The Atomic Energy Authority and University of Manchester in the UK are using technology from Nvidia to build a life sized digital twin of a fusion reactor.

The UK AEA has been using the Nvidia Omniverse simulation platform to accelerate the design and development of a full-scale fusion reactor that could be used for clean power from hydrogen in the future.

“We are working with researchers at UKAEA and we are able to help them build a digital twin,” said Dion Harris, head of data centre product marketing at Nvidia. “The experiment is extremely expensive so you want to make sure you can build it right. So we will help them build the digital twin of the structure itself, life size and in real time. In addition to the CAD design of the structure they plan to simulate the plasma itself and model the robotics for the reactor when it is on line,” he said. “We think this will be a path to sustainable energy.”

The digital twin starts with the design of a fusion reactor, which requires a large number of parts and inputs from large teams of engineering, design and research experts throughout the process.

“There are many different components, and we have to take into account lots of different areas of physics and engineering,” said Lee Margetts, UKAEA chair of digital engineering for nuclear fusion at the University of Manchester. “If we make a design change in one system, this has a knock-on effect on other systems.”

Experts from various domains use different computer-aided design applications or simulation tools, which all impact on each other.  By enabling all tools and applications to connect, Omniverse allows the engineers working on the reactor design to simultaneously collaborate from a single source.

“We can see three different engineers, from three different locations, working on three different components of a reactor in three different packages,” said Muhammad Omer, a researcher on the project.

The team achieved photorealism in their reactor designs using the platform’s core abilities to import full-fidelity 3D data. They could also visualize in real time with the RTX Renderer, which made it easy for them to compare different design options for components.

The teams also developed Python-based Omniverse Extensions with Omniverse Kit to connect and ingest data from the Monte Carlo Neutronics Code Geant4 tool. This allows them to simulate neutron transport in the reactor core.

They also built Omniverse Extensions to view JOREK plasma simulation code, which simulates visible light emissions, giving the researchers insight into the plasma’s state.

Researchers will begin to explore the Nvidia Modulus AI-physics framework to use with their existing simulation data to develop AI surrogate models to accelerate the fusion plasma simulations.

Using Omniverse Replicator, a software development kit for building custom synthetic data-generation tools and datasets, researchers can generate large quantities of physically accurate synthetic data of the reactor and plasma behaviour to train robotic systems. By learning in simulation, the robots can correctly handle tasks more accurately in the real world, improving predictive maintenance and reducing downtime.

In the future, sensor models could livestream observation data to the Omniverse digital twin, constantly keeping the virtual twin synchronized to the reactor’s physical state. Researchers will be able to explore various hypothetical scenarios by first testing in the virtual twin before deploying changes to the physical reactor.

All material on this site Copyright © 2022 European Business Press SA. All rights reserved.