How artificial intelligence can improve advanced nuclear reactors

Newswise – A technology developed in Argonne may help narrow the field of molten salt candidates, a new study shows.

Scientists are looking for new materials to power the next generation of nuclear power plants. In a recent study, researchers at the US Department of Energy’s (DOE) Argonne National Laboratory showed how artificial intelligence could help locate the right types of molten salts, a key component for advanced nuclear reactors.

The ability to absorb and retain heat makes molten salt important for clean energy and national climate goals. Molten salts can be used both as a coolant and as a fuel in nuclear power plants that generate electricity without emitting greenhouse gases. They can also store large amounts of energy, which is increasingly needed in a power grid with fluctuating sources such as wind and solar power.

If you heated the salt on your kitchen counter to 801 C (1,474 F) it would melt and you would have melted salt. However, not just any salt is enough to generate and store energy. Scientists are exploring different combinations of salts to obtain the exact properties needed to efficiently cool and fuel a nuclear power reactor for decades. These properties include lower melting temperatures, the right consistency and the ability to absorb high amounts of heat, among others.

“We used experimental results to validate our simulation. At the same time, the simulation results gave us more details about which salts should be studied further. They work together.” — Jicheng Guo, chemical engineer at Argonne National Laboratory

Which molten salt blueprints provide the desired properties for a nuclear reactor? The possible variations are almost endless. The study aimed to determine whether computer simulations powered by machine learning could guide and refine real-world experiments at the Advanced Photon Source (APS), a user facility of the DOE Office of Science in Argonne. The results were recently published in the journal Physical Review B.

READ :  Modeling The Growth Process of Neurons - News

“We used experimental results from the APS to validate our simulation. At the same time, the simulation results gave us more details about which salts should be studied further. They work together,” said Jicheng Guo, chemical engineer at Argonne and lead author of the publication. ​“This way we can study several compositions at the same time.”

Researchers use the powerful X-rays at the APS to better understand specific salt mixtures by looking closely at their structures. But the time and expense associated with real-world experimentation makes it desirable to narrow the field of candidates that undergo inspection.

“The possible compositional space for molten salts is enormous,” said Nathan Hoyt, an Argonne researcher and co-author of the paper. ​“So it would be impossible to try to take experimental data for every possible composition.”

At the facility’s 6-ID-D beamline, a technique called high-energy X-ray diffraction captures the patterns produced when X-rays are scattered off a sample of molten salt.

“APS is unique for this type of measurement,” said Chris Benmore, senior physicist at APS and co-author of the paper. ​“The high-energy X-rays it produces are very useful for studying the structure of molten liquids, glasses, and amorphous materials in general.”

Machine learning trains a computer to analyze a situation based on existing data. But in this case, the researchers didn’t have an abundance of validated examples to show the model. Building on previous models examining refractory materials, the researchers used what is known as active learning to create a transferrable model for analyzing molten salts.

Rather than being fitted for one or two specific compositions of molten salt mixtures, the transferable model can be applied to mixtures throughout the composition space. The model makes predictions based on principles, in other words, and not on a set of predefined answers. The machine learning simulations were performed using high-performance computing resources at the Argonne Leadership Computing Facility (ALCF), a user facility of the DOE Office of Science, and using the Bebop cluster at Argonne’s Labor Computing Resource Center.

READ :  Board approves 17 faculty appointments

“We didn’t train the model with examples of this sweet spot composition where you get the right melting point,” said Ganesh Sivaraman, an Argonne computer scientist and corresponding author of the article. ​“Our model managed to predict this sweet spot even without the appropriate training input.”

Now that the researchers have shown that this approach can work, the next step is to work with even more complex data.

“A molten salt reactor is a fairly dynamic environment. Conditions change over time, and sometimes impurities can get into the salt,” Guo said. ​“We want to introduce a tiny amount of these impurities to see if the model can predict how this affects the overall structure of molten salts and their properties.”

The DOE Office of Science and the DOE’s Advanced Scientific Computing Research Program supported the research. Co-authors with Guo, Hoyt, Sivaraman, and Benmore are Logan Ward, Yadu Babuji, Mark Williamson, and Ian Foster of Argonne and Nicholas Jackson of the University of Illinois Urbana-Champaign.

The Argonne Leadership Computing Facility provides supercomputing capabilities for the scientific and engineering community to advance fundamental discoveries and insights across a wide range of disciplines. The ALCF is supported by the US Department of Energy’s (DOE) Office of Science, Advanced Scientific Computing Research (ASCR) program and is one of two US DOE leadership computing facilities dedicated to open science.

About the Advanced Photon Source

The US Department of Energy Office of Science’s Advanced Photon Source (APS) at Argonne National Laboratory is one of the world’s most productive X-ray light source facilities. The APS makes high-brightness X-rays available to a diverse community of researchers in materials science, chemistry, condensed matter physics, life and environmental sciences, and applied research. These X-rays are ideal for studying materials and biological structures; elementary distribution; chemical, magnetic, electronic conditions; and a wide range of technologically important engineering systems, from batteries to fuel injectors, all of which form the basis of our nation’s economic, technological, and physical well-being. Each year, more than 5,000 researchers use the APS to produce over 2,000 publications detailing impactful discoveries and solve more vital biological protein structures than users of any other X-ray source research facility. APS scientists and engineers are inventing technologies that are at the heart of advancing accelerator and light source operations. These include the introducers that produce X-rays with extreme brightness valued by researchers, lenses that focus the X-rays down to a few nanometers, instruments that maximize the way the X-rays interact with the samples being examined, and software, which collects and manages the vast amount of data resulting from discovery research at the APS.

READ :  More than 30 teams present projects in the UNLV design competition

This research used resources from the Advanced Photon Source, a US DOE Office of Science User Facility operated for the DOE Office of Science by Argonne National Laboratory under contract number DE-AC02-06CH11357.

Argonne National Laboratory seeks solutions to pressing national problems in science and technology. Argonne, the nation’s premier national laboratory, conducts pioneering basic and applied scientific research in virtually every scientific discipline. Argonne researchers work closely with researchers from hundreds of corporations, universities, and federal, state, and local governments to help solve their specific problems, advance America’s scientific leadership, and prepare the nation for a brighter future. With employees from more than 60 nations, Argonne is managed by UChicago Argonne, LLC for the US Department of Energy’s Office of Science.

The Office of Science of the US Department of Energy is the largest single funder of basic science research in the United States, working to address some of the most pressing challenges of our time. For more information, see https://​ener​gy​.gov/​s​c​ience.

Leave a Reply

Your email address will not be published. Required fields are marked *