Safety analysis for integrity enhancement in nuclear power plants (NPPs) in case of seashore region site

被引:1
作者
Woo, Tae Ho [1 ]
Baek, Chang Hyun [1 ]
Jang, Kyung Bae [1 ]
机构
[1] Cyber Univ Korea, Dept Mech & Control Engn, 106 Bukchon Ro, Seoul 03051, South Korea
关键词
artificial intelligence; earthquake; Fukushima; nuclear; safety;
D O I
10.1515/kern-2022-0013
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
It is investigated for the seismic consequences in the nuclear power plant (NPP) where the radiological hazard could be one of critical issues when the safety system is in failure. The artificial learning is done during the calculations of each time step. There are the simulations for the artificial neural networking (ANN) as the precision, sensitivity (recall value), specificity, and accuracy which are 21.48%, 50.53%, 25.47%, and 32.68% respectively. Likewise, the recurrent neural network (RNN) modeling has 23.64%, 54.53%, 25.56%, and 34.17% respectively. In the comparisons for ANN and RNN, the values of ANN's parameters are lower than those of RNN in all values of precision, recall, specificity, and accuracy. As the designed factors for the nuclear matters increase, the estimations could be better in considering the conditional situations.
引用
收藏
页码:271 / 277
页数:7
相关论文
共 17 条
[1]  
[Anonymous], 2008, Advanced Data Mining Techniques
[2]   Earthquake magnitude prediction in Hindukush region using machine learning techniques [J].
Asim, K. M. ;
Martinez-Alvarez, F. ;
Basit, A. ;
Iqbal, T. .
NATURAL HAZARDS, 2017, 85 (01) :471-486
[3]   Continuous machine learning for abnormality identification to aid condition-based maintenance in nuclear power plant [J].
Ayo-Imoru, R. M. ;
Cilliers, A. C. .
ANNALS OF NUCLEAR ENERGY, 2018, 118 :61-70
[4]   Comparison of statistical and machine learning approaches to modeling earthquake damage to water pipelines [J].
Bagriacik, Adam ;
Davidson, Rachel A. ;
Hughes, Matthew W. ;
Bradley, Brendon A. ;
Cubrinovski, Misko .
SOIL DYNAMICS AND EARTHQUAKE ENGINEERING, 2018, 112 :76-88
[5]   Towards an integrated machine-learning framework for model evaluation and uncertainty quantification [J].
Buisson, Bertrand ;
Lakehal, Djamel .
NUCLEAR ENGINEERING AND DESIGN, 2019, 354
[6]   Identifying predictors of probable posttraumatic stress disorder in children and adolescents with earthquake exposure: A longitudinal study using a machine learning approach [J].
Ge, Fenfen ;
Li, Ying ;
Yuan, Minlan ;
Zhang, Jun ;
Zhang, Wei .
JOURNAL OF AFFECTIVE DISORDERS, 2020, 264 :483-493
[7]   Machine-learning based error prediction approach for coarse-grid Computational Fluid Dynamics (CG-CFD) [J].
Hanna, Botros N. ;
Dinh, Nam T. ;
Youngblood, Robert W. ;
Bolotnov, Igor A. .
PROGRESS IN NUCLEAR ENERGY, 2020, 118
[8]   Artificial intelligence in seismology: Advent, performance and future trends [J].
Jiao, Pengcheng ;
Alavi, Amir H. .
GEOSCIENCE FRONTIERS, 2020, 11 (03) :739-744
[9]   Deep-learning-based alarm system for accident diagnosis and reactor state classification with probability value [J].
Kim, Taek Kyu ;
Park, Jae Kwan ;
Lee, Byeong Hee ;
Seong, Seung Hwan .
ANNALS OF NUCLEAR ENERGY, 2019, 133 :723-731
[10]  
Lamarsh JR., 2017, Introduction to Nuclear Engineering, V4