scholarly journals Deep learning based surrogate model for first-principles global simulations of fusion plasmas

2021 ◽  
Author(s):  
Ge Dong ◽  
Xishuo Wei ◽  
Jian Bao ◽  
Guillaume Brochard ◽  
Zhihong Lin ◽  
...  
Keyword(s):  
Deep Learning ◽  
First Principles ◽  
Surrogate Model ◽  
Fusion Plasmas

scholarly journals Deep learning surrogate model for kinetic Landau-fluid closure with collision

AIP Advances ◽  
2020 ◽  
Vol 10 (7) ◽  
pp. 075108
Author(s):  
Libo Wang ◽  
X. Q. Xu ◽  
Ben Zhu ◽  
Chenhao Ma ◽  
Yi-an Lei
Keyword(s):  
Deep Learning ◽  
Surrogate Model

scholarly journals A DEEP LEARNING BASED SURROGATE MODEL FOR ESTIMATING THE FLUX AND POWER DISTRIBUTION SOLVED BY DIFFUSION EQUATION

2021 ◽  
Vol 247 ◽  
pp. 03013
Author(s):  
Qian Zhang ◽  
Jinchao Zhang ◽  
Liang Liang ◽  
Zhuo Li ◽  
Tengfei Zhang
Keyword(s):  
Deep Learning ◽  
Diffusion Equation ◽  
Power Distribution ◽  
Surrogate Model ◽  
High Efficiency ◽  
Reactor Core ◽  
Training Data ◽  
Diffusion Method ◽  
Convolutional Network ◽  
Learning Platform

A deep learning based surrogate model is proposed for replacing the conventional diffusion equation solver and predicting the flux and power distribution of the reactor core. Using the training data generated by the conventional diffusion equation solver, a special designed convolutional neural network inspired by the FCN (Fully Convolutional Network) is trained under the deep learning platform TensorFlow. Numerical results show that the deep learning based surrogate model is effective for estimating the flux and power distribution calculated by the diffusion method, which means it can be used for replacing the conventional diffusion equation solver with high efficiency boost.

scholarly journals Design of a Deep Learning Based Nonlinear Aerodynamic Surrogate Model for UAVs

2020 ◽  
Author(s):  
Hasan Karali ◽  
Mustafa U. Demirezen ◽  
Mahmut A. Yukselen ◽  
Gokhan Inalhan
Keyword(s):  
Deep Learning ◽  
Surrogate Model ◽  
Nonlinear Aerodynamic

scholarly journals SURROGATE MODEL OPTIMIZATION OF A ‘MICRO CORE’ PWR FUEL ASSEMBLY ARRANGEMENT USING DEEP LEARNING MODELS

2021 ◽  
Vol 247 ◽  
pp. 12003
Author(s):  
Andy Whyte ◽  
Geoff Parks
Keyword(s):  
Deep Learning ◽  
Objective Function ◽  
Fuel Assembly ◽  
Surrogate Model ◽  
Regression Models ◽  
Model Optimization ◽  
Learning Models ◽  
Training Set ◽  
Surrogate Model Optimization ◽  
The Cost

This paper investigates the applicability of surrogate model optimization (SMO) using deep learning regression models to automatically embed knowledge about the objective function into the optimization process. This paper demonstrates two deep learning SMO methods for calculating simple neutronics parameters. Using these models, SMO returns results comparable with those from the early stages of direct iterative optimization. However, for this study, the cost of creating the training set outweighs the benefits of the surrogate models.

Sign in / Sign up

Export Citation Format

Share Document