1 National Center of Technology Innovation for Digital Construction, Huazhong University of Science and Technology, Wuhan 430074, China
2 School of Civil and Hydraulic Engineering, Huazhong University of Science and Technology, Wuhan 430074, China
Show less
文章历史+
Received
Published
Revised
2025-07-02
2026-04-28
2025-12-16
Online Date
2026-05-29
PDF (12233K)
摘要
为提高复杂地层条件下泥水平衡盾构施工的姿态预测精度,保障隧道施工安全与质量,提出一种基于卷积神经网络-双向长短期记忆网络-注意力机制(convolutional neural network-bidirectional long short-term memory-Attention,CNN-BiLSTM-Attention)的盾构姿态预测方法。选取21个关键施工参数作为输入,预测盾头与盾尾的水平、垂直偏差及滚动角、俯仰角6个姿态参数,采用箱型图法、随机森林填补、离散小波变换、Pearson相关性分析及归一化等方法对原始数据进行预处理,并通过网格搜索法对模型进行超参数优化,有效提升了模型的预测性能;通过模型消融实验与对比实验,验证了模型在盾构姿态预测中的优势,并分析了模型各组件对整体预测性能的贡献。结果表明:基于CNN-BiLSTM-Attention的方法能有效提升泥水平衡盾构掘进姿态预测精度,具备良好的工程应用前景。
Abstract
In order to improve the prediction accuracy of slurry pressure balance shield attitude in complex strata and ensure tunneling safety and quality, a shield attitude prediction method was proposed based on a convolutional neural network-bidirectional long short-term memory-Attention (CNN-BiLSTM-Attention). Twenty-one key tunneling parameters were selected as inputs to predict six attitude parameters, including the horizontal and vertical deviations of the shield's head and tail, as well as roll and pitch angles. The raw data was preprocessed using boxplot analysis, random forest imputation, discrete wavelet transform, Pearson correlation analysis, and normalization methods. Model hyperparameters were optimized through grid search to achieve improved predictive performance. Ablation experiments and comparative studies were conducted to validate the model's superiority in shield attitude prediction and analyze the contribution of each component to overall prediction performance. The results show that the CNN-BiLSTM-Attention-based method effectively improves the attitude prediction accuracy of slurry balance shield tunneling, showing promising potential for engineering applications.
YANG Cong-zhen, CHEN Ke, LIU Tian-rui.
Prediction Method of Slurry Balance Shield Tunneling Attitude Based on CNN-BiLSTM-Attention[J].
Science Technology and Engineering, 2026, 26(12): 5255-5265 DOI:10.12404/j.issn.1671-1815.2504933
LeiH Y, ShiL, HuY, et al. Ground movement and settlement prediction induced by double-track curvature shield tunneling[J]. Acta Geotechnica, 2024, 19(9): 6179-6193.
ChenYang, LiuWen, LiuWenli, et al. Multi-objective optimization study based on the stability of shield tunnel excavation surface[J]. Science Technology and Engineering, 2024, 24(18): 7882-7888.
RenXudong, ZhangFengkai, DingWantao, et al. Prediction of ground settlement and optimization of tunneling parameters of slurry shield based on neural network[J]. Science Technology and Engineering, 2025, 25(5): 2090-2099.
PanQiujing, LiXiaoyu, HuangShan, et al. Application of machine learning to intelligent shield tunnelling: review and prospects[J]. Hazard Control in Tunnelling and Underground Engineering, 2022, 4(3): 10-30.
ZhuMeiheng, ChenZhaogeng, ZhangDongmei, et al. Prediction method of shield tunneling attitude based on AWPSO-GRU algorithm—taking the Shanghai suburban railway airport connection line as an example[J]. Science Technology and Engineering, 2025, 25(14): 6062-6071.
WangFamin, SunZhenchuan, ZhangLianghui, et al. Design of super-large diameter slurry shield used in Shantou Bay Tunnel and construction countermeasures for unfavorable geology[J]. Tunnel Construction, 2020, 40(5):735-746.
WeiXiaolong, LinFulong, MengXiangbo, et al. Real-Time diagnosis application of disc cutter in super-large diameter slurry shield: a case study on Shantou Su'ai tunnel[J]. Tunnel Construction, 2021, 41(5):865-870.
DaiHongbo, JiYuguo. Statistical analysis of Chinese large-diameter shield tunnel and state-of-art and prospective of comprehensive technologies[J]. Tunnel Construction, 2022, 42(5):757-783.
JianPeng, YangChen, YouYusong, et al. Research andapplication of automatic control technology for shield tunneling attitude[J]. Tunnel Construction, 2023, 43(10): 1795-1800.
PanGuorong, TangHang. A new method of shield attitude calculation based on combined adjustment[J]. Journal of Shandong University of Science and Technology(Natural Science), 2013, 32(6): 48-56.
[20]
王春凯. 盾构姿态控制研究[J]. 隧道建设, 2016, 36(11): 1389-1393.
[21]
WangChunkai. Analysis of shield attitude control technology[J]. Tunnel Construction, 2016, 36(11): 1389-1393.
[22]
SugimotoM, SramoonA, KonishiS, et al. Simulation of shield tunneling behavior along a curved alignment in a multilayered ground[J]. Journal of Geotechnical and Geoenvironmental Engineering, 2007, 133(6): 684-694.
[23]
ShenX, YuanD J, JinD L. Influence of shield attitude change on shield-soil interaction[J]. Applied Sciences, 2019, 9(9): 1812.
HuChangming, HouYajun, LiLiang, et al. Research on the combined prediction model of shield vertical attitude[J]. Journal of Railway Science and Engineering, 2021, 18(6): 1521-1528.
ZhangAijun. Study of fuzzy control on tunneling parameters of shield attitude inupper-soft and lower-hard ground[J]. Journal of Railway Science and Engineering, 2018, 15(11): 2920-2927.
WuHuiming, ChangJiaqi, LiGang, et al. Prediction ofdriving posture and optimization of construction parameters for shield based on support vector machine[J]. Tunnel Construction, 2021, 41(S1): 11-18.
[30]
XiaoH H, XingB, WangY J, et al. Prediction of shield machine attitude based on various artificial intelligence technologies[J]. Applied Sciences-Basel, 2021, 11(21): 10264.
Zhangwengang, YanYumiao, LiuHanlong, et al. Research on mud-water balance shield machine attitude prediction based on Transformer-LSTM[J]. Journal of Applied Basic and Engineering Sciences, 2025, 33(3): 690-700.
WangShuying, WangLai, PanQiujing. Data-driven deep learning model of shield vertical attitude prediction[J]. Journal of Central South University, 2024, 55(2): 485-499
[35]
ZhouC, XuH C, DingL Y, et al. Dynamic prediction for attitude and position in shield tunneling: a deep learning method[J]. Automation in Construction, 2019, 105: 102840.
WangLai, WangShuying, PanQiujing, et al. Research of prediction of shield attitude passing the soil-rock mixture backfill area based on the AM-BiLSTM[J]. Journal of Railway Science and Engineering, 2023, 20(8): 2948-2960.
ChenKe, LiuTianrui, YangZhao. Current status and future prospects of shield tunneling attitude control technology[J]. Tunnel Construction, 2024, 44(6): 1154-1164.
ZhangXiaoqin, ChengYuying. Imputation of missing values for compositional data based on random forest[J]. Chinese Journal of Applied Probability and Statistics, 2017, 33(1): 102-110.