ.)Gallagher J. E. Natural Gas Measurement Handbook. Gulf Publishing Company (2007).Gallagher J. E. Natural Gas Measurement Handbook. Gulf Publishing Company. 2007. 425 p.LaNasa P. J., Upp E. L. Fluid Flow Measurement. Butterworth-Heinemann (2014).LaNasa P. J., Upp E. L. Fluid Flow Measurement. Butterworth-Heinemann. 2014. 296 p.Reader-Harris M. Orifi ce plates and Venturi tubes. Springer International Publishing, London (2015).Reader-Harris M. Orifice plates and Venturi tubes. London: Springer International Publishing. 2015. 386 p.Stolz J. A Universal Equation for the Calculation of Discharge Coefficient of Orifice Plates. North-Holland, Amsterdam (1978).Stolz J. A Universal Equation for the Calculation of Discharge Coefficient of Orifice Plates. Amsterdam: North-Holland, 1978. 32 p.Reader-Harris M. J., Sattary J. A., Spearman E. P. The Orifice Plate Discharge Coefficient Equation. Progress Report No. PR14: EUEC/17 (EEC005). NEL, East Kilbride, Glasgow (1992).Reader-Harris M.J., Sattary J.A., Spearman E.P. The Orifice Plate Discharge Coefficient Equation. East Kilbride, Glasgow: NEL, Progress Report No. PR14: EUEC/17 (EEC005). 1992.Cristancho D. E., Hall K. R., Coy L. A., Iglesias-Silva G. A. An alternative formulation of the standard orifice equation for natural gas. Flow Measurement and Instrumentation, 21, 299–301 (2010). https://doi.org/10.1016/j.flowmeasinst.2010.03.003Cristancho D.E., Hall K.R., Coy L.A., Iglesias-Silva G.A. An alternative formulation of the standard orifice equation for natural gas // Flow Measurement and Instrumentation. 2010. Vol. 21. P. 299 – 301.Reader-Harris M. J., Barton N., Hodges D. The effect of contaminated orifice plates on the discharge coefficient. Flow Measurement and Instrumentation, 25, 2–7 (2012). https://doi.org/10.1016/j.flowmeasinst.2011.11.003Reader-Harris M.J., Barton N., Hodges D. The effect of contaminated orifice plates on the discharge coefficient // Flow Measurement and Instrumentation. 2012. Vol. 25. P. 2 – 7.Baker O., Lau P., Tawackolian K. Reynolds number dependence of an orifice plate. Flow Measurement and Instrumentation, 30, 123–132 (2013). https://doi.org/10.1016/j.flowmeasinst.2013.01.009Baker O., Lau P., Tawackolian K. Reynolds number dependence of an orifice plate // Flow Measurement and Instrumentation. 2013. Vol. 30. P. 123 – 132.Dayev Z. A., Kairakbaev A. K. Modeling of coefficient of contraction of differential pressure flowmeters. Flow Measurement and Instrumentation, 66, 128–131 (2019). https://doi.org/10.1016/j.flowmeasinst.2019.02.009Dayev Z.A., Kairakbaev A.K. Modeling of coefficient of contraction of differential pressure flowmeters. Flow Measurement and Instrumentation. 2019. Vol. 66. P. 128 – 131.Hua C., Geng Y. Wet gas metering technique based on slotted orifice and swirlmeter in series. Flow Measurement and Instrumentation, 30, 138–143 (2013). https://doi.org/10.1016/j.flowmeasinst.2013.02.001Hua C., Geng Y. Wet gas metering technique based on slotted orifice and swirlmeter in series // Flow Measurement and Instrumentation. 2013. Vol. 30. P. 138-143.Dayev Z. A. Theoretical modelling of natural gas unsteady flow rate measurement using variable differential pressure method. Flow Measurement and Instrumentation, 62, 33–36 (2018). https://doi.org/10.1016/j.flowmeasinst.2018.05.009Dayev Z.A. Theoretical modelling of natural gas unsteady flow rate measurement using variable differential pressure method // Flow Measurement and Instrumentation. 2018. Vol. 62. P. 33 – 36.Düz H. Effect of conical angle on the hydraulic properties of orifice plate flows: A numerical approach. Flow Measurement and Instrumentation, 81, 102026 (2021). https://doi.org/10.1016/j.flowmeasinst.2021.102026Düz H. Effect of conical angle on the hydraulic properties of orifice plate flows: A numerical approach // Flow Measurement and Instrumentation. 2021. Vol. 81. №102026.Sravani V., Venkata S. K. Parametric analysis of orifice plates on measurement of flow: A review. Ain Shams Engineering Journal, 13, 101639 (2022). https://doi.org/10.1016/j.asej.2021.11.008Sravani, V., Venkata, S.K. Parametric analysis of orifice plates on measurement of flow: A review // Ain Shams Engineering Journal. 2022. Vol. 13. №101639.Wu Y., Ma Y., Lyu J., Niu F., Jiao Q. Experimental study on effect of structural parameters on pressure drop characteristics of multi-orifice plates. Flow Measurement and Instrumentation, 91, 102346 (2023). https://doi.org/10.1016/j.flowmeasinst.2023.102346Wu Y., Ma Y., Lyu J., Niu F., Jiao Q. Experimental study on effect of structural parameters on pressure drop characteristics of multi-orifice plates. Flow Measurement and Instrumentation. 2023. Vol. 91. №102346.Borg D., Suetake M., Brandão D. A neural network developed in a Foundation Fieldbus environment to calculate flow rates for compressible fl uid. Flow Measurement and Instrumentation, 40, 142–148 (2014). https://doi.org/10.1016/j.flowmeasinst.2014.09.007Borg D., Suetake M., Brandão D. A neural network developed in a Foundation Fieldbus environment to calculate flow rates for compressible fluid // Flow Measurement and Instrumentation. 2014. Vol. 40. P. 142-148.Shaban H., Tavoularis S. Measurement of gas and liquid flow rates in two-phase pipe flows by the application of machine learning techniques to differential pressure signals. International Journal of Multiphase Flow, 67, 106–117 (2014). https://doi.org/10.1016/j.ijmultiphaseflow.2014.08.012Shaban H., Tavoularis S. Measurement of gas and liquid flow rates in two-phase pipe flows by the application of machine learning techniques to differential pressure signals // International Journal of Multiphase Flow. 2014. Vol. 67. P. 106 – 117.Dayev Zh. A. Application of artificial neural networks instead of the orifice plate discharge coefficient. Flow Measurement and Instrumentation, 71, 101674 (2020). https://doi.org/10.1016/j.flowmeasinst.2019.101674Dayev Zh.A. Application of artificial neural networks instead of the orifice plate discharge coefficient // Flow Measurement and Instrumentation. 2020. Vol. 71. №101674.Dayev Zh. A., Kairakbaev A. K. Fuzzy interpretation of the discharge coefficient for the orifice plate of automated flow rate measuring systems. Applied Artificial Intelligence, 35, 1128–1146 (2021). https://doi.org/10.1080/08839514.2021.1975378Dayev Z. A., Kairakbaev A. K. Fuzzy interpretation of the discharge coefficient for the orifice plate of automated flow rate measuring systems. Applied Artificial Intelligence, 35, 1128–1146 (2021). https://doi.org/10.1080/08839514.2021.1975378Dayev Z., Shopanova G., Toksanbaeva B. et al. Modeling the flow rate of dry part in the wet gas mixture using decision tree/kernel/non-parametric regression-based soft-computing techniques. Flow Measurement and Instrumentation, 86, 102195 (2022). https://doi.org/10.1016/j.flowmeasinst.2022.102195Dayev Z., Shopanova G., Toksanbaeva B. et al. Modeling the flow rate of dry part in the wet gas mixture using decision tree/kernel/non-parametric regression-based soft-computing techniques. Flow Measurement and Instrumentation, 86, 102195 (2022). https://doi.org/10.1016/j.fl owmeasinst.2022.102195Haykin S. Neural Networks. A Comprehensive Foundation. Prentice Hall (1999).Haykin S. Neural Networks. A Comprehensive Foundation. Prentice Hall (1999).Shaik M. E., Islam M. M., Hossain Q. S. A review on neural network techniques for the prediction of road traffic accident severity. Asian Transport Studies, 7, 100040 (2021). https://doi.org/10.1016/j.eastsj.2021.100040Shaik M. E., Islam M. M., Hossain Q. S. A review on neural network techniques for the prediction of road traffic accident severity. Asian Transport Studies, 7, 100040 (2021). https://doi.org/10.1016/j.eastsj.2021.100040Wu H., Cai X., Feng M. The evaluation of course teaching effectbased on improved RBF neural network. Systems and Soft Computing, 6, 200085 (2024). https://doi.org/10.1016/j.sasc.2024.200085Wu H., Cai X., Feng M. The evaluation of course teaching effect based on improved RBF neural network. Systems and Soft Computing, 6, 200085 (2024). https://doi.org/10.1016/j.sasc.2024.200085Nassajian Mojarrad F., Han Veiga M., Hesthaven J.S., Öffner P. A new variable shape parameter strategy for RBF approximation using neural networks. Computers & Mathematics with Applications, 143, 151–168 (2023). https://doi.org/10.1016/j.camwa.2023.05.005Nassajian Mojarrad F., Han Veiga M., Hesthaven J. S., Öffner P. A new variable shape parameter strategy for RBF approximation using neural networks. Computers & Mathematics with Applications, 143, 151–168 (2023). https://doi.org/10.1016/j.camwa.2023.05.005

The authors declare that there are no conflicts of interest present.