A team of MIT researchers thinks they may have lowered one of the main barriers to achieving large-scale nuclear fusion—putting us one step closer to making an abundant form of energy a reality.
By harnessing the same processes that power stars, we would have access to a clean, safe and virtually unlimited source of energy. Scientists have built reactors to try to tame fusion, one of the most explored being the tokamak. Essentially a donut-shaped tube that uses strong magnets to confine the plasma needed to power fusion reactions, the tokamak has shown great potential. But to fully realize this, scientists must first navigate the potential pitfalls this energy brings with it, including how to slow down a fusion reaction once it’s underway.
That’s where the new search enter: Using a combination of physics and machine learning, researchers predicted how the plasma inside a tokamak reactor would behave given a set of initial conditions—something researchers have long puzzled over (after all, it’s difficult to look inside a fusion reactor mid-run). The article was published Monday in Nature Communications.
“For fusion to be a useful energy source, it will have to be reliable,” said Allen Wang, lead author of the study and graduate student at MIT. MIT News. “To be reliable, we need to be good at managing our plasmas.”
With great power comes great risk
When a tokamak reactor is fully functioning, the plasma stream inside it can circulate at speeds of up to about 100 kilometers per second and at temperatures of 180 million degrees Fahrenheit (100 million degrees Celsius). That’s hotter than the Sun’s core.
If the reactor has to be shut down for any reason, operators begin a process to “reduce” the plasma current, slowly de-energizing it. But this process is complicated and the plasma can cause “scratches and scars inside the tokamak – minor damage that still requires considerable time and resources to repair,” the researchers explained.
“Uncontrolled plasma terminations, even during deceleration, can generate intense heat fluxes damaging the internal walls,” explained Wang. “Often, especially with high-performance plasmas, slowdowns can actually drive the plasma closer to some instability limits. So it’s a delicate balance.
In fact, any misstep in the operation of fusion reactors can be costly. In an ideal world, researchers would be able to run tests on working tokamaks, but because fusion is not yet efficient, running one of these reactors is incredibly expensive, and most facilities will only use them a few times a year.
Looking into the wisdom of physics
For their model, the team found a delightfully clever method to overcome limitations in data collection – they simply went back to the fundamental rules of physics. They paired their model’s neural network with another model that describes plasma dynamics, and then trained the model with data from the TCV, a small experimental fusion device in Switzerland. The dataset included information about variations in the initial temperature and energy levels of the plasma, as well as during and at the end of each experimental run.
From there, the team used an algorithm to generate “trajectories” that showed reactor operators how the plasma would likely behave as the reaction progressed. When they applied the algorithm to real TCV runs, they found that following the model’s “trajectory” instructions was perfectly capable of guiding operators to safely slow down the device.
“We’ve done this several times,” Wang said. “And we did things much better across the board. So we had statistical confidence that we improved things.”
“We are trying to address the scientific questions to make fusion routinely useful,” he added. “What we’ve done here is the beginning of a journey that’s still long. But I think we’ve made some good progress.”
Leave a Reply