Powering Strong Communities

DOE Details How Machine Learning, AI Can Help Lower Nuclear Reactor Operating Costs

Blue Wave AI Labs has successfully deployed machine learning tools at two nuclear power plants in the U.S. operated by Constellation, saving the company millions of dollars per reactor each year, the Department of Energy reported. 

The project was part of a $6 million effort supported by the DOE to help lower the operating costs of nuclear power plants using the latest artificial intelligence and machine learning technologies.  

Two U.S. national laboratories -- Argonne National Laboratory and Brookhaven National Laboratory -- contributed to the project. The effort also leveraged 158,000 core hours across the Nuclear Science User Facilities high-performance computing systems. 

Blue Wave projects that the new software could save up to $80 million per year once the tools are expanded to the nation’s fleet of 32 boiling water reactors.

Blue Wave tested its technology at Constellation’s Peach Bottom Atomic Power Station and Limerick Generating Station starting in 2022.    

“All three of Blue Wave’s AI tools ingested vast amounts of historical plant data to analyze and improve sensor measurements within the reactor core,” DOE reported.

Reactor operators depend on sensors to measure power generation, fuel consumption, and the overall state of the reactor with respect to operating limits. 

Over time, these sensors can become out of calibration and lose accuracy. If enough sensors stop working correctly, the reactor will reduce power or shut down as a precautionary measure, costing an operator millions of dollars per day in lost generation revenue. 

In 2023, Blue Wave identified sensors at Limerick 2 that were suspected to be out of calibration. These sensors were taken offline, allowing the plant to continue operating safely while staying in compliance with its operating license, DOE said. 

During the next sensor calibration cycle, the plant operators were able to verify that sensors that were taken offline were giving incorrect readings due to miscalibration, as was predicted by Blue Wave’s tool.

“The AI algorithms also improved engineers’ ability to predict how much fuel must be purchased and how to configure the fuel to generate the greatest amount of power while preserving margin to operating limits — another time-consuming and expensive process,” DOE said.

The company estimates that the AI tools combined have saved Constellation more than $1.6 million each year per reactor by reducing fuel costs, minimizing reactor downtime, and reducing the staff time spent on analysis and planning.  

The three-year Blue Wave project builds on previous AI/ML work funded by DOE to help lower the cost of operating BWRs. 

Operations and maintenance costs make up nearly 70 percent of the generating costs at nuclear power plants, and lowering these costs can help make existing reactors more cost-competitive in certain markets.  

With many plants extending operations through the 2050s to maintain this reliable source of clean energy, using the latest advancements in AI and machine learning “can help lower the cost, save on fuel, and reduce the amount of waste that is generated over the lifetime of the reactor while maintaining the same high standards for safety and security,” DOE noted. 

Because of the success of this project, Constellation plans to expand AI applications to additional reactors in its BWR fleet. 

Blue Wave projects that their technology could be deployed across all 32 of the nation’s BWRs within three years, saving the nuclear industry nearly $80 million over that span.

The company is also working to adapt these AI algorithms to support the U.S. pressurized water reactor fleet, which comprises the remaining two-thirds of America’s nuclear energy generation.  

NEW Topics