AI Can Accelerate Production of Safe, Clean Fusion Energy: Research

Artificial Intelligence (AI) can accelerate the development of safe, clean and practically limitless fusion energy for generating electricity, claim researchers. A team of scientists at the US Department of Energy's (DOE) Princeton Plasma Physics Laboratory (PPPL) and Princeton University are smearing deep learning to estimate sudden disruptions that can pause fusion reactions and damage the doughnut-shaped tokamaks that house the reactions.

"This research opens a promising new chapter in the effort to bring unlimited energy to Earth," believed Steve Cowley, director of PPPL

With AI, "we've accelerated the ability to predict with high accuracy the most dangerous challenge to clean fusion energy," added Bill Tang, a principal research physicist at PPPL.

Unlike traditional software, which carries out prescribed instructions, deep learning learns from its mistakes. Achieving this seeming magic are neural networks, layers of interconnected nodes-mathematical algorithms that are weighted by the programme to shape the desired output. The next step will be to move from forecast to the control of disruptions.

"Rather than predicting disruptions at the last moment and then mitigating them, we would ideally use future deep learning models to gently steer the plasma away from regions of instability with the goal of avoiding most disruptions in the first place," supposed collaborator Julian Kates-Harbeck, a physics graduate student at Harvard University.

Power R&D | News published on 19/04/2019 by Moulin

 
 
Next events

 

Last interview
 
 
 Energetica India is a publication from Editorial Omnimedia. No reproduction in whole or part of content posted on this website.