基于人工神经网络的深基坑支护结构侧移预测

doi:10.16183/j.cnki.jsjtu.2023.109

上海交通大学学报 ›› 2024, Vol. 58 ›› Issue (11): 1735-1744.doi: 10.16183/j.cnki.jsjtu.2023.109

基于人工神经网络的深基坑支护结构侧移预测

徐长节¹^,²^,³(), 李欣雨¹^,²

1.浙江大学滨海和城市岩土工程研究中心,杭州 310058
2.浙江大学平衡建筑研究中心, 杭州 310028
3.华东交通大学江西省岩土工程基础设施安全与控制重点实验室,南昌 330013

收稿日期:2023-03-27 修回日期:2023-07-11 接受日期:2023-07-24 出版日期:2024-11-28 发布日期:2024-12-02
作者简介:徐长节(1972—),教授,博士生导师,主要从事基坑工程支护结构方面的研究;E-mail:xucj@zju.edu.cn.
基金资助:
国家自然科学基金(51878276);浙江省自然科学基金委员会-华东院联合基金(LHZ19E080001);浙江大学平衡建筑研究中心配套资金(20203512-10C)

Lateral Deformation Prediction of Deep Foundation Retaining Structures Based on Artificial Neural Network

XU Changjie¹^,²^,³(), LI Xinyu¹^,²

1. Research Center of Coastal and Urban Geotechnical Engineering, Zhejiang University, Hangzhou 310058, China
2. Center for Balance Architecture, Zhejiang University, Hangzhou 310028, China
3. Jiangxi Key Laboratory of Infrastructure Safety Control in Geotechnical Engineering, East China Jiaotong University, Nanchang 330013, China

Received:2023-03-27 Revised:2023-07-11 Accepted:2023-07-24 Online:2024-11-28 Published:2024-12-02

摘要/Abstract

摘要：

为了更精准地预测基坑开挖引起的支护结构侧移,采用支持向量机模型、传统人工神经网络模型及2种考虑时序性输入的循环神经网络模型,建立了不同基坑支护结构最大侧移、同一基坑不同工况支护结构侧移的预测模型.结果显示,人工神经网络可以根据工程实测数据实时更新和预测支护结构变形,有助于及时规划工程下一步施工工艺.在支护结构不同工况侧移的预测上,考虑了时序性输入的循环神经网络模型效果优于传统人工神经网络模型.

关键词: 基坑工程, 变形预测, 机器学习, 支护结构

Abstract:

In order to more accurately predict the lateral deformation of retaining structures caused by foundation pit excavation, this paper adopts support the vector machine model, traditional artificial neural network model, and two kinds of recurrent neural network models considering temporal inputs to establish a prediction model for the maximum lateral deformation of retaining structures in different foundation pits, and for the same foundation pit under different working conditions. The results show that the artificial neural network can update and predict the deformation of the retaining structure in real time based on the measured data of the project, which is helpful for timely planning of the next construction process of the project. In the prediction of lateral deformation of retaining structures under different working conditions, the cyclic neural network model considering temporal inputs is better than the traditional artificial neural network model.

Key words: excavation, deformation prediction, machine learning, retaining structures

中图分类号:

TU46+3

徐长节, 李欣雨. 基于人工神经网络的深基坑支护结构侧移预测[J]. 上海交通大学学报, 2024, 58(11): 1735-1744.

XU Changjie, LI Xinyu. Lateral Deformation Prediction of Deep Foundation Retaining Structures Based on Artificial Neural Network[J]. Journal of Shanghai Jiao Tong University, 2024, 58(11): 1735-1744.

图/表 15

图1

图2

图3

图4

图5

图6

表1

表2

表3

图7

图8

表4

图9

表5

图10

参考文献 28

[1]	徐中华, 王建华, 王卫东. 上海地区深基坑工程中地下连续墙的变形性状[J]. 土木工程学报, 2008(8): 81-86.
	XU Zhonghua, WANG Jianhua, WANG Weidong. Deformation behavior of diaphragm walls in deep excavations in Shanghai[J]. China Civil Engineering Journal, 2008(8): 81-86.
[2]	陈保国, 闫腾飞, 王程鹏, 等. 深基坑地连墙支护体系协调变形规律试验研究[J]. 岩土力学, 2020, 41(10): 3289-3299.
	CHENG Baoguo, YAN Tengfei, WANG Chengpeng, et al. Experimental study on compatible deformation of diaphragm wall support system for deep foundation pit[J]. Rock and Soil Mechanics, 2020, 41(10): 3289-3299.
[3]	PENG X, KIANOOSH H. Sliding stability and lateral displacement analysis of reinforced soil retaining walls[J]. Geotextiles and Geomembranes, 2019, 47: 483-492.
[4]	孙小力, 孙铁成, 张旭, 等. 地铁基坑开挖数值模拟及变形特征研究[J]. 施工技术, 2020, 49(7): 41-44.
	SUN Xiaoli, SUN Tiecheng, ZHANG Xu, et al. Research on numerical simulation and deformation characteristics of subway foundation excavation[J]. Construction Technology, 2020, 49(7): 41-44.
[5]	RITWIK N, DEEPANKAR C. Displacement-controlled approach for the analysis of embedded cantilever retaining walls with a distanced strip surcharge[J]. Computers and Geotechnics, 2022, 151: 104970.
[6]	乔世范, 蔡子勇, 张震, 等. 南沙港区软土狭长深基坑围护体系性状[J]. 浙江大学学报(工学版), 2022, 56(8): 1473-1484.
	QIAO Shifan, CAI Ziyong, ZHANG Zhen, et al. Behavior of retaining system of narrow-long deep foundation pit in soft in Nansha Port Area[J]. Journal of Zhejiang University (Engineering Science), 2022, 56(8): 1473-1484.
[7]	秦会来, 黄俊, 李奇志, 等. 深厚淤泥地层深基坑变形影响因素分析[J]. 岩土工程学报, 2021, 43 (Sup.2): 23-26.
	QIN Huilai, HUANG Jun, LI Qizhi, et al. Influencing factors for deformation of deep foundation pits in thick mud stratum[J]. Chinese Journal of Geotechnical Engineering, 2021, 43 (Sup.2): 23-26.
[8]	刘新荣, 王林枫, 陈峰, 等. 内撑式地连墙变形特征及其参数优化研究[J]. 地下空间与工程学报, 2021, 17(3): 727-738.
	LIU Xinrong, WANG Linfeng, CHEN Feng, et al. Research on deformation characteristics and parameter optimization of diaphragm wall with interior bracing structure[J]. Chinese Journal of Underground Space and Engineering, 2021, 17(3): 727-738.
[9]	钟俊辉, 尹培林, 滕超, 等. 福州软土地区地铁车站基坑墙体变形特性分析[J]. 地下空间与工程学报, 2018, 14 (Sup.2): 821-827.
	ZHONG Junhui, YIN Peilin, TENG Chao, et al. The diaphragm walls of deformation properties of excavation for metro stations in Fuzhou soft soil deposits[J]. Chinese Journal of Underground Space and Engineering, 2018, 14 (Sup.2): 821-827.
[10]	申正洋, 黄华, 李新生, 等. 深大基坑中冠梁的变形特征及一种新型冠梁[J]. 工程地质学报, 2023, 31(2): 661-670.
	HUANG Zhengyang, HUANG Hua, LI Xinsheng, et al. Deformation characteristics of conventional and new top beams in deep and large foundation pit with numerical simulations[J]. Journal of Engineering Geology, 2023, 31(2): 661-670.
[11]	居玥辰, 宫全美, 赵昱, 等. 软土基坑开挖引起地下连续墙水平变形的能量法[J]. 地下空间与工程学报, 2021, 17(6): 1762-1774.
	JU Yuechen, GONG Quanmei, ZHAO Yu, et al. Energy method for horizontal deformation of diaphragm wall due to soft soil foundation pit excavation[J]. Chinese Journal of Underground Space and Engineering, 2021, 17(6): 1762-1774.
[12]	张福海, 周玉石, 刘学港, 等. 基于斜桩支护的框架结构基坑变形分析[J]. 山东大学学报(工学版), 2022, 52(1): 58-65.
	ZHANG Fuhai, ZHOU Yushi, LIU Xuegang, et al. Deformation analysis of frame structure foundation pit based on inclined pile support[J]. Journal of Shandong University (Engineering Science), 2022, 52(1): 58-65.
[13]	涂芬芬. 深基坑开挖对邻近既有建筑变形影响研究[J]. 土工基础, 2022, 36(1): 5-8.
	TU Fenfen. Influence of deep excavation induced deformation on the adjacent buildings[J]. Soil Engineering and Foundation, 2022, 36(1): 5-8.
[14]	尹利洁, 李宇杰, 朱彦鹏, 等. 兰州地铁雁园路站基坑支护监测与数值模拟分析[J]. 岩土工程学报, 2021, 43 (Sup.1): 111-116.
	YIN Lijie, LI Yujie, ZHU Yanpeng, et al. Monitoring and numerical simulation of support for foundation pit at Yanyuan Road Station of Lanzhou Metro[J]. Chinese Journal of Geotechnical Engineering, 2021, 43 (Sup.1): 111-116.
[15]	周勇, 王旭日, 朱彦鹏, 等. 强风化软硬互层岩质高边坡监测与数值模拟[J]. 岩土力学, 2018, 39(6): 2249-2258.
	ZHOU Yong, WANG Xuri, ZHU Yanpeng, et al. Monitoring and numerical simulation of an interbedding high slope composed of soft and hard strong-weathered rock[J]. Rock and Soil Mechanics, 2018, 39(6): 2249-2258.
[16]	张超翔, 张志强. 深基坑桩锚支护结构位移分析及数值模拟[J]. 科学技术与工程, 2022, 22(18): 8022-8029.
	ZHANG Chaoxiang, ZHANG Zhiqiang. Displacement analysis and numerical simulation of pile-anchor retaining structure in deep foundation pit[J]. Science Technology and Engineering, 2022, 22(18): 8022-8029.
[17]	蔡建军, 谢璨, 李树忱, 等. 复杂条件下深基坑多层支护方法及数值模拟研究[J]. 工程力学, 2018, 35(2): 188-194.
	CAI Jianjun, XIE Can, LI Shuchen, et al. Multi-larger supporting method and numerical simulation for deep foundation pit under complex condition[J]. Engineering Mechanics, 2018, 35(2): 188-194.
[18]	王恩钰, 周海祚, 郑刚, 等. 基坑倾斜桩支护的变形数值分析[J]. 岩土工程学报, 2019, 41 (Sup.1): 73-76.
	WANG Enyu, ZHOU Haizuo, ZHENG Gang, et al. Numerical analyses of deformation of inclined pile-retained excavations[J]. Chinese Journal of Geotechnical Engineering, 2019, 41 (Sup.1): 73-76.
[19]	张雯超, 史培新, 刘维, 等. 基于改进KNN与基坑参数对地连墙变形预测研究[J]. 华中科技大学学报(自然科学版), 2021, 49(9): 101-106..
	ZHANG Wenchao, SHI Peixin, LIU Wei, et al. Research on deformation prediction of diaphragm wall based on improved KNN and parameters of subway deep excavation[J]. Journal of Huazhong University of science and Technology(Natural Science Edition), 2021, 49(9): 101-106.
[20]	KUNG G T C, HSIAO E C L, SCHUSTER M, et al. A neural network approach to estimating deflection of diaphragm walls caused by excavation in clays[J]. Computers & Geotechnics, 2007, 34(5): 385-396.
[21]	VAPNIK V N. The nature of statistical learning theory[M]. New York,USA: Springer-Verlag, 1995.
[22]	BOSER B, GUYONG I, VAPNIK V. A training algorithm for optional margin classifiers[C] //Proceedings of The Fifth Annual Workshop on Computational Learning Theory. New York,USA: ACM Press, 1992: 144-152.
[23]	CORTES C, VAPNIK V. Support-vector networks[J]. Machine Learning, 1995, 20: 273-297.
[24]	SCHOLKOPF B, BURGES C, VAPNIK V. Extracting support data for a given task[C] //Proceedings of First International Conference on Knowledge Discovery & Data Mining. California, USA: AAAI Press, 1995: 252-257.
[25]	ROSENBLATT F. The perceptron: A probabilistic model for information storage and organization in the brain[J]. Psychological Review, 1958, 65(6): 386-408. doi: 10.1037/h0042519 pmid: 13602029
[26]	HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780. doi: 10.1162/neco.1997.9.8.1735 pmid: 9377276
[27]	CHO K, VAN M B, GULCEHRE C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. Maryland, USA:ACL, 2014: 1724-1734.
[28]	徐中华. 上海地区支护结构与主体地下结构相结合的深基坑变形性状研究[D]. 上海: 上海交通大学, 2007.
	XU Zhonghua. Deformation behavior of deep excavations supported by permanent structure in Shanghai soft deposit[D]. Shanghai: Shanghai Jiao Tong University, 2007.

编辑推荐 0

Metrics

阅读次数

全文

214

HTML			PDF

最新录用	在线预览	正式出版	最新录用	在线预览	正式出版
0	0	7	140	0	67

来源	本网站	其他网站

次数	90	124
比例	42%	58%

摘要

346

最新录用	在线预览	正式出版

119	0	227

来源	本网站	其他网站

次数	99	247
比例	29%	71%

编号	X₁/m	X₂	X₃/kN	X₄/kN	X₅/kN	X₆/kN	X₇/kN	X₈/d	X₉/(mm·h^-1)	Y/mm
1	5	1	1 913.59	0	0	0	0	22	-0.22	-0.66
2	5	1	2 369.11	0	0	0	0	25	0.43	0.63
3	5	1	2 309.13	0	0	0	0	27	0.37	1.37
︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙
78	26.05	7	1 870.24	7 096.59	968.79	845.28	1 107.62	118	1.54	58.14
79	26.05	7	1 677.10	7 336.54	925.58	791.38	1 100.69	119	-1.55	56.59
80	26.05	7	2 028.95	7 431.26	978.13	870.61	1 152.58	120	-0.4	56.19

独热编码前的参数	独热编码后的参数	对应的施工阶段
1	1000000	h≤5 m
2	0100000	5 m<h≤10 m
3	0010000	10 m<h≤15 m
4	0001000	15 m<h<26.05 m
5	0000100	h=26.05 m
6	0000010	架设第6道支撑
7	0000001	架设第7、8道支撑

模型	隐藏层层数	神经元数量	步长	学习率	激活函数	训练步数
MLP	3	64	-	0.000 1	ReLU	4 500
LSTM	1	64	4	0.000 1	ReLU	13 000
					Sigmoid	13 000
					tanh	13 000
GRU	1	64	6	0.000 5	ReLU	8 000
					Sigmoid	8 000
					tanh	8 000

模型	E_MSE	R²
SVM	4.99	0.99
MLP	36.96	0.95

模型	E_MSE	R²	预测用时/min
MLP	1.01	0.96	1.7
LSTM	0.77	0.97	4.7
GRU	0.75	0.97	4.3

基于人工神经网络的深基坑支护结构侧移预测

Lateral Deformation Prediction of Deep Foundation Retaining Structures Based on Artificial Neural Network

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 15

参考文献 28

相关文章 15

编辑推荐 0

Metrics

本文评价

[1]	刘俊城, 谭勇, 张生杰. 地铁车站深基坑开挖变形智能多步预测方法[J]. 上海交通大学学报, 2024, 58(7): 1108-1117.
[2]	刘月笙, 贺宁, 贺利乐, 张译文, 习坤, 张梦芮. 基于机器学习的移动机器人路径跟踪MPC控制器参数自整定[J]. J Shanghai Jiaotong Univ Sci, 2024, 29(6): 1028-1036.
[3]	孙乾洋, 周利, 丁仕风, 刘仁伟, 丁一. 基于人工神经网络的极地船舶冰阻力预报方法[J]. 上海交通大学学报, 2024, 58(2): 156-165.
[4]	鲍朱杰, 李祯, 王斐亮, 庞博, 杨健. 基于机器学习的直角扣件滑移和扭转性能预测方法[J]. 上海交通大学学报, 2024, 58(2): 242-252.
[5]	何文, 高斌, 王强强, 冯少孔, 叶冠林. 基于高斯混合聚类的综合物探方法及其在岩溶勘探中的应用[J]. 上海交通大学学报, 2024, 58(11): 1724-1734.
[6]	李明爱1,2,3，许冬芹1. 综述：运动想像脑机接口中的迁移学习[J]. J Shanghai Jiaotong Univ Sci, 2024, 29(1): 37-59.
[7]	苏泓嘉, 罗宇成, 刘飞. 装备体系效能评估及支撑技术综述[J]. 空天防御, 2023, 6(3): 29-38.
[8]	庞妍, 卿强, 王沙沙, 张翔宇, 龚景海. 膜结构在暴雨积水时材料模型研究[J]. 上海交通大学学报, 2023, 57(2): 213-220.
[9]	孙婕, 李子昊, 张书宇. 机器学习在化学合成及表征中的应用[J]. 上海交通大学学报, 2023, 57(10): 1231-1244.
[10]	甘娥忠, 刘焱, 王海荣, 王承光. 基于机器学习性能度量理论的保障资源指标综合权衡研究[J]. 空天防御, 2023, 6(1): 38-44.
[11]	贾岛, 陈磊, 朱志鹏, 余曜, 迟德建. 机器学习在引战系统设计中的应用研究[J]. 空天防御, 2022, 5(2): 27-31.
[12]	王卓鑫, 赵海涛, 谢月涵, 任翰韬, 袁明清, 张博明, 陈吉安. 反向传播神经网络联合遗传算法对复合材料模量的预测[J]. 上海交通大学学报, 2022, 56(10): 1341-1348.
[13]	李川, 聂熠文, 刘军伟, 孟凡钦, 沈晓静. 基于机器学习的多算法融合航迹稳健起始方法[J]. 空天防御, 2022, 5(1): 20-24.
[14]	周毅, 秦康平, 孙近文, 范栋琦, 郑义明. 台风气象环境电网设备风险量化预警及其N-m故障处置预案在线生成方法[J]. 上海交通大学学报, 2021, 55(S2): 22-30.
[15]	何夏维, 蔡云泽, 严玲玲. 一种合成残差式的反作用轮故障检测方法[J]. 上海交通大学学报, 2021, 55(6): 716-728.