Westinghouse and Google Aim to Speed Up Reactor Construction with AI

Westinghouse has announced it is to collaborate with Google Cloud to use artificial intelligence tools to streamline construction of new nuclear plants and enhance the operations of existing nuclear power plants.

In September last year, Westinghouse introduced the HiVE System – a generative artificial intelligence system built on more than 75 years of proprietary data, knowledge and expertise. The system features a Nuclear Large Language Model AI System named bertha, after Bertha Lamme who was the first woman in the US to receive a mechanical engineering degree – in 1893 – and then became the first female engineer hired by Westinghouse. According to Westinghouse, these nuclear-specific AI solutions will optimize new nuclear deployment of its AP1000 reactor, AP300 small modular reactors and eVinci microreactor technologies.

Under its agreement with Google Cloud, the two companies will pair Westinghouse’s HiVE and bertha nuclear AI solutions with Google Cloud technologies and expertise to “transform the construction of advanced Westinghouse nuclear reactors into an efficient, repeatable process and enhance the operations of existing nuclear power plants using data-driven insights”.

As part of this collaboration, Westinghouse and Google Cloud have successfully achieved a first-of-a-kind proof of concept leveraging Westinghouse’s WNEXUS digital plant design platform and HiVE artificial intelligence enhanced by Google Cloud technologies, including Vertex AI, Gemini and BigQuery, to autonomously generate and optimize AP1000 modular construction work packages.