NRC seeks comments on AI’s role in U.S. nuclear power fleet

April 22, 2021, 3:04PMNuclear News

As predictive analytical tools, artificial intelligence (AI) and machine learning (ML) show promise in improving nuclear reactor safety while offering economic savings. To get a better understanding of current usage and future trends in AI and ML in the commercial nuclear power industry, the Nuclear Regulatory Commission is seeking comments from the public, the nuclear industry, and other stakeholders, as well as other interested individuals and organizations.

As published in the April 21 Federal Register, the NRC is accepting comments until May 21 on the “state of practice, benefits, and future trends related to the advanced computational tools and techniques in predictive reliability and predictive safety assessments in the commercial nuclear power industry.”

Submitting comments: The NRC encourages electronic comment submission through the federal rulemaking website, with Docket ID NRC-2021-0048 included in the comment submission.

The issues: To improve its understanding of the potential applications of AI and ML in nuclear power operations, as well as potential pitfalls and challenges, the NRC is requesting comments on the following questions:

  1. What is the status of the nuclear power industry’s development or use of AI/ML tools to improve aspects of nuclear plant design, operations or maintenance, or decommissioning? What tools are being used or developed, and when are they expected to be put into use?
  2. What areas of commercial nuclear reactor operation and management will benefit the most, and the least, from the implementation of AI/ML? Possible examples include, but are not limited to, inspection support, incident response, power generation, cybersecurity, predictive maintenance, safety/risk assessment, system and component performance monitoring, operational/maintenance efficiency, and shutdown management.
  3. What are the potential benefits of incorporating AI/ML in terms of design or operational automation, preventive maintenance trending, and improved reactor operations staff productivity?
  4. What AI/ML methods are either currently being used or will be in the near future in nuclear plant management and operations? Examples of possible AI/ML methods include, but are not limited to, artificial neural networks, decision trees, random forests, support vector machines, clustering algorithms, dimensionality reduction algorithms, data mining and content analytics tools, Gaussian processes, Bayesian methods, natural language processing, and image digitization.
  5. What are the advantages or disadvantages of a high-level, top-down strategic goal for developing and implementing AI/ML across a wide spectrum of general applications versus an ad-hoc, case-by-case targeted approach?
  6. With respect to AI/ML, what phase of technology adoption is the nuclear power industry currently experiencing and why? The current technology adoption model characterizes phases into categories such as the innovator phase, the early adopter phase, the early majority phase, the late majority phase, and the laggard phase.
  7. What challenges are involved in balancing the costs associated with the development and application of AI/ML tools against plant operational and engineering benefits when integrating AI/ML into operational decision-making and workflow management?
  8. What is the general level of AI/ML expertise in the commercial nuclear power industry (e.g., expert, well-versed/skilled, or beginner)?
  9. How will AI/ML affect the commercial nuclear power industry in terms of efficiency, costs, and competitive positioning in comparison to other power generation sources?
  10. Does AI/ML have the potential to improve the efficiency and/or effectiveness of nuclear regulatory oversight or otherwise affect regulatory costs associated with safety oversight? If so, in what ways?
  11. AI/ML typically necessitates the creation, transfer, and evaluation of very large amounts of data. What concerns, if any, exist regarding data security in relation to proprietary nuclear plant operating experience and design information that may be stored in remote, off-site networks?

Related Articles

ANS Grand Challenge: Expedite licensing

September 22, 2022, 9:30AMNuclear NewsNicholas R. Brown

As the largest ultra-low-carbon electricity source in the United States, nuclear energy is a vital pillar of the effort to mitigate climate change. Deployment of advanced nuclear reactor and...

Advanced reactor licensing and the path to cost certainty

How Kairos Power is applying rapid iterative development to the licensing process as part of its strategy to deliver on cost

September 20, 2022, 3:13PMNuclear NewsMike Laufer

Developing a first-­of-­a-­kind reactor is a daunting endeavor. To be successful, advanced reactor designers need to achieve cost certainty by delivering a safe and affordable product at...

The “gold standard” of regulation

September 12, 2022, 3:04PMNuclear News

Much has been written about regulation over the years, including whether or not the nuclear industry is overregulated or whether the regulator is in the industry’s “pocket.” Having a...

The Future of Diablo Canyon

While many Californians are hopeful the state’s last nuclear power reactor can be saved, PG&E is actively preparing for decommissioning.

September 2, 2022, 3:00PMRadwaste Solutions

The reports of the death of the Diablo Canyon nuclear power plant may be greatly exaggerated. While Pacific Gas and Electric (PG&E) announced as early as 2016 that it would be closing...

Maintaining RIPB in commercial LWRs

ANS Standards Committee publishes new standard for light water reactor risk-informed, performance-based design

September 1, 2022, 12:08PMNuclear NewsKent B. Welter

The new standard ANSI/ANS-30.3-2022, Light Water Reactor Risk-Informed, Performance-Based Design, has just been issued by the American Nuclear Society. Approved by the American National...