Dynamic Multi-Objective Optimization Inverse Prediction of Excavation-Induced Tunnel Displacement

doi:10.16183/j.cnki.jsjtu.2021.282

Abstract

Abstract:

Control of the disturbed displacement of adjacent tunnel during excavation is a significant issue for design and construction. Based on the multi-objective optimization method, the multi-type monitoring data in the excavation of the excavation are integrated, the key soil parameters are inverted and identified, and the time effect of the tunnel displacement is quantified and corrected. A dynamic multi-objective optimization method with adaptive infill criterion (DMO-AIC) is proposed to improve the updating efficiency of dynamic surrogate models. The proposed method takes into account the computational redundancy of dynamic surrogate models in engineering optimization, and designs an adaptive point-adding discrimination strategy, which can autonomously identify invalid updates of surrogate models on the optimization path. The results show that the proposed DMO-AIC significantly reduces the invocations of the black-box model during optimization while ensuring the good search performance and the convergence speed of the algorithm. The improved computational efficiency of DMO-AIC is helpful for the application of dynamic surrogate models in engineering optimization. The results of the virtual numerical example show that DMO-AIC can predict and update multiple model responses during excavation, such as wall deflections and tunnel displacements. The engineering practice of Shanghai Bund 596 excavation indicates that the time effect is properly updated, and the staged vertical displacements of the adjacent tunnel are accurately predicted.

Key words: dynamic multi-objective optimization, surrogate model, adaptive infill criterion, excavation, tunnel, time effect

CLC Number:

TU43

HE Wei, SUN Honglei, TAO Yuanqin, CAI Yuanqiang. Dynamic Multi-Objective Optimization Inverse Prediction of Excavation-Induced Tunnel Displacement[J]. Journal of Shanghai Jiao Tong University, 2022, 56(12): 1688-1699.

Figures/Tables 21

Fig.1

Fig.2

Fig.3

Tab.1

Fig.4

Tab.2

Fig.5

Tab.3

Fig.6

Fig.7

Tab.4

Tab.5

Fig.8

Tab.6

Fig.9

Tab.7

Fig.10

Fig.11

Fig.12

Fig.13

Tab.8

References 26

[1]	JIN Y F, YIN Z Y, ZHOU W H, et al. Multi-objective optimization-based updating of predictions during excavation[J]. Engineering Applications of Artificial Intelligence, 2019, 78: 102-123. doi: 10.1016/j.engappai.2018.11.002 URL
[2]	吉茂杰, 刘国彬. 开挖卸荷引起地铁隧道位移预测方法[J]. 同济大学学报(自然科学版), 2001, 29(5): 531-535.
	JI Maojie, LIU Guobin. Prediction method of displacement of subway tunnel due to excavation[J]. Journal of Tongji University (Natural Science), 2001, 29(5): 531-535.
[3]	TAO Y Q, SUN H L, CAI Y Q. Predicting soil settlement with quantified uncertainties by using ensemble Kalman filtering[J]. Engineering Geology, 2020, 276: 105753. doi: 10.1016/j.enggeo.2020.105753 URL
[4]	郑栋, 黄劲松, 李典庆. 基于多源信息融合的路堤沉降预测方法[J]. 岩土力学, 2019, 40(2): 709-719.
	ZHENG Dong, HUANG Jinsong, LI Dianqing. An approach for predicting embankment settlement by integrating multi-source information[J]. Rock and Soil Mechanics, 2019, 40(2): 709-719.
[5]	蒋水华, 刘源, 张小波, 等. 有限数据条件下空间变异岩土力学参数随机反演分析及比较[J]. 岩石力学与工程学报, 2020, 39(6): 1265-1276.
	JIANG Shuihua, LIU Yuan, ZHANG Xiaobo, et al. Stochastic back analysis and comparison of spatially varying geotechnical mechanical parameters based on limited data[J]. Chinese Journal of Rock Mechanics and Engineering, 2020, 39(6): 1265-1276.
[6]	SUN Y, JIANG Q H, YIN T, et al. A back-analysis method using an intelligent multi-objective optimization for predicting slope deformation induced by excavation[J]. Engineering Geology, 2018, 239: 214-228. doi: 10.1016/j.enggeo.2018.03.019 URL
[7]	BOOKER A J, DENNIS J E, FRANK P D, et al. A rigorous framework for optimization of expensive functions by surrogates[J]. Structural Optimization, 1999, 17(1): 1-13. doi: 10.1007/BF01197708 URL
[8]	张扬, 张维刚, 马桃, 等. 基于全局敏感性分析和动态代理模型的复杂非线性系统优化设计方法[J]. 机械工程学报, 2015, 51(4): 126-131. doi: 10.3901/JME.2015.04.126
	ZHANG Yang, ZHANG Weigang, MA Tao, et al. Optimization design method of non-linear complex system based on global sensitivity analysis and dynamic metamodel[J]. Journal of Mechanical Engineering, 2015, 51(4): 126-131. doi: 10.3901/JME.2015.04.126
[9]	ZHOU Z, LI D Q, XIAO T, et al. Response surface guided adaptive slope reliability analysis in spatially varying soils[J]. Computers and Geotechnics, 2021, 132: 103966. doi: 10.1016/j.compgeo.2020.103966 URL
[10]	LIU J, HAN Z H, SONG W P. Comparison of infill sampling criteria in kriging-based aerodynamic optimization[C]//28th congress of the international council of the aeronautical sciences. Brisbane, Australia: ICAS, 2012: 23-28.
[11]	BISCHL B, WESSING S, BAUER N, et al. MOI-MBO: Multiobjective infill for parallel model-based optimization[M]. Cham: Springer International Publishing, 2014, 173-186.
[12]	WAGNER T, TRAUTMANN H, MARTÍ L. A taxonomy of online stopping criteria for multi-objective evolutionary algorithms[C]//International Conference on Evolutionary Multi-Criterion Optimization. Berlin, Heidelberg: Springer, 2011.
[13]	REGIS R G. Multi-objective constrained black-box optimization using radial basis function surrogates[J]. Journal of Computational Science, 2016, 16: 140-155. doi: 10.1016/j.jocs.2016.05.013 URL
[14]	WAGNER T, EMMERICH M, DEUTZ A, et al. On expected-improvement criteria for model-based multi-objective optimization[C]//International Conference on Parallel Problem Solving from Nature. Berlin, Heidelberg: Springer, 2010.
[15]	LOPHAVEN S, NIELSEN H B, SØNDERGAARD J. DACE: A Matlab kriging toolbox[M]. Copenhagen: The Technical University of Denmark, 2002.
[16]	COELLO C A C, PULIDO G T, LECHUGA M S. Handling multiple objectives with particle swarm optimization[J]. IEEE Transactions on Evolutionary Computation, 2004, 8(3): 256-279. doi: 10.1109/TEVC.2004.826067 URL
[17]	刘若辰, 李建霞, 刘静, 等. 动态多目标优化研究综述[J]. 计算机学报, 2020, 43(7): 1246-1278.
	LIU Ruochen, LI Jianxia, LIU Jing, et al. A survey on dynamic multi-objective optimization[J]. Chinese Journal of Computers, 2020, 43(7): 1246-1278.
[18]	LEVASSEUR S, MALÉCOT Y, BOULON M, et al. Soil parameter identification using a genetic algorithm[J]. International Journal for Numerical and Analytical Methods in Geomechanics, 2008, 32(2): 189-213. doi: 10.1002/nag.614 URL
[19]	ZHAO B D, ZHANG L L, JENG D S, et al. Inverse analysis of deep excavation using differential evolution algorithm[J]. International Journal for Numerical and Analytical Methods in Geomechanics, 2015, 39(2): 115-134. doi: 10.1002/nag.2287 URL
[20]	SCHULTE D O, ARNOLD D, GEIGER S, et al. Multi-objective optimization under uncertainty of geothermal reservoirs using experimental design-based proxy models[J]. Geothermics, 2020, 86: 101792. doi: 10.1016/j.geothermics.2019.101792 URL
[21]	徐中华, 宗露丹, 沈健, 等. 邻近地铁隧道的软土深基坑变形实测分析[J]. 岩土工程学报, 2019, 41 (Sup.1): 41-44.
	XU Zhonghua, ZONG Ludan, SHEN Jian, et al. Deformation of a deep excavation adjacent to metro tunnels in soft soils[J]. Chinese Journal of Geotechnical Engineering, 2019, 41 (Sup.1): 41-44.
[22]	ADDENBROOKE T I. A flexibility number for the displacement controlled design of multi propped retaining walls[J]. Ground Engineering, 1994, 27(7): 41-45.
[23]	ADDENBROOKE T I, POTTS D M, DABEE B. Displacement flexibility number for multipropped retaining[J]. Journal of Geotechnical and Geoenvironmental Engineering, 2000, 126(8): 718-726. doi: 10.1061/(ASCE)1090-0241(2000)126:8(718) URL
[24]	刘国彬, 侯学渊. 软土的卸荷模量[J]. 岩土工程学报, 1996, 18(6): 18-23.
	LIU Guobin, HOU Xueyuan. Unloading modulus of the Shanghai soft clay[J]. Chinese Journal of Geotechnical Engineering, 1996, 18(6): 18-23.
[25]	刘溢, 李镜培, 陈伟. 被动区深层搅拌桩加固对超大深基坑变形的影响[J]. 岩土工程学报, 2012, 34 (Sup.1): 465-469.
	LIU Yi, LI Jingpei, CHEN Wei. Effect of reinforcement of deep mixing piles on deformation of ultra-deep excavations in passive zone[J]. Chinese Journal of Geotechnical Engineering, 2012, 34 (Sup.1): 465-469.
[26]	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.

测试函数	优化方法	输入参数维度	种群规模	初始代理模型训练样本数	最大迭代次数	折减系数初始值
ZDT2	DMO-AIC	8	50	50	100	0.5
	DMO	8	50	50	100	0.5
FON	DMO-AIC	6	100	100	300	0.5
	DMO	6	100	100	300	0.5

测试函数	优化方法	D^G	Δ	新增样本数
ZDT2	DMO-AIC	8.60×10^-3	0.29	30
	DMO	8.30×10^-3	0.33	93
FON	DMO-AIC	1.23×10^-2	0.40	97
	DMO	1.22×10^-2	0.39	214

指标	M	κ	ν
真实值	1.20	0.020	0.30
更新参数平均值	1.40	0.020	0.31
更新参数标准差	2.9×10^-3	5.0×10^-4	2.3×10^-3

步骤	进度	周期/d	步骤	开挖进度	周期/d
1	S2-A开挖至-1.7 m	1	12	S2-B开挖至-4.8 m	2
2	S1-A开挖至-1.7 m	24	13	S2-B开挖至-7.65 m	2
3	S2-A开挖至-6.0 m	2	14	S2-B开挖至-10.5 m	4
4	S2-A 开挖至-10.1 m	14	15	S2-B开挖至-14.25 m	2
5	S1-A 开挖至-5.9 m	10	16	S2-B开挖至坑底	9
6	S2-A开挖-13.85 m	3	17	S1-B开挖至-1.7 m	3
7	S1-A开挖至-9.9 m	12	18	S1-B开挖至-4.8 m	1
8	S2-A开挖至坑底	13	19	S1-B开挖至-7.5 m	1
9	S1-A开挖-13.7 m	8	20	S1-B开挖至-10.2 m	2
10	S1-A开挖至坑底	6	21	S1-B开挖至-14.0 m	3
11	S2-B开挖至-1.7 m	5	22	S1-B开挖至坑底	3

土层	土质	厚度/m	重度γ/(kg·m^-3)	卸荷模量E_u/MPa	泊松比ν	黏聚力c'/kPa	摩擦角φ'/(°)
1	水泥搅拌桩	0~22, 0~28	22.0	180.0	0.40	50.0	40.0
2	淤泥质黏土	0~10	18.5	18.0(10~50)	0.28	7.0	27.6
3	粉质黏土	10~29	17.5	28.5(15~90)	0.31	15.0(0.22~0.40)	29.5(17~35)
4	杂填土	29~39	18.0	25.2	0.28	10.4	22.0
5	江滩土	39~49	19.3	40.3(30~150)	0.27	5.0	30.4
6	砂质粉土	49~64	18.8	74.8(50~180)	0.27	5.0	33.4
7	粉砂层	64~80	20.2	94.3(60~220)	0.27	4.0	34.3