数值核反应堆大数据及其应用

doi:10.11959/j.issn.2096-0271.2021048

Abstract

Abstract:

The massive amount of data involved in the operation of numerical nuclear reactor (numerical reactor) can be used to optimize existing numerical reactor models, obtain scientific discoveries in the field of nuclear energy, and promote numerical reactor research.Based on the review of the existing data-driven modeling and the prediction of microscopic phenomena in reactors, the concept of the big data of numerical nuclear reactor was put forward, and its important characteristics as industrial and simulation big data were analyzed according to the characteristics of the field of nuclear energy.Taking China virtual reactor 1.0 (CVR 1.0) as an example, starting from the variety, dependency and inaccuracy of the big data of numerical nuclear reactor, the research work of modeling optimization and scientific discovery was carried out by using the multidisciplinary techniques such as neural network, mathematical statistics and numerical analysis, which illustrates the guiding role of the characteristics of the big data of numerical nuclear reactors in numerical reactor research.

Key words: big data of numerical nuclear reactor, industrial big data, numerical nuclear reactor, big data mining

CLC Number:

TP274

An WANG, Shuai REN, Xue MIAO, Lingyu DONG, Ying ZHU, Dandan CHEN, Changjun HU. Big data of numerical nuclear reactor and its application[J]. Big Data Research, 2021, 7(5): 40-56.

Figures/Tables 16

References 43

[1]	邓力, 史敦福, 李刚 . 数值反应堆多物理耦合关键技术[J]. 计算物理, 2016,33(6): 631-638.
	DENG L , SHI D F , LI G . Key technologies of coupling for multiphysics in numerical reactor[J]. Chinese Journal of Computational Physics, 2016,33(6): 631-638.
[2]	杨文, 胡长军, 刘天才 ,等. 数值反应堆及CVR1.0研究进展[J]. 原子能科学技术, 2019,53(10): 1821-1832.
	YANG W , HU C J , LIU T C ,et al. Research progress of China virtual reactor (CVR1.0)[J]. Atomic Energy Science and Technology, 2019,53(10): 1821-1832.
[3]	HADAD K , PIROUZMAND A , AYOOBIAN N . Cellular neural networks (CNN) simulation for the TN approximation of the time dependent neutron transport equation in slab geometry[J]. Annals of Nuclear Energy, 2008,35(12): 2313-2320.
[4]	LONG Z C , LU Y P , MA X Z ,et al. PDENet:learning PDEs from data[C]// Proceedings of the 35th International Conference on Machine Learning.[S.l.:s.n.], 2018: 3208-3216.
[5]	VYAWAHARE V A , ESPINOSA-PAREDES G , DATKHILE G ,et al. Artificial neural network approximations of linear fractional neutron models[J]. Annals of Nuclear Energy, 2018,113: 75-88.
[6]	TANO M E , RAGUSA J C . SweepNet:an artificial neural network for radiation transport solves[J]. Journal of Computational Physics, 2021,426: 109757.
[7]	CHAN-WAI-NAM Q , MIKAEL J , WARIN X . Machine learning for semi linear PDEs[J]. Journal of Scientific Computing, 2019,79(3): 1667-1712.
[8]	HURé C , PHAM H , WARIN X . Some machine learning schemes for highdimensional nonlinear PDEs[J]. arXiv preprint,2019,arXiv:1902.01599..
[9]	RAISSI M , KARNIADAKIS G E . Hidden physics models:machine learning of nonlinear partial differential equations[J]. Journal of Computational Physics, 2018,357: 125-141.
[10]	DURAISAMY K , IACCARINO G , XIAO H . Turbulence modeling in the age of data[J]. Annual Review of Fluid Mechanics, 2019,51(1): 357-377.
[11]	LING J L , KURZAWSKI A , TEMPLETON J . Reynolds averaged turbulence modelling using deep neural networks with embedded invariance[J]. Journal of Fluid Mechanics, 2016,807: 155-166.
[12]	TRACEY B D , DURAISAMY K , ALONSO J J . A machine learning strategy to assist turbulence model development[C]// Proceedings of the 53rd AIAA Aerospace Sciences Meeting. Reston:American Institute of Aeronautics and Astronautics, 2015.
[13]	HUANG K , KRüGENER M ,, BROWN A ,et al. Machine learning-based optimal mesh generation in computational fluid dynamics[J]. arXiv preprint,2021,arXiv:2102.12923.
[14]	PODRYABINKIN E V , TIKHONOV E V , SHAPEEV A V ,et al. Accelerating crystal structure prediction by machinelearning interatomic potentials with active learning[J]. Physical Review B, 2019,99(6): 064114.
[15]	PILANIA G , WANG C C , JIANG X ,et al. Accelerating materials property predictions using machine learning[J]. Scientific Reports, 2013,99, 2810.
[16]	JIA W L , WANG H , CHEN M H ,et al. Pushing the limit of molecular dynamics with ab initio accuracy to 100 million atoms with machine learning[J]. arXiv preprint,2020,arXiv:2005.00223.
[17]	ALBARQI M , ALSULAMI R , GRAHAM J . Automated data processing of neutron depth profiling spectra using an artificial neural network[J]. Nuclear Instruments and Methods in Physics Research Section A:Accelerators,Spectrometers,Detectors and Associated Equipment, 2020,953: 163217.
[18]	CAO C L , GAN Q , SONG J ,et al. A twostep neutron spectrum unfolding method for fission reactors based on artificial neural network[J]. Annals of Nuclear Energy, 2020,139: 107219.
[19]	UPADHYAYA B R , ERYUREK E . Application of neural networks for sensor validation and plant monitoring[J]. Nuclear Technology, 1992,97(2): 170-176.
[20]	ZAVALJEVSKI N , GROSS K C . Support vector machines for nuclear reactor state estimation[R]. 2000.
[21]	陈涵瀛, 高璞珍, 谭思超 . 摇摆流动不稳定性的遗传算法优化神经网络预测[J]. 原子能科学技术, 2015,49(2): 273-278.
	CHEN H Y , GAO P Z , TAN S C . Prediction of flow instability under rolling motion based on neural network optimized by genetic algorithm[J]. Atomic Energy Science and Technology, 2015,49(2): 273-278.
[22]	张大林, 陈宇彤, 梁禹 ,等. 一种基于机器学习的棒束子通道热工水力特性预测方法:CN111081400A[P].2020-04-28.
	ZHANG D L , CHEN Y T , LIANG Y ,et al. Rod bundle sub-channel thermal hydraulic characteristic prediction method based on machine learning:CN111081400A[P].2020-04-28.
[23]	GóMEZ-BOMBARELLI R , ASPURUGUZIK A . Machine learning and bigdata in computational chemistry[M]// Handbook of materials modeling. Cham: Springer International Publishing, 2018: 1-24.
[24]	BUTLER K T , DAVIES D W , CARTWRIGHT H ,et al. Machine learning for molecular and materials science[J]. Nature, 2018,559(7715): 547-555.
[25]	GASPAROTTO P , CERIOTTI M . Recognizing molecular patterns by machine learning:an agnostic structural definition of the hydrogen bond[J]. The Journal of Chemical Physics, 2014,141(17): 174110.
[26]	ISAYEV O , FOURCHES D , MURATOV E N ,et al. Materials cartography:representing and mining materials space using structural and electronic fingerprints[J]. Chemistry of Materials, 2015,27(3): 735-743.
[27]	CERIOTTI M . Unsupervised machine learning in atomistic simulations,between predictions and understanding[J]. The Journal of Chemical Physics, 2019,150(15): 150901.
[28]	TORDA A E , VAN GUNSTEREN W F . Algorithms for clustering molecular dynamics configurations[J]. Journal of Computational Chemistry, 1994,15(12): 1331-1340.
[29]	KARPEN M E , TOBIAS D J , BROOKS C L . Statistical clustering techniques for the analysis of long molecular dynamics trajectories:analysis of 2.2-ns trajectories of YPGDV[J]. Biochemistry, 1993,32(2): 412-420.
[30]	HILL C . Summary report of the 6th biennial technical meeting,in:international atomic and molecular code centres network meeting on database services for radiation damage in nuclear materials[R]. 2019.
[31]	BHARDWAJ U , SAND A E , WARRIER M . Classification of clusters in collision cascades[J]. Computational Materials Science, 2020,172:109364.
[32]	BHARDWAJ U , SAND A E , WARRIER M . Graph theory based approach to characterize self interstitial defect morphology[J]. Computational Materials Science, 2021,195:110474.
[33]	STOLLER R E . Primary radiation damage formation[M]// Comprehensive nuclear materials. Amsterdam: Elsevier, 2012: 293-332.
[34]	VON TOUSSAINT U , DOMíNGUEZGUTIéRREZ F J , COMPOSTELLA M ,et al. FaVAD:a software workflow for characterization and visualizing of defects in crystalline structures[J]. Computer Physics Communications, 2021,262:107816.
[35]	GORYAEVA A M , LAPOINTE C , DAI C ,et al. Reinforcing materials modelling by encoding the structures of defects in crystalline solids into distortion scores[J]. Nature Communications, 2020,11(1): 4691.
[36]	HINSEN K . The approximation tower in computational science:why testing scientific software is difficult[J]. Computing in Science ＆ Engineering, 2015,17(4): 72-77.
[37]	单浩栋, 徐李, 胡赟 ,等. 三维高保真特征线程序ANT-MOC的开发与测试[J]. 核动力工程, 2020,41(S1): 1-5.
	SHAN H D , XU L , HU Y ,et al. Development and verification of three-dimensional MOC code ANT-MOC[J]. Nuclear Power Engineering, 2020,41(S1): 1-5.
[38]	TAKEDA T , IKEDA H . 3-D neutron transport benchmarks[J]. Journal of Nuclear Science and Technology, 1991,28(7): 656-669.
[39]	张雷, 许磊, 杜云涛 ,等. 一种基于三维R树的时空数据的存储及检索和更新方法:CN110532255A[P].2019-12-03.
	ZHANG L , XU L , DU Y T ,et al. Threedimensional R tree-based spatio-temporal data storage,retrieval and updating method:CN110532255A[P].2019-12-03.
[40]	汪学锋, 李锋, 周炜 ,等. 流固耦合网格插值方法研究[J]. 船舶力学, 2009,13(4): 571-578.
	WANG X F , LI F , ZHOU W ,et al. Research on grid interpolation method of fluidstructure coupling[J]. Journal of Ship Mechanics, 2009,13(4): 571-578.
[41]	MONGE A E , ELKAN C . An efficient domain-independent algorithm for detecting approximately duplicate database records[C]// Proceedings of the Workshop on Research Issues on Data Mining and Knowledge Discovery.[S.l.:s.n.], 1997.
[42]	ETIENNE A , HERNáNDEZ-MAYORAL M , GENEVOIS C ,et al. Dislocation loop evolution under ion irradiation in austenitic stainless steels[J]. Journal of Nuclear Materials, 2010,400(1): 56-63.
[43]	AUGER P , PAREIGE P , AKAMATSU M ,et al. APFIM investigation of clustering in neutron-irradiated FeCu alloys and pressure vessel steels[J]. Journal of Nuclear Materials, 1995,225: 225-230.

Metrics

Recommended 0

No Suggested Reading articles found!

模型	原子体系	总势能/J	总势能相对偏差	计算时间/min
EAM	FeCu	1.449 0	-	20.332
AIPM	FeCu	1.459 2	0.7%	8.876

数据名称	取值
方位角数量x_a/个	4、12、20、28、36
平面轨迹间距x_l/cm	0.009 75、0.025、0.05、0.075、0.1
极角数量x_p/个	2、6、10、14、18
轴向轨迹间距x_z/cm	0.025、0.05、0.075、0.1

参数	取值
相关系数R	0.743 43
校正的拟合优度R²	0.549 07
标准误差	0.052 20
F统计量	152.899 76
F检验的P值	4.64×10^-85

变量	t统计量	t检验的P值	参数标准误差
方位角数量x_a/个	-5.468 06	7.23×10^-8	0.000 21
平面轨迹间距x_l/cm	0.230 65	0.817 68	0.071 36
极角数量x_p/个	-24.115 46	1.49×10^-85	0.000 41
轴向轨迹间距x_z/cm	-0.301 09	0.763 47	0.083 52

实验组	棒数/根	燃料棒半径r₁/mm	绕丝半径r₂/mm	相邻棒圆心距D/mm	棒与绕丝圆心距d/mm	流道长L/mm	流道宽I/mm	流道高H/mm	流体顶点量/个	固体顶点量/个
组1	2	3	0.475	6.95	3.3	15	8.5	10	309 408	2 304
组2	2	3	0.475	6.95	3.3	15	8.5	50	1 628 544	10 944
组3	2	3	0.475	6.95	3.3	15	8.5	100	3 270 016	21 888
组4	2	3	0.475	6.95	3.3	15	8.5	150	4 944 192	32 640
组5	4	3	0.475	6.95	3.3	15	15	100	6 220 096	43 776
组6	6	3	0.475	6.95	3.3	21.95	15	100	9 470 048	65 664

Big data of numerical nuclear reactor and its application

RichHTML

PDF下载

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 16

References 43

Related Articles 8

Metrics

Recommended 0

[1]	Xiaoou DING, Hongzhi WANG, Shengjian YU. Data quality management of industrial temporal big data [J]. Big Data Research, 2019, 5(6): 19-29.
[2]	Yuhang YAO, Junjie OU, Yang LI, Luoyi FU, Xinbing WANG, Guihai CHEN. Turing index:cross-domain and cross-generation metric of unraveling scholars’ impact in academic big data [J]. Big Data Research, 2019, 5(5): 25-37.
[3]	Guang LI, Xin YANG. An industrial big data application research using deep learning [J]. Big Data Research, 2018, 4(5): 3-14.
[4]	Hongzhi WANG, Zhiyu LIANG, Jianzhong LI, Hong GAO. Survey on industrial big data analysis:models and algorithms [J]. Big Data Research, 2018, 4(5): 62-79.
[5]	Xin ZHAO, Dezhi WU, Zhizhong ZHOU. Big data mining and application of concrete pumping machinery [J]. Big Data Research, 2018, 4(4): 64-75.
[6]	Jianmin WANG. Survey on industrial big data [J]. Big Data Research, 2017, 3(6): 3-14.
[7]	Aijin YUAN, Binnan YUE, Xin YAN, Jian HUANG. Application and practice of industrial big data [J]. Big Data Research, 2017, 3(6): 27-41.
[8]	Shuquan ZHENG,Haihuan QIN,Qian WANG. Industrial big data technologies and architecture [J]. Big Data Research, 2017, 3(4): 67-80.