Draft:Artificial Intelligence Applied to Moisture Carryover
Submission declined on 2 February 2025 by Significa liberdade (talk).
Where to get help
How to improve a draft
You can also browse Wikipedia:Featured articles and Wikipedia:Good articles to find examples of Wikipedia's best writing on topics similar to your proposed article. Improving your odds of a speedy review To improve your odds of a faster review, tag your draft with relevant WikiProject tags using the button below. This will let reviewers know a new draft has been submitted in their area of interest. For instance, if you wrote about a female astronomer, you would want to add the Biography, Astronomy, and Women scientists tags. Editor resources
|  |
Comment: This article has a 95.9% AI-generation score according to https://wikipedia.gptzero.me/. Significa liberdade (she/her) (talk) 20:30, 2 February 2025 (UTC)
Introduction
[edit]Artificial Intelligence (AI) is being applied to the nuclear power industry, particularly in addressing carryover with steam (a.k.a. - "moisture carryover") (MCO) issues in boiling water reactors (BWRs). This article focuses on the use of AI techniques to predict and reduce high moisture carryover, which is a challenge in nuclear power plant operations.
Background
[edit]MCO refers to the weight percentage of entrained moisture in the steam leaving a nuclear reactor's moisture separator. High MCO can lead to several operational issues in nuclear power plants, including:
- Increased dose rates in the water-steam cycle
- Potential erosion of turbine components
- Possible erosion of internal surfaces of Main Steam Isolation Valves (MSIVs)
- Reduction in electrical output
- Increased fuel costs due to higher reload fuel quantities[1][2]
AI Application in MCO Prediction
[edit]In 2021, Exelon Corporation, now Constellation Energy, implemented an AI technique called neural networks to address high moisture carryover in BWRs. This approach uses machine learning to find complex patterns in large datasets, enabling more accurate MCO predictions.[1] The neural network model uses supervised learning for regression to predict MCO. It employs feature engineering to reduce the input feature space to key drivers of MCO by using a "canonical set" of a few dozen key variables that capture MCO dynamics.[2]
Application to Core Design
[edit]The AI-based model enhances nuclear reactor fuel cycle planning by enabling core designers to explore hundreds of potential configurations for bundle specifications, reload batch sizes, loading patterns, and reactivity control strategies. By leveraging predictive analytics, the system provides increasingly reliable forecasts of maximum core operating behavior up to a year in advance, allowing for proactive decision-making. This optimization capability facilitates reductions in reload batch size and fuel enrichment while ensuring MCO levels remain within prescribed safety limits, ultimately improving fuel efficiency and meeting regulated energy output requirements.[2]
Benefits of AI in MCO Management
[edit]The application of AI in moisture carryover management offers several advantages:
- Improved Efficiency: AI integration can significantly enhance the overall efficiency of nuclear power plants.[3]
- Better Decisions: Increased confidence for engineers and management in decision-making.
- Cost Reduction: By optimizing fuel usage and reducing wear on components, AI-driven MCO management can lead to substantial cost savings.
- Enhanced Safety: Better prediction and control of MCO can reduce radiation exposure and improve plant safety.[1]
Regulatory Considerations
[edit]As AI technologies become more prevalent in nuclear applications, regulatory bodies are developing frameworks to ensure their safe and secure implementation. The U.S. Nuclear Regulatory Commission (NRC), along with international counterparts, has outlined principles for the deployment of AI in nuclear facilities. Key considerations include:
- Ensuring continued safe and secure operation of nuclear facilities
- Addressing challenges arising from fast-developing AI technologies
- Developing appropriate guidance for AI system evaluation and deployment[4][5]
Future Prospects
[edit]The successful application of AI in moisture carryover management demonstrates the potential for broader AI integration in nuclear power plant operations. Future developments may include:
- Expansion of AI techniques to other operational challenges
- Further refinement of predictive models
- Integration with other smart technologies for comprehensive plant management
As the nuclear industry continues to explore AI applications, moisture carryover management serves as an example of how these technologies can address long-standing operational challenges and improve overall plant performance.[6]
References
[edit]- ^ a b c "Delivering the Nuclear Promise Top Innovative Practice" (PDF).
- ^ a b c "Powering our nuclear fleet with artificial intelligence".
- ^ "The use of Artificial Intelligence in the nuclear sector".
- ^ "CONSIDERATION FOR DEVELOPING ARTIFICIAL INTELLIGENCE SYSTEMS IN NUCLEAR APPLICATIONS" (PDF).
- ^ "REGULATORY FRAMEWORK GAP ASSESSMENT FOR THE USE OF ARTIFICIAL INTELLIGENCE IN NUCLEAR APPLICATIONS" (PDF).
- ^ "A review of the application of artificial intelligence to nuclear reactors: Where we are and what's next". PMC 9988575.
{{cite web}}: Missing or empty|url=(help)
- Promotional tone, editorializing and other words to watch
- Vague, generic, and speculative statements extrapolated from similar subjects
- Essay-like writing
- Hallucinations (plausible-sounding, but false information) and non-existent references
- Close paraphrasing
Please address these issues. The best way to do it is usually to read reliable sources and summarize them, instead of using a large language model. See our help page on large language models.