2022
DOI: 10.2172/1847070
|View full text |Cite
|
Sign up to set email alerts
|

Exploring Advanced Computational Tools and Techniques with Artificial Intelligence and Machine Learning in Operating Nuclear Plants

Abstract: This report presents the project Idaho National Laboratory conducted for the Nuclear Regulatory Commission (NRC) to explore the advanced computational tools and techniques, such as artificial intelligence (AI) and machine learning (ML), for operating nuclear plants. The report reviews the nuclear data sources, with the focus on operating experience data, that could be applied by advanced computational tools and techniques. Plant-specific and generic (national and international) data from different sources are … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
15
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5
1

Relationship

0
6

Authors

Journals

citations
Cited by 6 publications
(15 citation statements)
references
References 85 publications
0
15
0
Order By: Relevance
“…Although not without delays and growing pains, recent developments are encouraging. Updates central to digitalization efforts have included smart sensors and gauges, data tracking devices, EWPs, and DIs (Ma et al, 2022;Oxstrand, 2022). These efforts now provide information that was either previously manually recorded or not recorded at all.…”
Section: Approachmentioning
confidence: 99%
“…Although not without delays and growing pains, recent developments are encouraging. Updates central to digitalization efforts have included smart sensors and gauges, data tracking devices, EWPs, and DIs (Ma et al, 2022;Oxstrand, 2022). These efforts now provide information that was either previously manually recorded or not recorded at all.…”
Section: Approachmentioning
confidence: 99%
“…As a result, however, the licensees have also opted to discontinue use of the NRC-endorsed approach in NUMARC 93-01 (NEI 2011) for meeting requirements in 10 CFR 50.65. As such, NRC resident inspectors are tasked with understanding the underlying technologies employed in these new approaches (e.g., AI, ML, and data analytical tools) to ensure the adequate inspection of the licensee's ability to meet the requirements in 10 CFR 50.65 [20].…”
Section: Monitormentioning
confidence: 99%
“…ML is also being used to support nuclear data [68]. For more examples, see the comprehensive report INL prepared for the NRC, which consists of an industry survey and overview of AI and ML for nuclear applications [20].…”
Section: Figure 5 Relative Value and Complexity Of Different Types Of...mentioning
confidence: 99%
“…These two problems are even more significant than any technical development issues of predictive models. In NUREG/CR-7294 [106], the NRC has explored existing state of technology of AI/ML models. Repeated throughout the report is the issue of data quality, quantity, applicability, and uncertainty.…”
Section: Challenges Associated With Ai/ml Deployment and Risk Analysismentioning
confidence: 99%
“…Particularly, the "black box" nature of ML/AI brings challenges with respect to the trustworthiness and transparency of the results in nuclear industry. This challenge makes the deployment of ML/AI-guided applications difficult to satisfy the regulatory requirements of NRC [106]. This leads to the first proposed problem that existing regulation has not yet addressed.…”
Section: Challenges Associated With Ai/ml Deployment and Risk Analysismentioning
confidence: 99%