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.
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 | |
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