AI-Controlled Plasma: A New Breakthrough in Nuclear Fusion

AI-Controlled Plasma

Successfully achieving nuclear fusion promises to provide an unlimited and sustainable source of clean energy, but we can only realize this incredible dream if we can master the complex physics that take place inside the reactor.

For decades, scientists have made progress towards this goal, but many challenges remain. One of the main obstacles is to successfully control the unstable and overheated plasma in the reactor, but a new approach reveals how we can do this.

In a joint effort of the Swiss Plasma Center (SPC) of the EPFL and the research company artificial intelligence (AI) DeepMind, scientists used a deep reinforcement learning (RL) system to study the nuances of plasma behavior and control within a fusion tokamak, a donut-shaped device that uses a series of magnetic coils positioned around the reactor to control and manipulate the plasma within it.

This is not an easy balancing act, as the coils require an enormous amount of subtle voltage adjustments, up to thousands of times per second, to successfully keep the plasma confined within magnetic fields.

Hence, to sustain nuclear fusion reactions, which involves maintaining the pl stable asthma at hundreds of millions of degrees Celsius, hotter even than the Sun's core, complex, multilayer systems are required to handle the coils. In a new study, however, researchers show that a single AI system can supervise the task on its own.

“Using a learning architecture that combines deep RL and a simulated environment, we have produced controllers that they can both keep the plasma stable and be used to accurately sculpt it into different shapes, ”explains the team in a blog post from DeepMind.



Photo credit - Depositphotos.com To accomplish the feat, the researchers trained their artificial intelligence system in a tokamak simulator, in which the machine learning system discovered, through trial and error , how to navigate the intricacies of plasma magnetic confinement.

After its training window, AI moved to the next level, applying what it had learned in the simulator in the real world. By controlling the SPC's Variable Configuration Tokamak (TCV), the RL system sculpted the plasma into a range of different shapes within the reactor, including one that had never been seen before in the TCV: stabilizing "droplets" in which two plasmas coexisted simultaneously within the device.

In addition to conventional shapes, AI could also produce advanced configurations, sculpting the plasma into configurations of "negative triangularity" and "snowflake".

Each of these manifestations has different types of potential for energy harvesting in the future if we can maintain nuclear fusion reactions. One of the configurations controlled by the system could hold particular promise for the future study of the International Thermonuclear Experimental Reactor (ITER), the largest nuclear fusion experiment in the world, currently under construction in France.

According to the researchers, magnetic mastery of these plasma formations represents “one of the most challenging real-world systems to which reinforcement learning has been applied” and could set a radically new direction in how real-world tokamaks are designed. >
Indeed, some suggest that what we are seeing here will radically alter the future of advanced plasma control systems in fusion reactors. "This AI is, in my opinion, the only way forward," physicist Gianluca Sarri of Queen's University in Belfast, who was not involved in the study, told New Scientist. "There are so many variables and a small change in one of them can cause a big change in the final output. If you try to do it manually, it is a very long process. ”

---

DeepMind’s AI can control superheated plasma inside a fusion reactor

“This is one of the most challenging applications of reinforcement learning to a real-world system,” says Martin Riedmiller, a researcher at DeepMind.

In nuclear fusion, the atomic nuclei of hydrogen atoms get forced together to form heavier atoms, like helium. This produces a lot of energy relative to a tiny amount of fuel, making it a very efficient source of power. It is far cleaner and safer than fossil fuels or conventional nuclear power, which is created by fission—forcing nuclei apart. It is also the process that powers stars.

Controlling nuclear fusion on Earth is hard, however. The problem is that atomic nuclei repel each other. Smashing them together inside a reactor can only be done at extremely high temperatures, often reaching hundreds of millions of degrees—hotter than the center of the sun. At these temperatures, matter is neither solid, liquid, nor gas. It enters a fourth state, known as plasma: a roiling, superheated soup of particles.

The task is to hold the plasma inside a reactor together long enough to extract energy from it. Inside stars, plasma is held together by gravity. On Earth, researchers use a variety of tricks, including lasers and magnets. In a magnet-based reactor, known as a tokamak, the plasma is trapped inside an electromagnetic cage, forcing it to hold its shape and stopping it from touching the reactor walls, which would cool the plasma and damage the reactor.  

Controlling the plasma requires constant monitoring and manipulation of the magnetic field. The team trained its reinforcement-learning algorithm to do this inside a simulation. Once it had learned how to control—and change—the shape of the plasma inside a virtual reactor, the researchers gave it control of the magnets in the Variable Configuration Tokamak (TCV), an experimental reactor in Lausanne. They found that the AI was able to control the real reactor without any additional fine-tuning. In total, the AI controlled the plasma for only two seconds—but this is as long as the TCV reactor can run before getting too hot.

Quick reactions

Ten thousand times a second, the trained neural network takes in 90 different measurements describing the shape and position of the plasma and adjusts the voltage in 19 magnets in response. This feedback loop is far faster than previous reinforcement-learning algorithms have had to deal with. To speed things up, the AI was split into two neural networks. A large network, called a critic, learned via trial and error how to control the reactor inside the simulation. The critic’s ability was then encoded in a smaller, faster network, called an actor, that runs on the reactor itself.

“It’s an incredibly powerful method,” says Jonathan Citrin at the Dutch Institute for Fundamental Energy Research, who was not involved in the work. “It’s an important first step in a very exciting direction.”

The researchers believe that using AI to control plasma will make it easier to experiment with different conditions inside reactors, helping them understand the process and potentially speeding up the development of commercial nuclear fusion. The AI also learned how to control the plasma by adjusting magnets in a way that humans had not tried before, which suggests that there may be new reactor configurations to explore.

“We can take risks with this kind of control system that we wouldn’t dare take otherwise,” says Ambrogio Fasoli, director of the Swiss Plasma Center and chair of the Eurofusion Consortium. Human operators are often unwilling to push the plasma beyond certain limits. “There are events that we absolutely have to avoid because they damage the device,” he says. “If we are sure that we have a control system that takes us close to the limits but not beyond them, then we can explore more possibilities. We can accelerate research.”