Welcome to DU! The truly grassroots left-of-center political community where regular people, not algorithms, drive the discussions and set the standards. Join the community: Create a free account Support DU (and get rid of ads!): Become a Star Member Latest Breaking News Editorials & Other Articles General Discussion The DU Lounge All Forums Issue Forums Culture Forums Alliance Forums Region Forums Support Forums Help & Search

NNadir

(34,533 posts)
Sat Aug 19, 2023, 10:28 AM Aug 2023

Physics Informed CNN.

If you thought this was about the news network, go no further. My standard oft repeated joke is that one cannot get a degree in what is still called "journalism" if one has passed a college level science course with a grade of C or better.

It's about "convolutional neural network" (CNN) analysis of temperature fields, AI for kriging:

Physics-informed CNN for temperature field monitoring in advanced reactors

Some excerpts:

Advanced reactors are promising energy systems that can enable the world to transition to a more sustainable energy matrix. These concepts are potentially more fuel efficient and safer, compared with previous generations of nuclear reactors. Many designs, like high-­temperature gas reactors (HTGRs) and molten salt fast reactors (MSFRs), target high outlet temperatures, allowing for their operation in processes where high heating is required, such as for hydrogen production and desalination.

Their deployment, however, faces technological challenges, including the need to address specific instrumentation requirements. For example, local temperature measurements remain challenging in higher temperature regions of these reactors, where values can exceed 1,000 K. Despite many advances, there are still unique challenges in available thermometry technologies when dealing with extreme temperatures and irradiated environments,1, 2 which are typical in these reactors. Furthermore, developing economically viable monitoring approaches is another aspect that should be considered to ensure the economic competitiveness of these reactors...


(I personally think to get the best out this sustainable energy source, we need temperatures higher than 1000K, and they are feasible.)

...Here, we employ an innovative, physics-­informed machine learning (ML) approach to measuring temperature distributions in physical domains indirectly, adopting the convolutional neural network (CNN) algorithm from previous works.3–5 This algorithm leverages the Kirchhoff-Helmholtz integral equation6 to reconstruct the spatial distribution of diffusive and advective fields over domains with arbitrary geometry. The present work demonstrates that this method enables less invasive or indirect measurement techniques for advanced reactors...


It gets cooler, I mean hotter:

...The proposed methodology is geometry agnostic and can be applied to a broad range of conditions, provided the underlying numerical datasets are validated with benchmark data. Furthermore, reference benchmark data must be used to ensure the quality of the generated numerical data.

Here, we present recent advances in using the CNN field reconstruction approach targeting an application in the two nuclear systems mentioned above. This work showcases how the CNN-based field reconstruction technique developed can perform temperature monitoring for advanced reactors. In the HTGR case, the CNN reconstructs the temperature fields within the solid material of a prismatic fuel assembly (i.e., graphite and fuel compacts). Interestingly, the CNN can perform satisfactory predictions for multiple gas mass flow rates and also account for a blockage in one of the noninstrumented channels...


I like that locution, "geometry agnostic."

This is based on a presentation given at the ANS meeting, which I did not attend (it's not really my field), but the references are provided, and I hope to pick up those accessible to me.

I trust you'll have a pleasant weekend.
4 replies = new reply since forum marked as read
Highlight: NoneDon't highlight anything 5 newestHighlight 5 most recent replies
Physics Informed CNN. (Original Post) NNadir Aug 2023 OP
I'm encouraged that more elected officials are supportive. CoopersDad Aug 2023 #1
Thanks for asking. In reality, small reactors have been around since the 1950's. The first... NNadir Aug 2023 #2
SMRs John ONeill Aug 2023 #3
I didn't watch this episode, and probably won't. NNadir Aug 2023 #4

CoopersDad

(2,812 posts)
1. I'm encouraged that more elected officials are supportive.
Sat Aug 19, 2023, 10:44 AM
Aug 2023

I met with a US Congressman who expressed sincere interest in SMRs and wondered if they are ready for prime time.

I mentioned that I love the idea of smaller-scale systems that can support microgrids and provide resiliency as distributed generation elements but wasn't able to give a very clear answer, I just said that yes, I think we will see pilot projects soon, that some are even coming online (without being able over lunch to name names and places).

Incidentally, I took my fourth or fifth tour of the Diablo Canyon facility, it never fails to impress when you stand on the turbine deck knowing that 1/10 of the state's generation comes from those two generators.

Trusting you as a source, what would you tell a Congressman if asked how soon might we see Small Modular Reactors going online, and what other types of reactors are on the near horizon?

Thanks!

NNadir

(34,533 posts)
2. Thanks for asking. In reality, small reactors have been around since the 1950's. The first...
Sat Aug 19, 2023, 11:55 AM
Aug 2023

...commercial reactor built in the United States, in about three years time from conception to providing power to the grid, Shippingport, was a small reactor, one that was actually thorium fueled for one fuel cycle.

It was basically a submarine reactor built on land. (All submarine reactors are SMRs.)

It provided power to the grid beginning in 1957. It was rated at 60MWe whereas the most recent European reactor to come on line, the EPR in Finland at Olkiluoto is producing 1600 MWe, and the Vogtle 3 reactor which came on line in the US last month (soon to be followed by Vogtle 4) is a 1100 MWe reactor.

All the world's research reactors, including but not limited to those for producing medical isotopes, are small reactors. In a sense, research reactors installed in universities and research institutions were also modular, inasmuch they were largely all produced around the same technology, the GA Triga type reactors with hydride fuels. They made a lot of them, way back in the 1960's; some still function quite well.

What is different is the mode of manufacturing. I have linked this video before from Oak Ridge, showing that we are pretty much ready to print reactors:



The laboratory in which my son is pursing his Ph.D. is working on this technology. It's very real.

All over the planet, with some even in the United States, despite the power of antinuke ignorance here, people are designing and planning to build multi-mission reactors, reactors that do not merely produce electricity but provide heat for process chemistry, including but not limited to desalination and district heat.

New fuel facilities are being built.

The creativity that informed nuclear scientists in the 1960's is re-emerging at a very critical time.

We still have reactionaries, of course, who oppose nuclear energy, even some who consider themselves "environmentalists" although what they are really doing is working to destroy our environment.

Unfortunately there is a wing of our party that embraces these very dangerous, and frankly deadly ideas, that nuclear energy is something to oppose rather than embrace. I was very disappointed to learn that Illinois Governor Pritzker vetoed a bill to allow the construction of new reactors in that State. This is not progressive; it's regressive and reactionary, particularly when the climate shit is hitting the fan.

Here at DU our "E&E" forum is inconsistent with the idea that informed America's first great environmentalist, John Muir, who thought that wilderness should be protected from industrialization and fought to create that protection. (He lost the fight; the Hetch Hetchy dam was built.) The modern day Sierra club never sees a wilderness, whether marine or land based that it doesn't want industrialized.

SMR's are pretty much here. In a sense, since 1955, they've always been here. The question really comes down to whether nuclear energy is more "dangerous" than climate change and millions of deaths each year from air pollution. One has to be numerically and functionally (and indeed ethically) illiterate to believe this, yet people do, here and elsewhere.

We can and should authorize and order SMR's at a break neck pace. This issue is not technical. Nuclear energy has a 70 year old technology with a spectacular record of providing energy at low human and environmental cost, better than any other form of energy. The issue social, inasmuch as there is a readiness throughout our culture, on the right certainly but we on the left are hardly innocent, to embrace ignorance.

Complainants focusing on nuclear energy while ignoring the huge environmental, economic, moral, and human cost of all other forms of energy strike me exactly the same as the morons in the Republican party who want to carry on endlessly about Hunter Biden in the presence of the Trump crime family.

For most of the period of my nuclear advocacy, dating back to the time when I worked out in my own mind the consequences of Chernobyl, I've been a big reactor kind of guy. I've changed my mind. We can and should build small reactors on an assembly lime basis, thousands upon thousands of them. They are the only viable option for ending the use of fossil fuels.

John ONeill

(60 posts)
3. SMRs
Tue Aug 22, 2023, 07:05 AM
Aug 2023

Dr Chris Keefer's latest Decouple podcast is with Jigar Shah, head of the government agency making loans to new reactor startups (and I think other climate-related innovation). More contentious than with most of his guests - Jigar, who has apparently organised many billion dollars of solar plant finance , not surprisingly has a better opinion of their worth than the good doctor. Anyway, he says they're open to finance larger reactors, but none of the power companies want them - they're too shell shocked by Vogtle and Summer, and would rather start small and play safe. I found another podcast online, where Jigar was discussing the process of providing government funding to a Canadian based company doing lithium battery recycling at scale - he arranged $375 million for them to set up a plant in New York state. Thought as a chemist you might be interested.https://www.mcjcollective.com/my-climate-journey-podcast/jigar-shah-ajay-kochhar

NNadir

(34,533 posts)
4. I didn't watch this episode, and probably won't.
Wed Aug 23, 2023, 01:15 PM
Aug 2023

I'm not particularly interested in the opinions of people "investing" in solar energy or batteries, both of which have proved useless in addressing climate change.

It's unfortunate that this wasteful exercise in subsidizing solar and batteries continues since it's entirely counterproductive. The claim that we can recycle millions, even hundreds of millions of tons of electronic waste accumulated each year, and still can't recycle 80,000 tons of used nuclear fuel - which is far more valuable - accumulated over 70 years should be, in a rational world, too absurd to contenance.

We shall see what the economics of Vogtle will prove to be. It's making a big deal in the minds of people who seem not to believe that climate change is not "too expensive," but nuclear reactors built after deliberate destruction of nuclear manufacturing infrastructure by intellectual and moral vandals is too expensive.

Forty years from now, every solar cell on this planet will be electronic waste, and the leachates and side products of recycling batteries will be a well known environmental problem (if it in fact happens) and Vogtle will still be producing electricity. The generations benefitting from Vogtle will not give a rat's ass about what it cost.

This all said, I do believe there are economic and environmental advantages to building small modular reactors. For one thing, I am increasingly convinced they can be printed, and after being built in an assembly line fashion, transported by truck to facilities for flexible missions. It should in fact, reduce up front capital costs, but every capital cost spent on nuclear energy is actually an investment in humanity as opposed to an investment in wishful thinking and denial.

Latest Discussions»Culture Forums»Science»Physics Informed CNN.