Highly accurate digital representations of physical objects or systems, or “digital twins,” will enable the next era of industrial virtualization and AI, NVIDIA executives and BMW said Tuesday.

Launch of the ISC 2022 conference at Hamburg, GermanyNVIDIA’s Rev Lebaredian (left), Vice President for Omniverse and Simulation Technology, was joined by Michele MelchiorreSenior Vice President of Product System, Engineering Planning and Tool Shop at BMW Group.

“If you can build a virtual world that matches the real world in its complexity, scale, and precision, then there’s a lot you can do with that,” Lebaredian said.

While Lebaredian outlined the major trends and technological advancements driving the evolution of digital twin simulations, Melchiorre offered an in-depth look at how BMW made digital twins work in its own factories.

Melchiorre explained BMW plans to use digital twins as a tool to become more “lean, green and digital,” describing real-time collaboration with digital twins and AI training opportunities as a “revolution in factory planning.”

Digital twins like the BMW The iFACTORY initiative described by Melchiorre – which leverages real-time data, simulation and machine learning – is an example of how quickly digital twins have become workhorses for industrial companies such as Amazon Robotics. , BMW and others.

These systems will link our representations of the world to real-time data coming from those worlds, Lebaredian explained.

“What we’re trying to introduce now is a mechanism where we can tie the two together, where we can detect any changes in the physical version and reflect them in the digital world,” Lebaredian said. “If we can make that connection, we gain incredible superpowers.”

Supercomputing is transforming all areas of discovery

And it’s another powerful example of how the supercomputing industry’s technologies — particularly its focus on simulation and data center-scale GPU computing — are spreading around the world.

At the same time, converging technologies have transformed high-performance computing, Lebaredian said. GPU-accelerated systems have become a mainstay not only of scientific computing, but also of edge computing, data centers, and cloud systems.

NVIDIA’s Rev Lebaredian, Vice President for Omniverse and Simulation Technology, speaking at ISC 2022.

And AI-accelerated GPU computing has also become the cornerstone of modern high-performance computing. This positions the supercomputing to achieve the original intent of the computer graphics: simulation.

Computers, algorithms, and AI have all matured enough that we can begin simulating worlds complex enough to be useful on an industrial scale, even using those simulations as training grounds for AI.

One-man world simulation Inflection point

With digital twins, a new class of simulation is possible, Lebaredian said.

These require precise synchronization – the ability to simulate multiple autonomous systems at the same time.

They require physically accurate simulation.

And they require accurate ingestion of true twin information and continuous synchronization.

These simulations of digital twins will give us “superpowers”.

The first one Lebaradian dug into was teleportation. “Just like in a multiplayer video game, any human anywhere on earth can teleport into this virtual world,” Lebaradian said.

Next: time travel.

“If you record the state of the world over time, you can remember it at any time, it allows for time travel,” Lebaradian said.

“Not only can you now teleport into this world, but you can go back and forth through your timeline at any time, and explore this space at any time,” he added.

And, finally, these simulations, if they are sufficiently precise, will allow us to understand the rest.

“If you have a simulator that’s extremely accurate and really predictive of what’s going to happen in the future, if you understand the laws of physics well enough, you essentially get time travel to the future,” Lebaredian said.

“You can calculate not just one possible future, but many possible futures,” he added, explaining how this could allow city planners to see what might happen when they modify a city, plan the road and modify traffic systems to find “the best possible”. coming.’

Modern supercomputing unlocks these digital twins, which are extremely computationally intensive and require a precision synchronization network with extremely low latency.

“We need a new kind of supercomputer that can really accelerate artificial intelligence and run these massive simulations in real time,” Lebaradian said.

This will require GPU-accelerated systems optimized at every layer of the system to enable precise synchronization.

These systems will need to operate not only on the data center, but also reach to the edge of networks to integrate data into virtual simulations with precise timing.

Such systems will be essential for small-scale advances, such as drug discovery, and large-scale ones, such as climate simulation.

“We have to simulate our climate, we have to look very far, we have to do it with an accuracy that has never been done before, and we have to be able to be sure that our simulations are actually predictive and accurate, if we do that, we have some hope that we can cope with this climate change situation,” Lebaradian said.

BMW iFACTORY: “Lean, green and digital”

BMW Melchiorre gave an example of how this broad vision is being implemented today at BMWas the automaker seeks to become “lean, green and digital”.

Michelle MelchiorreSenior Vice President of Product System, Engineering Planning and Tool Shop at BMW Group.

BMW built exceptionally complex digital twins, simulating its factories with humans and robots interacting in the same space, at the same time.

It’s an effort that spans from the factory floor to the company’s data center, including its entire supply chain. This digital twin involves millions of moving parts and parts connected to a huge supply chain.

Melchiorre presented his audience with a number of examples of how digital twins simulate various parts of the factory, simulating how industrial machines, robots and people will move together.

Inside the digital twin of BMW assembly system, powered by Omniverse, an entire factory in simulation.

And he explained how they leverage NVIDIA technology to simulate entire factories before they’re even built.

Melchiorre showed an aerial image of the site where BMW built a new factory in Hungary. While the real-world factory is still mostly open field, the digital factory is 80% complete.

“This will be the first plant where we have a full digital twin well before production begins,” Melchiorre said.

In the future, the iFACTORY will be real in all BMW plants, explains Melchiorre, of BMW Centennial domestic plant in Munich at its future plant in Debrecen, Hungary.?

“This is our production network, not just a factory – every factory will go in this direction, every factory will become a BMW iFACTORY is our blueprint for our future,” said Melchiorre.