Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

A comparative study on applicability and efficiency of machine learning algorithms for modeling gamma-ray shielding behaviors

  • Bilmez, Bayram (Department of Physics, Faculty of Science and Art, Yildiz Technical University) ;
  • Toker, Ozan (Department of Physics, Faculty of Science and Art, Yildiz Technical University) ;
  • Alp, Selcuk (Department of Industrial Engineering, Faculty of Mechanical Engineering, Yildiz Technical University) ;
  • Oz, Ersoy (Department of Statistics, Faculty of Art and Science, Yildiz Technical University) ;
  • Icelli, Orhan (Department of Physics, Faculty of Science and Art, Yildiz Technical University)
  • Received : 2020.09.30
  • Accepted : 2021.07.18
  • Published : 2022.01.25
Download PDF
⟨ Previous Next ⟩

Abstract

The mass attenuation coefficient is the primary physical parameter to model narrow beam gamma-ray attenuation. A new machine learning based approach is proposed to model gamma-ray shielding behavior of composites alternative to theoretical calculations. Two fuzzy logic algorithms and a neural network algorithm were trained and tested with different mixture ratios of vanadium slag/epoxy resin/antimony in the 0.05 MeV-2 MeV energy range. Two of the algorithms showed excellent agreement with testing data after optimizing adjustable parameters, with root mean squared error (RMSE) values down to 0.0001. Those results are remarkable because mass attenuation coefficients are often presented with four significant figures. Different training data sizes were tried to determine the least number of data points required to train sufficient models. Data set size more than 1000 is seen to be required to model in above 0.05 MeV energy. Below this energy, more data points with finer energy resolution might be required. Neuro-fuzzy models were three times faster to train than neural network models, while neural network models depicted low RMSE. Fuzzy logic algorithms are overlooked in complex function approximation, yet grid partitioned fuzzy algorithms showed excellent calculation efficiency and good convergence in predicting mass attenuation coefficient.

Keywords

References

  1. J.K. Shultis, R.E. Faw, Radiation Shielding and Radiological Protection in Handbook of Nuclear Engineering, Springer, 2010.
  2. J.H. Hubbell, Review and history of photon cross section calculations, 13, Phys. Med. Biol. 51 (2006) 245, https://doi.org/10.1088/0031-9155/51/13/R15.
  3. H.O. Tekin, P.S. Vishwanath, T. Manici, E.E. Altunsoy, Validation of MCNPX with experimental results of mass attenuation coefficients for cement, gypsum and mixture, Journal of Radiation Protection and Research 42 (3) (2017) 154-157. https://doi.org/10.14407/jrpr.2017.42.3.154.
  4. V.P. Singh, S.P. Shirmardi, M.E. Medhat, N.M. Badiger, Determination of mass attenuation coefficient for some polymers using Monte Carlo simulation, Vacuum 119 (2015) 284-288, https://doi.org/10.1016/j.vacuum.2015.06.006.
  5. M. Berger, XCOM: Photon Cross Sections Database, 2010, https://doi.org/10.2172/6016002.
  6. O. Klein, Y. Nishina, Uber die Streuung von Strahlung durch freielektronen nach der neuen relativistischen quantendynamik von Dirac, Z. Phys. 52 (1928) 853-868.
  7. J. Hamilton, I. Overbo, I, B. Tromborg, Coulomb corrections in non-relativistic scattering, Nucl. Phys. B 60 (1973) 443-477. https://doi.org/10.1016/0550-3213(73)90193-4
  8. R.H. Pratt, P.M. Bergstrom Jr., L. Kissel, New Relativistic S-Matrix Results for Scattering beyond the Usual Anomalous Factors/beyond Impulse Approximation. No. UCRL-JC-114583, Lawrence Livermore National Lab., CA (United States), 1993. CONF-9208186-5.
  9. H.B. Kavanoz, O. Akcali, O. Toker, B. Bilmez, M. Caglar, O. Icelli, O, A novel comprehensive utilization of vanadium slag/epoxy resin/antimony trioxide ternary composite as gamma ray shielding material by MCNP 6.2 and BXCOM, Radiat. Phys. Chem. 165 (2019) 108446, https://doi.org/10.1016/j.radphyschem.2019.108446.
  10. S. Alp, T. Ozkan, Modelling of multi-objective transshipment problem with fuzzy goal programming, International Journal of Transportation 6 (2018) 9-20, https://doi.org/10.14257/ijt.2018.6.2.02.
  11. F. Rosenblatt, Principles of Neurodynamics. Perceptrons and the Theory of Brain Mechanisms, Cornell Aeronautical Lab Inc. Buffalo, NY, 1961.
  12. A.S. Lapedes, R.M. Farber, How Neural Nets Work. Neural Information Processing Systems, 1988, pp. 442-456.
  13. A.G. Bakirtzis, J.B. Theocharis, S.J. Kiartzis, K.J. Satsios, Short term load forecasting using fuzzy neural networks, IEEE Trans. Power Syst. 10 (3) (1995) 1518-1524. https://doi.org/10.1109/59.466494
  14. G. Zhang, B.E. Patuwo, M.Y. Hu, Forecasting with artificial neural networks: the state of the art, Int. J. Forecast. 14 (1) (1998) 35-62. https://doi.org/10.1016/S0169-2070(97)00044-7
  15. C.M. Bishop, Neural Networks for Pattern Recognition, Oxford university press, 1995.
  16. J.C.F. Pujol, J.M.A. Pinto, A neural network approach to fatigue life prediction, Int. J. Fatig. 33 (3) (2011) 313-322. https://doi.org/10.1016/j.ijfatigue.2010.09.003
  17. I. Akkurt, C. Basyigit, S. Kilincarslan, A. Beycioglu, Prediction of photon attenuation coefficients of heavy concrete by fuzzy logic, J. Franklin Inst. 347 (9) (2010) 1589-1597. https://doi.org/10.1016/j.jfranklin.2010.06.002
  18. E.E. Zadeh, S.A.H. Feghhi, G.H. Roshani, A. Rezaei, Application of artificial neural network in precise prediction of cement elements percentages based on the neutron activation analysis, The European Physical Journal Plus 131 (5) (2016) 167. https://doi.org/10.1140/epjp/i2016-16167-6
  19. N. Kucuk, Modeling of gamma ray energy-absorption buildup factors for thermoluminescent dosimetric materials using multilayer perceptron neural network: a comparative study, Radiat. Phys. Chem. 86 (2013) 10-22, https://doi.org/10.1016/j.radphyschem.2013.01.021.
  20. O. Gencel, The application of artificial neural networks technique to estimate mass attenuation coefficient of shielding barrier, 12, Int. J. Phys. Sci. 4 (2009) 743-751.
  21. A. Yadollahi, et al., Application of artificial neural network for predicting the optimal mixture of radiation shielding concrete, Prog. Nucl. Energy 89 (2016) 69-77, https://doi.org/10.1016/j.pnucene.2016.02.010.
  22. F.H. Attix, Introduction to Radiological Physics and Radiation Dosimetry, John Wiley & Sons, 2008.
  23. H. Bethe, W. Heitler, On the stopping of fast particles and on the creation of positive electrons, Proceedings of the Royal Society of London. Series A, Containing Papers of a Mathematical and Physical Character 146 (856) (1934) 83-112, https://doi.org/10.1098/rspa.1934.0140.
  24. The Math Works, Inc. MATLAB. Version 2020b, The Math Works, Inc., 2020 computer software, https://www.mathworks.com.
  25. L.A. Zadeh, 3, Fuzzy sets, Information and control 8 (1965) 338-353, https://doi.org/10.1016/S0019-9958(65)90241-X.
  26. M. Sugeno, G.T. Kang, Structure identification of fuzzy model, Fuzzy Set Syst. 28 (1) (1988) 15-33, https://doi.org/10.1016/0165-0114(88)90113-3.
  27. L.J. Herrera, et al., Clustering-Based TSK neuro-fuzzy model for function approximation with interpretable sub-models, in: International Work-Conference on Artificial Neural Networks, Springer, Berlin, Heidelberg, 2005, https://doi.org/10.1007/11494669_49.
  28. J.J. More, The Levenberg-Marquardt algorithm: implementation and theory, in: Numerical Analysis, Springer, Berlin, Heidelberg, 1978, pp. 105-116.
  29. A. Davydenko, R. Fildes, Forecast error measures: critical review and practical recommendations, in: Business Forecasting: Practical Problems and Solutions, 34, Wiley, 2016.
  30. P. Goyal, P. Dollar, P. Noordhuis, L. Wesolowski, A. Kyrola, A. Tulloch, Y. Jia, K. He, Accurate, Large Mini Batch Sgd: Training Image Net in 1 Hour, 2017 arXiv preprint arXiv:1706.02677, https://arxiv.org/abs/1706.02677v2.
  31. M.E. Medhat, Application of neural network for predicting photon attenuation through materials, 3-4, Radiat. Eff. Defect Solid 174 (2019) 171-181, https://doi.org/10.1080/10420150.2018.1547903.