Thickness Measurement of Metals Using Neural Network and Radioisotope Measurement-Modelling

Document Type : Original Article

Authors

1 Nuclear Science and Technology Research Institute (NSTRI), Radiation Applications Research School, AEOI, Tehran, Iran

2 Nuclear Science and Technology Research Institute (NSTRI), Radiation Applications Research School, AEOI, Tehran, Iran.

Abstract

The nuclear industry has undergone a significant technological revolution in recent years, with neural networks playing an increasingly important role. These advanced machine learning algorithms are now widely used to analyze nuclear data obtained from various sources, such as calculations, modeling, simulation, and nuclear sensors including gamma ray-based gauges, experimental tests, and non-destructive tests like radiography. Non-destructive measurement methods based on gamma rays passing through materials or processes have gained popularity due to their effectiveness and safety in the nuclear industry. These methods typically use radioactive radioisotope sources like cesium-137 and cobalt-60, along with scintillation detection units, to capture data related to fluid thickness, density, and flow. By applying neural networks, these measurements can be made even more accurate and reliable, ensuring optimal safety and efficiency in the nuclear sector. To investigate this further, a study was conducted to design the geometry of the transmission mode for radioisotope thickness measurement through simulation using the MCNPX Monte Carlo code. The model included three commonly used metals in industries: copper, iron, and aluminum, to determine their thickness. To create the dataset, the thickness of the samples was varied from 0.5 to 50 mm, with a step size of 0.5 mm, and the results of Monte Carlo calculations were recorded as pulse height in the detector. Artificial neural networks were trained based on radial basis functions (RBF) and multilayer perceptron (MLP) techniques using all the results obtained from different energies. After training, the networks were tested to predict the thickness of different metals. The results obtained from the two networks were compared for the output of the model. The study showed that the response of the MLP network was more satisfactory than that of the RBF network in this application. Overall, the study highlights the potential of neural networks in enhancing the accuracy and reliability of non-destructive measurements in the nuclear industry, particularly in predicting the thickness of different materials.

Keywords

Main Subjects

References

[1] S. Shanmuganathan, Artificial neural
network modelling: An introduction:
Springer, 2016.

[2] K. Moshkbar-Bakhshayesh and M. B.
Ghofrani, "Transient identification in nuclear
power plants: A review," Progress in Nuclear
Energy, vol. 67, pp. 23-32, 2013.
[3] D. Neudecker, M. Grosskopf, M. Herman, W.
Haeck, P. Grechanuk, S. Vander Wiel, et al.,
"Enhancing nuclear data validation analysis
by using machine learning," Nuclear Data
Sheets, vol. 167, pp. 36-60, 2020.

[4] P. Vicente-Valdez, L. Bernstein, and M.
Fratoni, "Nuclear data evaluation
augmented by machine learning," Annals of
Nuclear Energy, vol. 163, p. 108596, 2021.

[5] W. Troxler, "Development and industry
acceptance of nuclear gauges," in
Constructing and controlling compaction of
earth fills, ed: ASTM International, 2000.

[6] D. R. Carlson, "Level and density
measurement using non-contact nuclear
gauges," Measurement and Control, vol. 10,
pp. 83-87, 1977.

[7] B. A. C. d. Castro, "Application of portable
nuclear gauge to the control of soil, asphalt
and concrete compaction."

[8] P. Daponte and D. Grimaldi, "Artificial neural
networks in measurements," Measurement,
vol. 23, pp. 93-115, 1998.

[9] G. W. Irwin, G. W. Irwin, K. Warwick, and K.
J. Hunt, Neural network applications in
control: Iet, 1995.

[10] M. A. Sattari, G. H. Roshani, and R. Hanus,
"Improving the structure of two-phase flow
meter using feature extraction and GMDH
neural network," Radiation Physics and
Chemistry, vol. 171, p. 108725, 2020.

[11] C. Salgado, R. Dam, W. Salgado, R. Werneck, C.
Pereira, and R. Schirru, "The comparison of
different multilayer perceptron and General
Regression Neural Networks for volume fraction
prediction using MCNPX code," Applied Radiation
and Isotopes, vol. 162, p. 109170, 2020.

[12] R. S. d. F. Dam, T. P. Teixeira, W. L. Salgado, and
C. M. Salgado, "A new application of radioactive
particle tracking using MCNPX code and artificial
neural network," Applied Radiation and Isotopes,
vol. 149, pp. 38-47, 2019.

[13] G. Roshani, R. Hanus, A. Khazaei, M. Zych, E.
Nazemi, and V. Mosorov, "Density and velocity
determination for single-phase flow based on
radiotracer technique and neural networks," Flow
Measurement and Instrumentation, vol. 61, pp. 9-
14, 2018.

[14] E. Eftekhari Zadeh, S. Feghhi, G. Roshani, and 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, vol.
131, pp. 1-8, 2016.
[15] S. Islami rad, R. Gholipour Peyvandi, and S.
Sadrzadeh, "Determination of the volume
fraction in (water-gasoil-air) multiphase flows
using a simple and low-cost technique: Artificial
neural networks," Physics of Fluids, vol. 31, p.
093301, 2019.

[16] M. Khorsandi, S. Feghhi, A. Salehizadeh, and G.
Roshani, "Developing a gamma ray fluid
densitometer in petroleum products monitoring
applications using Artificial Neural Network,"
Radiation measurements, vol. 59, pp. 183-187,
2013.

[17] A. Belicic-Kolsek and T. Sutej, "Safety of radiation
sources in Slovenia," 2001.

[18] D. B. Pelowitz, "MCNPXTM user’s manual," Los
Alamos National Laboratory, Los Alamos, vol. 5,
p. 369, 2005.

[19] M.-M. Bé, V. Chisté, C. Dulieu, E. Browne, V.
Chechev, N. Kuzmenko, et al., Table of
radionuclides (Vol. 2-A= 151 to 242) vol. 2,
2004.

[20] J. E. Dayhoff, Neural network architectures: an
introduction: Van Nostrand Reinhold Co., 1990.

[21] R. M. Snyder, "Neural Networks for the
Beginner," 1996.

[22] R. Thoraeus, "Attenuation of Gamma
Radiation from 60Co, 137Cs, 192Ir, and 226Ra
in Various Materials Used in Radiotherapy."
Acta Radiologica: Therapy, Physics, Biology,
vol. 3, no. 2, 1965, pp. 81-86.

[23] O. Adedoyin and A. Ayodeji. “Measurement of
Shielding Effectiveness of Building Blocks
against 662 KeV Photons." Journal of Physical
Science, vol. 27, no. 2, 2016, pp. 55.

[24] OSHA. "Shielding Layer Examples." OSHA,
n.d., https://www.osha.gov/ionizingradiation/introduction/shielding-layerexamples
[25] NIST. "X-Ray Mass Attenuation
Coefficients." NIST, n.d.,
https://physics.nist.gov/cgi-bin/Xcom.

Files

History

  • Receive Date: 15 January 2023
  • Revise Date: 01 February 2023
  • Accept Date: 14 February 2023

Share

How to cite

Statistics