Ваш браузер устарел.

Для того, чтобы использовать все возможности сайта, загрузите и установите один из этих браузеров.

скрыть

Article

  • Title

    DIAGNOSTICS OF MECHANICAL ENGINEERING PRODUCTS ON SEVERAL GROUNDS

  • Authors

    Kovalevskyy S.
    Kovalevska O.
    Postavnichyi A.

  • Subject

    MACHINE BUILDING. PROCESS METALLURGY. MATERIALS SCIENCE

  • Year 2020
    Issue 3(62)
    UDC 667.64:678.026
    DOI 10.15276/opu.3.62.2020.02
    Pages 14-20
  • Abstract

    The article considers methods of non-destructive testing based on various physical laws and phenomena. The possibility of creating a new topical tool for obtaining a wide range of data of mechanical engineering products such as shape, size and location in space is considered. It is proposed to use sound diagnostics using a high-frequency broadband signal to capture the frequency characteristics of the object. The purpose of the study is to develop a method of non-contact measurement of mechanical engineering products on several grounds. With the help of vibroacoustic diagnostics and the method of quantitative control, the distribution of the entire volume of products was 100 pieces. on two parties: the main and control, quantitative parameters of each unit of a product are removed. A signal from 0 to 20,000 Hz was applied by means of a frequency generator. The frequency response of each sample was recorded in the Spectrum Analiyser program. Estimation of the deviation of the product size and its frequency spectrum was performed in the NeuroPro 0.25 software. The created neural network allows is predicted in real time values of several quantitative signs irrespective of their nature. A working model for collecting statistical data for the efficient operation of the neural network is obtained. The developed technique allows detecting the configuration of products on the basis of indirect measurements through the frequency spectrum. This technique can be used to diagnose parts by geometric features, physical properties, defects. This requires an increase in input data for neural network training. With a sufficient selection of parts with different defects of the neural network on the acoustic frequency characteristics will be able to divide the parts into groups of worthy and unworthy on various grounds.

  • Keywords non-destructive testing, neural network, diagnostics, frequency spectrum
  • Viewed: 130 Dowloaded: 2
  • Download Article
  • References

    Література

    1. Назолін А.Л. Оцінка можливості виявлення дефектів статора турбогенератора по спектру віброакус-тичнго сигналу. Заводская лаборатория. Диагностика материалов. 2017. Вип. 4. 314 с.

    2. Basaran F. U., Kurban M. A New Approach for the Short-Term Load Forecasting with Autoregressive and Artificial Neural Network Models. International Journal of Computational Intelligence Research. 2007. № 3. P. 66–71.

    3. Коновалова І.О., Беркович Ю.А., Єрохін А.Н. Оптимізація світлодіодної системи освітлення вітамі-нами космічної теплиці. Авіакосмічна і екологічна медицина. 2016. Вип. 50, № 3. С. 17–22.

    4. Кононюк А. Е. Обобщенная теория моделирования. Начала: Освіта України, 2012. 602 с.

    5. Бигус Г.А., Даниев Ю.Ф., Быстрова Н.А. Диагностика технических устройств. М. : Изд-во МГТУ им. Н.Э. Баумана, 2014. 615 с.

    6. Бобров В.Т., Самокрутов А.А., Шевалдыкин В.Г. Техническая диагностика и неразрушающий контроль Состояние и тенденции развития акустических (ультразвуковых) методов, средств и технологий неразрушающего контроля и технической диагностики. Территория NDT. 2018. № 2. С. 24–27.

    7. Ермолов И.Н. Техническая диагностика и неразрушающий контроль. Достижения в теоретиче-ских вопросах ультразвуковой дефектоскопии, задачи и перспективы. Дефектоскопия. 2018. № 2. C. 13–48.

    8. Терентьев В.Ф., Колмаков А.Г., Блинов В.М. Деформация и разрушение материалов. Деформа-ция и разрушение материалов. 2007. № 6. С. 2–9.

    9. Белолапотков Д.А., Добровинский И.Р., Медведик Ю.Т. Повышение точности активного контро-ля размеров деталей в процессе изготовления. Мир измерений М. РИА «Стандарты и качество». 2007. № 7. С. 43–46.

    10. Леньков С.В., Федорова Н.В. Резонансный электромагнитный  акустический метод измерения вязкоупругих свойств аморфных ферро магнитных лент, подвергнутых низкотемпературному отжигу. Физика металлов и металловедение. 2014. № 115. С. 749–755.

    11. Верещака А.С., Высоцкий В.В., Мокрицкий Б.Я. Технологические процессы повышения работо-способности металлорежущего инструмента. Комсомольск-на-Амуре : ФГБОУ ВПО «КнАГТУ», 2013. 208 с.

    12. Самотугин С.С., Лещинский Л.К. Плазменное упрочнение инструментальных материалов. До-нецк : Новый мир, 2002. 338 с.

    13. Golesorkhtabar R. А. ElaStic: A tool for calculating second-order elastic constants from first principles. Computer Physics Communications. 2013. № 8. P. 1861–1873.

    14. Kovalevska O. S., Kovalevskyy S. V. Application of acoustic analysis in control systems of robotic ma-chine tools. Radio Electronics, Computer Science, Control. 2018. № 2(45). С. 51–59.

    15. Kovalevskyy S.V., Kovalevska O.S., Turmanidze R.A. Acoustic diagnostics of lever mechanisms with subsequent processing of data on neural networks. New technologies, development and application. Springer International Publishing AG, part of Springer Nature. 2018. Vol. 42. P. 202–210.

    16. Kovalevskyy S. V., Kovalevska O.S. Resource optimization with systemic design of robotized techno-logical equipment. World Convention on Robots, Autonomous Vehicles and Deep Learning. 10-11 Sep-tember 2018, Singapore. 2018. P. 50. DOI: 10.4172/2168-9695-C3-0216th.

    References

    1. Nazolin, A.L. (2017). Evaluation of the possibility of detecting defects of the stator of the turbogenerator on the spectrum of the vibroacoustic signal. Factory laboratory. Diagnostics of materials.

    2. Basaran, F. U., & Kurban, M. A. (2007). New Approach for the Short-Term Load Forecasting with Au-toregressive and Artificial Neural Network Models. International Journal of Computational Intelligence Research, 3, 66–71.

    3. Konovalova, I.O., Berkovich, Yu.A., & Erohin, A.N. (2016). Optimization of the LED lighting system vitamins space greenhouse. Аviakosmicheskaja i jekologicheskaja medicina, 50, 3, 17–22

    4. Kononyuk, A.E. (2012). Generalized modeling theory. Beginnings: Education of Ukraine.

    5. Bigus, G.A., Daniev, Y.F., & Bystrova, N.A. (2014). Diagnostics of technical devices. Moscow: MSTU im. N.E. Bauman.

    6. Bobrov, V.T., Samokrutov, A.A., & Shevaldykin, V.G. (2018). Technical diagnostics and non-destructive testing. The state and trends in the development of acoustic (ultrasonic) methods, tools and technologies of non-destructive testing and technical diagnostics. NDT territory, 2, 24–27.

    7. Ermolov, I.N. (2018). Technical diagnostics and non-destructive testing. Advances in theoretical issues of ultrasonic flaw detection, tasks and prospects. Defectoscopy, 2, 13–48.

    8. Terentyev, V.F., Kolmakov, A.G., & Blinov, V.M. (2007). Deformation and destruction of materials. Deformation and destruction of materials, 6, 2–9.

    9. Belolapotkov, D.A., Dobrovinsky, I.R., & Medvedik, Yu.T. (2007). Improving the accuracy of active control of the size of parts in the manufacturing process. The world of measurements M. RIA Standards and quality, 7, 43–46.

    10. Lenkov, S.V., & Fedorova, N.V. (2014). Resonant electromagnetic is an acoustic method for measuring the viscoelastic properties of amorphous ferro magnetic tapes subjected to low-temperature annealing. Physics of metals and metallurgy, 115, 749–755.

    11. Vereshchaka, A.S., Vysotsky, V.V., & Mokritsky, B. Ya. (2013). Technological processes of increase of working capacity of the metal-cutting tool. Komsomolsk-on-Amur: FGBOU VPO KnAGTU.

    12. Samotugin, S.S., Leshchinsky, L.K. (2002). Plasma hardening of tool materials. Donetsk: New World.

    13. Golesorkhtabar, R. А. (2013). ElaStic: A tool for calculating second-order elastic constants from first principles. Computer Physics Communications, 8, 1861–1873.

    14. Kovalevska, O. S., & Kovalevskyy, S. V. (2018). Application of acoustic analysis in control systems of robotic machine tools. Radio Electronics, Computer Science, Control, 2 (45), 51–59.

    15. Kovalevskyy, S.V., Kovalevska, O.S., & Turmanidze, R.A. (2018). Acoustic diagnostics of lever mech-anisms with subsequent processing of data on neural networks. New technologies, development and ap-plication. Springer International Publishing AG, part of Springer Nature, 42, 202–210.

    16. Kovalevskyy, S.V., & Kovalevska, O.S. (2018). Resource optimization with systemic design of robot-ized technological equipment. World Convention on Robots, Autonomous Vehicles and Deep Learning. Singapore. DOI: 10.4172/2168-9695-C3-0216th.

  • Creative Commons License by Author(s)