首页|基于SBAS-InSAR和BPNN的铀尾矿坝形变智能监测与预测

基于SBAS-InSAR和BPNN的铀尾矿坝形变智能监测与预测

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
为提高铀尾矿库退役治理的监测工作效率,提出一个基于小基线合成孔径雷达干涉测量(SBAS-InSAR)技术和反向传播神经网络(BPNN)的铀尾矿库形变智能监测与预测模型.首先,利用SBAS-InSAR技术得到铀尾矿库 2020 年 12 月—2022 年 12 月的累计形变量与年均形变速率,并用第一拦水坝的7 个全球导航卫星系统(GNSS)监测站验证InSAR监测值的精度;然后,选取铀尾矿库中的雷公塘坝、南坡横坝、战斗坝和松林坝4 个坝段的累计沉降量并结合降雨量进行沉降分析;最后,随机提取铀尾矿坝100 个沉降点的累积沉降数据,通过BPNN预测铀尾矿坝的形变.结果表明:2 年间铀尾矿库的形变速率在-60.06～34.94 mm/a,铀尾矿坝整体处于下沉状态,累计沉降量最大为-46.67 mm.BPNN预测值与实际监测值的平均绝对误差为0.586 mm,均方误差为0.624 mm.
Intelligent monitoring and prediction of deformation of uranium tailings dam based on SBAS-InSAR and BPNN
To improve the efficiency of monitoring work in the retirement treatment of uranium tailings ponds,an intelligent monitoring and prediction model of deformation of uranium tailings ponds was proposed based on SBAS-InSAR technology and BPNN.Firstly,SBAS-InSAR technology was used to obtain the cumulative deformation and annual deformation rate of the uranium tailings pond over the past two years.The accuracy of InSAR monitoring values was verified using seven Global Navigation Satellite System(GNSS)monitoring stations on the first dam.Then,the cumulative settlement of four dam sections,including Leigongtang dam,nanpo cross dam,Battle dam and Songlin dam,was selected and analyzed in conjunction with rainfall.Finally,the cumulative settlement data of 100 settlement points of the uranium tailings dam were randomly extracted to predict the deformation of the uranium tailings dam.The results show that from December 2020 to December 2022,the deformation rate of uranium tailings dam is between-60.06-34.94 mm/a.The overall settlement of the uranium tailings dam is in a sinking state,with a maximum cumulative settlement of-46.67 mm.The average absolute error between the predicted values of BPNN and the actual monitoring values is 0.586 mm,and the mean square error is 0.624 mm.

small baseline subset-interferometric synthetic aperture radar(SBAS-InSAR)back propagation neural network(BPNN)uranium tailings pondintelligent deformation monitoringsentinel-1A

周怡、彭国文、黄召、阳鹏飞、刘丹丹、陈小丽

展开 >

南华大学 资源环境与安全工程学院,湖南 衡阳 421001

中核二七二铀业有限责任公司,湖南 衡阳 421004

小基线合成孔径雷达干涉测量(SBAS-InSAR) 反向传播神经网络(BPNN) 铀尾矿库 形变智能监测 Sentinel-1A

国家自然科学基金湖南省自然科学基金

423770762023JJ50129

2024

10.16265/j.cnki.issn1003-3033.2024.04.1693

中国安全科学学报
中国职业安全健康协会

中国安全科学学报

CSTPCD北大核心
影响因子：1.548
ISSN：1003-3033
年,卷(期)：2024.34(4)
  • 17