Computationally effective machine learning approach for modular thermal energy storage design

被引:1
作者
Singh, Davinder [1 ,2 ]
Rugamba, Tanguy [3 ]
Katara, Harsh [4 ]
Grewal, Kuljeet Singh [3 ]
机构
[1] Univ Toronto, Dept Chem, Chem Phys Theory Grp, Toronto, ON M5S 3H6, Canada
[2] Univ Toronto, Ctr Quantum Informat & Quantum Control, Toronto, ON M5S 3H6, Canada
[3] Univ Prince Edward Isl, Fac Sustainable Design Engn FSDE, Future Urban & Energy Lab Sustainabil FUEL S, Charlottetown, PE C1A 4P3, Canada
[4] Indian Inst Technol IIT Guwahati, Dept Comp Sci & Engn, Gauhati 781039, Assam, India
基金
加拿大自然科学与工程研究理事会;
关键词
Machine learning; Deep learning; Supervised learning; Neural network; Thermal energy storage; Computational and cost effectiveness; SYSTEMS;
D O I
10.1016/j.apenergy.2024.124430
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
This research presents an innovative approach that integrates computational fluid dynamics (CFD) and machine learning (ML) for the design and optimization of thermal energy storage (TES) systems. Heat discharging parametric analyses conducted using CFD serve as the basis for training ML models, including linear regression, K-nearest neighbor (KNN) regression, gradient boost regression (GBR), XGBoost, LightGBM, and neural network (NN). NN emerges as the most suitable for predicting time-dependent variations of concrete and heat transfer fluid (HTF) temperatures. The trained ML models offer an efficient alternative to traditional CFD simulations, enabling the prediction of temperatures in concrete thermal energy storage (CTES) modules under varying inlet conditions, velocities, and time. Leveraging these ML models, the research demonstrates the design of modular CTES cascaded systems with multiple modules in series and parallel configurations, significantly reducing computational cost and time by over 99% compared to full-scale CFD simulations. For instance, in predicting 4-hour time-dependent thermal behavior, CFD takes 97 s per data point and 238,500 s for a single module, compared to ML models' 16-20 ms per data point and around 290 s per module, indicating their efficiency and scalability in predicting thermal discharge, especially for modular CTES system design and optimization. ML models also demonstrate computational efficiency for designing CTES systems involving multiple modules, taking approximately 765 s - 1047 s for various CTES system configurations, indicating their effectiveness over CFD in predicting thermal discharge for modular CTES systems. The integration of CFD and ML provides a streamlined workflow for designing and optimizing CTES systems, reducing computational efforts, cost, and time. Moreover, this workflow can be updated with additional training data to implement it for unique modular designs with different conditions. Such a generalization of this ML-based approach makes it applicable to a wide range of thermal energy storage designs and geometries, offering a promising avenue for future research and development in the field of thermal energy storage.
引用
收藏
页数:16
相关论文
共 56 条
  • [1] AHA DW, 1991, MACH LEARN, V6, P37, DOI 10.1007/BF00153759
  • [2] Almaspoor Mohammad Hassan, 2021, Support vector machines in big data classification: A systematic literature review
  • [3] An integrated machine learning and metaheuristic approach for advanced packed bed latent heat storage system design and optimization
    Anagnostopoulos, Argyrios
    Xenitopoulos, Theofilos
    Ding, Yulong
    Seferlis, Panos
    [J]. ENERGY, 2024, 297
  • [4] [Anonymous], 1995, Neural Networks for Pattern Recognition
  • [5] [Anonymous], TensorFlow
  • [6] Thermal conductivity of concrete - A review
    Asadi, Iman
    Shafigh, Payam
    Bin Abu Hassan, Zahiruddin Fitri
    Mahyuddin, Norhayati Binti
    [J]. JOURNAL OF BUILDING ENGINEERING, 2018, 20 : 81 - 93
  • [7] Bastida H, 2019, Dynamic modelling and control of thermal energy storage, V158, P2890, DOI [10.1016/j.egypro.2019.01.942, DOI 10.1016/J.EGYPRO.2019.01.942]
  • [8] Bishop C. M., 2006, Springer google schola, DOI DOI 10.1007/978-0-387-45528-0
  • [9] Blazek J., 2015, Computational Fluid Dynamics: Principles and Applications
  • [10] Key Challenges for High Temperature Thermal Energy Storage in Concrete-First Steps towards a Novel Storage Design
    Cabeza, Luisa F.
    Verez, David
    Zsembinszki, Gabriel
    Borri, Emiliano
    Prieto, Cristina
    [J]. ENERGIES, 2022, 15 (13)