Prediction of electron density and pressure profile shapes on NSTX-U using neural networks

Boyer, Mark; Chadwick, Jason

doi:10.11578/1814948

Title: Prediction of electron density and pressure profile shapes on NSTX-U using neural networks

Dataset
Other Related Research

Abstract

A new model for prediction of electron density and pressure profile shapes on NSTX and NSTX-U has been developed using neural networks. The model has been trained and tested on measured profiles from experimental discharges during the first operational campaign of NSTX-U. By projecting profiles onto empirically derived basis functions, the model is able to efficiently and accurately reproduce profile shapes. In order to project the performance of the model to upcoming NSTX-U operations, a large database of profiles from the operation of NSTX is used to test performance as a function of available data. The rapid execution time of the model is well suited to the planned applications, including optimization during scenario development activities, and real-time plasma control. A potential application of the model to real-time profile estimation is demonstrated.

Authors:

Boyer, Mark; Chadwick, Jason

Princeton University (PPPL)

Publication Date:: Fri Feb 19 04:00:00 UTC 2021

DOE Contract Number:: AC02-09CH11466

Research Org.:: Princeton Plasma Physics Laboratory (PPPL), Princeton, NJ (United States)

Sponsoring Org.:: USDOE Office of Science (SC)

OSTI Identifier:: 1814948

DOI:: https://doi.org/10.11578/1814948

Citation Formats


                    Boyer, Mark, and Chadwick, Jason. Prediction of electron density and pressure profile shapes on NSTX-U using neural networks.  United States: N. p., 2021. 
        Web.  doi:10.11578/1814948.

Copy to clipboard


                    Boyer, Mark, & Chadwick, Jason. Prediction of electron density and pressure profile shapes on NSTX-U using neural networks.  United States.  doi:https://doi.org/10.11578/1814948

Copy to clipboard


                    Boyer, Mark, and Chadwick, Jason. 2021.  
"Prediction of electron density and pressure profile shapes on NSTX-U using neural networks".  United States.  doi:https://doi.org/10.11578/1814948.  https://www.osti.gov/servlets/purl/1814948. Pub date:Fri Feb 19 04:00:00 UTC 2021

Copy to clipboard


                    
@article{osti_1814948,

  title        = {Prediction of electron density and pressure profile shapes on NSTX-U using neural networks},

  author       = {Boyer, Mark and Chadwick, Jason},

  abstractNote = {A new model for prediction of electron density and pressure profile shapes on NSTX and NSTX-U has been developed using neural networks. The model has been trained and tested on measured profiles from experimental discharges during the first operational campaign of NSTX-U. By projecting profiles onto empirically derived basis functions, the model is able to efficiently and accurately reproduce profile shapes. In order to project the performance of the model to upcoming NSTX-U operations, a large database of profiles from the operation of NSTX is used to test performance as a function of available data. The rapid execution time of the model is well suited to the planned applications, including optimization during scenario development activities, and real-time plasma control. A potential application of the model to real-time profile estimation is demonstrated.},

  doi          = {10.11578/1814948},

  journal      = {},

  number       = ,

  volume       = ,

  place        = {United States},

  year         = {Fri Feb 19 04:00:00 UTC 2021},

  month        = {Fri Feb 19 04:00:00 UTC 2021}

}

Copy to clipboard

Dataset:

View Dataset

DOI: https://doi.org/10.11578/1814948

Save / Share:

Export Metadata

Save to My Library

Similar records in DOE Data Explorer and OSTI.GOV collections:

Prediction of electron density and pressure profile shapes on NSTX-U using neural networks

Journal Article Boyer, M. D. ; Chadwick, J. - Nuclear Fusion

A new model for prediction of electron density and pressure profile shapes on NSTX and NSTX-U has been developed using neural networks. The model has been trained and tested on measured profiles from experimental discharges during the first operational campaign of NSTX-U. By projecting profiles onto empirically derived basis functions, the model is able to efficiently and accurately reproduce profile shapes. In order to project the performance of the model to upcoming NSTX-U operations, a large database of profiles from the operation of NSTX is used to test performance as a function of available data. The rapid execution time ofmore »« less
Real-time capable modeling of neutral beam injection on NSTX-U using neural networks

Dataset Boyer, M D ; Kaye, S ; Erickson, K

A new model of heating, current drive, torque and other effects of neutral beam injection on NSTX-U that uses neural networks has been developed. The model has been trained and tested on the results of the Monte Carlo code NUBEAM for the database of experimental discharges taken during the first operational campaign of NSTX-U. By projecting flux surface quantities onto empirically derived basis functions, the model is able to efficiently and accurately reproduce the behavior of both scalars, like the total neutron rate and shine through, and profiles, like beam current drive and heating. The model has been tested onmore »« less
Time dependent analysis of visible helium line-ratios for electron temperature and density diagnostic using synthetic simulations on NSTX-U

Dataset Bergos, J. M. ; Barbui, T. ; Schmitz, O. ; ...

Helium line-ratios for electron temperature (Te) and density (ne) plasma diagnostic in the Scrape-Off-Layer (SOL) and Edge regions of tokamaks are widely used. Due to their intensities and proximity of wavelengths, the singlet 667.8 and 728.1 nm, and triplet 706.5 nm visible lines have been typically preferred. Time- dependency of the triplet line (706.5 nm) has been previously analyzed in detail by including transient effects on line-ratios during gas-puff diagnostic applications. In this work, several line-ratio combinations within each of the two spin systems are analyzed with the purpose of eliminating transient effects to extend the application of this powerfulmore »« less
Plasma boundary shape control and real-time equilibrium reconstruction on NSTX-U

Dataset Boyer, M ; Battaglia, D ; Mueller, D ; ...

The upgrade to the National Spherical Torus eXperiment (NSTX-U) included two main improvements: a larger center-stack, enabling higher toroidal field and longer pulse duration, and the addition of three new tangentially aimed neutral beam sources, which increase available heating and current drive, and allow for flexibility in shaping power, torque, current, and particle deposition profiles. To best use these new capabilities and meet the high-performance operational goals of NSTX-U, major upgrades to the NSTX-U Control System (NCS) hardware and software have been made. Several control algorithms, including those used for real-time equilibrium reconstruction and shape control, have been upgraded tomore »« less
Two-dimensional AXUV-based radiated power density diagnostics on NSTX-U

Dataset Faust, I. ; Delgado-Aparicio, L. ; Bell, R. E. ; ...

A new set of radiated-power-density diagnostics for the National Spherical Torus Experiment Upgrade (NSTX-U) tokamak have been designed to measure the two-dimensional poloidal structure of the total photon emissivity profile in order to perform power balance, impurity transport, and magnetohydrodynamic studies. Multiple AXUV-diode based pinhole cameras will be installed in the same toroidal angle at various poloidal locations. The local emissivity will be obtained from several types of tomographic reconstructions. The layout and response expected for the new radially viewing poloidal arrays will be shown for different impurity concentrations to characterize the diagnostic sensitivity. The radiated power profile inverted frommore »« less

Similar Records