Study of the Hamming network efficiency for the sucker-rod oil pumping unit status identification

dc.citation.epage50
dc.citation.issue1
dc.citation.spage45
dc.citation.volume7
dc.contributor.affiliationLviv Polytechnic National University
dc.contributor.authorМаляр, Андрій
dc.contributor.authorАндреїшин, Андрій
dc.contributor.authorКалужний, Богдан
dc.contributor.authorГоловач, Ігор
dc.contributor.authorMalyar, Andriy
dc.contributor.authorAndreishyn, Andriy
dc.contributor.authorKaluzhnyi, Bohdan
dc.contributor.authorHolovach, Ihor
dc.coverage.placenameLviv
dc.date.accessioned2018-06-07T11:41:57Z
dc.date.available2018-06-07T11:41:57Z
dc.date.created2017-02-19
dc.date.issued2017-02-19
dc.description.abstractПроцес нафтовидобутку нафти потребує проведення постійного моніторингу роботи обладнання свердловин. Одним з найдієвіших методів оперативного контролю роботи штангових глибинних насосів є отримання інформації від давача зусилля в полірованому штоці або давача струму привідного двигуна верстата-гойдалки. У багатьох випадках завчасне розпізнавання неполадок і здійснення профілактичного ремонту дають змогу уникати великих матеріальних витрат. У зв’язку з цим актуальними є дослідження, пов’язані з розробленням систем діагно- стики та створення на їхній основі автоматизованих систем керування ШГПУ. Розглянуто підхід до вирішення завдання прогнозування технічного стану штангових глибинних насосів з використанням нейромережевих технологій. Як нейронну мережу використано модифіковану мережу Хопфілда – мережу Хемінга. Для неї створено алгоритм ідентифікації стану ШГПУ, завдяки якому результатом розпізнавання є не сам зразок, а тільки його номер. У результаті прискорюється робота мережі і витрачаються менші обчислювальні ресурси та пам’ять. Для тестування працездатності запропонованого алгоритму розпізнавання створено лабораторний стенд, який імітує роботу системи діагностики стану ШГПУ. Отримані експериментальні результати показали, що система ідентифікації на основі мережі Хемінга може в реальному часі та з мінімальними похибками розпізнавати поточний стан глибиннопомпового обладнання.
dc.description.abstractThe oil extraction process requires continuous monitoring of the oil well equipment operation. One of the most effective methods of the online control of sucker-rod pumps operation is obtaining information from the force sensor in the polished rod or the current sensor of the pump jack driving motor. In many cases, timely troubleshooting and preventive repair allow saving large costs. Therefore, studies in the area of developing diagnostic systems and, on their basis, creating automated control systems for sucker-rod pumping units (SRPU) are of topical value. The paper discusses the neural-network-based approach to solving the tasks of forecasting the technical status of jack pumps. The modified Hopfield network (Hamming network) was used as a neural network, for which an SRPU status identification algorithm was devised. Due to it, the identification process outputs not the sample curve itself, but only its number, which results in the faster neural network and smaller computing resources and memory required. For testing the performance of the proposed identification algorithm, a laboratory bench simulating the operating SRPU status diagnostic system was created. The obtained experimental data show that the Hamming-network-based identification system can perform real-time diagnosing of the current status of the downhole equipment with the minimum error.
dc.format.extent45-50
dc.format.pages6
dc.identifier.citationStudy of the Hamming network efficiency for the sucker-rod oil pumping unit status identification / Andriy Malyar, Andriy Andreishyn, Bohdan Kaluzhnyi, Ihor Holovach // Computational Problems of Electrical Engineering. — Lviv : Lviv Politechnic Publishing House, 2017. — Vol 7. — No 1. — P. 45–50.
dc.identifier.citationenStudy of the Hamming network efficiency for the sucker-rod oil pumping unit status identification / Andriy Malyar, Andriy Andreishyn, Bohdan Kaluzhnyi, Ihor Holovach // Computational Problems of Electrical Engineering. — Lviv : Lviv Politechnic Publishing House, 2017. — Vol 7. — No 1. — P. 45–50.
dc.identifier.issn2224-0977
dc.identifier.urihttps://ena.lpnu.ua/handle/ntb/41502
dc.language.isoen
dc.publisherLviv Politechnic Publishing House
dc.relation.ispartofComputational Problems of Electrical Engineering, 1 (7), 2017
dc.relation.references[1] А. F. Shageev, А. М. Timusheva, L. N. Shageeva, and А. S. Grishkin, “Automated monitoring of the oil well treatment – the first stage of intelligent control systems”, Neftyanoye khozyaistvo, no. 11, pp. 48–49, Moscow, Russia, 2000. (Russian)
dc.relation.references[2] А. . Galeev, R. I. Аrslanov, P. P. Yermilov, and I. А. Kuzmin, “Control of technical condition oil-well pumping unit under periodic operation conditions”, http://ogbus.ru/authors/GaleevAS/GaleevAS_2.pdf. (Russian)
dc.relation.references[3] М. I. Khakimyanov and S. V. Svatlakova, “Optimal methods for encoding dynamogamms of deep-well pumping units”, іn Electrotechnology, electric drive and electrical equipment of enterprises, pp. 146–150, Ufa, Russia: UGNTU, 2005. (Russian)
dc.relation.references[4] P. Lionel Evina Ekombo, Noureddine Ennahnahi and Mohammed Oumsis, “Application of affine invariant Fourier descriptor to shape-based image retrieval”, International Journal of Computer Science and Network Security (IJCSNS), vol. 9, no. 7, pp. 240–247, 2009.
dc.relation.references[5] S. Mallat, A wavelet tour of signal processing. Мoscow, Russia:Mir, 2005. (Russian)
dc.relation.references[6] Т. Aliev and О. Nusratov, “The methods and diagnostic tools deep pumping oil well equipment”, Neftyanoye khozyaistvo, no. 9, pp. 78–80, Moscow, Russia, 1998. (Russian)
dc.relation.references[7] А. М. Zyuzev, and А. V. Kostylev, “A neuralnetwork- based system of the sucker-rod oil pumping unit diagnostics”, in Proc. 2nd Russian Scientific Conference “Design of engineering and scientific applications in the MATLAB”, pp.1273–1287, Moscow, Russia, May 25–26, 2004. (Russian)
dc.relation.references[8] A. S. Andreishyn, A. V. Malyar, B. S. Kaluzhnyy, and S. M. Leshchuk, “Neural network selection for detecting the state of an oil well”, Problemy avtomatizirovannoho elektroprivoda. Teoriya i praktika, no. 36, pp. 495–496, Kharkiv, Ukraine: NTU KhPI, 2013. (Ukrainian)
dc.relation.references[9] V. S. Medvedev, and V. G. Potyomkin, Neural networks. MATLAB 6. Мoscow, Russia: Dialog-MIFI, 2002. (Russian)
dc.relation.references[10] J. J. Hopfield, “Neural networks and physical systems with emergent collective computational abilities”, Proceedings of National Academy of Sciences USA, vol. 79, no. 8, pp. 2554–2558, 1982.
dc.relation.references[11] P. Wasserman, Neural Computing. New York, USA: Van Nostrand Reinhold, 1989.
dc.relation.references[12] R. P. Lippmann, B. Gold and M. L. Malpass, “A Comparison of Hamming and Hopfield Neural Nets for Pattern Classification”, in Technical Report 769, Massachusetts Institute of Technology, Lincoln Laboratory. 1987.
dc.relation.referencesen[1] A. F. Shageev, A. M. Timusheva, L. N. Shageeva, and A. S. Grishkin, "Automated monitoring of the oil well treatment – the first stage of intelligent control systems", Neftyanoye khozyaistvo, no. 11, pp. 48–49, Moscow, Russia, 2000. (Russian)
dc.relation.referencesen[2] A. . Galeev, R. I. Arslanov, P. P. Yermilov, and I. A. Kuzmin, "Control of technical condition oil-well pumping unit under periodic operation conditions", http://ogbus.ru/authors/GaleevAS/GaleevAS_2.pdf. (Russian)
dc.relation.referencesen[3] M. I. Khakimyanov and S. V. Svatlakova, "Optimal methods for encoding dynamogamms of deep-well pumping units", in Electrotechnology, electric drive and electrical equipment of enterprises, pp. 146–150, Ufa, Russia: UGNTU, 2005. (Russian)
dc.relation.referencesen[4] P. Lionel Evina Ekombo, Noureddine Ennahnahi and Mohammed Oumsis, "Application of affine invariant Fourier descriptor to shape-based image retrieval", International Journal of Computer Science and Network Security (IJCSNS), vol. 9, no. 7, pp. 240–247, 2009.
dc.relation.referencesen[5] S. Mallat, A wavelet tour of signal processing. Moscow, Russia:Mir, 2005. (Russian)
dc.relation.referencesen[6] T. Aliev and O. Nusratov, "The methods and diagnostic tools deep pumping oil well equipment", Neftyanoye khozyaistvo, no. 9, pp. 78–80, Moscow, Russia, 1998. (Russian)
dc.relation.referencesen[7] A. M. Zyuzev, and A. V. Kostylev, "A neuralnetwork- based system of the sucker-rod oil pumping unit diagnostics", in Proc. 2nd Russian Scientific Conference "Design of engineering and scientific applications in the MATLAB", pp.1273–1287, Moscow, Russia, May 25–26, 2004. (Russian)
dc.relation.referencesen[8] A. S. Andreishyn, A. V. Malyar, B. S. Kaluzhnyy, and S. M. Leshchuk, "Neural network selection for detecting the state of an oil well", Problemy avtomatizirovannoho elektroprivoda. Teoriya i praktika, no. 36, pp. 495–496, Kharkiv, Ukraine: NTU KhPI, 2013. (Ukrainian)
dc.relation.referencesen[9] V. S. Medvedev, and V. G. Potyomkin, Neural networks. MATLAB 6. Moscow, Russia: Dialog-MIFI, 2002. (Russian)
dc.relation.referencesen[10] J. J. Hopfield, "Neural networks and physical systems with emergent collective computational abilities", Proceedings of National Academy of Sciences USA, vol. 79, no. 8, pp. 2554–2558, 1982.
dc.relation.referencesen[11] P. Wasserman, Neural Computing. New York, USA: Van Nostrand Reinhold, 1989.
dc.relation.referencesen[12] R. P. Lippmann, B. Gold and M. L. Malpass, "A Comparison of Hamming and Hopfield Neural Nets for Pattern Classification", in Technical Report 769, Massachusetts Institute of Technology, Lincoln Laboratory. 1987.
dc.relation.urihttp://ogbus.ru/authors/GaleevAS/GaleevAS_2.pdf
dc.rights.holder© Національний університет „Львівська політехніка“, 2017
dc.rights.holder© Malyar А., Andreishyn А., Kaluzhnyi В., Holovach І., 2017
dc.subjectsucker-rod oil pumping unit
dc.subjectneural network
dc.subjectload curve
dc.subjectidentification system
dc.titleStudy of the Hamming network efficiency for the sucker-rod oil pumping unit status identification
dc.title.alternativeДослідження ефективності нейронної мережі Хемінга для задач розпізнавання стану глибиннопомпової установки
dc.typeArticle

Files

Original bundle

Now showing 1 - 2 of 2
Thumbnail Image
Name:
2017v7n1_Malyar_A-Study_of_the_Hamming_network_45-50.pdf
Size:
467.82 KB
Format:
Adobe Portable Document Format
Thumbnail Image
Name:
2017v7n1_Malyar_A-Study_of_the_Hamming_network_45-50__COVER.png
Size:
514.23 KB
Format:
Portable Network Graphics

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
3.1 KB
Format:
Plain Text
Description: