强激光与粒子束, 2011, 23 (8): 2224, 网络出版: 2011-09-20   

基于Elman神经网络的252Cf源核系统随机中子脉冲信号识别方法

Identification of stochastic neutron pulse signal of 252Cf nuclear system based on Elman neural network
作者单位
重庆大学 光电工程学院, 光电技术及系统教育部重点实验室, 重庆 400044
摘要
针对252Cf自发裂变中子源构成的核信息系统,以实际所测随机中子脉冲数据的自相关函数为研究对象,借助仿真实验, 利用Elman神经网络对不同质量核材料进行识别。在实测数据的基础上,通过叠加随机抖动,模拟产生了不同质量核材料的相关函数样本,并将其用于神经网络的训练与测试,实验结果表明,训练过的Elman神经网络能够较好地识别相关函数的特征,分辨不同质量的核材料,平均识别率达到85%,综合平均误差为0.04,且具有较高的鲁棒性。
Abstract
Correct and effective identification of nuclear material is a key part for nuclear weapon’s verification. Based on the nuclear information system constructed with 252Cf spontaneous neutron source, the simulated autocorrelation functions are utilized for identification of different fissile mass with Elman neural network. The experimental results show the trained Elman neural network is able to distinguish the characteristics of autocorrelation function, identify different fissile mass, and the average identification rate reaches 85% and keep average synthesis error smaller than 0.04 with high robustness.
参考文献

[1] 刘成安,伍钧.核军备控制核查技术概论[M].北京:国防工业出版社,2007:26-40.(Liu Cheng’an, Wu Jun. Nuclear arms control and verification technology concept. Beijing: National Defense Industry Press, 2007: 26-40)

[2] Mihalczo J T, Blackman E D, Ragan G E, et al. Dynamic sub-criticality measurements using the 252Cf-source-driven noise analysis method[J]. Nuclear Science Engineering, 1990,94(3): 336-360.

[3] Mihalczo J T , Mullens J A , Mattingly J K, et al. Physical description of nuclear materials identification system (NMIS) signatures[J].Nuclear Instruments and Methods in Physics Research A,2000,450(2):531-555.

[4] 郝樊华,胡广春,刘素萍,等. 钚体源样品γ能谱计算的蒙特卡罗方法[J]. 物理学报,2005,54(8):3523-3529.(Hao Fanhua, Hu Guangchun, Liu Suping, et al. Monte-Carlo method in calculating the γ spectrum of plutonium volume source.Acta Physica Sinica,2005,54(8):3523-3529)

[5] 边肇祺,张学工. 模式识别[M].北京:清华大学版社,2001:250-271.(Bian Zhaoqi, Zhang Xuegong. Pattern recognition.Beijing:Tsinghua University Press, 2001:250-271)

[6] 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(6):721-722.(Di Yuming, Xu Wei, Xu Peng, et al. A method of γ spectrum identification based on the BP neural network.Nuclear Electronics and Detection Technology,2006,26(6): 721-722)

[7] 高钦,王孙安. 基于Elman神经网络的非线性动态系统辨识[J].计算机工程与应用,2007,43(31):87-89.(Gao Qin, Wang Sun’an. Identification of nonlinear dynamic system based on Elman neural network.Computer Engineer and Applications,2007,43(31):87-89)

[8] 魏彪,任勇,冯鹏,等. 基于252Cf裂变中子源的核信息系统频谱分析[J]. 强激光与粒子束,2009,21(12):1898-1902.(Wei Biao, Ren Yong, Feng Peng, et al. Spectrum analysis of nuclear information system based on 252Cf fission source. High Power Laser and Particle Beams, 2009,21(12): 1898-1902)

[9] 任勇,米德伶,魏彪,等. 252Cf裂变中子信号功率谱密度分析系统[J]. 核动力工程,2010,31(2):140-144.(Ren Yong, Mi Deling,Wei Biao, et al. Power spectrum density analysis system of 252Cf neutron signals. Nuclear Power Engineering,2010,31(2):140-144)

[10] Mi Deling, Liu Siyuan, Feng Peng, et. al. The experimental research of nuclear stochastic signal measurement system based on 252Cf neutron source[C]//2010 International Conference on Computer Application and System Modeling.2010:525-528.

[11] Mattingly J K, Valentine T E, Mihalczo J T. NWIS measurements for uranium metal annular castings[R]. Y/LB-15.971, 1998.

[12] Pozzia S A, Segovia J. 252Cf source-correlated transmission measurements and genetic programming for nuclear safeguards[J]. Nucl Instru and Meth in Phys Res A, 2002,491(1/2): 326-341.

冯鹏, 刘思远, 米德伶. 基于Elman神经网络的252Cf源核系统随机中子脉冲信号识别方法[J]. 强激光与粒子束, 2011, 23(8): 2224. Feng Peng, Liu Siyuan, Mi Deling. Identification of stochastic neutron pulse signal of 252Cf nuclear system based on Elman neural network[J]. High Power Laser and Particle Beams, 2011, 23(8): 2224.

本文已被 2 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!