IDEAS home Printed from https://ideas.repec.org/a/eee/appene/v372y2024ics0306261924011061.html
   My bibliography  Save this article

Deep encoder–decoder hierarchical convolutional neural networks for conjugate heat transfer surrogate modeling

Author

Listed:
  • Ebbs-Picken, Takiah
  • Romero, David A.
  • Da Silva, Carlos M.
  • Amon, Cristina H.

Abstract

Conjugate heat transfer (CHT) analyses are vital for the design of many energy systems. However, high-fidelity CHT numerical simulations are computationally intensive, which limits their applications such as design optimization, where hundreds to thousands of evaluations are required. In this work, we develop a modular deep encoder–decoder hierarchical (DeepEDH) convolutional neural network, a novel deep-learning-based surrogate modeling methodology for computationally intensive CHT analyses. Leveraging convective temperature dependencies, we propose a two-stage temperature prediction architecture that couples velocity and temperature fields. The proposed DeepEDH methodology is demonstrated by modeling the pressure, velocity, and temperature fields for a liquid-cooled cold-plate-based battery thermal management system with variable channel geometry. A computational mesh and CHT formulation of the cold plate is created and solved using the finite element method (FEM), generating a dataset of 1,500 simulations. The FEM results are transformed and scaled from unstructured to structured, image-like meshes to create training and test datasets for DeepEDH models. The DeepEDH architecture’s performance is examined in relation to data scaling, training dataset size, and network depth. Our performance analysis covers the impact of the novel architecture, separate DeepEDH models for each field, output geometry masks, multi-stage temperature field predictions, and optimizations of the hyperparameters and architecture. Furthermore, we quantify the influence of the CHT analysis’ thermal boundary conditions on surrogate model performance, highlighting improved temperature model performance with higher heat fluxes. Compared to other deep learning neural network surrogate models, such as U-Net and DenseED, the proposed DeepEDH architecture for CHT analyses exhibits up to a 65% enhancement in the coefficient of determination R2.

Suggested Citation

  • Ebbs-Picken, Takiah & Romero, David A. & Da Silva, Carlos M. & Amon, Cristina H., 2024. "Deep encoder–decoder hierarchical convolutional neural networks for conjugate heat transfer surrogate modeling," Applied Energy, Elsevier, vol. 372(C).
    • Handle: RePEc:eee:appene:v:372:y:2024:i:c:s0306261924011061
    DOI: 10.1016/j.apenergy.2024.123723
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0306261924011061
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.apenergy.2024.123723?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Zhou, Wei & Li, Xiangchengzhen & Qi, ZhongLi & Zhao, HaiHang & Yi, Jun, 2024. "A shale gas production prediction model based on masked convolutional neural network," Applied Energy, Elsevier, vol. 353(PA).
    2. Naseri, F. & Gil, S. & Barbu, C. & Cetkin, E. & Yarimca, G. & Jensen, A.C. & Larsen, P.G. & Gomes, C., 2023. "Digital twin of electric vehicle battery systems: Comprehensive review of the use cases, requirements, and platforms," Renewable and Sustainable Energy Reviews, Elsevier, vol. 179(C).
    3. Di Natale, L. & Svetozarevic, B. & Heer, P. & Jones, C.N., 2022. "Physically Consistent Neural Networks for building thermal modeling: Theory and analysis," Applied Energy, Elsevier, vol. 325(C).
    4. Zhang, Jincheng & Zhao, Xiaowei, 2022. "Wind farm wake modeling based on deep convolutional conditional generative adversarial network," Energy, Elsevier, vol. 238(PB).
    5. Zhang, Jincheng & Zhao, Xiaowei, 2020. "A novel dynamic wind farm wake model based on deep learning," Applied Energy, Elsevier, vol. 277(C).
    6. Ren, Haoshan & Gao, Dian-ce & Ma, Zhenjun & Zhang, Sheng & Sun, Yongjun, 2024. "Data-driven surrogate optimization for deploying heterogeneous multi-energy storage to improve demand response performance at building cluster level," Applied Energy, Elsevier, vol. 356(C).
    7. He, Ning & Wang, Qiqi & Lu, Zhenfeng & Chai, Yike & Yang, Fangfang, 2024. "Early prediction of battery lifetime based on graphical features and convolutional neural networks," Applied Energy, Elsevier, vol. 353(PA).
    8. Maakala, Viljami & Järvinen, Mika & Vuorinen, Ville, 2018. "Optimizing the heat transfer performance of the recovery boiler superheaters using simulated annealing, surrogate modeling, and computational fluid dynamics," Energy, Elsevier, vol. 160(C), pages 361-377.
    9. Tikka, Ville & Haapaniemi, Jouni & Räisänen, Otto & Honkapuro, Samuli, 2022. "Convolutional neural networks in estimating the spatial distribution of electric vehicles to support electricity grid planning," Applied Energy, Elsevier, vol. 328(C).
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Li, Rui & Zhang, Jincheng & Zhao, Xiaowei, 2022. "Dynamic wind farm wake modeling based on a Bilateral Convolutional Neural Network and high-fidelity LES data," Energy, Elsevier, vol. 258(C).
    2. Zhou, Lei & Wen, Jiahao & Wang, Zhaokun & Deng, Pengru & Zhang, Hongfu, 2023. "High-fidelity wind turbine wake velocity prediction by surrogate model based on d-POD and LSTM," Energy, Elsevier, vol. 275(C).
    3. Feiyu Chen & Linghui Sun & Boyu Jiang & Xu Huo & Xiuxiu Pan & Chun Feng & Zhirong Zhang, 2025. "A Review of AI Applications in Unconventional Oil and Gas Exploration and Development," Energies, MDPI, vol. 18(2), pages 1-30, January.
    4. Li, Siyi & Zhang, Mingrui & Piggott, Matthew D., 2023. "End-to-end wind turbine wake modelling with deep graph representation learning," Applied Energy, Elsevier, vol. 339(C).
    5. Liang, Xinbin & Zhu, Xu & Chen, Siliang & Jin, Xinqiao & Xiao, Fu & Du, Zhimin, 2023. "Physics-constrained cooperative learning-based reference models for smart management of chillers considering extrapolation scenarios," Applied Energy, Elsevier, vol. 349(C).
    6. Di Natale, L. & Svetozarevic, B. & Heer, P. & Jones, C.N., 2023. "Towards scalable physically consistent neural networks: An application to data-driven multi-zone thermal building models," Applied Energy, Elsevier, vol. 340(C).
    7. Luo, Zhaohui & Wang, Longyan & Xu, Jian & Wang, Zilu & Yuan, Jianping & Tan, Andy C.C., 2024. "A reduced order modeling-based machine learning approach for wind turbine wake flow estimation from sparse sensor measurements," Energy, Elsevier, vol. 294(C).
    8. Karim Boubouh & Robert Basmadjian & Omid Ardakanian & Alexandre Maurer & Rachid Guerraoui, 2023. "PePTM : An Efficient and Accurate Personalized P2P Learning Algorithm for Home Thermal Modeling," Energies, MDPI, vol. 16(18), pages 1-22, September.
    9. Xiao, Tianqi & You, Fengqi, 2023. "Building thermal modeling and model predictive control with physically consistent deep learning for decarbonization and energy optimization," Applied Energy, Elsevier, vol. 342(C).
    10. Zhang, Jincheng & Zhao, Xiaowei, 2021. "Spatiotemporal wind field prediction based on physics-informed deep learning and LIDAR measurements," Applied Energy, Elsevier, vol. 288(C).
    11. Darbandi, Masoud & Fatin, Ali & Bordbar, Hadi, 2020. "Numerical study on NOx reduction in a large-scale heavy fuel oil-fired boiler using suitable burner adjustments," Energy, Elsevier, vol. 199(C).
    12. Taboga, Vincent & Gehring, Clement & Cam, Mathieu Le & Dagdougui, Hanane & Bacon, Pierre-Luc, 2024. "Neural differential equations for temperature control in buildings under demand response programs," Applied Energy, Elsevier, vol. 368(C).
    13. Gou, Liangjie & Yang, Zhaozhong & Min, Chao & Yi, Duo & Li, Xiaogang & Kong, Bing, 2024. "A novel domain adaptation method with physical constraints for shale gas production forecasting," Applied Energy, Elsevier, vol. 371(C).
    14. Hua Song & Huaizhi Chen & Yanbo Wang & Xiang-E Sun, 2024. "An Overview About Second-Life Battery Utilization for Energy Storage: Key Challenges and Solutions," Energies, MDPI, vol. 17(23), pages 1-26, December.
    15. Wang, Yu & Wei, Shanbi & Yang, Wei & Chai, Yi, 2023. "Adaptive economic predictive control for offshore wind farm active yaw considering generation uncertainty," Applied Energy, Elsevier, vol. 351(C).
    16. Jiang, Lidang & Li, Zhuoxiang & Hu, Changyan & Chen, Junxiong & Huang, Qingsong & He, Ge, 2024. "A robust adapted Flexible Parallel Neural Network architecture for early prediction of lithium battery lifespan," Energy, Elsevier, vol. 308(C).
    17. Wang, Fuwei & Chen, Dongxia & Li, Meijun & Chen, Zhangxin & Wang, Qiaochu & Jiang, Mengya & Rong, Lanxi & Wang, Yuqi & Li, Sha & Iltaf, Khawaja Hasnain & Wanma, Renzeng & Liu, Chen, 2024. "A novel method for predicting shallow hydrocarbon accumulation based on source-fault-sand (S-F-Sd) evaluation and ensemble neural network (ENN)," Applied Energy, Elsevier, vol. 359(C).
    18. Lim, Jonghun & Kim, Junghwan, 2022. "Optimizing ash deposit removal system to maximize biomass recycling as renewable energy for CO2 reduction," Renewable Energy, Elsevier, vol. 190(C), pages 1006-1017.
    19. Xu, Wenjie & Svetozarevic, Bratislav & Di Natale, Loris & Heer, Philipp & Jones, Colin N., 2024. "Data-driven adaptive building thermal controller tuning with constraints: A primal–dual contextual Bayesian optimization approach," Applied Energy, Elsevier, vol. 358(C).
    20. Daihong Gu & Rongchen Zheng & Peng Cheng & Shuaiqi Zhou & Gongjie Yan & Haitao Liu & Kexin Yang & Jianguo Wang & Yuan Zhu & Mingwei Liao, 2024. "Single Well Production Prediction Model of Gas Reservoir Based on CNN-BILSTM-AM," Energies, MDPI, vol. 17(22), pages 1-18, November.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:appene:v:372:y:2024:i:c:s0306261924011061. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/description#description .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.