Browse > Article
http://dx.doi.org/10.1016/j.net.2021.01.002

A novel radioactive particle tracking algorithm based on deep rectifier neural network  

Dam, Roos Sophia de Freitas (Universidade Federal do Rio de Janeiro, Programa de Engenharia Nuclear (UFRJ / PEN))
dos Santos, Marcelo Carvalho (Universidade Federal do Rio de Janeiro, Programa de Engenharia Nuclear (UFRJ / PEN))
do Desterro, Filipe Santana Moreira (Universidade Federal do Rio de Janeiro, Programa de Engenharia Nuclear (UFRJ / PEN))
Salgado, William Luna (Universidade Federal do Rio de Janeiro, Programa de Engenharia Nuclear (UFRJ / PEN))
Schirru, Roberto (Universidade Federal do Rio de Janeiro, Programa de Engenharia Nuclear (UFRJ / PEN))
Salgado, Cesar Marques (Instituto de Engenharia Nuclear (IEN))
Publication Information
Nuclear Engineering and Technology / v.53, no.7, 2021 , pp. 2334-2340 More about this Journal
Abstract
Radioactive particle tracking (RPT) is a minimally invasive nuclear technique that tracks a radioactive particle inside a volume of interest by means of a mathematical location algorithm. During the past decades, many algorithms have been developed including ones based on artificial intelligence techniques. In this study, RPT technique is applied in a simulated test section that employs a simplified mixer filled with concrete, six scintillator detectors and a137Cs radioactive particle emitting gamma rays of 662 keV. The test section was developed using MCNPX code, which is a mathematical code based on Monte Carlo simulation, and 3516 different radioactive particle positions (x,y,z) were simulated. Novelty of this paper is the use of a location algorithm based on a deep learning model, more specifically a 6-layers deep rectifier neural network (DRNN), in which hyperparameters were defined using a Bayesian optimization method. DRNN is a type of deep feedforward neural network that substitutes the usual sigmoid based activation functions, traditionally used in vanilla Multilayer Perceptron Networks, for rectified activation functions. Results show the great accuracy of the DRNN in a RPT tracking system. Root mean squared error for x, y and coordinates of the radioactive particle is, respectively, 0.03064, 0.02523 and 0.07653.
Keywords
Radioactive particle tracking; Gamma densitometry; MCNPX code; Deep learning; Deep neural networks;
Citations & Related Records
연도 인용수 순위
  • Reference
1 M.A.S.M. Yunos, S.A. Hussain, S.M. Sipaun, Industrial radiotracer application in flow rate measurement and flowmeter calibration using 99mTc and 198Au nanoparticles radioisotope, Appl. Radiat. Isot. 143 (2019) 24-28.   DOI
2 M.A.S.M. Yunos, M.D.A. Usang, H. Ithnin, S.A. Hussain, H.M. Yusoff, S. Sipaun, Reconstruction algorithm of calibration map for RPT techniques in quadrilateral bubble column reactor using MCNPX code, European Journal of Engineering Research and Science 3 (1) (2018).
3 F. Larachi, G. Kennedy, J. Chaouki, A gamma-ray detection system for 3-D particle tracking in multiphase reactors, Nucl. Instrum. Methods Phys. Res. Sect. A Accel. Spectrom. Detect. Assoc. Equip. 338 (2-3) (1994) 568-576.   DOI
4 L. Godfroy F. Larachi, G. Kennedy, B. Grandjean, J. Chaouki, On-line flow visualization in multiphase reactors using neural networks, Appl. Radiat. Isot. 48 (1997) 225-235.   DOI
5 X. Glorot, A. Bordes, Y. Bengio, Deep sparse rectifier neural networks. Proceedings of the fourteenth international conference on artificial intelligence and statistics, in: PMLR, vol. 15, 2011, pp. 315-323.
6 G.H. Roshani, A. Karami, A. Salehizadeh, E. Nazemi, The capability of radial basis function to forecast the volume fractions of the annular three-phase flow of gas-oil-water, Appl. Radiat. Isot. 129 (2017) 156-162.   DOI
7 B. Shahriari, K. Swersky, Z. Wang, R.P. Adams, N. Freitas, Taking the human out of the loop: a review of bayesian optimization, in: Proceedings of the IEEE, vol. 104, 2016, pp. 148-175, 1.   DOI
8 M. Pumperla, Hyperas: a Very Simple Convenience Wrapper Around Hyperopt for Fast Prototyping with Keras Models, 2017. https://maxpumperla.com/hyperas/. (Accessed 1 June 2020).
9 D. Pedamonti, Comparison of Non-linear Activation Functions for Deep Neural Networks on MNIST Classification Task, CoRR - Computing Research Repository, 2018.
10 X. Glorot, Y. Bengio, Understanding the difficulty of training deep feedforward neural networks, in: Proc. AISTATS, vol. 9, 2010, pp. 249-256.
11 R.J. McConn Jr., C.J. Gesh, R.A. Rucker, R.G. Williams II, Compendium of Material Composition Data for Radiation Transport Modeling, Pacific Northwest National Laboratory, 2011. PNNL-15870, Rev. 1.
12 J. Bergstra, Y. Bengio, Random search for hyper-parameter optimization, J. Mach. Learn. Res. 13 (2012) 281-305.
13 J.M. Ortiz-Rodriguez, M.R. Martinez-Blanco, J.M. Varamontes, H.R. Vega-Carrillo, Robust design of artificial neural networks methodology in neutron spectrometry, in: K. Prof Suzuki (Ed.), Artificial Neural Networks - Architectures and Application, s, 2013.
14 S. Haykin, Neural Networks, A Comprehensive Foundation, second ed., Prentice Hall, 1999.
15 J. Schmidhuber, Deep learning in neural networks: an overview, Neural Netw. Off. J. Int. Neural Netw. Soc. 61 (2015) 85-117.   DOI
16 J. Snoek, H. Larochelle, R. Adams, Practical Bayesian optimization of machine learning algorithms, in: Advances in Neural Information Processing Systems, vol. 25, 2012, pp. 2960-2968.
17 M.J. Berger, S.M. Seltzer, Response functions for sodium iodide scintillation detectors, Nucl. Instrum. Methods 104 (1972) 317-332.   DOI
18 C.M.N.A. Pereira, R. Schirru, K.J. Gomes, J.L. Cunha, Artificial Neural Networks for Radiation Dose Prediction in Nuclear Emergencies: Preliminary Investigations. Advances in Computer Science Research, Atlantis Press ISSN, 2016, https://doi.org/10.2991/msota-16.2016.98, 2352-538X.
19 M. Gheisari, G. Wang, M.Z.A. Bhuiyan, A survey on deep learning in big data, in: IEEE International Conference on Computational Science and Engineering (CSE) and IEEE International Conference on Embedded and Ubiquitous Computing, EUC), Guangzhou, 2017, pp. 173-180.
20 R.K. Srivastava, K. Greff, J. Schmidhuber, Training Very Deep Networks. The Swiss AI Lab IDSIA/USI/SUPSI, Neural Information Processing Systems, NIPS), 2015.
21 F. Chen, M.R. Jahanshahi, NB-CNN, Deep learning-based crack detection using convolutional neural network and naive bayes data fusion, in: IEEE Transactions on Industrial Electronics, vol. 65, 2018, pp. 4392-4400, https://doi.org/10.1109/TIE.2017.2764844, 5.   DOI
22 F.D.S. Ribeiro, F. Caliva, D. Chionis, A. Dokhane, A. Mylonakis, C. Demaziere, G. Leontidis, S.D. Kollias, Towards a deep unified framework for nuclear reactor perturbation analysis, in: IEEE Symposium Series on Computational Intelligence, SSCI), Bangalore, India, 2018, pp. 120-127, https://doi.org/10.1109/SSCI.2018.8628637.   DOI
23 F.S.M. Desterro, M.C. Santos, K.J. Gomes, A. Heimlich, R. Schirru, C.M.N.A. Pereira, Development of a Deep Rectifier Neural Network for dose prediction in nuclear emergencies with radioactive material releases, Prog. Nucl. Energy 118 (2020), https://doi.org/10.1016/j.pnucene.2019.103110.   DOI
24 N. Devanathan, D. Moslemian, M.P. Dudukovic, Flow mapping in bubble columns using CARPT, Chem. Eng. Sci. 45 (1990) 2285-2291.   DOI
25 S. Azizi, A. Yadav, Y.M. Lau, U. Hampel, S. Roy, M. Schubert, On the experimental investigation of gas-liquid flow in bubble columns using ultrafast Xray tomography and radioactive particle tracking, Chem. Eng. Sci. 170 (2017) 320-331, https://doi.org/10.1016/j.ces.2017.02.015.   DOI
26 V. Mosorov, J. Abdullah, MCNP5 code in radioactive particle tracking, Appl. Radiat. Isot. 69 (2011) 1287-1293.   DOI
27 L. Spreutels, B. Haut, R. Legros, F. Bertrand, J. Chaouki, Experimental investigation of solid particles flow in a conical spouted bed using radioactive particle tracking, AIChE J. 62 (2015) 26-37.   DOI
28 R.S.F. Dam, T.P. Teixeira, W.L. Salgado, C.M. Salgado, A new application of radioactive particle tracking using MCNPX code and artificial neural network, Appl. Radiat. Isot. 149 (2019) 38-47.   DOI
29 J. Doucet, F. Bertrand, J. Chaouki, An extended radioactive particle tracking method for systems with irregular moving boundaries, Powder Technol. 181 (2) (2008) 195-204.   DOI
30 C.M. Salgado, L.E.B. Brandao, C.M.N.A. Pereira, R. Schirru, R. Ramos, A.X. Silva, Prediction of volume fractions in three-phase flows using nuclear technique and artificial neural network, Appl. Radiat. Isot. 67 (2009) 1812-1818.   DOI
31 S. Bhusarapu, M.H. Al-Dahhan, M.P. Dudukovic, S. Trujillo, T.J. O'Hern, Experimental study of the solids velocity field in gasesolid risers, Ind. Eng. Chem. Res. 44 (25) (2005) 9739.   DOI
32 M.C. Santos, V.H.C. Pinheiro, F.S.M. Desterro, R.K. Avellar, R. Schirru, A.S. Nicolau, A.M.M. Lima, Deep rectifier neural network applied to the accident identification problem in a PWR nuclear power plant, Ann. Nucl. Energy 133 (2019) 400-408.   DOI
33 J.S. Lin, M.M. Chen, B.T. Chao, A novel radioactive particle tracking facility for measurement of solids motion in gas fluidized beds, AIChE J. 31 (3) (1985) 465-473.   DOI
34 D.A. Clevert, T. Unterthiner, S. Hochreiter, Fast and accurate deep network learning by exponential linear units (elus), ICLR, 2015 arXiv:1511.07289.
35 D.P. Kingma, J. Ba, Adam, A method for stochastic optimization, in: 3rd International Conference for Learning Representations, San Diego, 2015 arXiv:1412.6980.
36 B.B. Benuwa, Y.Z. Zhan, B. Ghansah, D.K. Wornyo, F.B. Kataka, A review of deep machine learning, Int. J. Eng. Res. Afr. 24 (2016) 124-136. https://doi.org/10.4028/www.scientific.net/JERA.24.124.   DOI
37 C.M. Salgado, L.E.B. Brandao, C.C. Conti, W.L. Salgado, Density prediction for petroleum and derivatives by gamma-ray attenuation and artificial neural networks, Appl. Radiat. Isot. 116 (2016) 143-149.   DOI
38 G.H. Roshani, R. Hanus, A. Khazaei, M. Zych, E. Nazemi, V. Mosorov, Density and velocity determination for single-phase flow based on radiotracer technique and neural networks, Flow Meas. Instrum. 61 (2018) 9-14.   DOI
39 A. Yadav, T.K. Gaurav, H.J. Pant, S. Roy, Machine Learning Based Position-rendering Algorithms for Radioactive Particle Tracking Experimentation, American Institute of Chemical Engineers, 2020, https://doi.org/10.1002/aic.16954.
40 A.A. Abdulrahman, E.M. Shokir, Artificial neural networks modeling for hydrocarbon gas viscosity and density estimation, J. King Saud Univ. - Eng. Sci. 23 (2011) 123-129.   DOI
41 D.B. Pelowitz, MCNPX TM User's Manual. Version 2.5.0, Los Alamos National Laboratory, 2005. LA-CP-05-0369.
42 V. Mosorov, M. Zych, R. Hanus, D. Sankowski, A. Saoud, Improvement of flow velocity measurement algorithms based on correlation function and twin plane electrical capacitance tomography, Sensors 20 (2020) 306, https://doi.org/10.3390/s20010306.   DOI
43 R. Hanus, M. Zych, R. Chorzepa, A. Golijanek-Jedrzejczyk, Investigations of the methods of time delay measurement of stochastic signals using crosscorrelation with the hilbert transform, in: IEEE 20th Mediterranean Electrotechnical Conference (MELECON), Palermo, Italy, vol. 2020, 2020, pp. 238-242, https://doi.org/10.1109/MELECON48756.2020.9140630.   DOI
44 M. Khorsandi, S.A. Feghhi, Design and construction of a prototype gamma-ray densitometer for petroleum products monitoring applications, Measurement 44 (2011) 1512-1515.   DOI
45 R.S.F. Dam, C.M. Barbosa, J.M. Lopes, J.L. Thalhofer, L.B. Silva, C.M. Salgado, A.X. Silva, Radioactive particle tracking methodology to evaluate concrete mixer using MCNPX code, Radiat. Phys. Chem. 160 (2019) 26-29.   DOI
46 J. Chaouki, F. Larachi, P. Dudukovic, Non-Invasive Monitoring of Multiphase Flows, Elsevier Science B.V., Amsterdam, The Netherlands, 1997.
47 Y. Mi, M. Ishii, L.H. Tsoukalas, Vertical two-phase flow identification using advanced instrumentation and neural networks, Nucl. Eng. Des. 184 (1998) 409-420.   DOI
48 M. Zych, R. Hanus, B. Wilk, L. Petryka, D. Swisulski, Comparison of noise reduction methods in radiometric correlation measurements of two-phase liquid-gas flows, Measurement 129 (2018) 288-295, https://doi.org/10.1016/j.measurement.2018.07.035.   DOI
49 V.H. Pinheiro, M.C. Santos, F.S.M. Desterro, R. Schirru, C.M.N.A. Pereira, Nuclear Power Plant accident identification system with "don't know" response capability: novel deep learning-based approaches, Ann. Nucl. Energy 137 (2020), https://doi.org/10.1016/j.anucene.2019.107111.   DOI
50 I. Dewancker, M. McCourt, S. Clark, Bayesian Optimization for Machine Learning: A Practical Guidebook, SigOpt, San Francisco, CA 94108, 2015 arXiv: 1612.04858.
51 R.R.W. Affonso, R.S.F. Dam, W.L. Salgado, A.X. Silva, C.M. Salgado, Flow regime and volume fraction identification using nuclear techniques, artificial neural networks and computational fluid dynamics, Appl. Radiat. Isot. 159 (2020) 109103, https://doi.org/10.1016/j.apradiso.2020.109103.   DOI
52 C.M. Salgado, R.S.F. Dam, W.L. Salgado, R.R.W. Affonso, C.M.N.A. Pereira, R. Schirru, The comparison of different multilayer perceptron and General Regression Neural Networks for volume fraction prediction using MCNPX code, Appl. Radiat. Isot. 162 (2020), https://doi.org/10.1016/j.apradiso.2020.109170.   DOI
53 G.H. Roshani, E. Nazemi, M.M. Roshani, A novel method for flow pattern identification in unstable operational conditions using gamma ray and radial basis function, Appl. Radiat. Isot. 123 (2017) 60-68.   DOI
54 V. Blet, P. Berne, S. Legoupil, et al., Radioactive tracing as aid for diagnosing chemical reactors, Oil and Gas Science and Technology - Rev. IFP. 55 (2) (2000) 171-183.   DOI
55 W.L. Salgado, R.S.F. Dam, T.P. Teixeira, C.C. Conti, C.M. Salgado, Application of artificial intelligence in scale thickness prediction on offshore petroleum using a gamma-ray densitometer, Radiat. Phys. Chem. 168 (2020) 108549, https://doi.org/10.1016/j.radphyschem.2019.108549.   DOI
56 G.H. Roshani, E. Nazemi, Intelligent densitometry of petroleum products in stratified regime of two phase flows using gamma ray and neural network, Flow Meas. Instrum. 58 (2017) 6-11.   DOI
57 R. Hanus, L. Petryka, M. Zych, Velocity measurement the liquid-solid flow in vertical pipeline using gamma-ray absorption and weighted cross-correlation, Flow Meas. Instrum. 40 (2014) 58-63.   DOI
58 R. Hanus, M. Zych, M. Kusy, M. Jaszczur, L. Petryka, Identification of liquid-gas flow regime in a pipeline using gamma-ray absorption technique and computational intelligence methods, Flow Meas. Instrum. 60 (2018) 17-23.   DOI
59 M.S. Abouelwafa, S.M. Kendall, The measurement of component ratios in multiphase systems using gamma-ray attenuation, J. Phys. E Sci. Instrum. 13 (1980) 341-345.   DOI
60 W.L. Salgado, R.S.F. Dam, C.M. Barbosa, A.X. Silva, C.M. Salgado, Monitoring system of oil by-products interface in pipelines using the gamma radiation attenuation, Appl. Radiat. Isot. 160 (2020), https://doi.org/10.1016/j.apradiso.2020.109125.   DOI
61 F. Caliva, F.D.S. Ribeiro, A. Mylonakis, C. Demaziere, P. Vinai, G. Leontidis, S. Kollias, A deep learning approach to anomaly detection in nuclear reactors, in: International Joint Conference on Neural Networks, IJCNN), Rio de Janeiro, 2018, pp. 1-8, https://doi.org/10.1109/IJCNN.2018.8489130.   DOI
62 Y. LeCun, Y. Bengio, G. Hinton, Deep learning, Nature 521 (2015) 436-444.   DOI
63 C.M. Salgado, C.M.N.A. Pereira, R. Schirru, L.E.B. Brandao, Flow regime identification and volume fraction prediction in multiphase flows by means of gamma-ray attenuation and artificial neural networks, Prog. Nucl. Energy 52 (6) (2010) 555-562.   DOI
64 C.M. Salgado, L.E.B. Brandao, R. Schirru, C.M.N.A. Pereira, C.C. Conti, Validation of aNaI(Tl) detector's model developed with MCNP-X code, Prog. Nucl. Energy 59 (2012) 19-25.   DOI