神经网络算法在我国核领域中的应用综述
An Overview of the Application of Neural Network Algorithm in the Nuclear Field of China
DOI: 10.12677/NST.2020.81003, PDF,  被引量   
作者: 杨红义, 王东东：中国原子能科学研究院，北京；王 端：核工业研究生部，北京
关键词: 人工智能；核领域；神经网络；深度学习；Artificial Intelligence； Nuclear Field； Neural Network； Deep Learning
摘要: 在新一轮科技革命的浪潮中，各国纷纷把人工智能提升到国家战略层面。本文首先介绍了人工智能概念、发展历史、当前的研究重点和发展态势，阐述推动人工智能与我国核工业融合应用的必要性。接着介绍了当前人工智能的核心技术——基于深度学习的神经网络算法的发展历史、主要的四种网络模型，重点分析它在核领域的典型实例、应用现状和未来趋势，最后为加强我国核工业智能化发展提出几点建议。
Abstract: In the new wave of scientific and technological revolution, countries have upgraded artificial in-telligence to the level of national strategy. This paper first introduces the concept, development history, current research focus and development trend of AI, and expounds the necessity of pro-moting the integration of AI and China’s nuclear industry. Then it introduces the development history and four main network models of the current core technology of artificial intelligence, which is based on the deep learning neural network algorithm. It focuses on the analysis of its typical examples, application status and future trend in the nuclear field. Finally, it puts forward some suggestions to strengthen the development of the intelligence of China's nuclear industry.
文章引用：杨红义, 王端, 王东东. 神经网络算法在我国核领域中的应用综述[J]. 核科学与技术, 2020, 8(1): 19-34. https://doi.org/10.12677/NST.2020.81003

参考文献

[1] McCarthy, J., Minsky, M.L., Shannon, C., et al. (1955) A Proposal for the Dartmouth Summer Research Project on Ar-tificial Intelligence. Dartmouth, 31 August 1955.
[2] Mcculloch, W.S. and Pitts, W.H. (1942) A Logical Calculus of Ideas Immanent in Nervous Activity. The Bulletin of Mathematical Biophysics, 5, 115-133. [Google Scholar] [CrossRef] 
[3] Rosenblatt, F. (1958) The Perceptron: A Probabilistic Model for Information Storage and Organization in the Brain. Psychological Review, 65, 386-408. [Google Scholar] [CrossRef] [PubMed]
[4] Minsky, M.L. and Papert, S. (1969) Perceptrons: An Introduction to Computational Geometry. MIT Press, Cambridge.
[5] Rumelhart, D.E. (1986) Learning Representations by Back-Propagating Errors. Nature, 23, 533-536. [Google Scholar] [CrossRef] 
[6] Cybenko, G. (1989) Approximation by Superpositions of a Sigmoidal Function. Mathematics of Control, Signals and Systems, 2, 303-314. [Google Scholar] [CrossRef] 
[7] Hornic, K. (1989) Multilayer Feed forward Networks Are Universal Approximators. Neural Networks, 2, 359-366. [Google Scholar] [CrossRef] 
[8] Lecun, Y., Boser, B., Denker, J.S., et al. (1989) Back-Propagation Applied to Handwritten Zip Code Recognition. Neural Computation, 1, 541-551. [Google Scholar] [CrossRef] 
[9] Lecun, Y. (1990) Handwritten Digit Recognition with a Back-Propagation Network. In: Touretzky, D.S., Ed., Advances in Neural Information Processing Systems, Vol. 2, Morgan Kaufmann, Burlington, 396-404.
[10] Cortes, C. and Vapnik, V. (1995) Support-Vector Networks. Machine Learning, 20, 273-297. [Google Scholar] [CrossRef] 
[11] Hinton, G.E. (2005) What Kind of a Graphical Model Is the Brain? In: International Joint Conference on Artificial Intelligence, Morgan Kaufmann Publishers Inc., Burlington, 1765-1775.
[12] Hinton, G.E. and Salakhutdinov, R.R. (2006) Reducing the Dimensionality of Data with Neural Networks. Science, 313, 504-507. [Google Scholar] [CrossRef] [PubMed]
[13] Hinton, G.E., Osindero, S. and The, Y.W. (2006) A Fast Learning Algorithm for Deep Belief Nets. Neural Computation, 18, 1527-1554. [Google Scholar] [CrossRef] [PubMed]
[14] Bengio, Y., Lamblin, P., Dan, P., et al. (2007) Greedy Layer-Wise Training of Deep Networks. Advances in Neural Information Processing Systems, 19, 153-160.
[15] Ranzato, M., Poultney, C., Chopra, S., et al. (2006) Efficient Learning of Sparse Representations with an Energy-Based Model. Advances in Neural Information Processing Systems (NIPS 2006), Vancouver, 1137-1144.
[16] Glorot, X., Bordes, A. and Bengio, Y. (2011) Deep Sparse Rectifier Neural Networks. In: International Conference on Artificial Intelligence and Statistics, IEEE, Piscataway, 315-323.
[17] Hinton, G., Deng, L., Yu, D., et al. (2012) Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups. IEEE Signal Processing Magazine, 29, 82-97. [Google Scholar] [CrossRef] 
[18] Dahl, G.E., Yu, D., Deng, L., et al. (2012) Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition. IEEE Transactions on Audio, Speech and Language Processing, 20, 30-42. [Google Scholar] [CrossRef] 
[19] Deng, J., Dong, W., Socher, R., et al. (2009) ImageNet: A Large-Scale Hierarchical Image Database. IEEE Conference on Computer Vision & Pattern Recognition, Miami, 20-25 June 2009, 248-255. [Google Scholar] [CrossRef] 
[20] Krizhevsky, A., Sutskever, I. and Hinton, G. (2012) ImageNet Classification with Deep Convolutional Neural Networks. In: NIPS, Curran Associates Inc., Red Hook, 84-90.
[21] Dauphin, Y., Pascanu, R., Gulcehre, C., et al. (2014) Identifying and Attacking the Saddle Point Problem in High-Dimensional Non-Convex Optimization. Advances in Neural Information Processing Systems, 27, 2933-2941.
[22] Choromanska, A., Henaff, M., Mathieu, M., et al. (2014) The Loss Surface of Multilayer Networks. 192-204.
[23] Montúfar, G., Pascanu, R., Cho, K., et al. (2014) On the Number of Linear Regions of Deep Neural Networks. Advances in Neural Information Processing Systems, Montreal, 8-13 December 2014, 2924-2932.
[24] Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., et al. (2014) Generative Adversarial Nets. Proceedings of the 27th International Conference on Neural Information Processing Systems, 2, 2672-2680.
[25] 王端, 王威策, 潘翠杰, 王东东. 基于自适应BP神经网络的压水堆堆芯换料关键参数的预测方法[J]. 原子能科学技术, 2019, doi:10.7538/yzk.2019.youxian.0016.
[26] 王东东, 杨红义, 王端, 林超, 王威策. 中国实验快堆热工参数的自适应BP神经网络预测方法研究[J]. 原子能科学技术, 2019, doi:10.7538/yzk.2019.youxian.0751.
[27] 蔡宛睿, 夏虹, 杨波. 基于BP神经网络的堆芯三维功率重构方法研究[J]. 原子能科学技术, 2018, 52(12): 2130-2135.
[28] 夏虹, 李彬, 刘建新. 基于RBF神经网络的压水堆堆芯三维功率分布方法研究[J]. 原子能科学技术, 2014(4): 698-702.
[29] 袁灿, 蔡琦, 刘钢, 等. 基于神经网络的核动力一回路专家系统故障诊断[J]. 原子能科学技术, 2014, 48(Z1): 485-490.
[30] 毛伟, 余刃, 周萌. 基于改进粒子群算法的神经网络及其在核电站故障诊断中的应用[J]. 海军工程大学学报, 2014, 26(3): 104-107.
[31] 韩龙, 周刚, 孙旭升. 基于集成神经网络与模糊逻辑融合的稳压器泄漏监测方法[J]. 原子能科学技术, 2014, 48(Z1): 474-479.
[32] 于志翔, 邹树梁, 徐守龙, 等. 基于BP神经网络的船用反应堆屏蔽设计快速计算功能研究[J]. 核电子学与探测技术, 2016, 36(2): 209-213.
[33] 李君利. 实验室γ能谱测量与分析[M]. 北京: 人民交通出版社, 2014.
[34] 张子平. 高能物理实验中的前馈式神经元网络法应用[J]. 现代物理知识, 1994, 6(6): 22.
[35] Marone, A., Fiorini, C., Baraldi, P., et al. (2009) Employing Neural Network to Determine the Position of Interaction of Medium-High Energy Gamma Rays. IEEE Nuclear Science Symposium Conference Record (NSS/MIC), Orlando, 24 October-1 November 2009, 645-649. [Google Scholar] [CrossRef] 
[36] 陈泽民, 李明涛, 徐四大, 等. 用人工神经网络识别复杂γ能谱[J]. 核技术, 1996, 19(8): 449-454.
[37] 刘议聪, 朱泓光, 宋永强. 一种改进粒子群算法优化BP神经网络实现核素识别方法[J]. 兵工自动化, 2016, 35(4): 91-95.
[38] 祝美英, 袁成前, 刘艳芳, 等. 基于BP神经网络的核素快速识别算法[J]. 核电子学与探测技术, 2018, 38(2): 138-142.
[39] 白立新, 张一云, 徐家云, 等. 基于MATLAB的γ谱人工神经网络分析方法[J]. 核电子学与探测技术, 2003, 23(5): 404-406.
[40] 赵立林, 杨亚新, 郑勇明, 等. 神经网络算法解析便携式高纯锗γ谱[J]. 东华理工大学学报(自然科学版), 2013, 36(s1): 79-83.
[41] Nil, K. (2008) Modeling of Gamma-Ray Energy Absorption Buildup Factors Using Neural Network. Annals of Nuclear Energy, 35, 1787-1790. [Google Scholar] [CrossRef] 
[42] 霍建文, 张华, 王坤朋, 等. 基于概率神经网络的放射性核素快速识别方法研究[J]. 核电子学与探测技术, 2015, 35(3): 35-40.
[43] 王百荣, 吴泽乾. 利用LVQ神经网络识别放射性核素[J]. 核电子学与探测技术, 2018, 38(4): 572-576.
[44] Zhang, C.F., et al. (2019) Identification of SNM Based on Low-Resolution Gamma-Ray Characteristics and Neural Network. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 927, 155-160. [Google Scholar] [CrossRef] 
[45] 吴珊珊. 基于神经网络与EM算法的稀疏投影SPECT重建[D]: [硕士学位论文]. 北京: 北京理工大学, 2015.
[46] 叶奇蓁. 未来我国核能技术发展的主要方向和重点[J]. 中国核电, 2018(2): 130-133.
[47] Szegedy, C., Zaremba, W., Sutskever, I., et al. (2013) Intriguing Properties of Neural Networks. Computer Science.