"This is where Google comes in, with help to develop a custom AI-powered platform to optimize the reactor construction process. The new system combines AI models and prediction tools from both companies with Westinghouse's WNEXUS, a 3D digital twin of its reactors. With current and historic data, it is able to predict bottlenecks, optimize construction task sequences, adjust staffing levels, and account for external factors like supply chain constraints, the pair claim."
"Google and atomic power biz Westinghouse Electric claim that AI will speed construction and cut the cost of building the new US power plants it is planning in response to rising demands for energy to fuel AI. The pair announced back in July that they are working together to transform how nuclear reactors are constructed and optimize their operation. Now, they are showing off how the first of those works in practice."
Google and Westinghouse Electric are collaborating to apply AI to nuclear reactor construction and operation. Westinghouse disclosed plans for ten additional large US reactors and received an $80 billion backing. The partnership integrates AI models with Westinghouse's WNEXUS 3D digital twin to use current and historical data to predict bottlenecks, optimize task sequences, adjust staffing, and manage supply chain constraints. The tool decomposes builds into millions of tasks and finds optimal daily schedules. A supervisor view highlights delays and an "AI Optimize" function reorganizes schedules to minimize delays and reduce cost overruns.
Read at Theregister
Unable to calculate read time
Collection
[
|
...
]