基于卷积神经网络-长短期记忆的施工期盾构管片上浮过程预测模型
CSTR:
作者:
作者单位:

1.长安大学 公路学院,陕西 西安 710064;2.贝尔福‒蒙贝利亚技术大学 信息学院,贝尔福 90000;3.中铁十二局集团第一工程有限公司, 陕西 西安710038

作者简介:

苏恩杰(1996—),男,工学博士,主要研究方向为隧道及地下工程。 E-mail: suenjie@chd.edu.cn

通讯作者:

叶飞(1977—),男,教授,博士生导师,工学博士,主要研究方向为隧道及地下工程。 E-mail : xianyefei@126.com

中图分类号:

U455

基金项目:

国家自然科学基金(51678062,51878060),中铁十二局科研开发项目


Prediction Model of Shield Segment Floating Process During Construction Based on Convolutional Neural Networks and Long Short-Term Memory
Author:
Affiliation:

1.School of Highway, Chang’an University, Xi’an, 710064, China;2.School of Information, University of Technology of Belfort Montbéliard, Belfort 90000, France;3.The 1st Engineering Co., Ltd. of China Railway 12th Bureau Group, Xi’an 710038, China

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [30]
  • |
  • 相似文献 [14]
  • | | |
  • 文章评论
    摘要:

    为了实现施工期盾构管片上浮过程的智能预测,采用动力水准仪对施工期盾构管片上浮过程进行自动化监测并建立了基于卷积神经网络?长短期记忆(CNN-LSTM)深度学习算法的管片上浮过程智能预测模型。结果表明:管片上浮阶段呈现出“阶梯状”,即管片上浮主要发生在盾构掘进期间,且掘进状态的上浮量最大,占峰值的75.24 %~98.29 %;CNN-LSTM模型对施工期盾构管片上浮过程具有较好的预测效果,在训练集上的均方误差MSE、平均绝对误差MAE和决定系数R2分别为0.038 7、0.148 2和0.999 3,在测试集上为0.030 7、0.138 9和0.801 9;相较于反向传播(BP)模型,CNN-LSTM模型在训练集与测试集上的性能均有所提升,且测试集的提升更明显,最高可达89.71 %。研究结果可为盾构管片上浮的现场实测及预防处治提供新思路。

    Abstract:

    To realize the intelligent prediction of the floating process of shield segment during construction, the dynamic level was used to automatically monitor the floating process of shield segment, and an intelligent prediction model of segment floating process based on convolutional neural networks and long short-term memory (CNN-LSTM) deep learning algorithm was established. The results show that the floating stage of segment is in a shape of “ladder”, i.e., the floating of segment mainly occurs during shield tunneling. In addition, the floating amount in the heading state is the largest, accounting for 75.24 % to 98.29 % of the peak value. The mean square error (MSE), average absolute error (MAE) and determination coefficient R2on the training set are 0.038 7, 0.148 2, and 0.999 3 respectively, and 0.030 7, 0.138 9 and 0.801 9 on the test set. Compared with the back propagation (BP) model, the performance of the CNN-LSTM model in the training set and test set has been improved, and the improvement of the test set is more obvious, up to 89.71 %. The research results can provide a new idea for field measurement, prevention, and treatment of shield segment floating.

    参考文献
    [1] 《中国公路学报》编辑部. 中国交通隧道工程学术研究综述·2022[J]. 中国公路学报, 2022, 35(4): 1.Editorial Department of China Journal of Highway and Transport. Review on China's traffic tunnel engineering research: 2022[J]. China Journal of Highway and Transport, 2022, 35(4): 1.
    [2] 王梦恕. 中国盾构和掘进机隧道技术现状、存在的问题及发展思路[J]. 隧道建设, 2014, 34(3): 179.WANG Mengshu. Tunneling by TBM / shield in China: State-of-art, problems and proposals[J]. Tunnel Construction, 2014, 34(3): 179.
    [3] 林楠, 李攀, 谢雄耀. 盾构隧道结构病害及其机理研究[J]. 地下空间与工程学报, 2015, 11(S2): 802.LIN Nan, LI Pan, XIE Xiongyao. Research on evolution mechanism of shield tunnel disease based on segment performance analysis[J]. Chinese Journal of Underground Space and Engineering, 2015, 11(S2): 802.
    [4] 朱令, 丁文其, 杨波. 壁后注浆引起盾构隧道上浮对结构的影响[J]. 岩石力学与工程学报, 2012, 31(S1): 3377.ZHU Ling, DING Wenqi, YANG Bo. Effect of shield tunnel uplift caused by back-field grouting on structure[J]. Chinese Journal of Rock Mechanics and Engineering, 2012, 31(S1): 3377.
    [5] 黄威然, 竺维彬. 施工阶段盾构隧道漂移控制的研究[J]. 现代隧道技术, 2005(1): 71.HUANG Weiran, ZHU Weibin. To control the displacement of a shield tunnel during construction[J]. Modern Tunnelling Technology, 2005(1): 71.
    [6] 叶飞, 朱合华, 丁文其. 基于弹性地基梁的盾构隧道纵向上浮分析[J]. 中国铁道科学, 2008, 29(4): 65.YE Fei, ZHU Hehua, DING Wenqi. Longitudinal upward movement analysis of shield tunnel based on elastic foundation beam[J]. China Railway Science, 2008, 29(4): 65.
    [7] 肖明清, 孙文昊, 韩向阳. 盾构隧道管片上浮问题研究[J]. 岩土力学, 2009, 30(4): 1041.XIAO Mingqing, SUN Wenhao, HAN Xiangyang. Research on upward moving of segments of shield tunnel[J]. Rock and Soil Mechanics, 2009, 30(4): 1041.
    [8] 戴志仁. 盾构隧道盾尾管片上浮机理与控制[J]. 中国铁道科学, 2013, 34( 1): 59.Dai Zhiren. The mechanism and control principle of upward movements of segments at the rear of shield tail[J]. China Railway Science, 2013, 34(1): 59.
    [9] 董赛帅, 杨平, 姜春阳, 等. 盾构隧道管片上浮机理与控制分析[J]. 地下空间与工程学报, 2016, 12(1): 49.DONG Saishuai, YANG Ping, JIANG Chunyang, et al. Analysis of mechanism and controls of segment floating of shield tunnels[J]. Journal of Underground Space and Engineering, 2016, 12 (1): 49.
    [10] 黄钟晖, 舒瑶, 季昌, 等. 基于等效梁模型的盾构隧道施工期管片上浮影响因素权重分析[J]. 隧道建设, 2016, 36(11): 1295.HUANG Zhonghui, SHU Yao, JI Chang, al et , YOU Xiaoming. Analysis of weight of influencing factors of shield tunnel segment uplifting during construction based on equivalent beam model[J]. Tunnel Construction, 2016, 36 (11): 1295.
    [11] 吕乾乾, 周建军, 杨振兴, 等. 基于地基回弹因素的盾构隧道管片上浮预测[J]. 隧道建设(中英文), 2017, 37(S2): 87.Qianqian LYU , ZHOU Jianjun, YANG Zhenxing, et al. Prediction of shield tunnel up-floating caused by formation rebound[J]. Tunnel Construction, 2018, 37(S2): 87.
    [12] 舒瑶, 周顺华, 季昌, 等. 多变复合地层盾构隧道施工期管片上浮实测数据分析与量值预测[J]. 岩石力学与工程学报, 2017, 36(S1): 3464.SHU Yao, ZHOU Shunhua, JI Chang, et al. Analysis of shield tunnel segment uplift data and uplift value forecast during tunnel construction in variable composite formation[J]. Chinese Journal of Rock Mechanics and Engineering, 2017, 36(S1): 3464.
    [13] 李明宇, 余刘成, 陈健, 等. 粉质黏土中大直径泥水盾构隧道管片上浮及错台现场测试分析[J]. 铁道科学与工程学报, 2022, 19(6): 1705.LI Mingyu, YU Liucheng, CHEN Jian, et al. In situ test analysis of segment uplift and dislocation of large-diameter slurry shield tunnel in silty clay[J]. Journal of Railway Science and Engineering, 2022, 19(6): 1705.
    [14] 焦建林, 傅鹤林. 曲线段大直径盾构掘进引发管片上浮影响[J]. 湖南理工学院学报(自然科学版), 2023, 36(1): 49.JIAO Jianlin, FU Helin. Influence of segment uplift caused by large-diameter shield tunneling in curved sections[J]. Journal of Hunan Institute of Science and Technology (Natural Sciences), 2023, 36(1): 49.
    [15] 叶飞. 软土盾构隧道施工期上浮机理分析及控制研究[D]. 上海: 同济大学, 2007.YE Fei. Analysis and control for upward movement of shield tunnel during construction[D]. Shanghai: Tongji University, 2007.
    [16] 张建勇, 李明宇, 陈健, 等. 基于双面弹性地基梁的大直径盾构隧道管片上浮预测方法[J]. 现代隧道技术, 2023, 60(2): 159.ZHANG Jianyong, LI Mingyu, CHEN Jian, et al. Prediction methods for segment uplift in large-diameter shield tunnels based on double elastic foundation beams[J]. Modern Tunnelling Technology, 2023, 60(2): 159.
    [17] 高玮, 王森, 崔爽, 等. 基于深度信念网络的盾构隧道施工安全研究[J]. 河北工程大学学报(自然科学版), 2023, 40(1): 75.GAO Wei, WANG Sen, CUI Shuang, et al. Research on construction safety of shield tunnel based on DBN[J]. Journal of Hebei University of Engineering(Natural Science Edition), 2023, 40(1): 75.
    [18] 杨志勇, 杨星, 张长旺, 等. 盾构管片上浮量理论计算模型及上浮控制措施研究[J]. 矿业科学学报, 2021, 6(5): 591.YANG Zhiyong, YANG Xing, ZHANG Changwang, et al. Research on theoretical calculation model of shield segments floating amount and floating control measures[J]. Journal of Mining Science and Technology, 2021, 6(5): 591.
    [19] KOIZUMI A, MURAKAMI H, ISHIDA T. Design method of segments at a sharply curved section[J]. Journal of Japanese Society of Civil Engineers, 1992, (448): 111.
    [20] SHIBA Y, KAWASHIMA K, OBINATA N. Seismic design method of shield tunnel using response displacement method[J]. Journal of Japanese Society of Civil Engineers, 1986, 5: 113.
    [21] 叶 飞, 朱合华, 丁文其. 基于弹性地基梁的盾构隧道纵向上浮分析[J]. 中国铁道科学, 2008, 29(4): 65.YE Fei, ZHU Hehua, DING wenqi. Longitudinal upward movement analysis of shield tunnel based on elastic foundation beam[J]. China Railway Science, 2008, 29(4): 65.
    [22] 杨方勤, 段创峰, 吴华柒, 等. 上海长江隧道抗浮模型试验与理论研究[J]. 地下空间与工程学报, 2010, 6(3): 454.YANG Fangqin, DUAN Chuangfeng, WU Huaqi, et al. Model experiment and theoretical study on stability against uplift of Shanghai Yangtze River tunnel[J]. Chinese Journal of Underground Space and Engineering, 2010, 6(3): 454.
    [23] 舒瑶, 季昌, 周顺华. 考虑地层渗透性的盾构隧道施工期管片上浮预测[J]. 岩石力学与工程学报, 2017, 36(S1): 3516.SHU Yao, JI Chang, ZHOU Shunhua. Prediction for shield tunnel segment uplift considering the effect of stratum permeability[J]. Chinese Journal of Rock Mechanic and Engineering, 2017, 36(S1): 3516.
    [24] 黄旭民, 黄林冲, 梁禹. 施工期同步注浆影响下盾构隧道管片纵向上浮特征分析与应用[J]. 岩土工程学报, 2021, 43(9): 1700.HUANG Xumin, HUANG Linchong, LIANG Yu. Analysis and application of longitudinal uplift characteristics of segments of shield tunnels affected by synchronous grouting during construction period[J]. Chinese Journal of Geotechnical Engineering, 2021, 43(9): 1700.
    [25] GU J, WANG Z, KUEN J, et al. Recent advances in convolutional neural networks[J]. Pattern Recognition, 2018, 77: 354.
    [26] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735.
    [27] 惠文珊, 李会军, 陈萌, 等. 基于CNN-LSTM的机器人触觉识别与自适应抓取控制[J]. 仪器仪表学报, 2019, 40(1): 211.HUI Wenshan, LI Huijun, CHEN Meng, et al. Robotic tactile recognition and adaptive grasping control based on CNN-LSTM [J]. Chinese Journal of Scientific Instrument, 2019, 40(1): 211.
    [28] LIVIERIS I E, PINTELAS E, PINTELAS P. A CNN–LSTM model for gold price time-series forecasting[J]. Neural Computing and Applications, 2020, 32(23): 17351.
    [29] 李梅, 宁德军, 郭佳程. 基于注意力机制的CNN-LSTM模型及其应用[J]. 计算机工程与应用, 2019, 55(13): 20.LI Mei, NING Dejun, GUO Jiacheng. Attention mechanism-based CNN-LSTM model and its application[J]. Computer Engineering and Applications, 2019, 55(13): 20.
    [30] 夏飞, 罗志疆, 张浩, 等.混合神经网络在变压器故障诊断中的应用[J]. 电子测量与仪器学报, 2017, 31(1): 118.XIA Fei, LUO Zhijiang, ZHANG Hao, et al. Application of mixed neural network in transformer fault diagnosis[J]. Journal of Electronic Measurement and Instrumentation, 2017, 31(1): 118.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

苏恩杰,叶飞,何乔,任超,李思翰,张宏权.基于卷积神经网络-长短期记忆的施工期盾构管片上浮过程预测模型[J].同济大学学报(自然科学版),2023,51(9):1352~1361

复制
分享
文章指标
  • 点击次数:260
  • 下载次数: 572
  • HTML阅读次数: 1288
  • 引用次数: 0
历史
  • 收稿日期:2023-06-30
  • 在线发布日期: 2023-09-27
文章二维码