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 fusion 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.
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.
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 neural network 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 plasma phenomena.
The Latest on: Fusion energy
via Google News
The Latest on: Fusion energy
- Laser fusion reactor approaches ‘burning plasma’ milestoneon November 26, 2020 at 3:58 pm
A decade and nearly 3000 shots later, NIF is still generating more fizz than bang, hampered by the complex, poorly understood behavior of the laser targets when they vaporize and implode. But with new ...
- Physicists make landmark discovery in how stars get their energyon November 26, 2020 at 2:59 pm
For the first time in history, scientists have detected the energy cycle that fuels the stars. In an article published Wednesday in the scientific journal Nature, physicists described their ...
- Scientists find neutrinos from star fusion for the first timeon November 26, 2020 at 1:04 pm
Scientists have detected neutrinos traced to star fusion for the first time, confirming physics theories dating back to the 1930s.
- Borexino spots solar neutrinos from elusive fusion cycleon November 25, 2020 at 9:26 am
Neutrinos produced by the elusive carbon–nitrogen–oxygen (CNO) cycle in the Sun have been observed for the first time – confirming a theory first proposed over 80 years ago. The observation was made ...
- This Nuclear Fusion Reactor Is Damn Close to Burning Plasmaon November 25, 2020 at 7:00 am
The National Ignition Facility bombards fuel with lasers to reach productive fusion. The fuel pellet is held inside a golden crucible that scientists are constantly redesigning. Scientists are doing ...
- Government investment in fusion energy boosts British economy by £1.4 billionon November 24, 2020 at 3:18 am
The British economy has gained £1.4 billion from the Government’s direct investment in fusion energy over the past decade and an average of 4,000 jobs each year. The findings were revealed in an ...
- Lehigh's Plasma Control Group awarded $1.5 million DOE grant for fusion researchon November 20, 2020 at 9:22 am
How is the future of fusion power shaping up? It could boil down to a question of apples versus donuts. Lehigh University's Plasma Control Group has been awarded more than $1.5 million in funding from ...
- Neutrinos yield first experimental evidence of catalyzed fusion dominant in many starson November 19, 2020 at 4:00 pm
Scientists report the detection of neutrinos from the sun, directly revealing for the first time that the carbon-nitrogen-oxygen (CNO) fusion-cycle is at work in our sun.
- Tungsten develops layers under fusion reactor extreme heat conditionson November 19, 2020 at 7:03 am
In tokamaks, magnetic confinement devices being explored for use as nuclear fusion reactors, anomalous events can cause a transfer of energy with 10 million times the intensity of the solar radiation ...
- Fusion Fuel Green plc and HL Acquisitions Corp. Announce Partnership with EREE Desarrollos Empresariales SLon November 18, 2020 at 1:53 pm
HL Acquisitions Corp and its business combination partner, Fusion Fuel Green plc, jointly announced that Fusion Fuel has entered into a partnership with EREE Desarrollos Empresariales SL to deploy its ...
via Bing News