Artificial intelligence-driven advances in nuclear technology: Exploring innovations, applications, and future prospects

被引:0
作者
Arhouni, Fatima Ezzahra [1 ]
Abdo, Maged Ahmed Saleh [1 ]
Ouakkas, Saad [1 ]
Bouhssa, Mohamed Lhadi [1 ]
Boukhair, Aziz [1 ,2 ]
机构
[1] Dept Phys, Lab Nucl Atom Mol Mech & Energet Phys, Radiat transfer energy waves particles, El Jadida 24000, Morocco
[2] Reg Ctr Trades Educ & Training, Casablanca Settat, Morocco
关键词
Artificial intelligence; Nuclear technology; Machine learning; Deep learning; Data analysis; Ethical considerations; NEURAL-NETWORKS; PATTERN-RECOGNITION; DIAGNOSIS; MODEL; PREDICTION; VALIDATION; SYSTEM;
D O I
10.1016/j.anucene.2024.111151
中图分类号
TL [原子能技术]; O571 [原子核物理学];
学科分类号
0827 ; 082701 ;
摘要
Artificial Intelligence (AI) is fundamentally transforming nuclear technology and energy applications by offering advanced solutions to long-standing challenges. Leveraging recent advancements in machine learning (ML) and deep learning (DL), AI enhances capabilities in data analysis, predictive modeling, and real-time decisionmaking. This study examines a brief review of how AI improves reactor design, optimizes safety protocols, and refines monitoring systems in nuclear operations. It also highlights AI's role in advancing radiation detection and supporting nuclear fusion research through enhanced pattern recognition and predictive accuracy. However, the integration of AI introduces significant ethical and technical challenges, including concerns about algorithmic biases and cybersecurity risks. The article emphasizes the necessity for interdisciplinary collaboration between AI specialists and nuclear technology experts to address these challenges effectively. Additionally, it explores the potential impact of AI on nuclear policy, safety regulations, and international agreements, stressing the importance of addressing these implications as AI technology continues to evolve in the nuclear sector.
引用
收藏
页数:15
相关论文
共 114 条
[1]   Machine learning for localization of radioactive sources via a distributed sensor network [J].
Abdelhakim, Assem .
SOFT COMPUTING, 2023, 27 (15) :10493-10508
[2]  
Ahsan S.N., 2013, Machine Learning-Based Fault Prediction System for the Primary Heat Transport System of CANDU Type Pressurized Heavy Water Reactor, P68, DOI [10.1109/ICOSST.2013.6720613, DOI 10.1109/ICOSST.2013.6720613]
[3]  
Ali A., 2023, Proceedings of SCOPE, V13, P15, DOI [10.1007/s00500-023-08447-8, DOI 10.1007/S00500-023-08447-8]
[4]   Artificial intelligence unfolding for space radiation monitor data [J].
Aminalragia-Giamini, S. ;
Papadimitriou, C. ;
Sandberg, I ;
Tsigkanos, A. ;
Jiggens, P. ;
Evans, H. ;
Rodgers, D. ;
Daglis, I. A. .
JOURNAL OF SPACE WEATHER AND SPACE CLIMATE, 2018, 8
[5]  
Attieh K., 2000, P 25 CNS CNA ANN STU
[6]  
Aymerich E., 2023, Machine Learning and Deep Learning applications for the protection of nuclear fusion devices
[7]   Deep learning for safety assessment of nuclear power reactors: Reliability, explainability, and research opportunities [J].
Ayodeji, Abiodun ;
Amidu, Muritala Alade ;
Olatubosun, Samuel Abiodun ;
Addad, Yacine ;
Ahmed, Hafiz .
PROGRESS IN NUCLEAR ENERGY, 2022, 151
[8]   Design of a Nuclear Monitoring System Based on a Multi-Sensor Network and Artificial Intelligence Algorithm [J].
Baek, Min Kyu ;
Chung, Yoon Soo ;
Lee, Seongyeon ;
Kang, Insoo ;
Ahn, Jae Joon ;
Chung, Yong Hyun .
SUSTAINABILITY, 2023, 15 (07)
[9]  
Barto A. G., 1997, Neural systems for control, P7, DOI 10.1016/B978-012526430-3/50003-9
[10]  
Batiha GES, 2022, ENVIRON SCI POLLUT R, V29, P43516, DOI [10.1007/s11356-022-20075-7, 10.23814/ethn.18.22.bat]