پیش بینی عدد نوسلت استوانه گرم شده قرار گرفته در معرض جریان آشفته توسط شبکه حافظه طولانی کوتاه مدت عمیق بهینه شده توسط الگوریتم ازدحام ذرات

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشکده مهندسی مکانیک، دانشگاه صنعتی اراک، اراک، ایران

2 گروه مهندسی مکانیک، دانشکده فنی و مهندسی، دانشگاه خوارزمی، تهران، ایران

چکیده

بهره‌گیری از هوش مصنوعی برای پیش‌بینی مشخصات انتقال حرارت در صنایع مختلف، توانایی بهبود طراحی تجهیزات حرارتی، افزایش کارایی انتقال حرارت، بهینه‌سازی سیستم‌های خنک‌کننده، و کاهش مصرف انرژی را فراهم می‌کند. نوآوری و هدف مقاله حاضر، پیش‌بینی رفتار زمانی عدد نوسلت در مسئله ارتعاشات ناشی از جریان آشفته بر روی استوانه گرم شده که آزادانه در جهات طولی و عرضی نوسان می‌کند، می‌باشد. پیش‌بینی عدد نوسلت بر مبنای جابجای‌های عرضی و طولی استوانه در سه سناریوی مختلف شامل ورودی جابجایی در جهت ، ورودی جابجایی در جهت ، و در نهایت ورودی ترکیبی  و  انجام شده است. پیش‌بینی توسط شبکه حافظه طولانی کوتاه مدت عمیق که معماری و ابرپارامترهای آن توسط الگوریتم ازدحام ذرات بهینه شده است، صورت گرفته است. نتایج نشان دهنده‌ی موفقیت شبکه‌های بهینه شده با ورودی‌های متفاوت می‌باشد؛ اگرچه دقت بالاتری در پیش‌بینی با ورودی‌های ترکیبی  و  بدست آمده است. ضریب همبستگی در بخش تست، برای شبکه‌های با ورودی ؛ با ورودی ؛ و با ورودی‌های  و  به ترتیب برابر با 0/967، 0/961، و 0/975 محاسبه شده‌اند. با بهره گیری از روش بکارگرفته شده در مطالعه حاضر، می‌توان مشخصات انتقال حرارت سازه‌های قرار گرفته در معرض جریان را پیش‌بینی نمود.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Prediction of Nusselt number of heated cylinder exposed to turbulent flow by deep long short-term memory network optimized by particle swarm algorithm

نویسندگان [English]

  • Amir Hossein Rabiee 1
  • mostafa esmaeili 2
1 mechanical engineering, arak university of technology
2 Department of Mechanical Engineering, Faculty of Engineering, Kharazmi University , Tehran, Iran
چکیده [English]

Leveraging artificial intelligence to forecast heat transfer characteristics across diverse industries holds significant potential for improving thermal equipment design, increasing heat transfer efficiency, optimizing cooling systems, and reducing energy consumption. The main contribution and purpose of the current study is predicting the Nusselt number in the context of turbulent flow-induced vibration around a heated cylinder experiencing unconfined oscillations along both streamwise and transverse axes. The anticipation of the Nusselt number relies on transverse and streamwise displacements of the oscillating cylinder and encompasses three distinct scenarios: displacement input in the x-direction, displacement input in the y-direction, and comprehensive amalgamation of both x and y inputs. This prediction is achieved through a sophisticated deep long short-term memory network, meticulously crafted and fine-tuned using a particle swarm optimization algorithm. The results highlight the effectiveness of the optimized networks across various inputs, with the highest predictive precision observed when employing combined x and y inputs. The correlation coefficients within the test segment are as follows: 0.967 for x input, 0.961 for y input, and 0.975 for combined x and y inputs. By applying the methodology elucidated in this study, the forecasting of heat transfer characteristics for structures subjected to fluid flow emerges as a feasible possibility.

کلیدواژه‌ها [English]

  • Nusselt number
  • fluid-solid interaction
  • vortex-induced vibration
  • long short-term memory network
  • Particle swarm optimization algorithm
[1] L. Ding, H. He, T. Song, Vortex-induced vibration and heat dissipation of multiple cylinders under opposed thermal buoyancy, Ocean Engineering, 270 (2023) 113669.
[2] A.A. Mosaferi, M. Esmaeili, A.H. Rabiee, Effect of aligned magnetic field on the 2DOF VIV suppression and convective heat transfer characteristics of a circular cylinder, International Communications in Heat and Mass Transfer, 130 (2022) 105807.
[3] M.A. Khan, S. Masood, S.F. Anwer, S.A. Khan, M.R. Arif, Vortex induced vibration for mixed convective flow past a square cylinder, International Journal of Heat and Mass Transfer, 202 (2023) 123722.
[4] M. Asif, R. Chaturvedi, A. Dhiman, Heat transfer enhancement from inline and staggered arrays of cylinders in a heat exchanger using alumina–water nanofluid, Journal of Thermal Science and Engineering Applications, 13(4) (2021) 041025.
[5] S.M. Ibrahim, A. Abdelmaksoud, W. Helal, Heat transfer characteristics for multi-silicon ingots irradiation in a typical research reactor, International Journal of Thermofluids, 20 (2023) 100411.
[6] D. Yu, D. Zhang, L. Wu, X. Kong, Q. Yue, Analysis of the influence of convection heat transfer in circular tubes on ships in a polar environment, Atmosphere, 13(2) (2022) 149.
[7] A.H. Rabiee, S.D. Farahani, Effect of synthetic jet on VIV and heat transfer behavior of heated sprung circular cylinder embedded in a channel, International Communications in Heat and Mass Transfer, 119 (2020) 104977.
[8] T.L. Frölicher, C. Laufkötter, Emerging risks from marine heat waves, Nature communications, 9(1) (2018) 650.
[9] Y.M. Seo, K. Luo, M.Y. Ha, Y.G. Park, Direct numerical simulation and artificial neural network modeling of heat transfer characteristics on natural convection with a sinusoidal cylinder in a long rectangular enclosure, International Journal of Heat and Mass Transfer, 152 (2020) 119564.
[10] S. Cai, Z. Wang, S. Wang, P. Perdikaris, G.E. Karniadakis, Physics-informed neural networks for heat transfer problems, Journal of Heat Transfer, 143(6) (2021) 060801.
[11] M. Sarmeili, H.R. Ashtiani, A. Rabiee, Nonlinear energy sinks with nonlinear control strategies in fluid-structure simulations framework for passive and active FIV control of sprung cylinders, Communications in Nonlinear Science and Numerical Simulation, 97 (2021) 105725.
[12] O.I. Abiodun, A. Jantan, A.E. Omolara, K.V. Dada, A.M. Umar, O.U. Linus, H. Arshad, A.A. Kazaure, U. Gana, M.U. Kiru, Comprehensive review of artificial neural network applications to pattern recognition, IEEE access, 7 (2019) 158820-158846.
[13] R. Kumar, R. Nadda, S. Kumar, A. Razak, M. Sharifpur, H.S. Aybar, C.A. Saleel, A. Afzal, Influence of artificial roughness parametric variation on thermal performance of solar thermal collector: An experimental study, response surface analysis and ANN modelling, Sustainable Energy Technologies and Assessments, 52 (2022) 102047.
[14] J. Solís-Pérez, J. Hernández, A. Parrales, J. Gómez-Aguilar, A. Huicochea, Artificial neural networks with conformable transfer function for improving the performance in thermal and environmental processes, Neural Networks, 152 (2022) 44-56.
[15] E. Ayli, E. Kocak, Prediction of the heat transfer performance of twisted tape inserts by using artificial neural networks, Journal of Mechanical Science and Technology, 36(9) (2022) 4849-4858.
[16] K. Tao, J. Zhu, Z. Cheng, D. Li, Artificial neural network analysis of the Nusselt number and friction factor of hydrocarbon fuel under supercritical pressure, Propulsion and Power Research, 11(3) (2022) 325-336.
[17] K. Kim, H. Lee, M. Kang, G. Lee, K. Jung, C.R. Kharangate, M. Asheghi, K.E. Goodson, H. Lee, A machine learning approach for predicting heat transfer characteristics in micro-pin fin heat sinks, International Journal of Heat and Mass Transfer, 194 (2022) 123087.
[18] N. Celik, B. Tasar, S. Kapan, V. Tanyildizi, Performance optimization of a heat exchanger with coiled-wire turbulator insert by using various machine learning methods, International Journal of Thermal Sciences, 192 (2023) 108439.
[19] F.Z. Benouis, Y.O. Amer, M. Arıcı, S. Meziane, Designing and optimizing a novel heat sink for the enhancement of hydrothermal performances: Modelling and analysis using artificial neural network, Engineering Analysis with Boundary Elements, 155 (2023) 766-778.
[20] Z. Li, Z. Feng, Q. Zhang, J. Zhou, J. Zhang, F. Guo, Thermal-hydraulic performance and multi-objective optimization using ANN and GA in microchannels with double delta-winglet vortex generators, International Journal of Thermal Sciences, 193 (2023) 108489.
[21] C. Zhai, Y. Sui, W. Wu, Machine learning-assisted correlations of heat/mass transfer and pressure drop of microchannel membrane-based desorber/absorber for compact absorption cycles, International Journal of Heat and Mass Transfer, 214 (2023) 124431.
[22] L.S. Sundar, K.V.C. Mouli, Experimental analysis and Levenberg-Marquardt artificial neural network predictions of heat transfer, friction factor, and efficiency of thermosyphon flat plate collector with MgO/water nanofluids, International Journal of Thermal Sciences, 194 (2023) 108555.
[23] Z. Han, J. Guo, J. Chen, X. Huai, Experimental and numerical investigations on thermal-hydraulic characteristics of supercritical CO2 flows in printed circuit heat exchangers, International Journal of Thermal Sciences, 194 (2023) 108573.
[24] A.T. Vu, S. Gulati, P.-A. Vogel, T. Grunwald, T. Bergs, Machine learning-based predictive modeling of contact heat transfer, International Journal of Heat and Mass Transfer, 174 (2021) 121300.
[25] G. Krishnayatra, S. Tokas, R. Kumar, Numerical heat transfer analysis & predicting thermal performance of fins for a novel heat exchanger using machine learning, Case Studies in Thermal Engineering, 21 (2020) 100706.
[26] L. Zhou, D. Garg, Y. Qiu, S.-M. Kim, I. Mudawar, C.R. Kharangate, Machine learning algorithms to predict flow condensation heat transfer coefficient in mini/micro-channel utilizing universal data, International Journal of Heat and Mass Transfer, 162 (2020) 120351.
[27] E. Kocak, E. Aylı, H. Turkoglu, A comparative study of multiple regression and machine learning techniques for prediction of nanofluid heat transfer, Journal of Thermal Science and Engineering Applications, 14(6) (2022) 061002.
[28] F. Nie, H. Wang, Y. Zhao, Q. Song, S. Yan, M. Gong, A universal correlation for flow condensation heat transfer in horizontal tubes based on machine learning, International Journal of Thermal Sciences, 184 (2023) 107994.
[29] Y. Qiu, T. Vo, D. Garg, H. Lee, C.R. Kharangate, A systematic approach to optimization of ANN model parameters to predict flow boiling heat transfer coefficient in mini/micro-channel heatsinks, International Journal of Heat and Mass Transfer, 202 (2023) 123728.
[30] S. Bhattacharya, M.K. Verma, A. Bhattacharya, Predictions of Reynolds and Nusselt numbers in turbulent convection using machine-learning models, Physics of Fluids, 34(2) (2022).
[31] B. Keshavarzian, J.M.N. Abad, M. Mir, M. Keshavarzian, R. Alizadeh, The optimization of natural frequency on the cross flow-induced vibration and heat transfer in a circular cylinder with LSTM deep learning model, Journal of the Taiwan Institute of Chemical Engineers,  (2023) 104969.
[32] F. Ren, F. Zhang, Y. Zhu, Z. Wang, F. Zhao, Enhancing heat transfer from a circular cylinder undergoing vortex induced vibration based on reinforcement learning, Applied Thermal Engineering, 236 (2024) 121919.
[33] L.R. Medsker, L. Jain, Recurrent neural networks, Design and Applications, 5(64-67) (2001).
[34] A. Graves, A. Graves, Long short-term memory, Supervised sequence labelling with recurrent neural networks,  (2012) 37-45.
[35] J. Kennedy, R. Eberhart, Particle swarm optimization (PSO), in:  Proc. IEEE International Conference on Neural Networks, Perth, Australia, 1995, pp. 1942-1948.
[36] E. Guilmineau, P. Queutey, Numerical simulation of vortex-induced vibration of a circular cylinder with low mass-damping in a turbulent flow, Journal of fluids and structures, 19(4) (2004) 449-466.
[37] X. Han, W. Lin, D. Wang, A. Qiu, Z. Feng, Y. Tang, J. Wu, Numerical simulation of super upper branch of a cylindrical structure with a low mass ratio, Ocean Engineering, 168 (2018) 108-120.
[38] X. Han, Y. Tang, Z. Feng, Z. Meng, A. Qiu, W. Lin, J. Wu, Vortex-Induced Vibration of a Marine Riser: Numerical Simulation and Mechanism Understanding, in:  New Innovations in Engineering Education and Naval Engineering, IntechOpen, 2018.
[39] N.B. Khan, Z. Ibrahim, M.I. Khan, T. Hayat, M.F. Javed, VIV study of an elastically mounted cylinder having low mass-damping ratio using RANS model, International Journal of Heat and Mass Transfer, 121 (2018) 309-314.
[40] W. Li, J. Li, S. Liu, Numerical simulation of vortex-induced vibration of a circular cylinder at low mass and damping with different turbulent models, in:  Oceans 2014-Taipei, IEEE, 2014, pp. 1-7.
[41] Z. Pan, W. Cui, Q. Miao, Numerical simulation of vortex-induced vibration of a circular cylinder at low mass-damping using RANS code, Journal of Fluids and Structures, 23(1) (2007) 23-37.
[42] J.B. Wanderley, G.H. Souza, S.H. Sphaier, C. Levi, Vortex-induced vibration of an elastically mounted circular cylinder using an upwind TVD two-dimensional numerical scheme, Ocean Engineering, 35(14-15) (2008) 1533-1544.
[43] M. Esmaeili, A.H. Rabiee, Active feedback VIV control of sprung circular cylinder using TDE-iPID control strategy at moderate Reynolds numbers, International Journal of Mechanical Sciences, 202 (2021) 106515.
[44] M. Esmaeili, A.H. Rabiee, Heat transfer characteristics in turbulent FIV of three circular cylinders with different isosceles-triangle arrangements, International Journal of Numerical Methods for Heat & Fluid Flow, 33(7) (2023) 2455-2477.
[45] A.H. Rabiee, M. Esmaeili, Effect of the flow incidence angle on the VIV-based energy harvesting from triple oscillating cylinders, Sustainable Energy Technologies and Assessments, 57 (2023) 103312.
[46] J. Scholten, D. Murray, Unsteady heat transfer and velocity of a cylinder in cross flow—I. Low freestream turbulence, International journal of heat and mass transfer, 41(10) (1998) 1139-1148.