ML24137A087
| ML24137A087 | |
| Person / Time | |
|---|---|
| Issue date: | 05/14/2024 |
| From: | Matrachisia J, Raj Iyengar NRC/RES/DE |
| To: | |
| Raj Iyengar 3014150770 | |
| References | |
| Download: ML24137A087 (14) | |
Text
Regulatory Considerations for Digital Twins for Nuclear Energy Systems Raj Iyengar and John Matrachisia U.S. Nuclear Regulatory Commission NAS Webinar - Regulatory Challenges and Approaches for Deploying Digital Twins May 16, 2024 1 The views expressed in this paper are those of the authors and do not reflect the views of the U.S. Nuclear Regulatory Commission. This material is declared a work of the U.S. Government and is not subject to copyright protection in the United States. Approved for public release; distribution is unlimited.
2 This report was prepared as an account of work sponsored by an agency of the U.S. Government. Neither the U.S. Government nor any agency thereof, nor any of their employees, makes any warranty, expressed or implied, or assumes any legal liability or responsibility for any third partys use, or the results of such use, of any information, apparatus, product, or process disclosed in this report, or represents that its use by such third party would not infringe privately owned rights. The views expressed in this paper are not necessarily those of the U.S. Nuclear Regulatory Commission.
REGULATORY IMPLICATIONS OF DIGITAL TWINS:
OBJECTIVES
- Understand the current state of digital twins (DT) technology and potential applications for the nuclear industry
- Identify and evaluate technical considerations that could benefit from regulatory guidance
- Identify and investigate potential regulatory methodologies, infrastructures, and guidance for DTs in nuclear application 2
DIGITAL TWINS: STATE OF TECHNOLOGY
- Increased interest and activity in digital twin technologies, both in the nuclear field and other industries
- Implementation of DTs in non-nuclear sectors offers significant leverage and experience to enable DT applications for nuclear energy systems
- Key digital twin enabling technologies Advanced Sensors and Instrumentation Data and Information Management Data Analytics Modeling and Simulation (AI/ML, physics-based models, data-informed models).
3
DIGITAL TWIN SYSTEM 4
DIGITAL TWIN CHARACTERISTICS & CAPABILITIES 5
DIGITAL TWINS: OPPORTUNITIES AND CHALLENGES Enabling Technology Key Challenge Advanced Sensors & Instrumentation (ASI) Building adequate ASI infrastructure Data and Information Management Developing user interfaces for data and information Data Analytics Implementing scalable, integrable data analytics AI/ML Establishing AI/ML trustworthiness and explainability Modeling and Simulation Constructing real-time, high-fidelity physics-based simulations Developing real-time, data-informed models Verifying and validating integrated models Regulatory Consideration Opportunity Information Reporting Data and report generation Operator Licensing Up-to-date and validated simulator model Component Performance Real-time condition-based monitoring and preventative maintenance Event Assessment Virtual environment event replay Safety Analysis Integrated modeling and simulation to support decision making 6
ML22192A046 Technical Letter Reports Future Focused Research Project ML23058A085 ML22235A643 ML21361A261 ML21160A074 ML21348A020 ML2108A132 Information Letters NRC Public Digital Twins Webpage 7
5 DIGITAL TWINS PROJECT Follow-on Reports 7
- Synthetic data from simulator ANOMALY DETECTION CASE STUDY Probabilistic Safety Assessment and Management (PSAM) 2023 Topical Conference on Artificial Intelligence (AI) and Risk Analysis, October 2325, 2023.
- Synthetic data from simulator
- Trained LSTM autoencoder ANOMALY DETECTION CASE STUDY Probabilistic Safety Assessment and Management (PSAM) 2023 Topical Conference on Artificial Intelligence (AI) and Risk Analysis, October 2325, 2023.
- Synthetic data from simulator
- Trained LSTM autoencoder
- Identified inserted anomalies ANOMALY DETECTION CASE STUDY Probabilistic Safety Assessment and Management (PSAM) 2023 Topical Conference on Artificial Intelligence (AI) and Risk Analysis, October 2325, 2023.
- Case studies for condition monitoring of mechanical systems and components
- Heat Pipe
- Pump
- AI/ML explainability ADDITIONAL RESEARCH IN PROGRESS INL/EXT-20-60782 Insights from these case studies will help prepare NRC staff to evaluate applications of condition monitoring to meet inservice testing requirements INL/EXT-17-43212
Planned Activities Investigate Considerations for a Graded Approach to Evaluate DT Technologies Demonstration of Applications of Digital Twins Communication and Knowledge Management 12
Key Takeaways/Messages
- The NRC regulatory framework is flexible enough to allow for the use of digital twins
- Digital twin technologies provide an opportunity for enhanced reactor safety and inspections and efficient operations
- The NRC has ongoing research to support the efficient review of applications of digital twin technologies
- Industry is encouraged to engage early with the NRC 13
THANK YOU NRC Digital Twins Public Page https://www.nrc.gov/reactors/power/digital-twins.html