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

101–110 of 167 posts

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

#101

Post by ben_w »

fusionadvocate wrote: post #59
khuey wrote: post #39

Earlier quoted context omitted.

Aneutronic fusion is even harder than regular fusion so it's not a realistic solution in any near-term scenario.

That is incorrect. Recent advances using attosecond lasers enable new tricks and fusion conditions to be realized tabletop. Search also for plasmonics. Using nano antennas and intense lasers to accelerate protons and electrons in a tabletop device (previously required large machines).

Fusors already enabled desktop fusion reactors, literally high school science fair projects even a couple of decades back.

What stops Fusors and Polywells from having already given us this decades ago with P-B11 etc. is that the cross section for fusing is so much lower than the cross section for elastic scattering, and that elastic scattering loses so much energy to EM via bremsstrahlung.

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

#102

Post by throwup238 »

Borg3 wrote: post #58
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…

Thats least of your problem imo. Neutron corrosion is bigger problem. There is trick to use Lithium shielding, with create Tritium needed for Fussion. But not sure how effective it is, especially for long term reactor lifetime. Those reactors are very expensive, not sure if its worth to shut it down every year and replace entire Li shielding...

I think beryllium is a better candidate. It can be grown as a single crystal and there’s lots of research into using it for shielding in nuclear lightbulb reactors.

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

#103

Post by winternewt »

avidphantasm wrote: post #68

I know AI is the buzzword du jour, but this is really ML, and really just advanced cybernetic control systems. Deep learning systems have a high enough degree of variety necessary to control short time step nonlinear systems like the plasma in a tokamak.

AI was defined by Marvin Minsky in 1956 as "the science of making machines do things that would require intelligence if done by men." Later in 1959, Arthur Samuel defined machine learning as a "field of study that gives computers the ability to learn without being explicitly programmed".

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

#104

Post by sroussey »

asdfman123 wrote: post #44
dekhn wrote: post #35

Earlier quoted context omitted.

When I used to work in grid computing almost 20 years ago, we were already running fusion experiments, realtime streaming the data to the grid, which would rapidly analyze it and compute some new parameters for the next run (I think they had a 20 minute downtime). I don't think it was considered machine learning at the time, though (and was certainly not deep learning as we practice it today).

Remember, AI is just procedurally generated data analysis.

Computers are just electron tunneling machines.

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

#105

Post by twothreeone »

> 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 credibility by negatively biasing readers) of the claims.

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

#106

Post by albumen »

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! :)

If you did, it's not very clear.

The OP to which you replied didn't say that coal is more radioactive than spent nuclear fuel; but that radioactive waste's volume is much smaller than the fly ash produced by a single coal plant in a decade.

Is fly ash per kg more radioactive than nuclear waste? No. But you did acknowledge that the coal plant emits its waste into the atmosphere, unlike a fission plant, which I think is the more relevant point.

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

#107

Post by nick3443 »

wruza wrote: post #79
spenczar5 wrote: post #15

Earlier quoted context omitted.

That’s really interesting! Do you have other interesting specific examples? I would have guessed that most industrial control problems were simpler sets of differential equations that could be directly estimated.

I’ve heard about a local packaging factory recently that uses an ML-first system for messaging their clients about what they will need to order soon, based on recent orders and global criteria. It’s not a simple problem, apparently. They signal the clients and start pre-producing, basically sort of algotrading themselves. Not really an industrial control though, but close to it.

PID control your customers :)

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

#108

Post by mathematicaster »

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.

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

#109

Post by rcxdude »

CuriousCosmic wrote: post #38
noname120 wrote: post #5

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

Yeah machine learning is more or less just very complex application of control theory techniques and notably it is usually done by people without formal control theory backgrounds. Super useful for control applications but obviously you really want to know control theory so that you aren't just using ML to throw darts at a wall.

More like optimization. Signal processing and control theory are basically the same maths with different applications, optimization is a bit different but has some overlap (especially with, e.g. optimal control techniques).

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

#110

Post by perihelions »

throwup238 wrote: post #102
Borg3 wrote: post #58

Earlier quoted context omitted.

Thats least of your problem imo. Neutron corrosion is bigger problem. There is trick to use Lithium shielding, with create Tritium needed for Fussion. But not sure how effective it is, especially for long term reactor lifetime. Those reactors are very expensive, not sure if its worth to shut it down every year and replace entire Li shielding...

I think beryllium is a better candidate. It can be grown as a single crystal and there’s lots of research into using it for shielding in nuclear lightbulb reactors.

You're overlooking the other requirement of the blanket—that it captures fusion neutrons to breed tritium, and provides a self-sustaining, closed fuel cycle. Lithium is mandatory for a D+T reactor blanket, because of these reactions:

https://en.wikipedia.org/wiki/Tritium#Lithium

(Do you have a link about that beryllium nuclear lightbulb rocket? It sounds interesting).

Post reply on HN