Radionuclide identification method based on a gamma-spectra template library simulated by radial basis function neural networks

DU Xiaochuang; TU Hongbing; LI Ke; ZHANG Jie; WANG Kang; LIU Hemin; LIANG Manchun; WANG Xiangwei

doi:10.16511/j.cnki.qhdxxb.2020.22.033

PDF(4987 KB)

Journal of Tsinghua University(Science and Technology) ›› 2021, Vol. 61 ›› Issue (11) : 1308-1315. DOI: 10.16511/j.cnki.qhdxxb.2020.22.033

NUCLEAR ENERGY AND NEW ENERGY

Radionuclide identification method based on a gamma-spectra template library simulated by radial basis function neural networks

{{article.zuoZhe_EN}}

Author information +

History +

Abstract

The traditional gamma ray spectrum analysis methods are usually computationally complex and time-consuming. This paper simulated 26 radionuclide spectra using Geant4 to develop a gamma-spectra template library by fitting the spectra with radial basis function neural networks. Unknown gamma ray spectra were then identified using a least-squares algorithm and a nonlinear programing algorithm to find the optimal combination of radionuclide spectra in the library that matched the unknown spectrum with ensemble learning used to integrate the results of the two algorithms for identification. A single spectrum and mixed spectra containing 2 or 3 kinds of radionuclides were generated to evaluate the method. The results show that this method can accurately identify the radionuclides in an efficient and effective way.

Key words

radionuclide identification / radial basis function neural networks / radionuclide gamma-spectra template library / least-squares method / nonlinear programming

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

DU Xiaochuang, TU Hongbing, LI Ke, ZHANG Jie, WANG Kang, LIU Hemin, LIANG Manchun, WANG Xiangwei. Radionuclide identification method based on a gamma-spectra template library simulated by radial basis function neural networks[J]. Journal of Tsinghua University(Science and Technology). 2021, 61(11): 1308-1315 https://doi.org/10.16511/j.cnki.qhdxxb.2020.22.033

References

[1] 钱晋. 基于遗传神经网络的γ能谱分析研究[D]. 杭州:中国计量学院, 2013. QIAN J. Gamma spectrum analysis based on genetic neural network[D]. Hangzhou:China Jiliang University, 2013. (in Chinese)
[2] 弟宇鸣, 许伟, 许鹏, 等. 一种基于BP神经网络的γ能谱识别方法[J]. 核电子学与探测技术, 2006, 26(4):397-399, 413. DI Y M, XU W, XU P, et al. A method of γ spectrum identification based on the BP neural network[J]. Nuclear Electronics & Detection Technology, 2006, 26(4):397-399, 413. (in Chinese)
[3] 史东生, 弟宇鸣, 周春林. 粒子群优化算法在神经网络识别γ能谱中的应用[J]. 核技术, 2007, 30(7):615-618. SHI D S, DI Y M, ZHOU C L. Application of particle swarm optimization to identify gamma spectrum with neural network[J]. Nuclear Techniques, 2007, 30(7):615-618. (in Chinese)
[4] 王崇杰, 贾慧慧, 冯琳懿, 等. 基于RBF人工神经网络的γ能谱分析[J]. 核电子学与探测技术, 2016, 36(1):56-59. WANG C J, JIA H H, FENG L Y, et al. γ-spectra analysis based on RBF artificial neural network[J]. Nuclear Electronics & Detection Technology, 2016, 36(1):56-59. (in Chinese)
[5] 刘议聪, 王伟, 牛德青. 基于人工神经网络的核素识别分析方法[J]. 兵工自动化, 2015, 34(11):86-91. LIU Y C, WANG W, NIU D Q. Nuclide identification and analysis using artificial neural network[J]. Ordnance Industry Automation, 2015, 34(11):86-91. (in Chinese)
[6] ROEMER K, SAUCKE K, PAUSCH G, et al. Simulation of template spectra for scintillator based radionuclide identification devices using GEANT4[C]//2006 IEEE Nuclear Science Symposium Conference Record. San Diego, USA:IEEE, 2006.
[7] HOGAN M A, YAMAMOTO S, COVELL D F. Multiple linear regression analysis of scintillation gamma-ray spectra:Automatic candidate selection[J]. Nuclear Instruments and Methods, 1970, 80(1):61-68.
[8] CARLEVARO C M, WILKINSON M V, BARRIOS L A. A genetic algorithm approach to routine gamma spectra analysis[J]. Journal of Instrumentation, 2008, 3(1):01001.
[9] ALAMANIOTIS M, MATTINGLY J, TSOUKALAS L H. Pareto-optimal gamma spectroscopic radionuclide identification using evolutionary computing[J]. IEEE Transactions on Nuclear Science, 2016, 60(3):2222-2231.
[10] IAEA. Identification of radioactive sources and devices. Reference manual[M]. Vienna, Austria. IAEA, 2011.
[11] 仇小鹏, 杨平利, 田传艳. 基于VC++. Net开发Geant4数值模拟程序[J]. 计算机仿真, 2007, 24(6):255-258, 262. QIU X P, YANG P L, TIAN C Y. Development of Geant4 numerical simulation program with VC++.Net[J]. Computer Simulation, 2007, 24(6):255-258, 262. (in Chinese)
[12] DING S, CHANG X H. A MATLAB-based study on the realization and approximation performance of RBF neural networks[J]. Applied Mechanics and Materials, 2013, 325-326:1746-1749.
[13] RAWLINGS J O, PANTULA S G, DICKEY D A. Applied regression analysis[M]. New York, USA:Springer, 1998.
[14] 陈雄达. 数学实验:下[M]. 上海:同济大学出版社, 2018. CHEN X D. Mathematical experiments:Part II[M]. Shanghai:Tongji University Press, 2018. (in Chinese)
[15] BERTSEKAS D P. Nonlinear programming[M]. 2nd ed. Cambridge, UK:Athena Scientific, 1999.
[16] KENNEDY J, EBERHART R. Particle swarm optimization[C]//Proceedings of International Conference on Neural Networks. Perth, Australia, 1995:1942-1948.