基于长短期记忆网络的涉核运输事故后果预测

阮灵盼; 陈春花; 陈黎伟; 阮方; 李夏娟; 汪建业

doi:10.11889/j.1000-3436.2023-0016

您当前的位置：

首页 >

文章列表页 >

基于长短期记忆网络的涉核运输事故后果预测

辐射防护 | 更新时间：2023-08-29

- 基于长短期记忆网络的涉核运输事故后果预测
- Consequence prediction in nuclear transport explosion accident using long short-term memory network
- 辐射研究与辐射工艺学报 2023年41卷第4期页码：40601
- 作者机构：
  
  1.中国科学院合肥物质科学研究院合肥 230031
  2.中国科学技术大学合肥 230026
  3.合肥师范学院合肥 230026
- 作者简介：
  
  阮灵盼，男，1998年2月出生，2020年毕业于浙江工业大学并获得理学学士学位，现为能源动力硕士研究生，从事核素扩散模拟技术研究
  陈春花，博士，副研究员，E-mail: chunhua.chen@inest.cas.cn
- 基金信息：
  
  安徽省高校优秀青年人才支持计划一般项目(gxyq2022060)
- DOI：10.11889/j.1000-3436.2023-0016
  中图分类号：
扫描看全文
阮灵盼, 陈春花, 陈黎伟, 等. 基于长短期记忆网络的涉核运输事故后果预测[J]. 辐射研究与辐射工艺学报, 2023,41(4):040601.

RUAN Lingpan, CHEN Chunhua, CHEN Liwei, et al. Consequence prediction in nuclear transport explosion accident using long short-term memory network[J]. Journal of Radiation Research and Radiation Processing, 2023,41(4):040601.
阮灵盼, 陈春花, 陈黎伟, 等. 基于长短期记忆网络的涉核运输事故后果预测[J]. 辐射研究与辐射工艺学报, 2023,41(4):040601. DOI： 10.11889/j.1000-3436.2023-0016.

RUAN Lingpan, CHEN Chunhua, CHEN Liwei, et al. Consequence prediction in nuclear transport explosion accident using long short-term memory network[J]. Journal of Radiation Research and Radiation Processing, 2023,41(4):040601. DOI： 10.11889/j.1000-3436.2023-0016.

摘要

涉核部件在运输过程中，会因不可抗力因素发生化学爆炸事故，造成放射性核素的泄漏。在此类源项信息不完整、地形复杂的放射性核素扩散情景下，实现核素浓度变化的快速预测对于核应急决策具有重要意义。本文以山丘下垫面下含钚炸药运输化学爆炸事故为研究场景，提出了一种基于堆叠式LSTM网络的核运输爆炸事故放射性核素浓度预测方法。本文通过计算流体学（CFD）软件OpenFOAM模拟生成放射性核素Pu-239的扩散数据，根据地理特征和人口密度，选择特定区域的核素浓度和气象时序数据作为堆叠式LSTM网络训练和预测的数据集。基于网格搜索寻找局部最优的模型结构，最终所提出的模型在150次迭代内可以稳定地达到平均绝对百分比误差（MAPE）低于5%的Pu-239核素浓度预测效果。该模型具有较好的预测效率，在突发核应急场景中具有较高的实用价值。

Abstract

During the transportation of components related to nuclear materials, accidental chemical explosions may occur, resulting in the release of radionuclides. Effective decision-making during nuclear transport accidents, especially in cases with incomplete source information and a complex terrain, requires the rapid prediction of changes in radionuclide concentration. This paper proposes a method for predicting the concentration of radionuclides resulting from nuclear transport explosion accidents based on stacked long short-term memory (LSTM) networks. Specifically, this study considered plutonium-containing explosive transport and chemical explosion accidents under the pad surface of a hill as a research scenario. The diffusion data of radionuclide Pu-239 were simulated using the computational fluid dynamics (CFD) software OpenFOAM. Nuclide concentration and meteorological time series data of a specific area were selected for stacked LSTM network training and prediction based on geographical characteristics and population density. The proposed model, optimized using grid search, can stably achieve a mean absolute percentage error (MAPE) of less than 5% within 150 iterations for Pu-239 nuclide concentration prediction. The model is highly efficient and has significant practical value for use in nuclear emergencies.

关键词

核应急化学爆炸事故涉核运输放射性核素

Keywords

Nuclear emergencyChemical explosion accidentNuclear transportRadionuclide concentration prediction

references

Scarlett H. Nuclear weapon accident response overview[R]. United States: Los Alamos Nation Laboray, 2020. DOI: 10.2172/1638614http://dx.doi.org/10.2172/1638614.

Niezing J. Broken arrows and bent spears: towards a social theory of nuclear weapon accidents[J]. Bulletin of Peace Proposals, 1980, 11(1): 71-78. DOI: 10.1177/096701068001100107http://dx.doi.org/10.1177/096701068001100107.

Wang W, Bai C, Huo Y, et al. Research of American nuclear weapon accident and response procedures[J]. International Core Journal of Engineering, 2022, 8(1): 648-655. DOI: 10.6919/ICJE.202201_8(1).0091http://dx.doi.org/10.6919/ICJE.202201_8(1).0091.

Mian Z, Ramana M V, Rajaraman R. Plutonium dispersal and health hazards from nuclear weapon accidents[J]. Current Science, 2001, 80(10): 1275-1284.

古晓娜, 王仲文, 刘占旗, 等. 钚作业人群流行病学研究进展[J]. 辐射防护, 2021, 41(4): 289-294.

GU Xiaona, WANG Zhongwen, LIU Zhanqi, et al. Research progress of epidemiology on plutonium workers[J]. Radiation Protection, 2021, 41(4): 289-294.

Kreisheimer M, Koshurnikova N A, Nekolla E, et al. Lung cancer mortality among male nuclear workers of the Mayak facilities in the former Soviet Union[J]. Radiation Research, 2000, 154(1): 3-11. DOI: 10.1667/0033-7587(2000)154http://dx.doi.org/10.1667/0033-7587(2000)154[0003:LCMAMN]2.0.CO;2.

Leelőssy Á, Lagzi I, Kovács A, et al. A review of numerical models to predict the atmospheric dispersion of radionuclides[J]. Journal of Environmental Radioactivity, 2018, 182: 20-33. DOI: 10.1016/j.jenvrad. 2017.11.009http://dx.doi.org/10.1016/j.jenvrad.2017.11.009.

Leelőssy Á, Molnár F, Izsák F, et al. Dispersion modeling of air pollutants in the atmosphere: a review[J]. Central European Journal of Geosciences, 2014, 6(3): 257-278. DOI: 10.2478/s13533-012-0188-6http://dx.doi.org/10.2478/s13533-012-0188-6.

Jeong H, Park M, Jeong H, et al. Terrain and building effects on the transport of radioactive material at a nuclear site[J]. Annals of Nuclear Energy, 2014, 68: 157-162. DOI: 10.1016/j.anucene.2014.01.004http://dx.doi.org/10.1016/j.anucene.2014.01.004.

Leelőssy Á, Mészáros R, Kovács A, et al. Numerical simulations of atmospheric dispersion of iodine-131 by different models[J]. PLoS One, 2017, 12(2): e0172312. DOI: 10.1371/journal.pone.0172312http://dx.doi.org/10.1371/journal.pone.0172312.

Vach M, Duong V M. Numerical modeling of flow fields and dispersion of passive pollutants in the vicinity of the temelín nuclear power plant[J]. Environmental Modeling & Assessment, 2011, 16(2): 135-143. DOI: 10.1007/s10666-010-9239-xhttp://dx.doi.org/10.1007/s10666-010-9239-x.

Vervecken L, Camps J, Meyers J. Dynamic dose assessment by Large Eddy Simulation of the near-range atmospheric dispersion[J]. Journal of Radiological Protection, 2015, 35(1): 165-178. DOI: 10.1088/0952-4746/35/1/165http://dx.doi.org/10.1088/0952-4746/35/1/165.

Ferziger J H, Perić M, Street R L. Computational methods for fluid dynamics[M]. 3rd ed. New York: Springer-Verlag Berlin Heidelberg, 2002. DOI: 10.1007/978-3-642-56026-2http://dx.doi.org/10.1007/978-3-642-56026-2.

Mazzoldi A, Hill T, Colls J J. CFD and Gaussian atmospheric dispersion models: a comparison for leak from carbon dioxide transportation and storage facilities[J]. Atmospheric Environment, 2008, 42(34): 8046-8054. DOI: 10.1016/j.atmosenv.2008.06.038http://dx.doi.org/10.1016/j.atmosenv.2008.06.038.

Fabritius B, Tabor G. Improving the quality of finite volume meshes through genetic optimisation[J]. Engineering with Computers, 2016, 32(3): 425-440. DOI: 10.1007/s00366-015-0423-0http://dx.doi.org/10.1007/s00366-015-0423-0.

Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780. DOI: 10.1162/neco.1997.9.8.1735http://dx.doi.org/10.1162/neco.1997.9.8.1735.

Zhao J C, Deng F, Cai Y Y, et al. Long short-term memory - Fully connected (LSTM-FC) neural network for PM2.5 concentration prediction[J]. Chemosphere, 2019, 220: 486-492. DOI: 10.1016/j.chemosphere.2018. 12.128http://dx.doi.org/10.1016/j.chemosphere.2018.12.128.

Yang G F, Yuan E B, Wu W J. Predicting the long-term CO2 concentration in classrooms based on the BO-EMD-LSTM model[J]. Building and Environment, 2022, 224: 109568. DOI: 1016/j.buildenv.2022.109568http://dx.doi.org/1016/j.buildenv.2022.109568.

Lyu P Y, Chen N, Mao S J, et al. LSTM based encoder-decoder for short-term predictions of gas concentration using multi-sensor fusion[J]. Process Safety and Environmental Protection, 2020, 137: 93-105. DOI: 10. 1016/j.psep.2020.02.021http://dx.doi.org/10.1016/j.psep.2020.02.021.

陈黎伟, 陶龙龙, 周百昌, 等. 乏燃料公路运输事故条件下放射性核素弥散模型研究[J]. 核科学与工程, 2020, 40(2): 233-243. DOI: 10.3969/j.issn.0258-0918.2020. 02.009http://dx.doi.org/10.3969/j.issn.0258-0918.2020.02.009.

CHEN Liwei, TAO Longlong, ZHOU Baichang, et al. Radionuclide dispersion model for accident condition of spent fuel highway transport[J]. Nuclear Science and Engineering, 2020, 40(2): 233-243. DOI: 10.3969/j.issn. 0258-0918.2020.02.009http://dx.doi.org/10.3969/j.issn.0258-0918.2020.02.009.

Guo D Q, Wang J K, Ge D C, et al. Oceanic radionuclide dispersion method investigation for nonfixed source from marine reactor accident[J]. Science and Technology of Nuclear Installations, 2022, 2022: 2822857. DOI: 10. 1155/2022/2822857http://dx.doi.org/10.1155/2022/2822857.

Hermans M, Schrauwen B. Training and analyzing deep recurrent neural networks[C]. Proceedings of the 26th International Conference on Neural Information Processing Systems - Volume 1. New York: ACM, 2013: 190-198. DOI: 10.5555/2999611.2999633http://dx.doi.org/10.5555/2999611.2999633.

Pascanu R, Gulcehre C, Cho K, et al. How to construct deep recurrent neural networks[EB/OL]. (2014-04-24)[2023-01-17]. https://arxiv.org/abs/1312.6026https://arxiv.org/abs/1312.6026. 10.1007/978-3-031-29642-0_8http://dx.doi.org/10.1007/978-3-031-29642-0_8

Graves A, Mohamed A R, Hinton G. Speech recognition with deep recurrent neural networks[C]. 2013 IEEE International Conference on Acoustics, Speech and Signal Processing. Vancouver BC, Canada: IEEE, 2013: 6645-6649. DOI: 10.1109/ICASSP.2013.6638947http://dx.doi.org/10.1109/ICASSP.2013.6638947.

Steele C M, Wald T L, Chanin D I. Plutonium explosive dispersal modeling using the MACCS2 computer code[R]. United States: Los Alamos Nation Lab, 1998. DOI: 10.2172/677008http://dx.doi.org/10.2172/677008.

Stephens D R. Source terms for plutonium aerosolization from nuclear weapon accidents[R]. United States: Lawrence Livermore National Laborator, 1995. DOI: 10.2172/109677http://dx.doi.org/10.2172/109677.

唐秀欢, 杨宁, 包利红, 等. 核武器运输炸药爆炸事故气溶胶扩散数值模拟[J]. 安全与环境学报, 2014, 14(1): 142-148. DOI: 10.13637/j.issn.1009-6094.2014.01.034http://dx.doi.org/10.13637/j.issn.1009-6094.2014.01.034.

TANG Xiuhuan, YANG Ning, BAO Lihong, et al. Numerical simulation of aerosol dispersion with the explosive’s detonation in the process of nuclear weapon transportation[J]. Journal of Safety and Environment, 2014, 14(1): 142-148. DOI: 10.13637/j.issn.1009-6094. 2014.01.034http://dx.doi.org/10.13637/j.issn.1009-6094.2014.01.034.

Ghasemian M, Amini S, Princevac M. The influence of roadside solid and vegetation barriers on near-road air quality[J]. Atmospheric Environment, 2017, 170: 108-117. DOI: 10.1016/j.atmosenv.2017.09.028http://dx.doi.org/10.1016/j.atmosenv.2017.09.028.

谢朝阳, 罗景润. 炸药爆炸条件下钚气溶胶扩散研究综述[J]. 安全与环境工程, 2007, 14(1): 122-126. DOI: 10.3969/j.issn.1671-1556.2007.01.033http://dx.doi.org/10.3969/j.issn.1671-1556.2007.01.033.

XIE Chaoyang, LUO Jingrun. The review of plutonium aerosol dispersal by explosive detonation[J]. Safety and Environmental Engineering, 2007, 14(1): 122-126. DOI: 10.3969/j.issn.1671-1556.2007.01.033http://dx.doi.org/10.3969/j.issn.1671-1556.2007.01.033.

刘文杰, 马庆鹏, 田立智, 等. 炸药化学爆炸环境中模拟钚气溶胶源项实验研究[J]. 兵工学报, 2016, 37(3): 447-454. DOI: 10.3969/j.issn.1000-1093.2016.03.009http://dx.doi.org/10.3969/j.issn.1000-1093.2016.03.009.

LIU Wenjie, MA Qingpeng, TIAN Lizhi, et al. Experimental simulation of aerosol source term of surrogate plutonium produced by high-explosive detonation[J]. Acta Armamentarii, 2016, 37(3): 447-454. DOI: 10.3969/j.issn.1000-1093.2016.03.009http://dx.doi.org/10.3969/j.issn.1000-1093.2016.03.009.

Kingma D P, Ba J. Adam: a method for stochastic optimization[EB/OL]. (2017-01-30)[2023-01-17]. https://arxiv.org/abs/1412.6980https://arxiv.org/abs/1412.6980.

Ruder S. An overview of gradient descent optimization algorithms[EB/OL]. (2017-06-15)[2023-01-17]. https://arxiv.org/abs/1609.04747https://arxiv.org/abs/1609.04747. 10.1017/9781108699211.008http://dx.doi.org/10.1017/9781108699211.008

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于剂量权重因子与蚁群算法耦合的核应急路径规划仿真