DEVELOPMENT OF ARTIFICIAL INTELLIGENCE MODEL IN THE FIELD OF ATOMIC ENERGY AS A TOOL OF SUPPORT IN DECISION-MAKING

Authors

DOI:

https://doi.org/10.20535/1813-5420.3.2024.314596

Keywords:

artificial intelligence, model, neural network, nuclear energy, machine learning.

Abstract

This article focuses on developing and applying an artificial intelligence (AI) model in the field of nuclear energy, emphasizing its importance as a decision-making support tool. The current state of AI in nuclear energy is discussed, with a special focus on the creation of a proprietary classification model.

The article outlines the main stages of AI model development and its practical application for classifying events at nuclear power plants. It utilizes machine learning technology and natural language processing to develop the model. The significance and innovative approach of using AI in nuclear energy are emphasized, considering its potential in enhancing the efficiency of processes at nuclear power plants.

Results demonstrate the high efficiency (accuracy) of the developed AI model during testing for event classification. The current era of digital transformation and rapid technological development highlights the increasing importance of AI as a tool in various sectors.

Additionally, the article covers the international promotion of AI in nuclear energy, particularly by the International Atomic Energy Agency (IAEA) and the United States Nuclear Regulatory Commission (NRC). It details the efforts of these organizations in exploring the application of AI technology in nuclear technologies and regulatory activities, emphasizing safe AI use and developing strategic plans for AI applications.

In conclusion, the article suggests the model's potential application in investigating nuclear power plant events, that can be used for classifying by categories, root causes, corrective actions etc. The article concludes that while AI is a modern technology finding application in various fields including nuclear energy, it cannot fully replace human involvement in the nuclear sector. However, AI combination with human input can improve the efficiency and safety of processes at nuclear power plants.

References

R. Goutham. A beginner’s guide to understanding the buzz words -AI, ML, NLP, Deep Learning, Computer Vision, and Data Science. [Online]. Available: https://medium.com/swlh/a-beginners-guide-to-understanding-the-buzz-words-ai-ml-nlp-deep-learning-computer-vision-a877ee1c2cde.

Artificial Intelligence for Accelerating Nuclear Applications, Science and Technology. IAEA, Vienna, 2022, 100 p.

The IAEA's platform for partnership on AI. AI for Atoms: the IAEA's knowledge-sharing platform for partnership on AI applications in the nuclear field. [Online]. Available: https://nucleus.iaea.org/sites/ai4atoms/SitePages/Home.aspx.

NUREG-2261. Artificial Intelligence Strategic Plan, Fiscal Years 2023-2027. U.S. NRC, May 2023, 44 p.

Data Science and Artificial Intelligence Regulatory Applications Workshops," Conferences & Symposia, [Online]. Available: https://www.nrc.gov/public-involve/conference-symposia/data-science-ai-reg-workshops.html#1.

NUREG/CR-7294. Exploring Advanced Computational Tools and Techniques with Artificial Intelligence and Machine Learning in Operating Nuclear Plants. U.S. NRC, February 2022, 117 p.

Natural Language Processing with Probabilistic Models. DeepLearning.AI. Coursera. [Online]. URL: https://www.coursera.org/learn/probabilistic-models-in-nlp/.

L. Jiang. Visual Explanation of Gradient Descent Methods (Momentum, AdaGrad, RMSProp, Adam). Towards Data Science. [Online]. Available: https://towardsdatascience.com/a-visual-explanation-of-gradient-descent-methods-momentum-adagrad-rmsprop-adam-f898b102325c.

Licensee Event Report Search. U.S. NRC. Available: https://lersearch.inl.gov/LERSearchCriteria.aspx

NUREG-1022, Rev. 3. Event Report Guidelines 10 CFR 50.72 and 50.73, Final Report. U.S. NRC, January 2013, 107 p.

Kim-Stevens K.. Power Industry Dictionary for Text-Mining and Natural Language Processing Application: A Proof of Concept. U.S. NRC Data Science and Artificial Intelligence Regulatory Applications Workshops, June 29, 2021. [Online]. Available: https://www.nrc.gov/docs/ML2120/ML21201A373.pdf.

Published

2024-11-06

Issue

Section

TECHNOLOGIES AND EQUIPMENT IN ENERGY