پیش بینی جریان در دیفیوزر نامتقارن دو بعدی توسط شبکه عصبی و مقایسه نتایج با سه مدل آشفتگی و داده های تجربی

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشکده مهندسی مکانیک- دانشگاه کاشان- کاشان- ایران

2 دانشکده مهندسی مکانیک، دانشگاه کاشان، کاشان، ایران

3 دانشکده مهندسی مکانیک، دانشگاه آزاد اسلامی واحد خمینی شهر، خمینی شهر، ایران

چکیده

در کار حاضر جریان آشفته در یک دیفیوزر دو بعدی نامتقارن مورد بررسی و مطالعه قرار گرفته‌است. در بسیاری از کاربردها، اطلاع از این‌که آیا لایه مرزی از سطح یا داخل یک جسم خاص جدا می‌شود و این‌که دقیقاً جداسازی جریان در کجا رخ می‌دهد، از اهمیت خاصی برخوردار است. ترکیب داده‌های آشفتگی با هوش مصنوعی در حال حاضر یک موضوع تحقیقاتی فعال برای مطالعه آشفتگی است. در این مقاله پیش‌بینی جدایش جریان با وجود گرادیان فشار معکوس در دیفیوزر دوبعدی نامتقارن، با استفاده از سه مدل آشفتگی شامل مدل استاندارد k-e، مدل استاندارد k-w و مدل SST k-w و مدل هوشمند شبکه عصبی مصنوعی (ANN) مورد بررسی و مقایسه قرار گرفته‌است. برای شبیه‌سازی عددی و حل معادلات حاکم از نرم افزار فلوئنت استفاده شده‌است. نتایج در فواصل 21، 29، 39 و 49 سانتی متری از لبه دیفیوزر مورد تحلیل قرار گرفتند و با داده‌های تجربی مقایسه شدند. x و y/H هر نقطه به‌عنوان ورودی و U/U0 سرعت در آن نقطه به‌عنوان خروجی شبکه عصبی درنظر گرفته شده‌است. شاخص‌های آماری RMSE, MBE, t-test برای نقاط موردنظر محاسبه و گزارش شده‌است. مدل شبکه مصنوعی نسبت‌به سه مدل آشفتگی، پیش‌بینی بهتری از جدایش جریان را نشان می‌دهد و مدل استاندارد k-e نسبت‌به مدل­های دیگر پیش­بینی ضعیف­تری را نشان می‌دهد. این تحقیق چشم‌انداز مدل‌سازی آشفتگی را با روش‌های یادگیری ماشین به‌خصوص شبکه عصبی نشان می‌دهد.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Flow prediction in two-dimensional asymmetric diffuser by neural network and comparison with three turbulence models and experimental data

نویسندگان [English]

  • Mostafa Zamani mohiabadi 1
  • Farid Soltani 2
  • Ahmad Reza Boroomandpour 3
  • Ghanbar Ali Sheikhzadeh 2
1 Department of Mechanical Engineering, University of Kashan, Kashan, Iran
2 Department of Mechanical Engineering, University of Kashan, Kashan, Iran
3 Department of Mechanical Engineering, Khomeinishahr Branch, Islamic Azad University, Khomeinishahr, Iran
چکیده [English]

In this paper, turbulent flow in an asymmetric two-dimensional diffuser is investigated. In many applications, it is important to know whether the boundary layer separates from the surface or inside a particular object, it is also important to know exactly where the flow separation occurs. Combining turbulence data with artificial intelligence is currently an active research topic for studying turbulence. This research makes it possible to replace traditional turbulent models with artificial neural networks (ANN). In this study, to predict flow separation in an asymmetric two-dimensional diffuser, three turbulence models, standard k-, standard k-and SST k-, and intelligent neural network model with reverse pressure gradient were investigated. Fluent software was used to solve the Navier-Stokes-Reynolds equations. Three types of networking are designed and at the end, the second type is used to analyze the flow. 21, 29, 39 and 49 cm distances from the edge of the diffuser were analyzed and compared with experimental data. x and y/H are considered as the input point and U/U0 is the velocity at that point as the output of the neural network model. RMSE, MBE, t-test statistical indices have been calculated and reported for the desired points, The ANN had a better prediction of separation than the other three standard models, and the standard k- had a lower prediction than the other models. This research shows the perspective of chaotic modeling with machine learning methods, especially neural networks.

کلیدواژه‌ها [English]

  • Neural network
  • turbulence
  • diffuser

مراجع

  1. Bradshaw, P., "Understanding and Prediction of Turbulent Flow- 1996", International Journal of Heat and Fluid Flow, Vol. 18, No. 1, Pp. 45–54, Feb, (1997). doi: 10.1016/S0142-727X(96)00134-8.
  2. Versteeg, H. K., and Malalasekera, W., An Introduction to Computational Fluid Dynamics: The Finite Volume Method. Longman group Ltd, (1998).
  3. Launder, B. E., and Spalding, D. B., "The Numerical Computation of Turbulent Flows", Numerical prediction of flow, heat transfer, Turbulence and Combustion, Vol. 3, No. 2, Pp. 269–289, (1974).
  4. Launder, B. E., and Sharma, B. I., "Application of the Energy-dissipation Model of Turbulence to the Calculation of Flow Near a Spinning Disc", Letters in Heat and Mass Transfer, Vol. 1, No. 2, Pp. 131–137, Nov, (1974).
  5. Yakhot, V., and Smith, L. M., "The Renormalization Group, the ɛ-expansion and Derivation of Turbulence Models", Jouranl Scince Computer., 7, No. 1, Pp. 35–61, (1992).
  6. Wilcox, D. C., "Turbulence Modeling for CFD", DCW Industries, Inc., La Canada, CA.", (1993).
  7. Menter, F. R., "Two-equation Eddy-viscosity Turbulence Models for Engineering Applications", American Institute of Aeronautics and Astronautics Journal, 32, No. 8, Pp. 1598–1605, Accessed: May 14, )2021(. [Online].
  8. Madaliev, E. U., Madaliev, M. E. U., Mullaev, I. I., Shoev, M. A. U., & Ibrokhimov, A. R. U. "Comparison of Turbulence Models for the Problem of an Asymmetric Two-Dimensional Plane Diffuser", Middle European Scientific Bulletin, 18, Pp. 119-127, (2021).
  9. J. Kaltenbach, M. Fatica, R. Mittal, T. S. Lund, and P. Moin, "Study of Flow in a Planar Asymmetric Diffuser Using Large-eddy Simulation", Journal of Fluid Mechanics, Vol. 390, Pp. 151–185, (1999),.
  10. Malikov, A. Mirzoev, M. Madaliev, D. Yakhshibayev and A. Usmonov, "Numerical Simulation of Flow through an Axisymmetric Two-dimensional Plane Diffuser Based on a New Two-fluid Turbulence Model", International Conference on Information Science and Communications Technologies (ICISCT),IEEE , Pp. 1-4, (2021).
  11. U. Buice and J. K. Eaton, "Experimental Investigation of Flow through an Asymmetric Plane Diffuser", Journal of Fluids Engineering-transactions of The ASME, Vol. 122, No. 2, Pp. 433–435, (2000).
  12. Parpanchi, Seyed Morteza, et al. "Experimental Investigation of a Diffuser for Use in Skydiving Vertical Wind Tunnel", Experimental Thermal and Fluid Science, 125, Pp. 110393, (2021).‏
  13. Ling, J., Kurzawski, A., Templeton, J., "Reynolds Averaged Turbulence Modelling Using Deep Neural Networks with Embedded Invariance", Journal of Fluid Mechanics, Vol. 807, Pp. 155–66, (2016).
  14. Geneva, Nicholas, and Nicholas Zabaras, "Quantifying Model Form Uncertainty in Reynolds-Averaged Turbulence Models with Bayesian Deep Neural Networks", Journal of Computational Physics, Vol. 383, Pp. 125-147, (2019).‏
  15. Zhu, Linyang, et al. "Turbulence Closure for High Reynolds Number Airfoil Flows by Deep Neural Networks", Aerospace Science and Technology, 110, Pp. 106452, (2021).‏
  16. Ti, Zilong, Xiao Wei Deng, and Mingming Zhang, "Artificial Neural Networks based wake model for power prediction of wind farm", Renewable Energy, Vol. 172, Pp. 618-631, (2021).‏
  17. Buice, C. U., & Eaton, J. K. (1996). "Experimental Investigation of Flow through an Asymmetric Plane Diffuser",CTR Annual Research Briefs, 21, Pp. 243-248, (1996).
  18. Heydari Nejad, Qasim, "Introduction to Turbulence", Tarbiat Modares University Publications, (2017). In Persian
  19. Hamisu, Muhammad Tukur, et al. "Numerical Study Of Flow In Asymmetric 2D Plane Diffusers With Different Inlet Channel Lengths", CFD Letters, 11(5), Pp. 1-21, (2019).‏
  20. Zamani Mohiabadi M., "The Instantaneous Prediction of the Global Solar Radiation in the Rafsanjan City", Iranian Journal of Energy, 16, No. 4, Pp. 15-31, (2012).
  21. Menhaj M. B., "Fundamentals of Neural Networks", Amirkabir University,37-40, (2013). In Persian
  22. Zamani Mohiabadi M., and Mirzaei M., "Comparison of Two Intelligent Models to Estimate the Instantaneous Global Solar Radiation in Semi-arid Climate Conditions: Application in Iran", Journal of Earth System Science, 126, No. 5, Pp. 75-88, (2017).
  23. Shafiey Dehaj, M., Zamani Mohiabadi, M., & Hosseini, S. M. S., "Sensitivity Analysis of 9 Models for Estimating the Power of Photovoltaic Monocrystal and Polycrystalline Panels", Journal of Mechanical Engineering, 51(4), Pp. 193-202, (2022).‏
  24. Zamani Mohiabadi, M., Jahromi, R., Hasani Dastjerdi, M., & Mehrabi Gouhari, E., "Estimating Efficiency of Monocrystalline and Polycrystalline Photovoltaic Panels Using Neural Network Models", Iranian Journal of Energy, 21, No.3, Pp. 87-100, (2018).‏
  25. Jacovides, C. P., "Reply to comment on Statistical procedures for the evaluation of evapotranspiration models", Agricultural Water Management, 3, Pp. 95-97, (1997).
ارسال نظر در مورد این مقاله
CAPTCHA Image

فایل ها

هم رسانی

ارجاع به این مقاله

آمار