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

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

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 p...

Full description

Bibliographic Details
Main Authors: Whyte Andy, Parks Geoff
Format: Article
Language:English
Published: EDP Sciences 2021-01-01
Series:EPJ Web of Conferences
Subjects:
deep learning
fuel management
pwr
optimization,
surrogate model
Online Access:https://www.epj-conferences.org/articles/epjconf/pdf/2021/01/epjconf_physor2020_12003.pdf
id doaj-23e31a89e0784d159e11641aad997940
record_format Article
spelling doaj-23e31a89e0784d159e11641aad9979402021-08-02T16:01:03ZengEDP SciencesEPJ Web of Conferences2100-014X2021-01-012471200310.1051/epjconf/202124712003epjconf_physor2020_12003SURROGATE MODEL OPTIMIZATION OF A ‘MICRO CORE’ PWR FUEL ASSEMBLY ARRANGEMENT USING DEEP LEARNING MODELSWhyte Andy0Parks Geoff1University of Cambridge Department of EngineeringUniversity of Cambridge Department of EngineeringThis 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.https://www.epj-conferences.org/articles/epjconf/pdf/2021/01/epjconf_physor2020_12003.pdfdeep learningfuel managementpwroptimization,surrogate model
collection DOAJ
language English
format Article
sources DOAJ
author Whyte Andy
Parks Geoff
spellingShingle Whyte Andy
Parks Geoff
SURROGATE MODEL OPTIMIZATION OF A ‘MICRO CORE’ PWR FUEL ASSEMBLY ARRANGEMENT USING DEEP LEARNING MODELS
EPJ Web of Conferences
deep learning
fuel management
pwr
optimization,
surrogate model
author_facet Whyte Andy
Parks Geoff
author_sort Whyte Andy
title SURROGATE MODEL OPTIMIZATION OF A ‘MICRO CORE’ PWR FUEL ASSEMBLY ARRANGEMENT USING DEEP LEARNING MODELS
title_short SURROGATE MODEL OPTIMIZATION OF A ‘MICRO CORE’ PWR FUEL ASSEMBLY ARRANGEMENT USING DEEP LEARNING MODELS
title_full SURROGATE MODEL OPTIMIZATION OF A ‘MICRO CORE’ PWR FUEL ASSEMBLY ARRANGEMENT USING DEEP LEARNING MODELS
title_fullStr SURROGATE MODEL OPTIMIZATION OF A ‘MICRO CORE’ PWR FUEL ASSEMBLY ARRANGEMENT USING DEEP LEARNING MODELS
title_full_unstemmed SURROGATE MODEL OPTIMIZATION OF A ‘MICRO CORE’ PWR FUEL ASSEMBLY ARRANGEMENT USING DEEP LEARNING MODELS
title_sort surrogate model optimization of a ‘micro core’ pwr fuel assembly arrangement using deep learning models
publisher EDP Sciences
series EPJ Web of Conferences
issn 2100-014X
publishDate 2021-01-01
description 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.
topic deep learning
fuel management
pwr
optimization,
surrogate model
url https://www.epj-conferences.org/articles/epjconf/pdf/2021/01/epjconf_physor2020_12003.pdf
work_keys_str_mv AT whyteandy surrogatemodeloptimizationofamicrocorepwrfuelassemblyarrangementusingdeeplearningmodels
AT parksgeoff surrogatemodeloptimizationofamicrocorepwrfuelassemblyarrangementusingdeeplearningmodels
_version_ 1721230199313399808

Similar Items