[1]李翔宇,李新源,李明宇,等.基于实测数据的地铁隧道长期沉降预测模型研究[J].西安建筑科技大学学报(自然科学版),2021,53(02):186-193.[doi:10.15986/j.1006-7930.2021.02.006]
　LI Xiangyu,LI Xinyuan,LI Mingyu,et al.Research on prediction model of the long-term subsidence of shield tunnels based on in-situ monitoring data[J].J. Xi’an Univ. of Arch. & Tech.(Natural Science Edition),2021,53(02):186-193.[doi:10.15986/j.1006-7930.2021.02.006]
点击复制

基于实测数据的地铁隧道长期沉降预测模型研究()
分享到：

西安建筑科技大学学报（自然科学版）[ISSN:1006-7930/CN:61-1295/TU]

卷:
53
期数:
2021年02期
页码:
186-193
栏目:
出版日期:
2021-04-28

文章信息/Info

Title:
Research on prediction model of the long-term subsidence of shield tunnels based on in-situ monitoring data
文章编号:
1006-7930(2021)02-0186-08
作者:
李翔宇1; 2; 李新源3; 李明宇4; 聂俊霞5; 冯晓波6
(1.建筑安全与环境国家重点实验室,北京 100013; 2.中国建筑科学研究院有限公司 地基基础研究所,北京 100013; 3.徐州工程学院 土木工程学院,江苏 徐州 221018; 4.郑州大学 土木工程学院,河南 郑州450001; 5.中铁十五局集团城市轨道交通工程有限公司,河南 洛阳 471499; 6.新华通讯社机关事务管理局,北京 100803)
Author(s):
LI Xiangyu1; 2;  LI Xinyuan3;  LI Mingyu4;  NIE Junxia5;  FENG Xiaobo6
(1.State Key Laboratory of Building Safety and Built Environment,Beijing100013,China;2.Institute of Foundation Engineering,China Academy of Building Research,Beijing100013,China;3.School of Civil Engineering,Xuzhou Institute of Technology,Xuzhou221018,China;4.School of Civil Engineering,Zhengzhou University,Zhengzhou450001,China;5.Urban Rail Transit Engineering Company Limited of China Railway 15th Bureau,Luoyang471499,China;6.Government Offices Administration,Xinhua News Agency,Beijing100803,China)
关键词:
盾构隧道;  长期沉降预测模型;  GA-BP神经网络模型;  PSO-BP神经网络模型;  经验曲线模型
Keywords:
shield tunnel;  prediction model of the long-term subsidence;  GA-BP neural network model;  PSO-BP neural network model;  empirical curve model
分类号:
U45
DOI:
10.15986/j.1006-7930.2021.02.006
文献标志码:
A
摘要:
基于上海地铁二号线的实测沉降数据,运用遗传算法(GA)和粒子群算法(PSO)对传统BP神经网络进行了优化,以弥补BP神经网络在网络结构、权值和阈值选择上的随机性以及容易局部收敛等缺陷,据此提出了两种新型隧道长期沉降预测模型,即GA-BP神经网络和PSO-BP神经网络模型; 并对比研究了经验曲线、BP神经网络、GA-BP神经网络以及PSO-BP神经网络等模型方法的优缺点及预测效果.研究发现,以上各神经网络模型均取得了较为满意的预测结果,其中PSO-BP神经网络模型的预测精度最佳,且运算速度最快,是文中所提方法中最适用的盾构隧道长期沉降预测模型.
Abstract:
Based on in-situ monitoring data of Shanghai metro line 2, two new subsidence prediction models of tunnels, GA-BP neural network model and PSO-BP neural network model are proposed. These two models optimize the conventional BP neural network model by means of genetic algorithm(GA)and particle swarm optimization(PSO)in order to remedy the defects of BP neural network model,i.e. the randomness of selection on network structure, weight values and threshold values, as well as the inclination to local convergence. A comparative analysis is carried out between empirical curve, BP neural network model, GA-BP neural network model and PSO-BP neural network model, about their strengths, weaknesses and prediction effects. The results show that, PSO-BP neural network model turns to be the best model with optimal accuracy and fast operation speed, which is the most suitable prediction model for the long-term subsidence of shield tunnels, although the above prediction models have achieved appropriate prediction.

参考文献/References:

[1]刘建航, 侯学渊. 盾构法隧道[M].北京: 中国铁道出版社, 1991.
LIU Jianhang, HOU Xueyuan. Shield tunnels[M].Beijing: China Railway Press, 1991.
[2]谢雄耀, 王培, 李永盛, 等. 甬江沉管隧道长期沉降监测数据及有限元分析[J].岩土力学, 2014, 35(8): 2314-2324.
XIE Xiongyao, WANG Pei, LI Yongsheng, et al. Long-term settlement monitoring data and finite element analysis of Yongjiang immersed tunnel[J].Geotechnical Mechanics, 2014, 35(8): 2314-2324.
[3]MAIR, R J, TAYLOR R N. Bored tunnelling in the urban environment[A]//Proc.14th Int.Conf.Soil Mech.Found.Engng.Hamburg: Germany Society of Soil Mechanics and Foundation, 1997:2353-2385.
[4]张金菊. 盾构隧道引起土体变形分析研究[D].杭州:浙江大学, 2006.
ZHANG Jinju. An analytical study of soil deformation caused by shield tunnel[D].Hangzhou:Zhejiang University, 2006.
[5]李明宇. 运营地铁盾构隧道纵向变形和受力特征及规律研究[D].上海:同济大学,2011.
LI Mingyu. Longitudinal deformation and force characteristics and regularity study of operating subway shield tunnel[D].Shanghai:Tongji University, 2011.
[6]余腾, 胡伍生, 孙小荣. 基于灰色模型的地铁运营期轨行区沉降预测研究[J].现代测绘,2017,40(2):33-36.
YU Teng, HU Wusheng, SUN Xiaorong. Prediction analysis for the settlement of metro rail line interval based on the grey model during traffic operation[J].Modern Mapping, 2017,40(2):33-36.
[7]朱伟刚,徐超. BP神经网络算法在长春地铁二号线地表沉降预测中的应用[J].测绘与空间地理信息, 2018, 41(12):211-214.
ZHU Weigang, XU Chao. Application of BP neural network algorithm to surface settlement prediction of Changchun metro line two[J].Geomatics & Spatial Information Technology, 2018, 41(12):211-214.
[8]乔金丽, 范永利, 刘波, 等. 基于改进BP网络的盾构隧道开挖地表沉降预测[J].地下空间与工程学报, 2012, 8(2):352-357.
QIAO Jinli, FAN Yongli, LIU Bo, et al. Predicting the surface settlement by shield tunneling based on modified BP network[J].Chinese Journal of Underground Space and Engineering, 2012, 8(2):352-357.
[9]赵久彬, 刘元雪, 刘娜, 等. 海量监测数据下分布式BP神经网络区域滑坡空间预测方法[J].岩土力学, 2019, 40(7): 2866-2872.
ZHAO Jiubin, LIU Yuanxue, LIU Na, et al. Spatial prediction method of regional landslide based on distributed bp neural network algorithm under massive monitoring data[J].Geotechnics, 2019, 40(7): 2866-2872.
[10]崔学杰, 晏鄂川, 陈武. 基于改进遗传算法的岩体结构面产状聚类分析[J].岩土力学, 2019, 40(S1): 374-380.
CUI Xuejie, YAN Echuan, CHEN Wu. Cluster analysis of discontinuity occurrence of rock mass based on improved genetic algorithm[J].Geotechnics, 2019, 40(S1): 374-380.
[11]马春辉, 杨杰, 程琳, 等. 基于量子遗传算法与多输出混合核相关向量机的堆石坝材料参数自适应反演研究[J].岩土力学, 2019, 40(6): 2397-2406.
MA Chunhui, YANG Jie, CHENG Lin, et al. Adaptive inversion study of the material parameters of a heapstone dam based on quantum genetic algorithm and multi-output mixed-core correlation vector machine[J].Geotechnics, 2019, 40(6):2397-2406.
[12]MATLAB中文论坛编著. MATAB神经网络30个案例分析[M].北京: 北京航空航天大学出版社, 2010.
MATLAB Chinese Forum. 30 case studies of MATLAB neural networks[M].Beijing: Beijing University of Aeronautics and Astronautics Press, 2010.
[13]KENNEDY J, Eberhart R C. Particle swarm optimization[A]//IEEE International Conference on Neural Network[C].New York: IEEE Press, 1995: 1942-1948.
[14]EBERHART R C, KENNEDY J. A new optimizer using particles swarm theory[A].Sixth International Symposium on Micro Machine and Human Science. Nagoya: IEEE Service Center, 1995: 39-43.
[15]黄继红. 基于改进PSO的BP网络的研究及应用[D].长沙:长沙理工大学, 2008.
HUANG Jihong. Research and application on BP networks based on improved PSO[D].Changsha: Changsha University of Technology, 2008.
[16]邵新宇. 制造系统运行优化理论与方法[M].北京:科学出版社, 2010.
SHAO Xinyu. Theory and method of manufacturing system operation optimization[M].Beijing:Science Press, 2010.
[17]魏秀业, 潘宏侠. 粒子群优化及智能故障诊断[M].北京:国防工业出版社, 2010.
WEI Xiuye, PAN Hongyan. Particle swarm optimization and intelligent troubleshooting[M].Beijing: Defense Industry Press, 2010.
[18]沈圆顺. 青岛地区土岩组合基坑变形特性与风险评价研究[D].上海:同济大学, 2012.
SHEN Yuanshun. Study on the deformation characteristics and risk evaluation of soil and rock combination pit in Qingdao[D].Shanghai:Tongji University, 2012.
[19]王爱平, 江丽. 基于PSO的BP神经网络学习算法[J].计算机工程, 2012, 38(21): 193-196.
WANG Aiping, JIANG Li. BP neural network learning algorithm based on PSO[J].Computer Engineering, 2012, 38(21): 193-196.
(编辑 桂智刚)

相似文献/References:

[1]朱艳峰,张雪松,王和平.复变函数法计算圆形盾构隧道周边土体位移[J].西安建筑科技大学学报(自然科学版),2020,52(03):335.[doi:10.15986/j.1006-7930.2020.03.005]
　ZHU Yanfeng,ZHANG Xuesong,WANG Heping.Calculation of settlement of soil around circular shield tunnel by complex variable method[J].J. Xi’an Univ. of Arch. & Tech.(Natural Science Edition),2020,52(02):335.[doi:10.15986/j.1006-7930.2020.03.005]
[2]胡长明,郭建霞,梅 源,等.盾构同步注浆浆液压力影响因素及扩散机理[J].西安建筑科技大学学报(自然科学版),2020,52(05):617.[doi:10.15986j.1006-7930.2020.05.001 ]
　HU Changming,GUO Jianxia,MEI Yuan,et al.Influence factors and diffusion mechanism of pressure of shield synchronous grouting slurry[J].J. Xi’an Univ. of Arch. & Tech.(Natural Science Edition),2020,52(02):617.[doi:10.15986j.1006-7930.2020.05.001 ]

备注/Memo

备注/Memo:
收稿日期:2020-07-26 修改稿日期:2021-03-18
基金项目:中国建筑科学研究院有限公司青年科研基金资助项目(20161602331030048); 国家自然科学基金资助项目(51508520); 河南省住房城乡建设科技计划资金资助项目(K-1817、K-1818、K1816、K-1940)
第一作者:李翔宇(1984-),男,博士,高级工程师.主要从事岩土工程及地下结构工程方面的研究.E-mail:leexiangyu@126.com
更新日期/Last Update: 2021-04-28