مجله مهندسی مکانیک

مجله مهندسی مکانیک

مروری بر مدل‌ های یادگیری ماشین نظارت ‌شده در بهینه سازی سیستم ‌های ذخیره‌ سازی حرارت نهان PMC

نوع مقاله : مقاله مروری

نویسندگان
امیرعلی سیف الدین 1
شیدا نادعلی پور کلده 2
محمدعلی اله ربی شیرازی 3
1 دانشیار، دانشکده انرژی و منابع پایدار، دانشکدگان علوم و فناوری های میان رشته ای / رئیس مؤسسه فناوری های نرم، دانشگاه تهران، تهران
2 دانشجوی کارشناسی ارشد، دانشکده انرژی و منابع پایدار، دانشکدگان علوم و فناوری های میان رشته ای، دانشگاه تهران، تهران
3 دانشجوی دکتری، دانشکده انرژی و منابع پایدار، دانشکدگان علوم و فناوری های میان رشته ای، دانشگاه تهران، تهران
10.30506/mmep.2026.2072015.2265
چکیده
در این پژوهش، مروری جامع بر کاربرد مدل ‌های یادگیری ماشین نظارت‌ شده در پیش ‌بینی و بهینه ‌سازی عملکرد سیستم ‌های ذخیره‌ سازی حرارت نهان با استفاده از مواد تغییر فاز انجام شده است. هدف اصلی مطالعه، شناسایی مدل‌ های پرکاربرد، مقایسه دقت آن ‌ها و بررسی نوآوری‌ های طراحی هندسی و بهبود انتقال حرارت در این سیستم ‌ها می‌ باشد. نتایج نشان داد که شبکه ‌های عصبی مصنوعی و عمیق به ‌عنوان محبوب ‌ترین مدل‌ ها اغلب در ترکیب با الگوریتم های تکاملی نظیر الگوریتم ژنتیک و بهینه‌ سازی ازدحام ذرات برای بهینه‌ سازی همزمان به کار گرفته شده ‌اند. سایر مدل ‌های مؤثر شامل جنگل تصادفی و رگرسیون بردار پشتیبان برای داده‌ های محدود و مدل ‌های تقویتی (XGBoost و LightGBM) برای بهبود دقت و تفسیرپذیری می ‌باشند. همچنین، رگرسیون فرایند گاوسی با قابلیت تخمین عدم‌ قطعیت در برخی مطالعات به کار رفته است. این مرور بیان می ‌کند که یادگیری ماشین توانسته محدودیت ‌های مدل ‌سازی دینامیک سیالات محاسباتی را جبران کرده و روابط پیچیده میان پارامترهای هندسی و عملیاتی را با دقت بالا مدل ‌سازی نماید. در نهایت، استفاده از مدل‌ های ترکیبی و رویکردهای چندهدفه، راهکار مؤثری برای بهینه ‌سازی سیستم ‌های ذخیره ‌سازی حرارت نهان مبتنی بر مواد تغییر فاز خواهد بود.
کلیدواژه‌ها
مدل سازی سیستم ‌های انرژی
ذخیره ساز حرارت انرژی نهان
مواد تغییر فاز دهنده
یادگیری ماشین
مدل ‌های یادگیری ماشین نظارت شده
موضوعات
[1] C. Lamnatou, C. Cristofari, and D. Chemisana, "Renewable energy sources as a
catalyst for energy transition: Technological innovations and an example of the energy transition in France," Renewable Energy, vol. 221, p. 119600, 2024, doi: https://doi.org/10.1016/j.renene.2023.119600.
 
[2] K. K. Sen, S. C. Karmaker, A. J. Chapman, and B. B. Saha, "Women's empowerment in driving the energy transition for sustainable development in developing nations," Renewable and Sustainable Energy Reviews, vol. 216, p. 115647, 2025, doi: https://doi.org/10.1016/j.rser.2025.115647.
 
[3] S. Nadalipour Kaldeh, H. Yousefi, Y. Noorollahi, and M. Abdoos, "Integration of renewable sources in buildings: A review of energy savings, feasibility, and challenges," Energy Reports, vol. 14, pp. 3905–3934, 2025/12/01/ 2025, doi: https://doi.org/10.1016/j.egyr.2025.10.046.
 
[4] Y. Manoharan, K. Olson, and A. J. Headley, "Sensitivity of energy storage system optimization program to the source of renewable energy in the presence of demand side management: A behind-the-meter case study," Applied Energy, vol. 388, p. 125557, 2025, doi: https://doi.org/10.1016/j.apenergy.2025.125557.
 
[5] T. B. K. Christensen, H. Lund, and P. Sorknæs, "The role of thermal energy storages in future smart energy systems," Energy, vol. 313, p. 133948, 2024, doi: https://doi.org/10.1016/j.energy.2024.133948.
 
[6] A. Nassar et al., "Enhancing the thermal transfer properties of phase change material for thermal energy storage by impregnating hybrid nanoparticles within copper foams," Results in Engineering, vol. 21, p. 101885, 2024, doi: https://doi.org/10.1016/j.rineng.2024.101885.
 
[7] H. M. Ali et al., "Advances in thermal energy storage: Fundamentals and applications," Progress in Energy and Combustion Science, vol. 100, p. 101109, 2024, doi: https://doi.org/10.1016/j.pecs.2023.101109.
 
[8] S. Nadalipour Kaldeh, H. Yousefi, M. Abdoos, M. Allahrabbi Shirazi, and Y. Noorollahi, "Mapping thermal energy storage research in buildings (2020–2025): a bibliometric analysis of trends, themes, and global collaboration," Energy Conversion and Management: X, vol. 28, p. 101345, 2025/10/01/ 2025, doi: https://doi.org/10.1016/j.ecmx.2025.101345.
 
[9] V. K. Sonker, P. Sharma, R. Ram, and A. Sarkar, "A CFD simulation analysis of the effects of PCM and nanoparticles stored in copper cylinders inside a solar still," Journal of Energy Storage, vol. 108, p. 115091, 2025, doi: https://doi.org/10.1016/j.est.2024.115091.
 
[10]         S. Xie, C. Xu, W. Li, Y. Kang, X. Feng, and W. Wu, "Machine learning accelerated the performance analysis on PCM-liquid coupled battery thermal management system," Journal of Energy Storage, vol. 100, p. 113479, 2024, doi: https://doi.org/10.1016/j.est.2024.113479.
 
[11]         W. Li et al., "Optimisation of PCM passive cooling efficiency on lithium-ion batteries based on coupled CFD and ANN techniques," Applied Thermal Engineering, vol. 259, p. 124874, 2025, doi: https://doi.org/10.1016/j.applthermaleng.2024.124874.
 
[12]         A. Naziri, A. R. Tahavvor, M. A. Shirazi, and R. Zahedi, "Feasibility study on heat recovery from gas turbine exhaust for absorption chiller operation and efficiency enhancement using neural networks," Thermal Science and Engineering Progress, vol. 67, p. 104210, Nov. 2025, doi: https://doi.org/10.1016/j.tsep.2025.104210.
 
[13]         K. Vaferi, S. Nekahi, S. Nekahi, and H. Ghaebi, "Charging/Discharging Performance Examination in a Finned-tube Heat Storage Tank: Based on Artificial Neural Network, Pareto Optimization, and Numerical Simulation," Case Studies in Thermal Engineering, p. 106388, 2025, doi: https://doi.org/10.1016/j.csite.2025.106388.
 
[14]         S. Shen, C. Wu, and F. Duan, "Machine learning for predicting the PCM melting process in a rectangular enclosure energy storage," AI Thermal Fluids, vol. 1, p. 100001, 2025, doi: https://doi.org/10.1016/j.aitf.2024.100001.
 
[15]         A. A. R. Darzi, S. M. Mousavi, M. Razbin, and M. Li, "Utilizing neural networks and genetic algorithms in AI-assisted CFD for optimizing PCM-based thermal energy storage units with extended surfaces," Thermal Science and Engineering Progress, vol. 54, p. 102795, 2024, doi: https://doi.org/10.1016/j.tsep.2024.102795.
 
[16]         A. Saifoddin, N. Mirzaei, M. Allahrabbi Shirazi, and H. Yousefi, "Comparative Applications of Supervised and Unsupervised Machine Learning Models in Energy Systems," (in en), Journal of Energy Management and Technology, vol. 9, no. 4, pp. 284–290, 2025, doi: https://10.22109/jemt.2025.547118.1573.
 
[17]         R. K. Kottala, B. K. Ramaraj, J. BS, M. G. Vempally, and M. Lakshmanan, "Experimental investigation and neural network modeling of binary eutectic/expanded graphite composites for medium temperature thermal energy storage," Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, vol. 47, no. 2, p. 2043490, 2025, doi: https://doi.org/10.1080/15567036.2022.2043490.
 
[18]         R. Bharathiraja, T. Ramkumar, M. Selvakumar, and K. Sasikumar, "Experimental and numerical analysis of hybrid nano-enhanced phase change material (PCM) based flat plate solar collector," Journal of Energy Storage, vol. 96, p. 112649, 2024, doi: https://doi.org/10.1016/j.est.2024.112649.
 
[19]         O. Kazaz and E. Abu-Nada, "Thermal performance of nano-architected phase change energetic materials for a next-generation solar harvesting system," Energy Conversion and Management, vol. 327, p. 119541, 2025, doi: https://doi.org/10.1016/j.enconman.2025.119541.
 
[20]         A. Nandi and N. Biswas, "Melting dynamics and energy efficiency of nano-enhanced phase change material (NePCM) with graphene, Al2O3, and CuO for superior thermal energy storage (TES)," Journal of Energy Storage, vol. 109, p. 115076, 2025, doi: https://doi.org/10.1016/j.est.2024.115076.
 
[21]         A. Vedrtnam et al., "Combined CFD and FEM analysis of 3D printed PCM integrated concrete panels for passive thermal management in buildings," Applied Thermal Engineering, vol. 279, p. 127544, 2025, doi: https://doi.org/10.1016/j.applthermaleng.2025.127544.
 
[22]         X. Huang et al., "Multi-phase flow and heat transfer characteristics of composite heat storage materials during melting process: simulation and optimization," International Journal of Heat and Mass Transfer, vol. 253, p. 127599, 2025, doi: https://doi.org/10.1016/j.ijheatmasstransfer.2025.127599.
 
[23]         Y.-T. Lee, Y.-R. Liao, L.-H. Chien, F.-B. Cheung, and A.-S. Yang, "Performance enhancement of latent heat thermal energy storage systems via dynamic melting process of PCM under different control strategies," Applied Thermal Engineering, vol. 259, p. 124903, 2025, doi: https://doi.org/10.1016/j.applthermaleng.2024.124903.
 
[24]         G. Yan et al., "Solar-powered compact thermal energy storage system with rapid response time and rib-enhanced plate via techniques of CFD, ANN, and GA," Journal of Energy Storage, vol. 105, p. 114807, 2025, doi: https://doi.org/10.1016/j.est.2024.114807.
 
[25]         H. E. Abdellatif, A. Belaadi, A. Arshad, B. X. Chai, and D. Ghernaout, "Enhancing thermal energy storage system efficiency: Geometric analysis of phase change material integrated wedge-shaped heat exchangers," Applied Thermal Engineering, vol. 262, p. 125268, 2025, doi: https://doi.org/10.1016/j.applthermaleng.2024.125268.
 
[26]         S. Agrebi, B. Tashtoush, and A. Guizani, "Performance analysis of helical coil heat exchangers for latent heat thermal storage in solar applications," Energy Conversion and Management, vol. 343, p. 120205, 2025, doi: https://doi.org/10.1016/j.enconman.2025.120205.
 
[27]         A. Almadhor et al., "Optimizing novel thermal energy storage systems: Enhancing melting efficiency with tubes, stands, and advanced machine learning techniques," Journal of Energy Storage, vol. 124, p. 116908, 2025, doi: https://doi.org/10.1016/j.est.2025.116908.
 
[28]         A. S. Soliman, A. Radwan, M. S. Fouda, A. A. Sultan, and O. Abdelrehim, "Energy assessment of a sliding window integrated with PV cell and multiple PCMs," Journal of Energy Storage, vol. 86, p. 111341, 2024, doi: https://doi.org/10.1016/j.est.2024.111341.
 
[29]         R. G. Elenga, L. Zhu, and S. Defilla, "Performance evaluation of different building envelopes integrated with phase change materials in tropical climates," Energy and Built Environment, vol. 6, no. 2, pp. 332–346, 2025, doi: https://doi.org/10.1016/j.enbenv.2023.11.008.
 
[30]         O. O. Issa and V. Thirunavukkarasu, "Experimental study on charging and discharging behavior of PCM encapsulations for thermal energy storage of concentrating solar power system," Journal of Energy Storage, vol. 85, p. 111071, 2024, doi: https://doi.org/10.1016/j.est.2024.111071.
 
[31]         A. Sharma, P. K. Singh, E. Makki, J. Giri, and T. Sathish, "A comprehensive review of critical analysis of biodegradable waste PCM for thermal energy storage systems using machine learning and deep learning to predict dynamic behavior," Heliyon, vol. 10, no. 3, 2024, doi: https://doi.org/10.1016/j.heliyon.2024.e25800.
 
[32]         A. Basem et al., "Integrating artificial intelligence-based metaheuristic optimization with machine learning to enhance Nanomaterial-containing latent heat thermal energy storage systems," Energy Conversion and Management: X, vol. 25, p. 100835, 2025, doi: https://doi.org/10.1016/j.ecmx.2024.100835.
 
[33]         B. İzgi, "Machine learning predictions and optimization for thermal energy storage in cylindrical encapsulated phase change material," International Journal of Energy Studies, vol. 9, no. 2, pp. 199–218, 2024, doi: https://doi.org/10.58559/ijes.1420875.
 
[34]         W. Zhang, H. Tian, and T. Liu, "Unraveling the structure and thermophysical property of heterogeneous eutectic salt by machine learning potential for solar thermal energy storage," Sustainable Materials and Technologies, vol. 45, p. e01451, 2025, doi: https://doi.org/10.1016/j.susmat.2025.e01451.
 
[35]         L. Ran et al., "Advancing solar thermal utilization by optimization of phase change material thermal storage systems: A hybrid approach of artificial neural network (ANN)/Genetic algorithm (GA)," Case Studies in Thermal Engineering, vol. 64, p. 105513, 2024, doi: https://doi.org/10.1016/j.csite.2024.105513.
 
[36]         A. Anagnostopoulos, T. Xenitopoulos, Y. Ding, and P. Seferlis, "An integrated machine learning and metaheuristic approach for advanced packed bed latent heat storage system design and optimization," Energy, vol. 297, p. 131149, 2024, doi: https://doi.org/10.1016/j.energy.2024.131149.
 
[37]         V. K. Venkatraman Balakrishnan and K. Kumaresan, "Thermal analysis of PCM magnesium chloride hexahydrate using various machine learning and deep learning models," 2023, doi: https://doi.org/10.1016/j.engappai.2023.107159.
 
[38]         A. Nokhosteen and S. Sobhansarbandi, "Melting behavior prediction of latent heat storage materials: A multi-pronged solution," Journal of Energy Storage, vol. 65, p. 107018, 2023, doi: https://doi.org/10.1016/j.est.2023.107018.
 
[39]         K. Vaferi, A. Farajollahi, T. Gholizadeh, and M. Rostami, "Enhancing charging and discharging performance in a novel latent heat storage via design optimization and artificial neural network modeling," Journal of Energy Storage, vol. 114, p. 115757, 2025, doi: https://doi.org/10.1016/j.est.2025.115757.
 
[40]         H. E. Abdellatif, S. A. Khan, A. Belaadi, and D. Ghernaout, "Enhancing thermal energy storage: The impact of inclined enclosure geometry and artificial neural network based modeling on phase change material melting performance," Journal of Energy Storage, vol. 114, p. 115750, 2025, doi: https://doi.org/10.1016/j.est.2025.115750.
 
[41]         C. Yan et al., "Heat release efficiency Betterment inside a novel-designed latent heat exchanger featuring arc-shaped fins and a rotational mechanism via numerical model and artificial neural network," Case Studies in Thermal Engineering, vol. 61, p. 105093, 2024, doi: https://doi.org/10.1016/j.csite.2024.105093.
 
 
[42]         H. S. Sultan et al., "Improving phase change heat transfer in an enclosure filled by uniform and heterogenous metal foam layers: A neural network design approach," Journal of Energy Storage, vol. 85, p. 110954, 2024/04/30/ 2024, doi: https://doi.org/10.1016/j.est.2024.110954.
 
[43]         Z. Zheng et al., "Optimizing and investigating the charging time of phase change materials in a compact-latent heat storage using pareto front analysis, artificial neural networks, and numerical simulations," Journal of Energy Storage, vol. 102, p. 113966, 2024, doi: https://doi.org/10.1016/j.est.2024.113966.
 
[44]         B. İzgi and H. Z. Demirağ, "Optimizing thermal energy storage in rectangular unit: Exploring the impact of moving fin with phase change material," Journal of Energy Storage, vol. 99, p. 113452, 2024, doi: https://doi.org/10.1016/j.est.2024.113452.
 
[45]         T. Xenitopoulos, A. Anagnostopoulos, G. Gaidajis, Y. Ding, and P. Seferlis, "Insights into advanced packed bed latent heat storage systems through explainable artificial intelligence techniques," International Journal of Heat and Mass Transfer, vol. 253, p. 127577, 2025, doi: https://doi.org/10.1016/j.ijheatmasstransfer.2025.127577.
 
[46]         Y. Zhang, Z. He, W. Guo, and P. Zhang, "Data-driven optimization of packed bed thermal energy storage heating system with encapsulated phase change material," Journal of Energy Storage, vol. 79, p. 110017, 2024, doi: https://doi.org/10.1016/j.est.2023.110017.
 
[47]         X. Yang, J. Cui, Y. Li, H. Chi, and J. Xie, "Multi-factor analysis and optimization design of a cascaded packed-bed thermal storage system coupled with adiabatic compressed air energy storage," Energy Conversion and Management, vol. 300, p. 117961, 2024, doi: https://doi.org/10.1016/j.enconman.2023.117961.
 
[48]         X. Yang, Y. Li, Y. Ma, J. Cui, and J. Xie, "Optimization of thermal storage performance of cascaded multi-PCMs and carbon foam energy storage system based on GPR-PSO algorithm," Journal of Energy Storage, vol. 83, p. 110626, 2024, doi: https://doi.org/10.1016/j.est.2024.110626.
مجله مهندسی مکانیک
دوره 34، شماره 6 - شماره پیاپی 165
بهمن و اسفند 1404
صفحه 72-86

  • تاریخ دریافت 26 شهریور 1404
  • تاریخ بازنگری 15 دی 1404
  • تاریخ پذیرش 25 بهمن 1404