基于特征融合并行优化模型的环境γ辐射剂量率数据分析与预测

辐射防护 ›› 2024, Vol. 44 ›› Issue (2): 126-133.

基于特征融合并行优化模型的环境γ辐射剂量率数据分析与预测

刘君武¹, 吴允平^1,2,3, 林明贵⁴

1.福建师范大学光电与信息工程学院,福州 350007;
2.数字福建环境监测物联网实验室,福州 350007;
3.福建省光电传感应用工程技术研究中心,福州 350007;
4.福建省辐射环境监督站,福州 350013

收稿日期:2022-09-19 出版日期:2024-03-20 发布日期:2024-04-19
通讯作者: 吴允平。E-mail:wyp@Fjnu.edu.cn
作者简介:刘君武(1996—),男,2018年6月毕业于河南大学物理与电子学院通信工程专业,2022年毕业于福建师范大学大数据挖掘专业,获硕士学位。E-mail:2417222070@qq.com
基金资助:
国家自然科学海峡联合基金重点项目(No.U1805263);福建省自然科学基金项目(No.2019J01427);江西省核地学数据科学与系统工程技术研究中心资助项目(JETRCNGDSS202101)。

Prediction of HPIC dose rate in radiation environment based on feature fusion and parallel optimization model

LIU Junwu¹, WU Yunping^1,2,3, LIN Minggui⁴

1. College of Photonic and Electronic Engineering, Fujian Normal University, Fuzhou 350007;
2. Digit Fujian Internet-of-Things Laboratory of Environmental Monitoring, Fuzhou 350007;
3. Fujian Provincial Engineering Technology Research Center of Photoelectric Sensing Application, Fujian Normal University, Fuzhou 350007;
4. Fujian Radiation Environment Supervision Station, Fuzhou 350013

Received:2022-09-19 Online:2024-03-20 Published:2024-04-19

摘要/Abstract

摘要： 核电辐射环境监测网(ERMS)能提供实时、连续的监测数据,是核电最重要的外围监督性设施,为辐射环境评估提供数据依据。为掌握影响辐射数据质量的特征要素与及时发现环境的辐射异常,开展高压电离室探测器(HPIC)剂量率数据的特征挖掘与预测研究,提出一种基于奇异谱分析算法(singular spectrum analysis,SSA)的γ辐射剂量率数据预处理方法,从其历史数据中学习涨幅趋势和拐点细节变化;针对数据的多维度特点,设计一种特征融合并行优化模型预测框架,以福建宁德核电站外围11个自动站辐射监测数据、天顶方向总电子含量(VTEC)数据进行实验验证。实验结果表明,该模型对环境γ辐射剂量率预测取得了较好的预测性能与精度。

关键词: 时间序列, 辐射环境, 高压电离室探测器, γ辐射剂量率, 奇异谱分析, 特征融合网络

Abstract: Environment radiation monitoring system (ERMS) around nuclear power plant can provide real-time and continuous monitoring data, which is the most important peripheral supervision facility of nuclear power plant and provides data basis for radiation environment assessment. In order to master the characteristic elements that affect the quality of radiation data and timely detect environmental radiation anomalies, data feature exploring and prediction research of γ radiation dose rate data were carried out. A preprocessing method of HPIC dose-rate data based on singular spectrum analysis was proposed to learn the increase trend and inflection point details from its historical data. According to the multidimensional characteristics of data, a SSA feature fusion parallel optimization model prediction framework was designed, and simulation experiments were carried out. Data of 11 automatic radiation monitoring stations around Ningde Nuclear Power Plant in Fujian Province and Vertical Total Electron Content (VTEC) were used for experimental verification. The experimental results show that the feature fusion network model achieves good prediction performance and accuracy for γ radiation dose rate prediction.

Key words: time series, radiation environment, HPIC, γ radiation dose rate, singular spectrum analysis, feature fusion network

中图分类号:

TP183

刘君武, 吴允平, 林明贵. 基于特征融合并行优化模型的环境γ辐射剂量率数据分析与预测[J]. 辐射防护, 2024, 44(2): 126-133.

LIU Junwu, WU Yunping, LIN Minggui. Prediction of HPIC dose rate in radiation environment based on feature fusion and parallel optimization model[J]. RADIATION PROTECTION, 2024, 44(2): 126-133.

参考文献

[1] 中国原子能科学研究院.环境地表γ辐射剂量率测定规范:GB/T 14583—1993[S].北京:中国标准出版社,1993.
[2] 朱耀明,林明贵.宁德核电厂外围环境γ辐射连续监测系统[J].海峡科学,2015,102(6):75-78+92.
[3] 沙连茂.辐射环境监测数据合理性评价中的问题探讨[J].环境监控与预警,2017,9(3):1-10.
[4] 陈爱,周睿东,陈文涛,等.降雨对连续γ辐射测量影响的数值拟合[J]. 辐射防护, 2017,37(5):361-368.
[5] 罗敦烨,沙向东,上官志洪,等.环境γ辐射剂量率连续监测数据影响因素和特征分析 [J]. 辐射防护, 2018,38(4):308-318.
LUO Dunye, SHA Xiangdong, SHANGGUAN Zhihong, et al.Study on influence factors and characteristics of continuousmonitoring data of environmental γ dose rate[J]. Radiation Protection,2018,38(4):308-318.
[6] Bossew P, Cinelli G, Hernández-Ceballos M, et al. Estimating the terrestrial gamma dose rate by decomposition of the ambient doseequivalent rate [J]. Journal of Environmental Radioactivity, 2016,166:296-308.
[7] 王蕾,王晓芬,赵顺平.核电基地周围辐射环境监督性监测概况[J].辐射防护,2019,39(2):118-123.
WANG Lei, WANG Xiaofen, ZHAO Shunping.Study on influence factors and characteristics of continuousmonitoring data of environmental γ dose rate[J].Radiation Protection,2019,39(2):118-123.
[8] FENG W, ZHANG Y, LI Y, et al. Spatial distribution, risk assessment and influence factors of terrestrial gamma radiation dose in China [J].Journal of Environmental Radioactivity, 2020,222:106325.
[9] 王明明,张晓妍.辐射环境监测领域面向大数据的应急监测数据管理与利用的探讨[J].环境保护与循环经济,2016,36(4):60-62.
[10] Sangiorgi M, Ceballos M A H, Iurlaro G, et al.30 years of European Commission Radioactivity Environmental Monitoring data bank (REMdb)—An open door to boost environmental radioactivity research[J]. Earth System Science Data, 2019(11):589-601.
[11] US DOE.US DOE(Department of Energy) to fund nuclear data research[EB/OL]. (2019-04-25)[2023-11-15].https://www.world-nuclear-news.org/Articles/US-DOE-to-fund-nuclear-data-research.2019.
[12] James Douglas Hamilton.Time series analysis[M]. Princeton: Princeton University Press,1994:43-64.
[13] Mejia J, Avelar-Sosa L, Mederos B, et al. Prediction of time series using an analysis filter bank of LSTM units[J]. Computers & Industrial Engineering, 2021, 157: 107371.
[14] Farhi N, Kohen E, Mamane H, et al. Prediction of wastewater treatment quality using LSTM neural network[J]. Environmental Technology & Innovation, 2021, 23: 101632.
[15] 袁华,陈泽濠.基于时间卷积神经网络的短时交通流预测算法[J].华南理工大学学报(自然科学版),2020,48(11):107-113+122.
[16] 张雪薇,韩震.基于ConvGRU深度学习网络模型的海表面温度预测[J].大连海洋大学学报,2022,37(3):531-538.
[17] 胡丹,孟新,路帅,等.一种并行LSTM-FCN模型在船舶航迹预测中的应用[J].控制与决策,2022,37(8):1955-1961.
[18] David H S.Singular spectrum analysis for time series with missing data[J]. Geophysical Research Letters, 2011,28(16): 3187-3190.
[19] 李嘉文,盛德仁,李蔚.基于分解去噪和LSSVM的短期风速预测[J].能源工程,2021(4):17-24.
[20] 吴坚,项颂,阎诚,等.基于奇异谱分析的超短期风电功率多步预测[J].可再生能源,2021,39(11):1548-1555.
[21] Janik M, Bossew P, Kurihara O. Machine learning methods as a tool to analyse incomplete or irregularly sampled radon time series data[J]. Science of the Total Environment,2018,630:1155-1167.
[22] 朱武峰,王廷银,林明贵,等.基于Gradient Boosting算法的ERMS辐射数据预测[J].计算机系统应用,2019,28(11):37-44.
ZHU Wufeng,WANG Tingyin,LIN Minggui, et al.Prediction of ERMS radiation data based on Gradient Boosting algorithm[J].Computer System Application,2019,28(11):37-44.
[23] 林武辉,王诗玥,黄亚萍,等.大气中γ辐射空气吸收剂量率的波动机制[J].中国环境科学,2022,42(3):1097-1103.
LIN Wuhui,WANG Shiyue,HUANG Yaping,et al.Mechanism of the variable γ radiation air absorbed dose rate in the atmosphere[J].China Environmental Science,2022,42(3):1097-1103.