Introduction
Nuclear vitality ranks among the many world’s most regulated industries. AI and particularly generative AI have created sufficient affect that thought leaders rank it amongst different transformative “common goal applied sciences” comparable to electrical energy and the steam engine. Harnessing AI to reimagine nuclear operations throughout the trade means extra carbon-free nuclear vitality for electrical grids and knowledge facilities, which the Worldwide Vitality Company estimates demand to double by 2026. In September 2024, Westinghouse unveiled its HiVE™ AI system, powered by its fine-tuned bertha™ generative AI mannequin, reworking how clients collaborate with Westinghouse.
Constructing a Higher Information Administration Resolution
Westinghouse’s digital transformation began greater than 5 years in the past with a deep bench of knowledge and nuclear specialists and over 70 years’ price of cleaned and contextualized industrial knowledge distinctive to the nuclear world. Nevertheless, the workforce wanted to enhance the corporate’s knowledge infrastructure if it wished to comprehend its AI ambitions. The prevailing on-premises analytics database lacked some essential scalability options and choices. And not using a scalable cloud resolution, the information workforce struggled with an absence of computing assets, an incapacity to quickly experiment with large quantities of knowledge, and restrictions on safely sharing knowledge throughout functions.
To construct a world-class, nuclear-specific AI functionality, Westinghouse wanted a greater resolution. Westinghouse determined to construct on the Databricks Information Intelligence Platform, a transfer that may show essential in its mission to drive innovation. The nuclear trade has at all times been deeply dedicated to security and lowering threat, with each element inspected and controlled. Managing and securing important nuclear knowledge just isn’t negotiable. With this in thoughts, Westinghouse got down to design a knowledge spine that might host AI functions for a few of the most trusted utilities on this planet. Databricks was the best associate to assist Westinghouse obtain this purpose.
As Westinghouse got down to design a knowledge spine so safe and strong that it might host AI functions for a few of the most trusted utilities on this planet, it turned to Databricks. The Databricks workforce rapidly turned a “guiding mild” for Westinghouse, offering essential assist because the Westinghouse infrastructure workforce took the lead in configuring our methods to fulfill the nuclear trade’s strict regulatory necessities. Westinghouse was in a position to leverage Databricks’ state-of-the-art governance with Unity Catalog. It was constructed in line with greatest practices outlined within the Databricks AI Safety Framework (DASF), complementing Microsoft’s strong safety requirements. These foundations bolster the credibility of Westinghouse’s knowledge administration practices and provides its clients peace of thoughts, which is crucial in an trade the place belief and reliability are paramount.
When it got here time to modernize how the information was organized, the Databricks skilled providers workforce delivered. Collectively, Westinghouse and Databricks created a scalable and multi-tiered analytics setting, full with an ML Ops course of that streamlines all the machine studying lifecycle. This basis additionally featured a sturdy prototyping setting, together with devoted workspaces, for testing and deploying AI fashions, all backed by a safe and dependable knowledge lakehouse structure.
The brand new infrastructure instantly saved a whole lot of hours yearly for the Digital Optimization Providers enterprise unit and allowed the Westinghouse workforce to reinvest of their product traces to incorporate AI for customer-facing functions and providers.
To make this imaginative and prescient a actuality, Westinghouse had to make sure that its knowledge was correctly ready, managed, and ruled. That’s the place Databricks’ highly effective applied sciences, together with Auto Loader, Photon engine, and Lakeflow Jobs, actually shined. Then, when Westinghouse wanted real-time insights into its knowledge high quality and pipeline efficiency, they tapped into options like Lakehouse Monitoring and Expectations. Now, with Unity Catalog (UC) governing its knowledge, Westinghouse has full visibility into its knowledge’s journey, from supply to vacation spot. Within the nuclear trade, all the pieces revolves round security and belief. As Westinghouse continues to develop pioneering new AI options, Databricks providers reinforce the belief Westinghouse earns for managing knowledge securely and reliably.
Accelerating AI in a Advanced Business
On September 4, 2024, Westinghouse launched its HiVE™ nuclear particular AI system and its bertha™ generative AI mannequin to the world. Not solely has the Westinghouse workforce quickly superior its AI capabilities utilizing the Databricks Information Intelligence Platform, however it may now create future AI merchandise and options restricted solely by creativeness.
To help in growing bertha™, Westinghouse leveraged the Databricks Mosaic AI Agent Framework, to quickly consider numerous foundational fashions and GenAI methods. Utilizing Databricks Experiments and MLFlow, Westinghouse performed speedy experimentation to find out the perfect fashions, whereas logging statistics to judge efficiency. This method enabled Westinghouse to speed up the event of its customized Generative AI resolution.
Westinghouse can now leverage its superior knowledge infrastructure to create options throughout the nuclear trade. For instance, massive industrial services talk and retailer monumental portions of knowledge. With an structure constructed on Databricks, Westinghouse maintains an AI resolution to extract, cleanse, and retailer machine knowledge from over 200 nuclear services worldwide. One other instance consists of an AI utility designed to course of video knowledge in real-time inside Stress Water and Boiling Water Reactors with the potential to detect particles no less than 90% higher than guide inspections and save as much as 25% on inspection prices.
Lastly, one other nice instance consists of leveraging the bertha™ generative AI mannequin to generate licensing knowledge and documentation dramatically sooner. Historically, it may take months to manually compile new nuclear web site licenses or environmental assessments. It is a essential step in streamlining nuclear growth.
The Databricks infrastructure has freed knowledge and nuclear specialists to give attention to nuclear innovation. Because of this, the Westinghouse knowledge scientists delivered 4 proofs of idea in December 2024, two production-grade methods within the first quarter of 2025, and helped generate 45 distinct innovation concepts within the first two months of 2025.
Conclusion
The Westinghouse-configured Databricks Information Intelligence Platform removes large limitations to attaining Westinghouse’s AI ambitions. Now, Westinghouse can scale compute, quickly and safely experiment with mass quantities of manufacturing knowledge, and share data securely throughout functions. Westinghouse HiVE™ nuclear-specific AI system clients respect the ability of auditability, enter and output transparency, real-time knowledge processing, and operational analytics. The Westinghouse groups worth the unimaginable and adaptable partnership with Databricks to create a singular platform that positions it for continued pioneering AI innovation.
“With Databricks at all times offering the most recent options that hit the market, Westinghouse is ready to regularly incorporate new AI capabilities for our clients.”
— Catherine Stanley, Information, Digital, and AI Supervisor at Westinghouse