Machine learning speeds modeling of experiments aimed at capturing fusion energy on Earth

Machine learning speeds modeling of experiments aimed at capturing fusion energy on Earth
Fast-camera photo of a plasma produced by the first NSTX-U operations campaign. Credit: NSTX-U experiment

Machine learning (ML), a form of artificial intelligence that recognizes faces, understands language and navigates self-driving cars, can help bring to Earth the clean fusion energy that lights the sun and stars. Researchers at the U.S. Department of Energy's (DOE) Princeton Plasma Physics Laboratory (PPPL) are using ML to create a model for rapid control of plasma—the state of matter composed of free electrons and atomic nuclei, or ions—that fuels fusion reactions.

The sun and most stars are giant balls of plasma that undergo constant reactions. Here on Earth, scientists must heat and control the plasma to cause the particles to fuse and release their energy. PPPL research shows that ML can facilitate such control.

Neural Networks

Researchers led by PPPL physicist Dan Boyer have trained neural networks—the core of ML software—on data produced in the first operational campaign of the National Spherical Torus Experiment-Upgrade (NSTX-U), the flagship fusion facility, or tokamak, at PPPL. The trained model accurately reproduces predictions of the behavior of the energetic particles produced by powerful neutral beam injection (NBI) that is used to fuel NSTX-U plasmas and heat them to million-degree, fusion-relevant temperatures.

These predictions are normally generated by a complex computer code called NUBEAM, which incorporates information about the impact of the beam on the plasma. Such complex calculations must be made hundreds of times per second to analyze the behavior of the plasma during an experiment. But each calculation can take several minutes to run, making the results available to physicists only after an experiment that typically lasts a few seconds is completed.

The new ML software reduces the time needed to accurately predict the behavior of energetic particles to under 150 microseconds—enabling the calculations to be done online during the experiment.

Initial application of the model demonstrated a technique for estimating characteristics of the plasma behavior not directly measured. This technique combines ML predictions with the limited measurements of plasma conditions available in real-time. The combined results will help the real-time plasma control system make more informed decisions about how to adjust beam injection to optimize performance and maintain stability of the plasma—a critical quality for fusion reactions.

Rapid evaluations

The rapid evaluations will also help operators make better-informed adjustments between experiments that are executed every 15-20 minutes during operations. "Accelerated modeling capabilities could show operators how to adjust NBI settings to improve the next experiment," said Boyer, lead author of a paper in Nuclear Fusion that reports the new model.

Boyer, working with PPPL physicist Stan Kaye, generated a database of NUBEAM calculations for a range of plasma conditions similar to those achieved in experiments during the initial NSTX-U run. Researchers used the database to train a neural network to predict effects of neutral beams on the plasma, such as heating and profiles of the current. Software engineer Keith Erickson then implemented software for evaluating the model on computers used to actively control the experiment to test the calculation time.

New work will include development of models tailored to the planned conditions of future NSTX-U campaigns and other fusion facilities. In addition, researchers plan to expand the present modeling approach to enable accelerated predictions of other fusion phenomena.


Explore further

Machine set to see if lithium can help bring fusion to Earth

More information: M.D. Boyer et al, Real-time capable modeling of neutral beam injection on NSTX-U using neural networks, Nuclear Fusion (2019). DOI: 10.1088/1741-4326/ab0762
Citation: Machine learning speeds modeling of experiments aimed at capturing fusion energy on Earth (2019, May 17) retrieved 19 June 2019 from https://phys.org/news/2019-05-machine-aimed-capturing-fusion-energy.html
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.
841 shares

Feedback to editors

User comments

May 17, 2019
The rapid development of tokamak fusion isn't going to happen with machine-learning analysis alone, but by tokomaks with reconfigurable physical and magnetic geometries, on-the-fly, at least as far as their path-cross-sections are concerned: OO Dꓷ, ꓷD , and anything in between.

May 17, 2019
Until such time as these so-called scientists learn the fundamentals of subatomic structure, they will continue to tilt at dragons. There is no such thing as high-energy fusion, if they understood subatomic structure, they would know that.

May 17, 2019
Until such time as these so-called scientists learn the fundamentals of subatomic structure, they will continue to tilt at dragons. There is no such thing as high-energy fusion, if they understood subatomic structure, they would know that.
Yeah, and atoms. Atoms?...  w h a t  atoms? No such thing as atoms... They laughed, I'll show them...

May 17, 2019
Until such time as these so-called scientists learn the fundamentals of subatomic structure, they will continue to tilt at dragons. There is no such thing as high-energy fusion, if they understood subatomic structure, they would know that.
Yeah, and atoms. Atoms?...  w h a t  atoms? No such thing as atoms... They laughed, I'll show them...


Cute. }:o) ....

May 18, 2019
Yeah well when they finally throw it in they can always put a thorium pile in front of the tokomak for a relatively cheap and clean nuclear system.

May 18, 2019
Fusion will never occur as we are only guessing

What exactly is this Core Temperature and pressure of our Sun
No guessing no supposing the truth
for what temperature is our Sun's solar fusion in actual fact fusing hydrogen
without know precisely this critical temperature
our earthly fusion is going nowhere
or Suns fusion relies on hydrogen pressure temperature
these 3 variables are critical in there composition
just as a recipe for that perfect loaf requires exact ingredients rising temperature and time in the oven
so it is with our Suns fusion at its core
for as we duplicate this Sun in earthly solar fusion
we are guessing its ingredients its temperature it pressure its recipe its time in this solar oven before fusion occurs
untill we measure this temperature
until we measure this pressure
until we count these requisite number of hydrogen atoms
Until we know the exact conditions and ingredients at this Suns core we are only guessing

Fusion will never occur as we are only guessing

May 18, 2019
For once we mix the perfect recipe to take that perfect loaf out this oven

So it is with earthly fusion
For when we know the exact conditions and ingredients at this Suns core
When we have this solar fusions recipe
When we mix this solar fusion recipe
When we bake this fusion recipe in our fusion reactors
We will produce solar fusion in our fusion reactors every time
Just as we lift our perfect loaf every time out our ovens
As the smell of bread drifts in this air
Powered by our perfect solar fusion recipe in our fusion reactor ovens every time!

May 18, 2019
Fusion will never occur as we are only guessing

What exactly is this Core Temperature and pressure of our Sun

for as we duplicate this Sun in earthly solar fusion
we are guessing its ingredients its temperature it pressure its recipe its time in this solar oven
Fusion will never occur as we are only guessing


According to 'Cool Cosmos' --
"The temperature at the surface of the Sun is about 10,000 Fahrenheit (5,600 Celsius). The temperature rises from the surface of the Sun inward towards the very hot center of the Sun where it reaches about 27,000,000 Fahrenheit (15,000,000 Celsius). The temperature of the Sun also rises from the surface outward into the Solar atmosphere. The uppermost layer of the Solar atmosphere, called the corona, reaches temperatures of millions of degrees. The corona is the bright halo of light that can be seen during a total Solar eclipse."

15 million degrees Celsius - a bit warm isn't it? I don't know if any tokamak on Earth could do

May 19, 2019
Until such time as these so-called scientists learn the fundamentals of subatomic structure,...
rodkeh

I have news for you; they ALREADY HAVE learned that. Which planet have you just come from?

There is no such thing as high-energy fusion, if they understood subatomic structure, they would know that.
I have MORE news for you; There IS such thing as high-energy fusion. It is known to happen in the stars and Sun. And you know nothing about subatomic structure they don't. If you claim otherwise then a challenge you to report your science evidence for it here and get it presented for scientific peer review.

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more