Convolutional Neural Networks for Heat Flux Model Validation on NSTX-U

Tom Looby; Matthew Reinke; David Donovan; Travis Gray; Mike Messineo; Andrei Khodak

doi:10.1109/TPS.2019.2919288

Convolutional Neural Networks for Heat Flux Model Validation on NSTX-U

Tom Looby, Matthew Reinke, David Donovan, Travis Gray, Mike Messineo, Andrei Khodak

Power Exhaust and Particle Control

Research output: Contribution to journal › Article › peer-review

6 Scopus citations

Abstract

To demonstrate the use of embedded thermocouples in new National Spherical Tokamak eXperiment Upgrade (NSTX-U) graphite plasma-facing components (PFCs), a convolutional neural network (CNN) has been trained using the ANSYS simulations to predict the scrape-off layer (SOL) heat flux width, λ_q , given various machine operational parameters and diagnostic data as inputs. The proof-of-concept CNN was trained on the thermocouple data generated by the approximated NSTX-U heat loads applied to real PFC designs in ANSYS. Once trained, the CNN is capable of high precision reconstruction of parameterized heat flux profiles expected in NSTX-U. In addition, to test the system's ability to cope with noise and systematic error, pseudonoise was injected into the simulated data. CNN can accurately predict the incident heat flux despite this noise and error.

Original language	English
Article number	8733008
Pages (from-to)	3-13
Number of pages	11
Journal	IEEE Transactions on Plasma Science
Volume	48
Issue number	1
DOIs	https://doi.org/10.1109/TPS.2019.2919288
State	Published - Jan 2020

Funding

Manuscript received March 14, 2019; revised April 25, 2019; accepted May 20, 2019. Date of publication June 7, 2019; date of current version January 20, 2020. This work was supported in part by U.S. Department of Energy under Award DE-AC05-00OR22725 and Award DE-AC02-09CH11466. The review of this paper was arranged by Senior Editor S. J. Gitomer. (Corresponding author: Tom Looby.) T. Looby and D. Donovan are with the University of Tennessee, Knoxville, TN 37916 USA (e-mail: [email protected]).

Funders	Funder number
U.S. Department of Energy	DE-AC05-00OR22725, DE-AC02-09CH11466

Keywords

Convolutional
National Spherical Tokamak eXperiment Upgrade (NSTX-U)
divertor
heat flux
machine learning
neural network
nuclear fusion

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/TPS.2019.2919288

Cite this

@article{cb87c95fcf414a44964df53532366b0a,

title = "Convolutional Neural Networks for Heat Flux Model Validation on NSTX-U",

abstract = "To demonstrate the use of embedded thermocouples in new National Spherical Tokamak eXperiment Upgrade (NSTX-U) graphite plasma-facing components (PFCs), a convolutional neural network (CNN) has been trained using the ANSYS simulations to predict the scrape-off layer (SOL) heat flux width, λq , given various machine operational parameters and diagnostic data as inputs. The proof-of-concept CNN was trained on the thermocouple data generated by the approximated NSTX-U heat loads applied to real PFC designs in ANSYS. Once trained, the CNN is capable of high precision reconstruction of parameterized heat flux profiles expected in NSTX-U. In addition, to test the system's ability to cope with noise and systematic error, pseudonoise was injected into the simulated data. CNN can accurately predict the incident heat flux despite this noise and error.",

keywords = "Convolutional, National Spherical Tokamak eXperiment Upgrade (NSTX-U), divertor, heat flux, machine learning, neural network, nuclear fusion",

author = "Tom Looby and Matthew Reinke and David Donovan and Travis Gray and Mike Messineo and Andrei Khodak",

note = "Publisher Copyright: {\textcopyright} 1973-2012 IEEE.",

year = "2020",

month = jan,

doi = "10.1109/TPS.2019.2919288",

language = "English",

volume = "48",

pages = "3--13",

journal = "IEEE Transactions on Plasma Science",

issn = "0093-3813",

publisher = "Institute of Electrical and Electronics Engineers",

number = "1",

}

TY - JOUR

T1 - Convolutional Neural Networks for Heat Flux Model Validation on NSTX-U

AU - Looby, Tom

AU - Reinke, Matthew

AU - Donovan, David

AU - Gray, Travis

AU - Messineo, Mike

AU - Khodak, Andrei

PY - 2020/1

Y1 - 2020/1

N2 - To demonstrate the use of embedded thermocouples in new National Spherical Tokamak eXperiment Upgrade (NSTX-U) graphite plasma-facing components (PFCs), a convolutional neural network (CNN) has been trained using the ANSYS simulations to predict the scrape-off layer (SOL) heat flux width, λq , given various machine operational parameters and diagnostic data as inputs. The proof-of-concept CNN was trained on the thermocouple data generated by the approximated NSTX-U heat loads applied to real PFC designs in ANSYS. Once trained, the CNN is capable of high precision reconstruction of parameterized heat flux profiles expected in NSTX-U. In addition, to test the system's ability to cope with noise and systematic error, pseudonoise was injected into the simulated data. CNN can accurately predict the incident heat flux despite this noise and error.

AB - To demonstrate the use of embedded thermocouples in new National Spherical Tokamak eXperiment Upgrade (NSTX-U) graphite plasma-facing components (PFCs), a convolutional neural network (CNN) has been trained using the ANSYS simulations to predict the scrape-off layer (SOL) heat flux width, λq , given various machine operational parameters and diagnostic data as inputs. The proof-of-concept CNN was trained on the thermocouple data generated by the approximated NSTX-U heat loads applied to real PFC designs in ANSYS. Once trained, the CNN is capable of high precision reconstruction of parameterized heat flux profiles expected in NSTX-U. In addition, to test the system's ability to cope with noise and systematic error, pseudonoise was injected into the simulated data. CNN can accurately predict the incident heat flux despite this noise and error.

KW - Convolutional

KW - National Spherical Tokamak eXperiment Upgrade (NSTX-U)

KW - divertor

KW - heat flux

KW - machine learning

KW - neural network

KW - nuclear fusion

UR - http://www.scopus.com/inward/record.url?scp=85078516718&partnerID=8YFLogxK

U2 - 10.1109/TPS.2019.2919288

DO - 10.1109/TPS.2019.2919288

M3 - Article

AN - SCOPUS:85078516718

SN - 0093-3813

VL - 48

SP - 3

EP - 13

JO - IEEE Transactions on Plasma Science

JF - IEEE Transactions on Plasma Science

IS - 1

M1 - 8733008

ER -

Convolutional Neural Networks for Heat Flux Model Validation on NSTX-U

Abstract

Funding

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this