[KSCI] Korea Science Citation Index Service

http://dx.doi.org/10.1016/j.net.2021.05.037

Machine learning of LWR spent nuclear fuel assembly decay heat measurements

Ebiwonjumi, Bamidele (Department of Nuclear Engineering, Ulsan National Institute of Science and Technology)
Cherezov, Alexey (Department of Nuclear Engineering, Ulsan National Institute of Science and Technology)
Dzianisau, Siarhei (Department of Nuclear Engineering, Ulsan National Institute of Science and Technology)
Lee, Deokjung (Department of Nuclear Engineering, Ulsan National Institute of Science and Technology)

Publication Information

Nuclear Engineering and Technology / v.53, no.11, 2021 , pp. 3563-3579 More about this Journal

Abstract

Measured decay heat data of light water reactor (LWR) spent nuclear fuel (SNF) assemblies are adopted to train machine learning (ML) models. The measured data is available for fuel assemblies irradiated in commercial reactors operated in the United States and Sweden. The data comes from calorimetric measurements of discharged pressurized water reactor (PWR) and boiling water reactor (BWR) fuel assemblies. 91 and 171 measurements of PWR and BWR assembly decay heat data are used, respectively. Due to the small size of the measurement dataset, we propose: (i) to use the method of multiple runs (ii) to generate and use synthetic data, as large dataset which has similar statistical characteristics as the original dataset. Three ML models are developed based on Gaussian process (GP), support vector machines (SVM) and neural networks (NN), with four inputs including the fuel assembly averaged enrichment, assembly averaged burnup, initial heavy metal mass, and cooling time after discharge. The outcomes of this work are (i) development of ML models which predict LWR fuel assembly decay heat from the four inputs (ii) generation and application of synthetic data which improves the performance of the ML models (iii) uncertainty analysis of the ML models and their predictions.

Keywords

Decay heat; Spent nuclear fuel; Machine learning; Light water reactor; Synthetic data; Uncertainty analysis;

Citations & Related Records

Reference

1	W. Huang, Y. Nakamori, S.Y. Wang, Forecasting stock market movement direction with support vector machine, Comput. Oper. Res. 32 (2005) 2513-2522. DOI
2	K. Trontl, D. Pevec, T. Smuc, Machine Learning of the reactor core loading pattern critical parameters, Sci. Tech. Nuc. Install. 2008 (2008) 695153.
3	G. An, The effects of adding noise during backpropagation training on a generalization performance, Neural Comput. 8 (1996) 643-674. DOI
4	B. Nowok, G. Raab, C. Dibben, Synthpop: bespoke creation of synthetic data in R, J. Stat. Software 74 (2016) 1-26.
5	H. Surendra, H.S. Mohan, A review of synthetic data generation methods for privacy preserving data publishing, Int. J. Sci. Tech. Res. 6 (2017) 95-101.
6	S. Vaccaro, S.J. Tobin, A. Favalli, B. Grogan, P. Jansson, H. Liljenfeldt, V. Mozin, J. Hu, P. Schwalbach, A. Sjoland, H. Trellue, D. Vo, PWR and BWR spent fuel assembly gamma spectra measurements, Nucl. Instrum. Methods Phys. Res. A 833 (2016) 208-225. DOI
7	B. Ebiwonjumi, C. Kong, P. Zhang, C. Alexey, D. Lee, Uncertainty quantification of PWR Spent Fuel due to nuclear data and modeling parameters, Nucl. Eng. Tech. (2021), https://doi.org/10.1016/j.net.2020.07.012 article in press. DOI
8	H. Ping, J. Stoyanovich, B. Howe, DataSynthesizer: privacy-preserving synthetic datasets, in: 29th International Conference on Scientific and Statistical Database Management, June 27-29, 2017. Chicago, IL, USA.
9	G. Ilas, H. Liljenfeldt, Decay heat uncertainty for BWR used fuel due to modeling and nuclear data uncertainties, Nucl. Eng. Des. 319 (2017) 176-184. DOI
10	J. Yang, X. Yu, Z.Q. Xie, J.P. Zhang, A novel virtual sample generation method based on Gaussian distribution, Knowl. Base Syst. 24 (2011) 740-748. DOI
11	C. Lataniotis, D. Wicaksono, S. Marelli, B. Sudret, UQLab User Manual - Kriging (Gaussian Process Modeling), Chair of Risk, Safety and Uncertainty Quantification, ETH Zurich, Switzerland, 2019. Report # UQLab-V1.3-105.
12	M. Moustapha, C. Lataniotis, S. Marelli, B. Sudret, UQLab User Manual - Support Vector Machines for Regression, Chair of Risk, Safety and Uncertainty Quantification, ETH Zurich, Switzerland, 2019. Report # UQLab-V1.3-111.
13	P. Jansson, A. Hakansson, A. Backlin, S. Jacobsson, Gamma ray spectroscopy measurements of decay heat in spent nuclear fuel, Nucl. Sci. Eng. 141 (2002) 129-139. DOI
14	B. Ebiwonjumi, D. Lee, Bayesian method and polynomial chaos expansion based inverse uncertainty quantification of spent fuel using decay heat measurements, Nucl. Eng. Des. 378 (2021) 11158.
15	D.A. Van Dyk, X.L. Meng, The art of data augmentation, J. Comput. Graph Stat. 10 (2012) 1-50. DOI
16	M. Sabatino, M. Fabiani, M. Bozovic, S. Garzoli, L. Antonini, M.E. Marcocci, A.T. Palamara, G. De Chiara, R. Ragno, R. Experimental data based machine learning classification models with predictive ability to select in vitro active antiviral and non-toxic essential oils, Molecules 25 (2020) 2452. DOI
17	SKB, Measurements of Decay Heat in Spent Nuclear Fuel at Swedish Interim Storage Facilit, in: Y, CLAB. Svensk Karnbranslehantering AB (SKB), Swedish Nuclear Fuel and Waste Management Co., 2006, pp. R-05-62.
18	B.D. Murphy, I.C. Gauld, Spent Fuel Decay Heat Measurements Performed at the Swedish Central Interim Storage Facility, US Nuclear Regulatory Commission, Technical Report, 2010. NUREG/CR-6971.
19	G. Ilas, I.C. Gauld, H. Liljenfeldt, Validation of ORIGEN for LWR used fuel decay heat analysis with SCALE, Nucl. Eng. Des. 273 (2014) 58-67. DOI
20	G. Ilas, I.C. Gauld, SCALE analysis of CLAB decay heat measurements for LWR spent fuel assemblies, Ann. Nucl. Energy 35 (2008) 37-48. DOI
21	C.M. Bishop, Training with noise is equivalent to Tikhonov regularization, Neural Comput. 7 (1995) 108-116. DOI
22	T. Shaikhina, N. Khovanova, Handling limited datasets with neural networks in medical applications: a small-data approach, Artif. Intell. Med. 75 (2017) 51-63. DOI
23	P. Cunningham, J. Carney, S. Jacob, Stability problems with artificial neural networks and the ensemble solution, Artif. Intell. Med. 20 (2000) 217-225. DOI
24	I. Bose, R.K. Mahapatra, Business data mining - a machine learning perspective, Inf. Manag. 39 (2001) 211-225. DOI
25	Y. LeCun, L. Bottou, Y. Bengio, P. Haffner, Gradient-based learning applied to document recognition, Proc. IEEE 86 (1998) 2278-2324. DOI
26	J.R. Dorronsoro, F. Ginel, C. Sanchez, C.S. Cruz, Neural fraud detection in credit card operations, IEEE Trans. Neural Network. 8 (1997) 827-834. DOI
27	C. Willman, A. Hakansson, O. Osifo, A. Backlin, S.J. Svard, Nondestructive assay of spent nuclear fuel with gamma-ray spectroscopy, Ann. Nucl. Energy 33 (2006) 427-438. DOI
28	OECD/NEA, Evaluation Guide for the Evaluated Spent Nuclear Fuel Assay Database (SFCOMPO), Organization for Economic Cooperation and Development, Nuclear Energy Agency, Nuclear Science Committee, Working Party on Nuclear Criticality Safety, NEA/NSC/R, 2016, p. 8 (2015).
29	S.S. Lee, Noisy replication in skewed binary classification, Comput. Stat. Data Anal. 34 (2000) 165-191. DOI
30	S. Choi, C. Lee, D. Lee, Resonance treatment using pin-based pointwise energy slowing-down method, J. Comput. Phys. 330 (2017) 137-155.
31	M.H. Beale, M.T. Hagan, H.B. Denmuth, Deep Learning Toolbox User's Guide, The MathWorks, Inc., 2018.
32	S. Alfeo, H. Laurie, B. Vivek, J.S. Karen, Overcoming small data limitations in heart disease prediction by using surrogate data, SMU Data Science Review 1 (3) (2018), 12. Available at: https://scholar.smu.edu/datasciencereview/vol1/iss3/12. (Accessed 15 July 2020).
33	N.V. Chawla, K.W. Bowyer, L.O. Hall, W.P. Kegelmeyer, SMOTE: synthetic minority over-sampling technique, J. Artif. Intell. Res. 16 (2002) 321-357. DOI
34	Z. Ceylan, B. Sungur, Estimation of coal elemental composition from proximate analysis using machine learning techniques, Energy Sources, Part A Recovery, Util. Environ. Eff. 38 (2020) 1-11.
35	A. Hsu, B. Cheng, P.A. Bradley, Analysis of NIF scaling using physics informed machine learning, Phys. Plasmas 27 (2020), 012703. DOI
36	P. Sadowski, Deep Learning for Experimental Physics, (PhD Thesis), University of California, Irvine, 2016.
37	T. Shaikhina, D. Lowe, S. Daga, D. Briggs, R. Higgins, N. Khovanova, Machine learning for predictive modelling based on small data in biomedical engineering, IFAC-Papers Online 48 (2015) 469-474.
38	J. Hoffmann, Y. Bar-Sinai, L.M. Lee, J. Andrejevic, S. Mishra, S.M. Rubinstein, C.H. Rycroft, Machine learning in a data-limited regime: augmenting experiments with synthetic data uncovers order in crumpled sheets, Sci. Adv. 5 (2019), eaau6792. DOI
39	A. Smith, A. Keane, J.A. Dumesic, G.W. Huber, V.M. Zavala, A machine learning framework for the analysis and prediction of catalytic activity from experimental data, Appl. Catal. B Environ. 263 (2020) 118257. DOI
40	T.R. Willemain, R.A. Bress, L.S. Halleck, Enhanced simulation inference using bootstraps of historical inputs, IIE Trans. 35 (2003) 851-862. DOI
41	F. Khoshahval, S. Yum, H.C. Shin, J. Choe, P. Zhang, D. Lee, Smart sensing of the axial power and offset in NPPs using GMDH method, Ann. Nucl. Energy 121 (2018) 77-88. DOI
42	P. Grechanuk, M.E. Rising, T.S. Palmer, Using machine learning methods to predict bias in nuclear criticality safety, J. of Comput. Theoretical Transport 47 (2018) 552-565. DOI
43	M.G. Fernandez, A. Tokuhiro, K. Welter, Q. Wu, Nuclear energy system's behavior and decision making using machine learning, Nucl. Eng. Des. 324 (2017) 27-34. DOI
44	J.J. Ortiz, A. Castillo, J.L. Montes, R. Perusquia, J.L. Hernandez, Nuclear fuel lattice optimization using neural networks and a fuzzy logic system, Nucl. Sci. Eng. 162 (2009) 148-157. DOI
45	A. Pirouzmand, M.K. Dehdashti, Estimation of relative power distribution and power peaking factor in a VVER-1000 reactor core using artificial neural networks, Prog. Nucl. Energy 85 (2015) 17-27. DOI
46	I.H. Bae, M.G. Na, Y.J. Lee, G.C. Park, Calculation of the power peaking factor in a nuclear reactor using support vector regression models, Ann. Nucl. Energy 35 (2008) 2200-2205. DOI
47	M.G. Park, H.C. Shin, Reactor power shape synthesis using group method of data handling, Ann. Nucl. Energy 72 (2014) 467-470. DOI
48	E. Nissan, An overview of AI methods for in-core fuel management: tools for the automatic design of nuclear reactor core configurations for fuel reload, (re)arranging new and partly spent fuel, Design 3 (2020) 37. DOI
49	I.C. Gauld, G. Ilas, B.D. Murphy, C.F. Weber, Validation of SCALE 5 Decay Heat Predictions for LWR Spent Nuclear Fuel, US Nuclear Regulatory Commission, Technical Report, 2010. NUREG/CR-6972.
50	R.W. Mills, Decay heat calculations a study of their validation and accuracy, in: 2nd International Workshop on Nuclear Data Evaluation for Reactor (WONDER 2009), Cadarache, France, 2009, p. 152. September 29 - October 2.
51	J.J. Faraway, Practical regression and anova using R, pp. 117, 118. Available at: https://cran.r-project.org/doc/contrib/Faraway-PRA.pdf. (Accessed 27 August 2020).
52	O. Osifo, S.J. Svard, A. Hakansson, C. Willman, A. Backlin, T. Lundqvist, Verification and determination of the decay heat in spent PWR fuel by means of gamma scanning, Nucl. Sci. Eng. 160 (2008) 129-143. DOI
53	M.I. Radaideh, T. Kozlowski, Combining simulations and data with deep learning and uncertainty quantification for advanced energy modeling, Int. J. Energy Res. 43 (2019) 7866-7890. DOI
54	S. Marelli, B. Surety, UQLab: a framework for uncertainty quantification in MATLAB, in: 2nd International Conference on Vulnerability, Risk Analysis and Management, July 13-16, 2014. Liverpool, United Kingdom.