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

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 a 137Cs 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.

[1]  Roberto Schirru,et al.  Prediction of volume fractions in three-phase flows using nuclear technique and artificial neural network. , 2009, Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine.

[2]  Richard T. Pagh,et al.  Compendium of Material Composition Data for Radiation Transport Modeling , 2011 .

[3]  M. Duduković,et al.  Flow mapping in bubble columns using CARPT , 1990 .

[4]  Siti Aslina Hussain,et al.  Reconstruction Algorithm of Calibration Map for RPT Techniques in Quadrilateral Bubble Column Reactor Using MCNPX Code , 2018, European Journal of Engineering and Technology Research.

[5]  M. Abouelwafa,et al.  The measurement of component ratios in multiphase systems using alpha -ray attenuation , 1980 .

[6]  Marcin Zych,et al.  Velocity measurement of the liquid–solid flow in a vertical pipeline using gamma-ray absorption and weighted cross-correlation , 2014 .

[7]  Dabal Pedamonti,et al.  Comparison of non-linear activation functions for deep neural networks on MNIST classification task , 2018, ArXiv.

[8]  Ademir Xavier da Silva,et al.  Radioactive particle tracking methodology to evaluate concrete mixer using MCNPX code , 2019, Radiation Physics and Chemistry.

[9]  Lefteri H. Tsoukalas,et al.  Vertical two-phase flow identification using advanced instrumentation and neural networks , 1998 .

[10]  Mohammad R. Jahanshahi,et al.  NB-CNN: Deep Learning-Based Crack Detection Using Convolutional Neural Network and Naïve Bayes Data Fusion , 2018, IEEE Transactions on Industrial Electronics.

[11]  Faïçal Larachi,et al.  Non-invasive monitoring of multiphase flows , 1997 .

[12]  Roberto Schirru,et al.  Deep rectifier neural network applied to the accident identification problem in a PWR nuclear power plant , 2019, Annals of Nuclear Energy.

[13]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[14]  S. A. Hussain,et al.  Industrial radiotracer application in flow rate measurement and flowmeter calibration using 99mTc and 198Au nanoparticles radioisotope. , 2019, Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine.

[15]  Roberto Schirru,et al.  Validation of a NaI(Tl) detector's model developed with MCNP-X code , 2012 .

[16]  B. T. Chao,et al.  A novel radioactive particle tracking facility for measurement of solids motion in gas fluidized beds , 1985 .

[17]  Uwe Hampel,et al.  On the experimental investigation of gas-liquid flow in bubble columns using ultrafast X-ray tomography and radioactive particle tracking , 2017 .

[18]  C M Salgado,et al.  The comparison of different multilayer perceptron and General Regression Neural Networks for volume fraction prediction using MCNPX code. , 2020, Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine.

[19]  Jasper Snoek,et al.  Practical Bayesian Optimization of Machine Learning Algorithms , 2012, NIPS.

[20]  Volodymyr Mosorov,et al.  Density and velocity determination for single-phase flow based on radiotracer technique and neural networks , 2018, Flow Measurement and Instrumentation.

[21]  Milorad P. Dudukovic,et al.  Experimental Study of the Solids Velocity Field in Gas-Solid Risers , 2005 .

[22]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[23]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..

[24]  Roberto Schirru,et al.  Nuclear Power Plant accident identification system with “don’t know” response capability: Novel deep learning-based approaches , 2020 .

[25]  César Marques Salgado,et al.  Application of artificial intelligence in scale thickness prediction on offshore petroleum using a gamma-ray densitometer , 2020, Radiation Physics and Chemistry.

[26]  Volodymyr Mosorov,et al.  MCNP5 code in radioactive particle tracking. , 2011, Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine.

[27]  Benjamin Ghansah,et al.  A Review of Deep Machine Learning , 2016, International Journal of Engineering Research in Africa.

[28]  E. Nazemi,et al.  Intelligent densitometry of petroleum products in stratified regime of two phase flows using gamma ray and neural network , 2017 .

[29]  Shantanu Roy,et al.  Machine learning based position‐rendering algorithms for radioactive particle tracking experimentation , 2020 .

[30]  Cláudio Márcio do Nascimento Abreu Pereira,et al.  Artificial Neural Networks for Radiation Dose Prediction in Nuclear Emergencies-Preliminary Investigations , 2016 .

[31]  J. Chaouki,et al.  On-line flow visualization in multiphase reactors using neural networks , 1997 .

[32]  Sepp Hochreiter,et al.  Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) , 2015, ICLR.

[33]  M. Roshani,et al.  A novel method for flow pattern identification in unstable operational conditions using gamma ray and radial basis function. , 2017, Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine.

[34]  S. Legoupil,et al.  Radioactive Tracing As Aid for Diagnosing Chemical Reactors , 2000 .

[35]  C M Salgado,et al.  Density prediction for petroleum and derivatives by gamma-ray attenuation and artificial neural networks. , 2016, Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine.

[36]  Roberto Schirru,et al.  Development of a Deep Rectifier Neural Network for dose prediction in nuclear emergencies with radioactive material releases , 2020 .

[37]  Rodrigo Castañeda-Miranda,et al.  A study using the robust design of artificial neural networks methodology in neutron spectrometry , 2016, ICIT.

[38]  Ademir Xavier da Silva,et al.  Flow regime and volume fraction identification using nuclear techniques, artificial neural networks and computational fluid dynamics. , 2020, Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine.

[39]  Martin J. Berger,et al.  Response functions for sodium iodide scintillation detectors , 1972 .

[41]  Dominik Sankowski,et al.  Improvement of Flow Velocity Measurement Algorithms Based on Correlation Function and Twin Plane Electrical Capacitance Tomography , 2020, Sensors.

[42]  G. Roshani,et al.  The capability of radial basis function to forecast the volume fractions of the annular three-phase flow of gas-oil-water. , 2017, Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine.

[43]  William L Salgado,et al.  Monitoring system of oil by-products interface in pipelines using the gamma radiation attenuation. , 2020, Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine.

[44]  R. Schirru,et al.  Flow regime identification and volume fraction prediction in multiphase flows by means of gamma-ray attenuation and artificial neural networks , 2010 .

[45]  François Bertrand,et al.  An extended radioactive particle tracking method for systems with irregular moving boundaries , 2008 .

[46]  J. Chaouki,et al.  A γ-ray detection system for 3-D particle tracking in multiphase reactors , 1994 .

[47]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[48]  Seyed Amir Hossein Feghhi,et al.  Design and construction of a prototype gamma-ray densitometer for petroleum products monitoring applications , 2011 .

[49]  J. Chaouki,et al.  Experimental investigation of solid particles flow in a conical spouted bed using radioactive particle tracking , 2016 .

[50]  E. M. El-M. Shokir,et al.  Artificial neural networks modeling for hydrocarbon gas viscosity and density estimation , 2011 .

[51]  Nando de Freitas,et al.  Taking the Human Out of the Loop: A Review of Bayesian Optimization , 2016, Proceedings of the IEEE.

[52]  Md. Zakirul Alam Bhuiyan,et al.  A Survey on Deep Learning in Big Data , 2017, 22017 IEEE International Conference on Computational Science and Engineering (CSE) and IEEE International Conference on Embedded and Ubiquitous Computing (EUC).

[53]  Stefanos D. Kollias,et al.  A Deep Learning Approach to Anomaly Detection in Nuclear Reactors , 2018, 2018 International Joint Conference on Neural Networks (IJCNN).

[54]  Maciej Kusy,et al.  Identification of liquid-gas flow regime in a pipeline using gamma-ray absorption technique and computational intelligence methods , 2018 .

[55]  Ian Dewancker,et al.  Bayesian Optimization for Machine Learning : A Practical Guidebook , 2016, ArXiv.

[56]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[57]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[58]  Stefanos D. Kollias,et al.  Towards a Deep Unified Framework for Nuclear Reactor Perturbation Analysis , 2018, 2018 IEEE Symposium Series on Computational Intelligence (SSCI).

[59]  Roos Sophia de F Dam,et al.  A new application of radioactive particle tracking using MCNPX code and artificial neural network. , 2019, Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine.

[60]  Barbara Wilk,et al.  Comparison of noise reduction methods in radiometric correlation measurements of two-phase liquid-gas flows , 2018, Measurement.