地铁车站施工过程中地表沉降的NARXNN时间序列预测模型

doi:10.13722/j.cnki.jrme.2014.0643

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (319 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract How to precisely predict the ground subsidence induced by metro station construction becomes the key problem in urban underground engineering. A NARXNN time series prediction model is proposed due to the single linearity of traditional time series prediction model and its static limitation caused by ignorance of construction factor. In order to take the process of metro station construction into consideration nonlinearly and dynamically，construction impact factors，as a part of external inputs，are applied in this model that itself has delay unit and feedback architecture. Based on the NARXNN time series prediction model，the prediction results of ground subsidence induced by the Beihaibei station of Beijing metro line 6 construction show that：(1) Compared with traditional ARMA time series prediction model，NARXNN time series prediction model has a better adaptability and precision. (2) The NARXNN time series prediction model has a precise trend forecast at breakpoints of the settlement-time curve. (3) Multiple construction impact factors or subdividing each group of construction impact factors can be used to improve forecasting precision in using NARXNN time series prediction model.

Key words： underground engineering nonlinear autoregressive with exogenous input neural network construction impact factors time series metro station ground subsidence

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors

Cite this article:

URL:

https://rockmech.whrsm.ac.cn/EN/10.13722/j.cnki.jrme.2014.0643 OR https://rockmech.whrsm.ac.cn/EN/Y2015/V34/Is1/3306

[1] 黄宏伟. 城市隧道与地下工程的发展与展望[J]. 地下空间，2001，(4)：311–317.(HUANG Hongwei. Development and prospect of urban tunnel and underground construction[J]. Underground Space，2001，(4)：311–317.(in Chinese)) [2] PECK R B. Deep excavation and tunneling in soft ground[C]// Proceedings of the 7th International Conference on Soil Mechanics and Foundation Engineering. Mexico City：[s. n.]，1969：225–290. [3] BOBET A. Analytical solutions for shallow tunnels in saturated ground[J]. Journal of Engineering Mechanics.，2001，(12)：1 258–1 266. [4] 吴波，刘维宁，索晓明. 隧道降水施工地表沉降的渗流–应力耦合分析[J]. 岩石力学与工程学报，2006，25(增1)：2 979–2 984.(WU Bo，LIU Weining，SUO Xiaoming. Seepage and stress coupling analysis of land subsidence induced by dewatering and tunneling[J]. Chinese Journal of Rock Mechanics and Engineering，2006，25(Supp.1)：2 979–2 984.(in Chinese)) [5] 宋卫东，谢政平，张继清. 天坛东门站浅埋暗挖施工顺序对地表沉降影响的数值模拟分析[J]. 岩石力学与工程学报，2005，24(增2)：5 773–5 778.(SONG Weidong，XIE Zhengping，ZHANG Jiqing. Numerical analysis of ground surface subsidence caused by construction orders of shallow excavation method at TIANTAN east station[J]. Chinese Journal of Rock Mechanics and Engineering，2005，24(Supp.2)：5 773–5 778.(in Chinese)) [6] 贾剑，石景山，周顺华，等. 盾构隧道扩建地铁车站地表沉降预测及分析[J]. 岩石力学与工程学报，2013，32(增1)：2 883–2 890. (JIA Jian，SHI Jingshan，ZHOU Shunhua，et al. Forecast and analysis of surface settlement of metro station constructed by shield tunnel expanding[J]. Chinese Journal of Rock Mechanics and Engineering，2013，32(Supp.1)：2 883–2 890.(in Chinese)) [7] 翁效林，王俊，张刚，等. 黄土地区地铁开挖引起地表沉降试验分析[J]. 岩石力学与工程学报，2007，26(增2)：4 348–4 352. (WENG Xiaolin，WANG Jun，ZHANG Gang，et al. Test study on ground subsidence caused by metro excavation in loess area[J]. Chinese Journal of Rock Mechanics and Engineering，2007，26(Supp.2)：4 348–4 352.(in Chinese)) [8] 潘国荣，王穗辉，刘大杰. 预测地铁施工中地表变形的动态系统方法[J]. 同济大学学报：自然科学版，2001，29(3)：294–298.(PAN Guorong，WANG Suihui，LIU Dajie. Dynamic model and forecasting of ground deformation in subway construction[J]. Journal of Tongji University：Nature Science，2001，29(3)：294–298.(in Chinese)) [9] 尹光志，岳顺，钟焘，等. 基于ARMA模型的隧道位移时间序列分析[J]. 岩土力学，2009，30(9)：2 727–2 732.(YIN Guangzhi，YUE Shun，ZHONG Tao，et al. Time series analysis of tunnel displacement based on ARMA model[J]. Rock and Soil Mechanics，2009，(9)：2 727–2 732.(in Chinese)) [10] 刘勇健，李彰明，张建龙，等. 基于遗传–神经网络的深基坑变形实时预报方法研究[J]. 岩石力学与工程学报，2004，23(6)：1 010– 1 014.(LIU Yongjian，LI Zhangming，ZHANG Jianlong，et al. Real time prediction method based on genetic algorithm and neural network for deformation caused by deep excavation[J]. Chinese Journal of Rock Mechanics and Engineering，2004，23(6)：1 010–1 014.(in Chinese)) [11] LIN T G，HORNE B G，TINO P，et al. Learning long-term dependencies in NARX recurrent neural networks[J]. IEEE Transactions on Neural Networks，1996，7(6)：1 329–1 338. [12] BEYHAN S，ALCI M. Fuzzy functions based ARX model and new fuzzy basis function models for nonlinear system identification[J]. Applied Soft Computing，2010，10(2)：439–444. [13] HAGAN M T，MENHAJ M B. Training feedforward networks with the marquardt algorithm[J]. IEEE Trans on Neural Networks，1994，5(6)：989–993. [14] 李秀珍，孔纪名，王成华. 高斯-牛顿法在滑坡预测预报模型参数优化中的应用[J]. 水土保持通报，2008，28(5)：132–135.(LI Xiuzhen，KONG Jiming，WANG Chenghua. Gauss-Newton method and its application in parameter optimization of landslide prediction models[J]. Bulletin of Soil and Water Conservation，2008，28(5)：132–135.(in Chinese)) [15] 吴启蒙，魏明，庞雷，等. 基于NARX神经网络的电子电路电磁脉冲响应建模[J]. 高压电器，2013，49(11)：62–68.(WU Qimeng，WEI Ming，PANG Lei，et al. Modeling electromagnetic pulse response of electronic circuits based on NARX neural network[J]. High Voltage Apparatus，2013，49(11)：62–68.(in Chinese)) [16] 陈明. MATLAB 神经网络原理与实例精解[M]. 北京：清华大学出版社，2013：364.(CHEN Ming. Principle and applications of neural network of MATLAB[M]. Beijing：Tsinghua University Press，2013：364.(in Chinese))