Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AI for real-time fusion plasma behavior prediction and manipulation

control.princeton.edu

Post reply on HN
Print view View original

111–120 of 167 posts

Re: AI for real-time fusion plasma behavior prediction and manipulation

#111

Post by aftbit »

perihelions wrote: post #99
aftbit wrote: post #93

Earlier quoted context omitted.

Sure, the spent fuel is considerably more radioactive per kilogram, but how many kilograms of coal does a typical plant burn in a decade, versus how many kilograms of nuclear fuel are spent?

I answered that exact question! :)

My mistake - I reread your post, and I understand you to be saying that a nuclear plant generates a 10^6 (USA million) times as much long-lived radioactive waste as a coal plant for each unit of energy.

As everyone acknowledges, coal plants don't contain their waste, and fly ash has bad chemical, medical, and ecological properties aside from its radioactivity. Everyone fears nuclear waste and requires it to be contained in nearly impervious vessels with century long management plans. Those same people happily let the coal plants just pump their wastes into the air and discharge captured fly ash into ponds and piles on the ground.

Coal also produces many times more fly ash by volume and mass than nuclear plants produce high-level long-lived wastes.

Luckily even fossil-fuel power generation is moving away from coal in favor of natural gas plants right now, which are cheaper and cleaner (still CO₂ though).

More about fly ash as an underappreciated pollutant:

https://www.sciencedirect.com/science/article/abs/pii/S00128...

https://en.wikipedia.org/wiki/Kingston_Fossil_Plant_coal_fly...

Re: AI for real-time fusion plasma behavior prediction and manipulation

#112

Post by fragmede »

ben_w wrote: post #98
adrian_b wrote: post #65

Earlier quoted context omitted.

Deuterium is also not renewable, even if it is more abundant than uranium. The H1-B11 reaction would be a much better energy source than anything else, but for now nobody knows any method to do it. There is no chance to do it by heating, but only by accelerating ions, and it is not known how a high enough reaction rate could be obtained.

> Deuterium is also not renewable, even if it is more abundant than uranium Technology correct, in that after around a hundred trillion years even the red dwarf stars will have stopped burning hydrogen. But last I checked as yet there is no known way to harness the only (and even then merely suspected) infinitely renewable energy source: the expansion of the universe.

Just tie the end of an infinitely long string to the edge of the universe and have it pull on a generator to spin it.

Re: AI for real-time fusion plasma behavior prediction and manipulation

#113

Post by fragmede »

atomic128 wrote: post #12

Neutrons make hardware radioactive. Many on Hacker News fantasize about fusion (not fission) reactors. These fusion reactors will be an intense source of fast neutrons. All the hardware in a fusion reactor will become radioactive. Not to mention the gamma rays. If you have to deal with radioactive materials, why not just use fission? After 70 years of working with fission reactors, we know how to build and operate th…

> Many on Hacker News fantasize about fusion (not fission) reactors. These fusion reactors will be an intense source of fast neutrons. All the hardware in a fusion reactor will become radioactive. Not to mention the gamma rays.

My personal ideology about fusion aside, it should be mentioned there is an easy fix for these radiation problems. What you do is put the fusion reactor in space, and collect the energy with specialized fusion energy collectors on Earth (or in space). They'll have the problem that they aren't able to collect energy if the fusion reaction is below the horizon, so this design is imperfect, but having the fusion reaction take place in space means you don't have to deal with a radioactive casing by not including it in your fusion reaction space station design because you don't need any. Just a bit of hydrogen, a tiny bit of helium, and a some time.

Re: AI for real-time fusion plasma behavior prediction and manipulation

#114

Post by pas »

adrian_b wrote: post #71
vilhelm_s wrote: post #53

Earlier quoted context omitted.

The radioactivity generated from neutron activation is low-level, so you don't need to worry about accidents releasing lots of radioactivity, or about how to store waste for a long time. There are a lot of people worrying about those two things for fission reactors. Also, the fuel for fusion reactors is much more plentiful. If we went all in on fission we might run out of easily minable uranium ore in a century or so…

The radioactivity generated from neutron activation is not at all low-level, because the neutron flux is huge, providing most of the energy generated by the fusion reactor. The intense neutron flux will transmute a very high number of atoms, so when taken out of the reactor all materials are very highly radioactive. What can be hoped is that there may be choices for the materials used in a fusion reactor that will en…

How does the waste distribution and amount compare to fission reactors? (Pressure vessels, spent fuel rods, what else?)

If we need to to dump every 50 year a few thousand tons of steel into the old uranium mines that seems like a good deal, no?

Re: AI for real-time fusion plasma behavior prediction and manipulation

#115

Post by twothreeone »

mathematicaster wrote: post #108
twothreeone wrote: post #105

> However, uncovering these inter-correlations analytically is too complex to be achieved analytically. sigh.. I guess that's cool and all, you're exited about your work, that's great. But can we please polish our prose a little more and stop using buzz words like "groundbreaking", "now.. for the first time", "unprecedented" etc? Such distractions seriously undermine the legibility (and frankly, also taint the credib…

Likely due to using an LLM as part of the writing process.

Maybe, though in my experience beginner PhD students will often write like this in early manuscript drafts after they've been working on some project for a few months. Usually it's easily fixed by having someone more experienced proof-read it with comments explaining why that is bad style. Worst case, they'll learn the hard way (i.e., conference reviewers). But seeing this without any proof-reading on some public physics lab site just makes me cringe that they have unchecked write access to that site.

Re: AI for real-time fusion plasma behavior prediction and manipulation

#116

Post by to11mtm »

jylam wrote: post #62
atomic128 wrote: post #12

Neutrons make hardware radioactive. Many on Hacker News fantasize about fusion (not fission) reactors. These fusion reactors will be an intense source of fast neutrons. All the hardware in a fusion reactor will become radioactive. Not to mention the gamma rays. If you have to deal with radioactive materials, why not just use fission? After 70 years of working with fission reactors, we know how to build and operate th…

I'm not a specialist but here is what I think I know (I'm talking with the point of view of a Frenchman, who consumes most of his electricity from (fission) nuclear power plants): 1/ Uranium is not a renewable (quite the opposite), needs to be mined and treated (which is expensive and very polluting), and not present at the required concentrations in most of the world (this creates geopolitical issues). 2/ Fission nu…

1: Well if society could get at least some of their shit together we could do breeders. Alas, someone shot an RPG at Superphenix and that put a damper on a lot of things...

But it's not impossible. Japan seems to do most things decent from a 'security' standpoint, also interestingly for all of the other 'grey-market' stuff out there in the category of "shouldn't be radioactive but is" I have yet to find anything about AliExpress selling fissiable materials.

2: Yes and no and how much do you want to spend to improve the breach/damage ratio. i.e. PBRs have relatively low risk under a number of circumstances but have higher operating/etc costs.

I should also possibly question, what are the potential failure modes of 'not short timeframe fusion reactions'? I honestly have no clue whether they would quickly cease or if there are other potential side effects.

3: Agreed that neutron stuff can be solved in many ways, I do have some questions about maintaining that across various fusion designs. Big challenge is that we aren't 'there' yet.

> So fusion doesn't seem the best option on the short term, because of the complexity and cost of research, but definitely seems to be the very best option in the middle and long term. And we made the short term catastrophic choice already with coal and oil, it'll be good to learn from that.

Agreed that Fusion is the ideal long term, hopefully my comments didn't cause thoughts otherwise. I think we need more funding into it, and maybe even research as to how to have other renewables (e.x. solar) help feed into the initial startup/restart process for plants. We have had decades without sufficient funding of research.

I will say however, especially in relation to my other point-comments, that other countries (re?)embracing fission in the meantime will likely still lead to discovery of better techniques to deal with 'shared' concerns between fission/fusion such as neutrons/weigner engergy/etc

Re: AI for real-time fusion plasma behavior prediction and manipulation

#117

Post by vlovich123 »

samsartor wrote: post #34
noname120 wrote: post #5

TIL: it's not just buzzwords. https://en.wikipedia.org/wiki/Fusion_power#Machine_learning

My advisor also worked on this ML project for estimating electron density and temperature within tokomaks: https://www.cs.wm.edu/~ppeers/showPublication.php?id=Ozturk:... Technically that counts as "AI in nuclear fusion", but it isn't any sort of breakthrough. In almost every case the effects of AI are marginal. Not zero exactly, but nowhere near the breathless hype.

Depends on what you count as ML and what counts as AI and the distinctions are meaningless. It’s just that ML techniques have lost their magic and are now just part of the toolkit of how you do things. But I wouldn’t say they’re zero because you need a lot of wins all over the place compounded over time to get the true win. It’s a hard multi disciplinary project with unknown physics on top of engineering. It’s now known physics in some ways on the theoretical side but the practical physics of it and how to scale it up and make it work are not solved and that’s real R&D that has to be done. There’s glimmers of progress here and there, achievements we never had before but it all still feels so far away because it’s not coalescing as fast as the advertised wins might suggest.

Re: AI for real-time fusion plasma behavior prediction and manipulation

#118

Post by cossatot »

adrian_b wrote: post #83
cosmic_quanta wrote: post #33

Earlier quoted context omitted.

> Neutrons make hardware radioactive True, but two caveats: 1. Neutron bombardment due to fusion makes hardware radioactive for less than 10 years, which isn't great but does not compare to fission waste; 2. Some fusion processes don't emit neutrons (aneutronic fusion). As I understand it, these processes aren't as efficient, but there is the possibility of a tradeoff between generation of ratioactive waste vs. effic…

> Neutron bombardment due to fusion makes hardware radioactive for less than 10 years Very false. The current design target for fusion reactors is that the materials taken out of the reactor should become "low-level radioactive waste" after being stored for one hundred years . It is acknowledged however that it is likely that a small fraction of the materials will not satisfy the criteria for "low-level radioactive w…

There is a trade off between the half life and the intensity of radiation (i.e. the number of particle emissions per unit time), correct? So even if waste products are radioactive for thousand of years, they can be more easily handled than materials with a faster decay rate, even if they need to be stored for longer.

Re: AI for real-time fusion plasma behavior prediction and manipulation

#119

Post by nightowl_games »

chriskanan wrote: post #74

There is a lot of AI research in the nuclear fusion space. For inertial confinement fusion (a competing technology to magnetic confinement fusion, e.g., tokamaks) the National Ignition Facility (NIF) used it for their experiment that resulted in "ignition." My lab is collaborating with researchers at the Laboratory for Laser Energetics to use AI to improve inertial confinement fusion (ICF). We recently put out this p…

Isn't there a lot of daylight between old Fortran code and AI?

What if we rewrote the old algorithms in C with modern techniques? Multitthreading? Or GPU compute? If there's value there, I could do these things. Probably wouldn't take that long

Re: AI for real-time fusion plasma behavior prediction and manipulation

#120

Post by ziofill »

About 20 years ago I was an undergrad at the university of Padova (italy), and in the outskirts of the city (in Legnaro) there was a fusion experiment. The fusion device was in one building and the control room was in an adjacent building. Back then we were using CRT monitors and each time there was a fusion event, the magnetic confinement field was so strong that the image on all the screens in the control room would simultaneously shift on one side and then spring back when the field was turned off. Across buildings.
Post reply on HN