Neutron spectrum unfolding using artificial neural network and modified least square method

被引:34
作者
Hosseini, Seyed Abolfazl [1 ]
机构
[1] Sharif Univ Technol, Dept Energy Engn, Tehran 863911365, Iran
基金
美国国家科学基金会;
关键词
Neutron pulse height distribution; MCNPX-ESUT; Cf-252; Am-241-Be-9; Unfolding; ANN; MLSQR; MAXIMUM-ENTROPY; CODE;
D O I
10.1016/j.radphyschem.2016.05.010
中图分类号
O64 [物理化学(理论化学)、化学物理学];
学科分类号
070304 ; 081704 ;
摘要
In the present paper, neutron spectrum is reconstructed using the Artificial Neural Network (ANN) and Modified Least Square (MLSQR) methods. The detector's response (pulse height distribution) as a required data for unfolding of energy spectrum is calculated using the developed MCNPX-ESUT computational code (MCNPX-Energy engineering of Sharif University of Technology). Unlike the usual methods that apply inversion procedures to unfold the energy spectrum from the Fredholm integral equation, the MLSQR method uses the direct procedure. Since liquid organic scintillators like NE-213 are well suited and routinely used for spectrometry of neutron sources, the neutron pulse height distribution is simulated/measured in the NE-213 detector. The response matrix is calculated using the MCNPX-ESUT computational code through the simulation of NE-213 detector's response to monoenergetic neutron sources. For known neutron pulse height distribution, the energy spectrum of the neutron source is unfolded using the MLSQR method. In the developed multilayer perception neural network for reconstruction of the energy spectrum of the neutron source, there is no need for formation of the response matrix. The multilayer perception neural network is developed based on logsig, tansig and purelin transfer functions. The developed artificial neural network consists of two hidden layers of type hyperbolic tangent sigmoid transfer function and a linear transfer function in the output layer. The motivation of applying the ANN method may be explained by the fact that no matrix inversion is needed for energy spectrum unfolding. The simulated neutron pulse height distributions in each light bin due to randomly generated neutron spectrum are considered as the input data of ANN. Also, the randomly generated energy spectra are considered as the output data of the ANN. Energy spectrum of the neutron source is identified with high accuracy using both MLSQR and ANN methods. The results obtained from MLSQR and ANN methods for Cf-252 and Am-241-Be-9 source are validated against the ISO spectrum. The unfolded neutron energy spectra from both MLSQR and ANN methods show a good agreement with the actual spectrum of Cf-252 and Am-241-Be-9 source. (C) 2016 Elsevier Ltd. All rights reserved.
引用
收藏
页码:75 / 84
页数:10
相关论文
共 28 条
[11]  
ITOH S, 1989, J NUCL SCI TECHNOL, V26, P833, DOI [10.1080/18811248.1989.9734394, 10.3327/jnst.26.833]
[13]  
Johnson R., 1975, PNE75107 RAD SHIELD
[14]  
Johnson R., 1976, FORIST UNFOLDING CO
[15]  
Levenberg K., 1944, Quarterly of Applied Mathematics, V2, P164, DOI [DOI 10.1090/QAM/10666, 10.1090/QAM/10666]
[16]  
Marrone S, 2002, NUCL INSTRUM METH A, V490, P299, DOI 10.1016/S0168-9002(02)01063-X
[17]   Unfolding of particle spectra [J].
Matzke, M .
NEUTRONS IN RESEARCH AND INDUSTRY, INTERNATIONAL CONFERENCE, 1997, 2867 :598-607
[18]   NEUTRON-SPECTRUM UNFOLDING BY THE MONTE-CARLO METHOD [J].
MATZKE, M ;
WEISE, K .
NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH SECTION A-ACCELERATORS SPECTROMETERS DETECTORS AND ASSOCIATED EQUIPMENT, 1985, 234 (02) :324-330
[19]   BONDI-97: A novel neutron energy spectrum unfolding tool using a genetic algorithm [J].
Mukherjee, B .
NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH SECTION A-ACCELERATORS SPECTROMETERS DETECTORS AND ASSOCIATED EQUIPMENT, 1999, 432 (2-3) :305-312
[20]  
Mullens JA, 2004, I NUCL MAT MAN 45 AN