基于MK-LSTM算法的盾构掘进参数相关性分析及结构变形预测

doi:10.13229/j.cnki.jdxbgxb.20220975

摘要/Abstract

摘要：

提出了MIC-K-median-LSTM（MK-LSTM）算法，用于对盾构掘进过程进行参数相关性分析和结构变形预测。首先，运用改进的MIC（MK）算法对涉及盾构掘进过程中的各参数与结构变形进行相关性分析；然后，在得到相关系数的基础上提出输入参数的修正方法；最后，通过LSTM模型对不同维度输入参数的预测效果进行分析，确定合理的输入参数维度。结果表明：盾构参数对既有结构变形的影响大于土体参数；MK算法可以有效降低计算复杂度和减小噪声对数据的影响，基于参数相关系数的数据前处理方法有利于提高模型的预测精度；MK-LSTM可以有效预测结构随时间的变形规律，考虑数据维度对预测精度的提升效果和计算效率的影响，进行实际工程预测时可以根据参数相关性大小进行维度删减。

关键词: 盾构隧道, 机器学习, 参数维度, 参数相关性, 变形

Abstract:

MIC-K-median-LSTM（MK-LSTM）algorithm was proposed to analyze the correlation of parameters and predict the structural deformation. Firstly， the improved MIC algorithm is developed to analyze the correlation between the different input parameters and structural deformation， then to preprocess the input parameters based on their correlation coefficients. The prediction accuracy and efficiency using different dimensions of input parameters are analyzed through the LSTM model and the optimal input parameter dimensions are selected. The results show that： The influence of the shield parameters on the existing structural deformation is larger than soil parameters； The MK algorithm can effectively reduce the computational complexity and the impact of noise in raw data and the data pre-process is beneficial to improve prediction accuracy； MK-LSTM algorithm can effectively predict the deformation law of the structure over time， considering the effect of the data dimension on the improvement of the prediction accuracy and the influence of the calculation efficiency， dimension pruning can be adopted in the actual engineering based on the parameter correlation.

Key words: shield tunnelling, machine learning, parameter dimension, parameter correlation, deformation

中图分类号:

TU472

陈城,史培新,贾鹏蛟,董曼曼. 基于MK-LSTM算法的盾构掘进参数相关性分析及结构变形预测[J]. 吉林大学学报(工学版), 2024, 54(6): 1624-1633.

Cheng CHEN,Pei-xin SHI,Peng-jiao JIA,Man-man DONG. Correlation analysis of shield driving parameters and structural deformation prediction based on MK-LSTM algorithm[J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(6): 1624-1633.

图/表 13

图1

图2

图3

图4

表1

图5

图 6

表2

图 7

图8

图9

表3

图10

参考文献 24

1	Wang L T, Yang X, Gong G F, et al. Pose and trajectory control of shield tunneling machine in complicated stratum[J]. Automation in Construction, 2018,93: 192-199.
2	Huo J, Xu Z, Meng Z, et al. Coupled modeling and dynamic characteristic of TBM cutterhead system under uncertain factors[J]. Mechanical Systems and Signal Processing, 2020, 140: No.106664.
3	崔国华, 王国强, 王继新, 等. 全断面盾构掘进机切削刀具的计算力学模型求解[J]. 吉林大学学报: 工学版, 2008, 38(): 139-143.
	Cui Guo-hua, Wang Guo-qiang, Wang Ji-xin, et al. Cutting dynamic model for cutters of shield machine under soft soil[J]. Journal of Jilin University (Engineering and Technology Edition), 2008, 38(Sup.2): 139-143.
4	Deng K, Tang X, Wang L, et al. On the analysis of force transmission performance for the thrust systems of shield tunneling machines[C]∥International Conference on Intelligent Robotics and Applications.Berlin: Springer-Verlag, 2009.
5	朱合华, 丁文其, 乔亚飞, 等. 盾构隧道微扰动施工控制技术体系及其应用[J]. 岩土工程学报, 2014,36(11): 1983-1993.
	Zhu He-hua, Ding Wen-qi, Qiao Ya-fei, et al. Micro-disturbed construction control technology system for shield driven tunnels and its application [J]. Chinese Journal of Geotechnical Engineering, 2014,36(11): 1983-1993.
6	张顶立, 曹利强, 房倩. 城市隧道施工的环境力学响应预测及动态控制[J]. 北京交通大学学报, 2021,45(4): 1-8.
	Zhang Ding-li, Cao Li-qiang, Fang Qian. Environmental mechanical response prediction and in-process control of urban tunnel construction[J]. Journal of Beijing Jiaotong University, 2021, 45(4): 1-8.
7	高利宏. 新建地铁穿越既有地铁引起结构变形预测[J]. 市政技术, 2020, 38(4): 146-148, 152.
	Gao Li-hong. Prediction of structural deformation caused by a new subway crossing existing subway[J]. Journal of Municipal Technology, 2020, 38(4): 146-148, 152.
8	张成平, 张顶立, 王梦恕. 大断面隧道施工引起的上覆地铁隧道结构变形分析[J]. 岩土工程学报,2009, 31(5): 805-810.
	Zhang Cheng-ping, Zhang Ding-li, Wang Meng-shu. Structural deformation of overlying subway tunnels induced by tunnelling[J]. Chinese Journal of Geotechnical Engineering, 2009, 31(5): 805-810.
9	刘栋. 深度学习框架下时空关联的基坑变形预测方法研究[D]. 泰安: 山东农业大学水利土木工程学院,2022.
	Liu Dong. Research on prediction method of foundation pit deformation based on spatio-temporal correlation under deep learning framework [D].Tai´an:College of Water Conservancy and Civil Engineering,Shandong Agricultural University, 2022.
10	李洛宾, 龚晓南, 甘晓露, 等. 基于循环神经网络的盾构隧道引发地面最大沉降预测[J]. 土木工程学报,2020, 53(): 13-19.
	Li Luo-bin, Gong Xiao-nan, Gan Xiao-lu, et al. Prediction of maximum ground settlement induced by shield tunneling based on recurrent neural network [J]. China Civil Engineering Journal, 2020, 53(Sup.1): 13-19.
11	Chen R P, Zhang P, Kang X, et al. Prediction of maximum surface settlement caused by earth pressure balance (EPB) shield tunneling with ANN methods [J]. Soils and Foundations, 2019, 59(2): 284-295.
12	陈仁朋, 戴田, 张品, 等. 基于机器学习算法的盾构掘进地表沉降预测方法[J]. 湖南大学学报: 自然科学版, 2021, 48(7): 111-118.
	Chen Ren-peng, Dai Tian, Zhang Pin, et al. Prediction method of tunneling-induced ground settlement using machine learning algorithms[J]. Journal of Hunan University(Natural Sciences), 2021, 48(7):111-118.
13	孙捷城, 王国富, 路林海, 等. 厚冲积地层盾构掘进参数设定及地表变形规律研究[J]. 防灾减灾工程学报, 2018, 38(3): 487-497.
	Sun Jie-cheng, Wang Guo-fu, Lu Lin-hai, et al. Study on parameters setting of EPB shield driving and laws of surface deformation in thick alluvial clay[J]. Journal of Disaster Prevention and Mitigation Engineering, 2018, 38(3): 487-497.
14	周振梁, 谭忠盛, 李宗林, 等. 一种基于数据挖掘的掘进速度预测模型[J]. 应用基础与工程科学学报,2021, 29(5): 1201-1219.
	Zhou Zhen-liang, Tan Zhong-sheng, Li Zong-lin, et al. A data mining based prediction model for penetration rate[J]. Journal of Basic Science and Engineering, 2021, 29(5): 1201-1219.
15	裴浩东, 叶社保, 杨平, 等. 软土地层盾构掘进参数分析及掘进速度预测[J]. 郑州大学学报: 工学版, 2022, 11(26): 1-8.
	Pei Hao-dong, Ye She-bao, Yang Ping, et al. Analysis of boring parameters of shield in soft soil strata and prediction of driving speed[J]. Journal of Zhengzhou University (Engineering Science), 2022, 11(26):1-8.
16	Reshef D N, Reshef Y A, Finucane H K, et al. Detecting novel associations in large data sets[J]. Science, 2011, 334(6062): 1518-1524.
17	邵福波. 最大信息系数改进算法及其在铁路事故分析中的应用[D]. 北京: 北京交通大学交通运输学院,2016.
	Shao Fu-bo. The improved algorithm of the maximal information coefficient and its applications in railway accident analysis[D]. Beijing: School of Traffic and Tansportation, Beijing Jiaotong University, 2016.
18	Cormen T H, Leiserson C E, Rivest R L, et al. Introduction to Algorithms[M]. 3rd ed. Cambridge: MIT Press, 2009.
19	Zhang D M, Zhang J Z, Huang H W, et al. Machine learning-based prediction of soil compression modulus with application of 1D settlement[J]. Journal of Zhejiang University-SCIENCE A, 2020, 21(6): 430-444.
20	Shao H D, Zhao H W, Jiang H K, et al. An enhancement deep feature fusion method for rotating machinery fault diagnosis[J]. Knowledge-Based Systems,2016, 119: 200-220.
21	Zhang W, Zhang R, Wu C, et al. State-of-the-art review of soft computing applications in underground excavations[J]. Geoscience Frontiers, 2020, 11(4): 1095-1106.
22	Koo T K, Li M Y. A guideline of selecting and reporting intraclass correlation coefficients for reliability research[J]. Journal of Chiropractic Medicine, 2016,15(2): 155-163.
23	李增良. 基于MIC-LSTM的盾构施工地表变形动态预测[J]. 隧道建设, 2021, 41(2): 199-205.
	LI Zeng-liang. Dynamic prediction of surface deformation induced by shield tunneling based on maximal information coefficient-long short-term memory[J]. Tunnel Construction, 2021, 41(2): 199-205.
24	Reshef D N, Reshef Y A, Finucane H K, et al. Detecting novel associations in large data sets, Science,2011, 334(6062): 1518-1524.

相关文章 15

[1]	邸振勇,杨新辉. 地震后建筑结构层间变形特征分布[J]. 吉林大学学报(工学版), 2024, 54(5): 1377-1384.
[2]	娄淑梅,李一明,李鑫,陈鹏,白雪峰,程宝嘉. 基于BP神经网络和Arrhenius本构模型的石墨烯/7075复合材料热变形行为[J]. 吉林大学学报(工学版), 2024, 54(5): 1237-1245.
[3]	万铜铜,汪海年,郑文华,冯珀楠,陈玉,张琛. 级配碎石层协调沥青混合料层温度收缩变形行为[J]. 吉林大学学报(工学版), 2024, 54(4): 1045-1057.
[4]	何银水,肖贺,罗沧海,张宇,余卓骅,袁海涛. 基于层次分析过程的厚板T形接头弧焊焊接位置自主决策[J]. 吉林大学学报(工学版), 2024, 54(3): 657-662.
[5]	付忠良,陈晓清,任伟,姚宇. 带学习过程的随机K最近邻算法[J]. 吉林大学学报(工学版), 2024, 54(1): 209-220.
[6]	李义,吕晨阳,梁继才,梁策. 不规则Y形铝型材多点拉弯成形截面变形分析[J]. 吉林大学学报(工学版), 2024, 54(1): 105-113.
[7]	周晓,梁燚杰,奚中轩,王宇涛. 白车身B柱焊接变形模拟及预变形控制方法[J]. 吉林大学学报(工学版), 2023, 53(8): 2212-2218.
[8]	耿庆田,刘植,李清亮,于繁华,李晓宁. 基于一种深度学习模型的土壤湿度预测[J]. 吉林大学学报(工学版), 2023, 53(8): 2430-2436.
[9]	张哲,付伟,张军辉,黄超. 循环荷载下冻融路基黏土长期塑性行为[J]. 吉林大学学报(工学版), 2023, 53(6): 1790-1798.
[10]	潘恒彦,张文会,梁婷婷,彭志鹏,高维,王永岗. 基于MIMIC与机器学习的出租车驾驶员交通事故诱因分析[J]. 吉林大学学报(工学版), 2023, 53(2): 457-467.
[11]	孙琪凯,张楠,刘潇,周子骥. 基于Timoshenko梁理论的钢-混组合梁动力折减系数[J]. 吉林大学学报(工学版), 2023, 53(2): 488-495.
[12]	袁伟,袁小慧,高岩,李坤宸,赵登峰,刘朝辉. 基于自然驾驶数据的电动公交踏板误操作辨识方法[J]. 吉林大学学报(工学版), 2023, 53(12): 3342-3350.
[13]	梁策,黄富雷,梁继才,李义. 日字形防护梁绕弯成形形变数值模拟[J]. 吉林大学学报(工学版), 2023, 53(12): 3397-3403.
[14]	周丰丰,颜振炜. 基于混合特征的特征选择神经肽预测模型[J]. 吉林大学学报(工学版), 2023, 53(11): 3238-3245.
[15]	孙舒杨,程玮斌,张浩桢,邓向萍,齐红. 基于深度学习的两阶段实时显式拓扑优化方法[J]. 吉林大学学报(工学版), 2023, 53(10): 2942-2951.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

方案	输入参数
1	T 、R 、N 、P₄ 、V、 P₂、c、φ、 P₃ 、G 、P₁ 、F
2	T 、R 、N 、P₄ 、V、 P₂、c、φ、 P₃ 、G 、P₁
3	T 、R 、N 、P₄ 、V、 P₂、c、φ、 P₃ 、G
4	T 、R 、N 、P₄ 、V、 P₂、c、φ、 P₃
5	T 、R 、N 、P₄ 、V、 P₂、c、φ
6	T 、R 、N 、P₄ 、V、 P₂、c
7	T 、R 、N 、P₄ 、V、 P₂
8	T 、R 、N 、P₄ 、V
9	T 、R 、N 、P₄
10	T 、R 、N
11	T 、R

指标	方案1	方案2	方案3	方案4	方案5	方案6	方案7	方案8	方案9	方案10	方案11
MAE	0.111	0.144	0.157	0.179	0.189	0.231	0.274	0.299	0.354	0.421	0.654
RMSE	0.112	0.131	0.164	0.189	0.202	0.254	0.297	0.342	0.417	0.528	0.749
R²	0.977	0.946	0.934	0.922	0.903	0.872	0.846	0.802	0.763	0.721	0.618