Neural network surrogate models for equations of state

被引:5
|
作者
Mentzer, Katherine L. [1 ,2 ]
Peterson, J. Luc [1 ]
机构
[1] Lawrence Livermore Natl Lab, POB 808, Livermore, CA 94551 USA
[2] Stanford Univ, Inst Computat & Math Engn, 475 Via Ortega Suite B060, Stanford, CA 94305 USA
关键词
Classification (of information) - Entropy - Errors - Inertial confinement fusion - Regression analysis;
D O I
10.1063/5.0126708
中图分类号
O35 [流体力学]; O53 [等离子体物理学];
学科分类号
070204 ; 080103 ; 080704 ;
摘要
Equation of state (EOS) data provide necessary information for accurate multiphysics modeling, which is necessary for fields such as inertial confinement fusion. Here, we suggest a neural network surrogate model of energy and entropy and use thermodynamic relationships to derive other necessary thermodynamic EOS quantities. We incorporate phase information into the model by training a phase classifier and using phase-specific regression models, which improves the modal prediction accuracy. Our model predicts energy values to 1% relative error and entropy to 3.5% relative error in a log-transformed space. Although sound speed predictions require further improvement, the derived pressure values are accurate within 10% relative error. Our results suggest that neural network models can effectively model EOS for inertial confinement fusion simulation applications.
引用
收藏
页数:13
相关论文
共 50 条
  • [1] Sobolev trained neural network surrogate models for optimization
    Tsay, Calvin
    [J]. COMPUTERS & CHEMICAL ENGINEERING, 2021, 153
  • [2] Optimal experimental design with fast neural network surrogate models
    Stuckner, Joshua
    Piekenbrock, Matthew
    Arnold, Steven M.
    Ricks, Trenton M.
    [J]. COMPUTATIONAL MATERIALS SCIENCE, 2021, 200
  • [3] Feasibility of Deep Neural Network Surrogate Models in Fluid Dynamics
    Bender, Niels C.
    Andersen, Torben O.
    Pedersen, Henrik C.
    [J]. MODELING IDENTIFICATION AND CONTROL, 2019, 40 (02) : 71 - 87
  • [4] Multiscale topology optimization using neural network surrogate models
    White, Daniel A.
    Arrighi, William J.
    Kudo, Jun
    Watts, Seth E.
    [J]. COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, 2019, 346 : 1118 - 1135
  • [5] Predicting Noisy Data with an Improvement RBF Neural Network for Surrogate Models
    Jiang, Yaping
    Wei, Guosong
    Sun, Xueyan
    Zhang, Yueqiang
    [J]. PROCEEDINGS OF THE 2016 4TH INTERNATIONAL CONFERENCE ON MACHINERY, MATERIALS AND COMPUTING TECHNOLOGY, 2016, 60 : 539 - 542
  • [6] Neural network surrogate models for absorptivity and emissivity spectra of multiple elements
    Wal, Michael D. Vander
    McClarren, Ryan G.
    Humbird, Kelli D.
    [J]. MACHINE LEARNING WITH APPLICATIONS, 2022, 8
  • [7] Convolutional Neural Network Surrogate Models for the Mechanical Properties of Periodic Structures
    Messner, Mark C.
    [J]. JOURNAL OF MECHANICAL DESIGN, 2020, 142 (02)
  • [8] From Differential Equations to Multilayer Neural Network Models
    Kaverzneva, Tatiana T.
    Malykhina, Galina F.
    Tarkhov, Dmitriy A.
    [J]. ADVANCES IN NEURAL NETWORKS - ISNN 2019, PT I, 2019, 11554 : 19 - 27
  • [9] Echo state network ensembles for surrogate models with an application to urban mobility
    Cervellera, Cristiano
    Maccio, Danilo
    Rebora, Francesco
    [J]. 2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2022,
  • [10] Transient Modeling of Induction Machine Using Artificial Neural Network Surrogate Models
    Tahkola, Mikko
    Mukherjee, Victor
    Keranen, Janne
    [J]. IEEE TRANSACTIONS ON MAGNETICS, 2022, 58 (09) : 1 - 1