Latest News

California's only nuclear plant to utilize AI to help comply with brand-new licensing obstacles

California's only remaining nuclear power plant prepares to utilize artificial intelligence tools to assist it adhere to brand-new licensing requirements to keep the decadesold facility running.

Atomic Canyon, a start-up based in San Luis Obispo, California, said on Wednesday it has actually signed a deal with Pacific Gas & & Electric (PG&E) to install an AI software application system called Neutron Business at PG&E's Diablo Canyon center. The deal, whose worth was not disclosed, will assist PG&E sift through decades of documents to develop plans to handle the plant's aging concrete and systems.

Commissioned in 1985 and situated about midway between San Francisco and Los Angeles on California's coast, Diablo Canyon was once slated to shut down. California officials reversed course in 2022 in an effort to remain on track with the state's. carbon-reduction goals.

Maureen Zawalick, vice president of business and technical. services at Diablo Canyon, informed Reuters the center has about. 9,000 procedures in place and 9 million documents saved in its. systems, many of them scanned from paper or microfiche. As part. of the PG&E's federal license keep the center running for up. to 20 more years, the company must create strategies to handle it as. it ages, with much of the info drawn from decades-old. documents.

Atomic Canyon's software, which will operate on computer systems. provided by Nvidia, will check out the documents and make. them searchable in natural language. The startup dealt with. researchers at Oak Ridge National Lab in Tennessee to. establish an AI design trained to understand the specialized terms. utilized in nuclear regulative files.

Many nuclear plants have this huge corpus of data, however it. can be truly challenging to find documents when you have so. much data that's offered, Trey Lauderdale, Atomic Canyon's. creator, informed Reuters. A lot of this information is microfiche. It's. not like they went and identified what all this data was.

PG&E's Zawalick said the AI system might eventually assist. with more complex jobs, like scheduling upkeep on the. plant, which need to take into account how all its systems work. together.

Maintenance scheduling is labor extensive, Zawalick stated. That's where we're going to acquire a great deal of effectiveness..

(source: Reuters)