Role of Artificial Intelligence Tools in U.S. Commercial Nuclear Power Operations, 20744-20745 [2021-08177]

Download as PDF 20744 Federal Register / Vol. 86, No. 75 / Wednesday, April 21, 2021 / Notices approximately 385,000 lbs. net weight, was, consistent with waste management best practices, segregated, packaged, and stored in a secured location for removal from the station. SUPPLEMENTARY INFORMATION: The waste was to be removed in February 2021, at the end of the 2021–2021 season. Due to the world-wide pandemic, the United States Antarctic Program severely curtailed its activities on the continent and directed efforts to activities required to ensure the safe and continuous operation of all three USAP stations and activities required to avoid irreversible damage to science or operational infrastructure. In order to minimize the risk of introducing COVID–19 to the Antarctic continent, personnel was reduced to a minimum and the annual ships for resupply and waste removal were cancelled for the season. The removal of the hazardous waste is a priority for removal during the January-February 2022 time period. FOR FURTHER INFORMATION CONTACT: Dr. Polly A. Penhale, Senior Advisor, Environment at 703–292–7420. Authority: 45 CFR 671.17. Erika N. Davis, Program Specialist, Office of Polar Programs. [FR Doc. 2021–08186 Filed 4–20–21; 8:45 am] BILLING CODE 7555–01–P NUCLEAR REGULATORY COMMISSION [NRC–2021–0048] Role of Artificial Intelligence Tools in U.S. Commercial Nuclear Power Operations Nuclear Regulatory Commission. ACTION: Request for comment. AGENCY: The U.S. Nuclear Regulatory Commission (NRC) is requesting public comment on the current state of commercial nuclear power operations relative to the use of artificial intelligence (AI) and machine learning (ML) tools. DATES: Submit comments by May 21, 2021. Comments received after this date will be considered if it is practical to do so, but the Commission is able to ensure consideration only for comments received on or before this date. ADDRESSES: You may submit comments by any of the following methods; however, the NRC encourages electronic comment submission through the Federal Rulemaking website: • Federal Rulemaking Website: Go to https://www.regulations.gov and search khammond on DSKJM1Z7X2PROD with NOTICES SUMMARY: VerDate Sep<11>2014 18:12 Apr 20, 2021 Jkt 253001 for Docket ID NRC–2021–0048. Address questions about Docket IDs in Regulations.gov to Stacy Schumann; telephone: 301–415–0624; email: Stacy.Schumann@nrc.gov. For technical questions, contact the individual listed in the FOR FURTHER INFORMATION CONTACT section of this document. • Mail comments to: Office of Administration, Mail Stop: TWFN–7– A60M, U.S. Nuclear Regulatory Commission, Washington, DC 20555– 0001, ATTN: Program Management, Announcements and Editing Staff. For additional direction on obtaining information and submitting comments, see ‘‘Obtaining Information and Submitting Comments’’ in the SUPPLEMENTARY INFORMATION section of this document. John C. Lane, Office of Nuclear Regulatory Research, U.S. Nuclear Regulatory Commission, Washington, DC 20555– 0001, telephone: 301–415–2476, email: John.Lane@nrc.gov. FOR FURTHER INFORMATION CONTACT: SUPPLEMENTARY INFORMATION: I. Obtaining Information and Submitting Comments A. Obtaining Information Please refer to Docket ID NRC–2021– 0048 when contacting the NRC about the availability of information for this action. You may obtain publicly available information related to this action by any of the following methods: • Federal Rulemaking Website: Go to https://www.regulations.gov and search for Docket ID NRC–2021–0048. • NRC’s Agencywide Documents Access and Management System (ADAMS): You may obtain publicly available documents online in the ADAMS Public Documents collection at https://www.nrc.gov/reading-rm/ adams.html. To begin the search, select ‘‘Begin Web-based ADAMS Search.’’ For problems with ADAMS, please contact the NRC’s Public Document Room (PDR) reference staff at 1–800–397–4209, at 301–415–4737, or by email to pdr.resource@nrc.gov. The AI/ML general solicitation request for comment is also available in ADAMS under Accession No. ML21085A611. • Attention: The PDR, where you may examine and order copies of public documents, is currently closed. You may submit your request to the PDR via email at pdr.resource@nrc.gov or call 1– 800–397–4209 or 301–415–4737, between 8:00 a.m. and 4:00 p.m. (EST), Monday through Friday, except Federal holidays. PO 00000 Frm 00093 Fmt 4703 Sfmt 4703 B. Submitting Comments The NRC encourages electronic comment submission through the Federal Rulemaking website (https:// www.regulations.gov). Please include Docket ID NRC–2021–0048 in your comment submission. The NRC cautions you not to include identifying or contact information that you do not want to be publicly disclosed in your comment submission. The NRC will post all comment submissions at https:// www.regulations.gov as well as enter the comment submissions into ADAMS. The NRC does not routinely edit comment submissions to remove identifying or contact information. If you are requesting or aggregating comments from other persons for submission to the NRC, then you should inform those persons not to include identifying or contact information that they do not want to be publicly disclosed in their comment submission. Your request should state that the NRC does not routinely edit comment submissions to remove such information before making the comment submissions available to the public or entering the comment into ADAMS. II. Discussion The NRC is exploring the potential for advanced computational and predictive capabilities involving AI and ML in the various phases of nuclear power generation operational experience and plant management. The NRC is soliciting comments 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. III. Specific Request for Comment The NRC requests comments from the public, the nuclear industry and other stakeholders, as well as other interested individuals and organizations. The focus of this request is to gather information that will provide the NRC staff with a better understanding of current usage and future trends in AI and ML in the commercial nuclear power industry. IV. Requested Information and Comments AI and ML are emerging, analytical tools, which, if used properly, show promise in their ability to improve reactor safety, yet offer economic savings. The NRC requests comments on issues listed below in this solicitation to enhance the NRC’s understanding of the short- and long-term applications of AI E:\FR\FM\21APN1.SGM 21APN1 20745 khammond on DSKJM1Z7X2PROD with NOTICES Federal Register / Vol. 86, No. 75 / Wednesday, April 21, 2021 / Notices and ML in nuclear power industry operations and management, as well as potential pitfalls and challenges associated with their application. 1. What is status of the commercial nuclear power industry 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? When are the tools currently under development 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 to commercial nuclear power operations of incorporating AI/ML in terms of (a) design or operational automation, (b) preventive maintenance trending, and (c) improved reactor operations staff productivity? 4. What AI/ML methods are either currently being used or will be in the near future in commercial nuclear plant management and operations? Example 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 commercial 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 VerDate Sep<11>2014 18:12 Apr 20, 2021 Jkt 253001 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 effect 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, offsite networks? The teleconference meeting will be held on Thursday, May 27, 2021, 1:00 p.m. to 5:00 p.m. Eastern Daylight Time. DATES: Date May 27, 2021 ... Webinar information Link: https:// usnrc.webex.com Event number: 199 574 5068. Dated: April 15, 2021. For the Nuclear Regulatory Commission. Mehdi Reisi Fard, Chief, Performance and Reliability Branch, Division of Risk Analysis, Office of Nuclear Regulatory Research. Public Participation: The meeting will be held as a webinar using Cisco WebEx. Any member of the public who wishes to participate in any portion of this meeting should register in advance of the meeting by accessing the provided link above. Upon successful registration, a confirmation email will be generated providing the telephone bridge line and a link to join the webinar on the day of the meeting. Members of the public should also monitor the NRC’s Public Meeting Schedule at https://www.nrc.gov/pmns/ mtg for any meeting updates. If there are any questions regarding the meeting, persons should contact Ms. Jamerson using the information below. Contact Information: Kellee Jamerson, email: Kellee.Jamerson@nrc.gov, telephone: 301–415–7408. [FR Doc. 2021–08177 Filed 4–20–21; 8:45 am] Conduct of the Meeting BILLING CODE 7590–01–P The ACMUI Chair, Darlene F. Metter, M.D., will preside over the meeting. Dr. Metter will conduct the meeting in a manner that will facilitate the orderly conduct of business. The following procedures apply to public participation in the meeting: 1. Persons who wish to provide a written statement should submit an electronic copy to Ms. Jamerson at the contact information listed above. All written statements must be received by May 24, 2021, three business days prior to the meeting, and must pertain to the topics on the agenda for the meeting. 2. Questions and comments from members of the public will be permitted during the meeting, at the discretion of the ACMUI Chairman. 3. The draft transcript and meeting summary will be available on ACMUI’s website https://www.nrc.gov/readingrm/doc-collections/acmui/meetings/ 2021.html on or about July 9, 2021. 4. Persons who require special services, such as those for the hearing impaired, should notify Ms. Jamerson of their planned participation. This meeting will be held in accordance with the Atomic Energy Act of 1954, as amended (primarily Section 161a); the Federal Advisory Committee Act (5 U.S.C. App); and the Commission’s regulations in 10 CFR part 7. NUCLEAR REGULATORY COMMISSION Advisory Committee on the Medical Uses of Isotopes: Meeting Notice U.S. Nuclear Regulatory Commission. ACTION: Notice of Meeting. AGENCY: The U.S. Nuclear Regulatory Commission (NRC) will convene a public teleconference meeting of the Advisory Committee on the Medical Uses of Isotopes (ACMUI) on May 27, 2021, to discuss the NRC staff’s assessment of medical related events for fiscal year 2020 and the ACMUI Abnormal Occurrence Subcommittee’s draft report on the proposed limited revisions to abnormal occurrence criteria for medical events. The meeting agenda is subject to change. Meeting information, including a copy of the agenda and related documents, will be available on the ACMUI’s Meetings and Related Documents web page at https:// www.nrc.gov/reading-rm/doccollections/acmui/meetings/2021.html. The agenda and related meeting documents may also be obtained by contacting Ms. Kellee Jamerson using the information below. SUMMARY: PO 00000 Frm 00094 Fmt 4703 Sfmt 4703 E:\FR\FM\21APN1.SGM 21APN1

Agencies

[Federal Register Volume 86, Number 75 (Wednesday, April 21, 2021)]
[Notices]
[Pages 20744-20745]
From the Federal Register Online via the Government Publishing Office [www.gpo.gov]
[FR Doc No: 2021-08177]


=======================================================================
-----------------------------------------------------------------------

NUCLEAR REGULATORY COMMISSION

[NRC-2021-0048]


Role of Artificial Intelligence Tools in U.S. Commercial Nuclear 
Power Operations

AGENCY: Nuclear Regulatory Commission.

ACTION: Request for comment.

-----------------------------------------------------------------------

SUMMARY: The U.S. Nuclear Regulatory Commission (NRC) is requesting 
public comment on the current state of commercial nuclear power 
operations relative to the use of artificial intelligence (AI) and 
machine learning (ML) tools.

DATES: Submit comments by May 21, 2021. Comments received after this 
date will be considered if it is practical to do so, but the Commission 
is able to ensure consideration only for comments received on or before 
this date.

ADDRESSES: You may submit comments by any of the following methods; 
however, the NRC encourages electronic comment submission through the 
Federal Rulemaking website:
     Federal Rulemaking Website: Go to https://www.regulations.gov and search for Docket ID NRC-2021-0048. Address 
questions about Docket IDs in Regulations.gov to Stacy Schumann; 
telephone: 301-415-0624; email: [email protected]. For technical 
questions, contact the individual listed in the FOR FURTHER INFORMATION 
CONTACT section of this document.
     Mail comments to: Office of Administration, Mail Stop: 
TWFN-7-A60M, U.S. Nuclear Regulatory Commission, Washington, DC 20555-
0001, ATTN: Program Management, Announcements and Editing Staff.
    For additional direction on obtaining information and submitting 
comments, see ``Obtaining Information and Submitting Comments'' in the 
SUPPLEMENTARY INFORMATION section of this document.

FOR FURTHER INFORMATION CONTACT: John C. Lane, Office of Nuclear 
Regulatory Research, U.S. Nuclear Regulatory Commission, Washington, DC 
20555-0001, telephone: 301-415-2476, email: [email protected].

SUPPLEMENTARY INFORMATION:

I. Obtaining Information and Submitting Comments

A. Obtaining Information

    Please refer to Docket ID NRC-2021-0048 when contacting the NRC 
about the availability of information for this action. You may obtain 
publicly available information related to this action by any of the 
following methods:
     Federal Rulemaking Website: Go to https://www.regulations.gov and search for Docket ID NRC-2021-0048.
     NRC's Agencywide Documents Access and Management System 
(ADAMS): You may obtain publicly available documents online in the 
ADAMS Public Documents collection at https://www.nrc.gov/reading-rm/adams.html. To begin the search, select ``Begin Web-based ADAMS 
Search.'' For problems with ADAMS, please contact the NRC's Public 
Document Room (PDR) reference staff at 1-800-397-4209, at 301-415-4737, 
or by email to [email protected]. The AI/ML general solicitation 
request for comment is also available in ADAMS under Accession No. 
ML21085A611.
     Attention: The PDR, where you may examine and order copies 
of public documents, is currently closed. You may submit your request 
to the PDR via email at [email protected] or call 1-800-397-4209 or 
301-415-4737, between 8:00 a.m. and 4:00 p.m. (EST), Monday through 
Friday, except Federal holidays.

B. Submitting Comments

    The NRC encourages electronic comment submission through the 
Federal Rulemaking website (https://www.regulations.gov). Please 
include Docket ID NRC-2021-0048 in your comment submission.
    The NRC cautions you not to include identifying or contact 
information that you do not want to be publicly disclosed in your 
comment submission. The NRC will post all comment submissions at 
https://www.regulations.gov as well as enter the comment submissions 
into ADAMS. The NRC does not routinely edit comment submissions to 
remove identifying or contact information.
    If you are requesting or aggregating comments from other persons 
for submission to the NRC, then you should inform those persons not to 
include identifying or contact information that they do not want to be 
publicly disclosed in their comment submission. Your request should 
state that the NRC does not routinely edit comment submissions to 
remove such information before making the comment submissions available 
to the public or entering the comment into ADAMS.

II. Discussion

    The NRC is exploring the potential for advanced computational and 
predictive capabilities involving AI and ML in the various phases of 
nuclear power generation operational experience and plant management. 
The NRC is soliciting comments 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.

III. Specific Request for Comment

    The NRC requests comments from the public, the nuclear industry and 
other stakeholders, as well as other interested individuals and 
organizations. The focus of this request is to gather information that 
will provide the NRC staff with a better understanding of current usage 
and future trends in AI and ML in the commercial nuclear power 
industry.

IV. Requested Information and Comments

    AI and ML are emerging, analytical tools, which, if used properly, 
show promise in their ability to improve reactor safety, yet offer 
economic savings. The NRC requests comments on issues listed below in 
this solicitation to enhance the NRC's understanding of the short- and 
long-term applications of AI

[[Page 20745]]

and ML in nuclear power industry operations and management, as well as 
potential pitfalls and challenges associated with their application.
    1. What is status of the commercial nuclear power industry 
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? When are the tools currently under development 
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 to commercial nuclear power 
operations of incorporating AI/ML in terms of (a) design or operational 
automation, (b) preventive maintenance trending, and (c) improved 
reactor operations staff productivity?
    4. What AI/ML methods are either currently being used or will be in 
the near future in commercial nuclear plant management and operations? 
Example 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 
commercial 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 effect 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, offsite networks?

    Dated: April 15, 2021.

    For the Nuclear Regulatory Commission.
Mehdi Reisi Fard,
Chief, Performance and Reliability Branch, Division of Risk Analysis, 
Office of Nuclear Regulatory Research.
[FR Doc. 2021-08177 Filed 4-20-21; 8:45 am]
BILLING CODE 7590-01-P