YaBeSH Engineering and Technology Library

    • Journals
    • PaperQuest
    • YSE Standards
    • YaBeSH
    • Login
    View Item 
    •   YE&T Library
    • ASME
    • Journal of Computing and Information Science in Engineering
    • View Item
    •   YE&T Library
    • ASME
    • Journal of Computing and Information Science in Engineering
    • View Item
    • All Fields
    • Source Title
    • Year
    • Publisher
    • Title
    • Subject
    • Author
    • DOI
    • ISBN
    Advanced Search
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Archive

    Untitled

    Source: Journal of Computing and Information Science in Engineering:;2022:;volume( 023 ):;issue: 003::page 31008-1
    Author:
    Liu, Dehao
    ,
    Pusarla, Pranav
    ,
    Wang, Yan
    DOI: 10.1115/1.4055316
    Publisher: The American Society of Mechanical Engineers (ASME)
    Abstract: Data sparsity is still the main challenge to apply machine learning models to solve complex scientific and engineering problems. The root cause is the “curse of dimensionality” in training these models. Training algorithms need to explore and exploit in a very high-dimensional parameter space to search the optimal parameters for complex models. In this study, a new scheme of multifidelity physics-constrained neural networks with minimax architecture is proposed to improve the data efficiency of training neural networks by incorporating physical knowledge as constraints and sampling data with various fidelities. In this new framework, fully connected neural networks with two levels of fidelities are combined to improve the prediction accuracy. The low-fidelity neural network is used to approximate the low-fidelity data, whereas the high-fidelity neural network is adopted to approximate the correlation function between the low-fidelity and high-fidelity data. To systematically search the optimal weights of various losses for reducing the training time, the Dual-Dimer algorithm is adopted to search high-order saddle points of the minimax optimization problem. The proposed framework is demonstrated with two-dimensional heat transfer, phase transition, and dendritic growth problems, which are fundamental in materials modeling. With the same set of training data, the prediction error of the multifidelity physics-constrained neural network with minimax architecture can be two orders of magnitude lower than that of the multifidelity neural network with minimax architecture.
    • Download: (1.756Mb)
    • Show Full MetaData Hide Full MetaData
    • Get RIS
    • Item Order
    • Go To Publisher
    • Price: 5000 Rial
    • Statistics

    URI
    http://yetl.yabesh.ir/yetl1/handle/yetl/4292071
    Collections
    • Journal of Computing and Information Science in Engineering

    Show full item record

    contributor authorLiu, Dehao
    contributor authorPusarla, Pranav
    contributor authorWang, Yan
    date accessioned2023-08-16T18:30:52Z
    date available2023-08-16T18:30:52Z
    date copyright12/9/2022 12:00:00 AM
    date issued2022
    identifier issn1530-9827
    identifier otherjcise_23_3_031008.pdf
    identifier urihttp://yetl.yabesh.ir/yetl1/handle/yetl/4292071
    description abstractData sparsity is still the main challenge to apply machine learning models to solve complex scientific and engineering problems. The root cause is the “curse of dimensionality” in training these models. Training algorithms need to explore and exploit in a very high-dimensional parameter space to search the optimal parameters for complex models. In this study, a new scheme of multifidelity physics-constrained neural networks with minimax architecture is proposed to improve the data efficiency of training neural networks by incorporating physical knowledge as constraints and sampling data with various fidelities. In this new framework, fully connected neural networks with two levels of fidelities are combined to improve the prediction accuracy. The low-fidelity neural network is used to approximate the low-fidelity data, whereas the high-fidelity neural network is adopted to approximate the correlation function between the low-fidelity and high-fidelity data. To systematically search the optimal weights of various losses for reducing the training time, the Dual-Dimer algorithm is adopted to search high-order saddle points of the minimax optimization problem. The proposed framework is demonstrated with two-dimensional heat transfer, phase transition, and dendritic growth problems, which are fundamental in materials modeling. With the same set of training data, the prediction error of the multifidelity physics-constrained neural network with minimax architecture can be two orders of magnitude lower than that of the multifidelity neural network with minimax architecture.
    publisherThe American Society of Mechanical Engineers (ASME)
    typeJournal Paper
    journal volume23
    journal issue3
    journal titleJournal of Computing and Information Science in Engineering
    identifier doi10.1115/1.4055316
    journal fristpage31008-1
    journal lastpage31008-10
    page10
    treeJournal of Computing and Information Science in Engineering:;2022:;volume( 023 ):;issue: 003
    contenttypeFulltext
    DSpace software copyright © 2002-2015  DuraSpace
    نرم افزار کتابخانه دیجیتال "دی اسپیس" فارسی شده توسط یابش برای کتابخانه های ایرانی | تماس با یابش
    yabeshDSpacePersian
     
    DSpace software copyright © 2002-2015  DuraSpace
    نرم افزار کتابخانه دیجیتال "دی اسپیس" فارسی شده توسط یابش برای کتابخانه های ایرانی | تماس با یابش
    yabeshDSpacePersian