作者中心
专家审稿
编委审稿
主编审稿
APPLICATION OF SOIL PARAMETERS INVERSION BASED ON PSO-MLSSVR IN DEEP FOUNDATION PIT ENGINEERING
-
摘要: 为了确保基坑工程安全,常常会采用数值模拟的方法预测支护结构的位移,其中岩土体力学参数的选取对于结果的影响最大。本文使用了一种粒子群(PSO)算法结合多输出最小二乘支持向量回归机(MLSSVR)的基坑土体参数位移反分析法,以深圳某深基坑的支护桩顶水平位移监测数据为依据,基于正交设计生成具有代表性的土体参数组合,通过有限元计算得到研究点的位移作为训练样本,使用粒子群PSO算法对多输出MLSSVR模型参数寻优,利用MLSSVR构建反演参数与位移之间的映射关系,反演填石层、淤泥层和砂质黏土层的土体参数,将反演参数代入有限元模型计算测点位移。结果表明：在反演参数过程中,MLSSVR模型比单输出最小二乘支持向量回归机(LSSVR)耗时更短,而且将两个模型的反演参数代入有限元模型进行计算时,MLSSVR的结果较LSSVR更贴近于实际监测值,对比结果验证了研究方法的优越性; 在施工的不同阶段,使用MLSSVR得到反演参数进行数值模拟,得到的模拟结果与监测数据吻合较好,验证该方法具有准确性和实用性。结果分析证明本文研究方法可以有助于土体参数的选取,提高基坑数值模拟结果的准确性。Abstract: In order to ensure the safety of foundation pit construction,numerical simulation is used to predict the displacement of support structure. The selection of geotechnical parameters has the greatest influence on the numerical simulation results. A back analysis method based on multioutput least-squares support vector regression machine(MLSSVR) and particle swarm(PSO) is proposed to estimate multiple geotechnical parameters. This paper uses PSO-MLSSVR method to invert geotechnical parameters based on horizontal displacement monitoring data from the top of the supporting piles in a deep foundation pit in Shenzhen. Based on the orthogonal design method,representative combinations of geotechnical parameters are generated. Using these combinations,finite element method(FEM) is used to calculate the displacement of the measured points. PSO algorithm is used to optimize the parameters of MLSSVR model. Using MLSSVR to construct mapping relationships between inversion parameters and displacements to invert soil parameters in rock-fill,silt and sandy clay layers. The inverse parameters are substituted into the finite element model to calculate the measured point displacements. The results show that the MLSSVR model takes less time than the single output least squares support vector regressor(LSSVR) in inverting the parameters. When the inversion parameters of both models are substituted into the finite element model for calculation,the results of MLSSVR are closer to the actual monitoring values than LSSVR. The comparative results validate the superiority of the study methodology. In different stages of construction,the inversion parameters obtained by MLSSVR are used for numerical simulation. The simulation results are in good agreement with the monitoring data,which verified the accuracy and practicability of this method. The results show that the method in this paper is helpful to the selection of soil parameters and improve the accuracy of numerical simulation results.
-
Key words:
- Excavation /
- MLSSVR /
- Deformation prediction /
- Displacement back-analysis /
- Numerical simulation /
- PSO
-
图 5 工况3有限元计算值与监测值对比图
Figure 5. Comparison of finite element model calculated values with monitored values in the third construction stage
图 6 有限元计算值与监测值对比
Figure 6. Comparison of finite element model calculated values with monitored values
表 1 模型土层参数取值
Table 1. Values of model soil parameter
土层 反演参数范围 填石 10~30 淤泥 2~12 砂质黏土 20~36 
下载: 导出CSV
表 2 正交试验设计表
Table 2. Orthogonal test design table
序号 填石层E50/MPa 淤泥E50/MPa 砂质黏土E50/MPa 1 10 7 28 2 10 4.5 24 3 15 7 20 4 20 2 24 5 25 7 24 6 20 12 20 7 20 7 32 8 25 9.5 28 9 30 9.5 20 10 15 9.5 24 11 20 9.5 36 12 25 2 36 13 30 4.5 32 14 30 7 36 15 15 12 28 16 30 12 24 17 10 9.5 32 18 10 12 36 19 10 2 20 20 25 12 32 21 30 2 28 22 15 4.5 36 23 20 4.5 28 24 25 4.5 20 25 15 2 32
下载: 导出CSV
表 3 模拟施工工况
Table 3. Simulation of construction stages
工况 施工方案 天 1 第一层开挖, 安装第一层支撑 24 2 第二层开挖, 安装第二层支撑 36 3 第三层开挖, 安装第三层支撑 42 4 第四层开挖 35
下载: 导出CSV
表 4 模型土层参数取值
Table 4. Values of model soil parameter
序号 岩土名称 厚度h/m 天然重度γ/kN·m-3 饱和重度γsat/kN·m-3 黏聚力c/kPa 内摩擦角φ/(°) 泊松比μ 割线模量E50/MPa 切线模量Eoed/MPa 卸载弹性模量Eref/MPa 应力相关幂指数m 1 素填土 1.0 19.7 21.2 32.8 18.37 0.38 3 3 9 0.5 2 填石 9.5 20.0 21.5 6.5 35.00 0.30 E50 E50 3.5E50 0.5 3 淤泥 2.5 16.5 17.4 15.0 10.00 0.40 E50 E50 7E50 0.5 4 砂质黏性土 26.7 18.9 20.2 26.7 20.60 0.28 E50 1.1E50 3E50 0.5 5 全风化带 7.7 19.5 21.5 35.0 26.00 0.22 50 50 150 0.5 6 强风化带 15.5 20.5 22.5 45.0 30.00 0.22 80 80 240 0.5
下载: 导出CSV
表 5 正交设计学习样本
Table 5. Orthogonal design learning sample
工况 序号 填石E50/MPa 淤泥E50/MPa 砂质黏性土E50/MPa J1/mm J2/mm J3/mm J4/mm J5/mm J6/mm J7/mm J8/mm 工况1 1 10 7.0 28 1.12 1.20 0.50 0.33 0.27 0.21 0.50 0.27 2 1 4.5 24 1.16 1.25 0.54 0.35 0.2 0.19 0.52 0.2 3 15 7.0 20 1.11 1.1 0.5 0.40 0.32 0.27 0.54 0.34 4 2 2. 24 1.03 1.10 0.50 0.35 0.2 0.25 0.4 0.29 5 25 7. 24 0.9 1.02 0.53 0.3 0.33 0.29 0.50 0.34 6 2 12. 20 1.06 1.11 0.59 0.41 0.35 0.30 0.54 0.37 7 2 7. 32 0.96 1.01 0.46 0.33 0.29 0.25 0.46 0.2 8 25 9.5 28 0.94 0.99 0.49 0.36 0.32 0.2 0.4 0.32 9 3 9.5 20 0.99 1.03 0.5 0.43 0.36 0.33 0.53 0.39 10 15 9.5 24 1.07 1.13 0.54 0.37 0.31 0.26 0.51 0.31 11 2 9.5 36 0.94 0.99 0.44 0.32 0.2 0.25 0.45 0.27 12 25 2. 36 0.92 0.99 0.40 0.29 0.25 0.22 0.41 0.24 13 3 4.5 32 0.90 0.96 0.45 0.33 0.29 0.24 0.44 0.2 14 3 7. 36 0.5 0.91 0.43 0.32 0.29 0.27 0.43 0.29 15 15 12. 28 1.03 1.09 0.50 0.35 0.29 0.25 0.49 0.30 16 3 12. 24 0.94 0.9 0.54 0.39 0.35 0.32 0.50 0.36 17 1 9.5 32 1.09 1.16 0.4 0.31 0.26 0.21 0.4 0.26 18 1 12. 36 1.06 1.13 0.45 0.30 0.25 0.20 0.47 0.25 19 1 2. 20 1.24 1.33 0.5 0.3 0.2 0.22 0.55 0.27 20 25 12. 32 0.91 0.96 0.47 0.34 0.31 0.27 0.46 0.30 21 3 2. 28 0.91 0.97 0.44 0.33 0.2 0.26 0.43 0.2 22 15 4.5 36 0.7 0.91 0.42 0.31 0.2 0.26 0.43 0.27 23 2 4.5 2 0.9 1.05 0.4 0.35 0.29 0.25 0.4 0.29 24 25 4.5 20 0. 0.94 0.41 0.31 0.27 0.24 0.43 0.26 25 15 2. 32 1.05 1.12 0.44 0.31 0.25 0.21 0.46 0.24 26 1.00 1.10 0.50 0.40 0.30 0.30 0.50 0.30 工况2 1 1 7. 28 3.70 3.79 1.69 0.95 0.72 0.43 1.67 1.0 2 1 4.5 24 3.92 4.00 1. 5 1.01 0.73 0.40 1.7 1.15 3 15 7. 20 3.42 3.62 1.79 1.05 0. 1 0.50 1.74 1.17 4 2 2. 24 3.31 3.51 1.74 1.00 0.74 0.43 1.6 1.12 5 25 7. 24 2.90 3.07 1.59 1.01 0. 4 0.5 1.5 1.10 6 2 12. 20 3.09 3.27 1.72 1.03 0. 5 0.57 1.64 1.14 7 2 7. 32 3.01 3.09 1.50 0.94 0.77 0.52 1.52 1.02 8 25 9.5 2 2.6 2.93 1.49 0.96 0. 2 0.5 1.51 1.04 9 3 9.5 20 2.3 2.99 1.04 1.10 0. 0.63 1.59 1.14 10 15 9.5 24 3.25 3.44 1.65 0.9 0.79 0.51 1.64 1.10 11 2 9.5 36 2.1 2.9 1.42 0.90 0.76 0.53 1.46 0.9 12 25 2. 36 2.90 3.0 1.4 0.90 0.71 0.45 1.4 0.99 13 3 4.5 32 2.6 2. 4 1.44 0.93 0.79 0.55 1.46 1.01 14 3 7. 36 2.64 2.71 1.36 0.90 0.79 0.57 1.41 0.97 15 15 12. 2 3.22 3.31 1.55 0.93 0.77 0.51 1.56 1.04 16 3 12. 24 2.7 2. 5 1.50 0.99 0. 6 0.63 1.51 1.0 17 1 9.5 32 3.55 3.64 1.5 0.90 0.71 0.44 1.59 1.02 18 1 12. 36 3.43 3.53 1.50 0. 6 0.69 0.45 1.53 0.9 19 10 2.0 20 4.13 4.37 2.07 1.08 0.72 0.25 1.94 1.25 20 25 12.0 32 2.6 2.4 1.41 0.92 0.80 0.58 1.45 1.00 21 30 2.0 28 2.9 3.04 1.53 0.94 0.76 0.48 1.51 1.04 22 15 4.5 36 3.29 3.3 1.52 0.91 0.72 0.45 1.57 1.02 23 20 4.5 28 3.17 3.25 1.60 0.97 0.77 0.49 1.59 1.07 24 25 4.5 20 3.0 3.26 1.71 1.05 0.84 0.55 1.67 1.16 25 15 2.0 32 3.43 3.63 1.75 0.95 0.69 0.39 1.65 1.07 26 3.00 3.20 1.50 1.00 0.80 0.60 1.50 1.10 工况3 1 10 7. 28 4.77 4.7 3.13 2.43 2.08 2.56 4.24 3.70 2 10 4.5 24 4.99 4.9 3.62 2.22 2.24 2.62 4.48 3.86 3 15 7. 20 4.24 4.5 3.41 2.15 2.21 2.33 4.07 3.52 4 20 2. 24 4.46 4.45 3.32 2.12 2.09 2.50 3.60 3.43 5 25 7. 24 4.02 4.05 2.76 2.29 2.11 2.45 3.20 3.11 6 20 12. 20 4.21 4.23 2.54 2.33 2.14 2.30 3.37 3.23 7 20 7. 32 3.6 3.90 2.5 1.95 2.06 2.07 3.05 3.02 8 25 9.5 28 3. 3.92 2.61 1.96 2.09 2.13 3.39 2.65 9 30 9.5 20 3.93 3.95 2.94 2.02 2.16 2.26 3.13 3.02 10 15 9.5 24 4.40 4.42 2.96 2.06 2.10 2.26 3.00 3.40 11 20 9.5 36 3.94 3.99 2.5 1.93 2.0 2.07 2.67 3.09 12 25 2. 36 4.01 4.03 2.67 1.95 2.0 2.04 2.72 3.12 13 30 4.5 32 3.77 3.0 2.53 1.92 2.05 2.04 2.94 2.98 14 30 7. 36 3.64 3.69 2.59 1.87 2.03 2.00 2.48 2.85 15 15 12. 28 4.26 4.30 3.01 1.99 2.09 2.19 3.39 3.31 16 30 12. 24 3.79 3.2 2.77 1.51 2.13 2.17 2.99 2.93 17 10 9.5 32 4.61 4.64 2.95 2.02 2.08 2.22 3.68 3.59 18 10 12. 36 4.49 4.53 3.02 1.97 2.10 2.19 3.57 3.50 19 10 2. 20 5.06 5.09 3.29 2.25 2.24 2.29 4.06 3.97 20 25 12. 32 3.54 3.2 2.6 1.90 2.07 2.07 2.57 2.94 21 30 2. 2 3.95 3.96 2.90 1.96 2.10 2.09 3.15 3.05 22 15 4.5 36 4.37 4.40 3.10 1.53 2.07 2.13 3.49 3.42 23 20 4.5 2 3.93 4.24 3.0 2.06 2.07 2.16 2.88 3.28 24 25 4.5 20 4.01 4.03 2.01 2.56 2.07 2.12 3.19 3.11 25 15 2. 32 4.62 4.62 3.33 2.13 2.09 2.17 3.72 3.59 26 4.10 3.0 3.10 2.00 2.10 2.00 3.50 3.20
下载: 导出CSV
表 6 工况3土体参数反演值
Table 6. Back-analysis validation results in the third construction stage
反演方法 填石 淤泥 砂质黏土 MLSSVR 23.01 5.89 27.57 LSSVR 19.96 7.02 26.52
下载: 导出CSV
表 7 工况3反演验证结果
Table 7. Back-analysis validation results in the third construction stage
反演方法 平均绝对误差/mm 最大绝对误差/mm 平均相对误差/% 最大相对误差/% 总cpu时间/s MLSSVR 0.06 0.134 2.09% 4.32% 185 LSSVR 0.167 0.46 6.00% 10.45% 2840
下载: 导出CSV
表 8 MLSSVR模型参数
Table 8. Model parameters of MLSSVR
工况 γbest λbest gbest 工况1 0.0009765 512 0.0000305 工况2 8 0.25 0.125 工况3 8 4 0.5
下载: 导出CSV
表 9 土体参数反演值
Table 9. Inversion values of soil parameters
土层 原始参数/MPa 工况1反演参数/MPa 工况2反演参数/MPa 工况3反演参数/MPa 填石 18 25.44 24.19 23.01 淤泥 6 8.80 9.22 5.89 砂质黏性土 30 29.61 24.75 27.57
下载: 导出CSV
表 10 反演验证结果
Table 10. Back-analysis validation results
测点 工况1监测值/mm 工况1计算值/mm 工况1绝对误差/mm 工况1相对误差/% 工况2监测值/mm 工况2计算值/mm 工况2绝对误差/mm 工况2相对误差/% 工况3监测值/mm 工况3计算值/mm 工况3绝对误差/mm 工况3相对误差/% J1 1.0 0.951 0.049 4.90 3.0 2.962 0.038 1.27 4.1 4.082 0.018 0.44 J2 1.1 0.975 0.125 11.36 3.2 3.138 0.062 1.94 3.8 3.950 0.150 3.95 J3 0.5 0.480 0.020 4.00 1.5 1.556 0.056 3.73 3.1 2.966 0.134 4.32 J4 0.4 0.362 0.038 9.50 1.0 0.911 0.089 8.90 2.0 2.020 0.020 1.00 J5 0.3 0.310 0.010 3.33 0.8 0.833 0.033 4.12 2.1 2.146 0.046 2.19 J6 0.3 0.278 0.022 7.33 0.6 0.583 0.017 2.83 2.0 1.946 0.054 2.70 J7 0.5 0.471 0.029 5.80 1.5 1.548 0.048 3.20 3.5 3.544 0.044 1.26 J8 0.3 0.246 0.054 18.00 1.1 1.083 0.017 1.55 3.2 3.228 0.028 0.88
下载: 导出CSV
-
Bao T F,Li J M,Lu Y F,et al. 2020. IDE-MLSSVR-based back analysis method for multiple mechanical parameters of concrete dams[J]. Journal of Structural Engineering, 146(8): 04020155. doi: 10.1061/(ASCE)ST.1943-541X.0002602 Chen H C. 2017. Study on backing analysis of the silty parameters in reclamation area and predicting the deformation of foundation pit[D]. Guangzhou: Guangzhou University. Chen W L, Wang Z G, Wei M R. 2014. Effect of anchor-pile to foundation pit support and its influences on the surroundings[J]. Journal of Jilin University: Earth Science Edition, 44 (4): 1269-1275. Dou H Q, Wang H, Wu F B, et al. 2018. Corner effects of deep excavations with multi exposed corners in square crossing of utility tunnel[J]. Journal of Engineering Geology, 26 (6): 1657-1665. Ge Z J, Li X K. 2000. An artificial neural network method for parametric identification in deep foundation excavation[J]. Journal of Dalian University of Technology, 40 (3): 271-275. Guo Z Q, Yang S S, Li Y B, et al. 2020. Back analysis of soil parameters of metro shield site based on PSO-BP neural network[J]. Journal of Taiyuan University of Technology, 51 (2): 171-176. Hu B, Wang X G, Feng X L, et al. 2014. Analytical prediction and numerical simulation of effect of a deep excavation project of Wuhan metro on nearby viaduct[J]. Chinese Journal of Geotechnical Engineering, 36 (S2): 368-373. Hu J L, Sun L C, Cui H H, et al. 2021. Numerical analysis of deep foundation pit deformation based on modified Mohr Coulomb model[J]. Journal of Liaoning Technical University (Natural Science), 40(2): 134-140. Hu R G, Liu H J, Wang Z Y, et al. 2020. Deformation analysis of supporting structure for soil-rock combination foundation pit with adjacent buildings in coastal area[J]. Journal of Engineering Geology, 28 (6): 1368-1377. Li A G, Qin Z, Bao F M, et al. 2002. Particle swarm optimization algorithms[J]. Computer Engineering and Applications, (21): 1-3. Li L X, Zhang Y L, Hu X B. 2016. Finite element analysis of a pit-in-pit excavation based on PLAXIS 3D[J]. Chinese Journal of Underground Space and Engineering, 12(S1): 254-261. Li M, Xu Y, Zhang B. 2020. Research on lateral stiffness of strutted retaining structure for deep excavation[J]. Journal of Engineering Geology, 28 (5): 1116-1122. Li Z W. 2015. Analysis the function of engineering geological survey in the design and construction of foundation pit[J]. Low Carbon World, (11): 95-96. Liu C G, Gu C S, Chen B. 2017. Zoned elasticity modulus inversion analysis method of a high arch dam based on unconstrained Lagrange support vector regression(support vector regression arch dam)[J]. Engineering with Computers, 33 (3): 443-456. doi: 10.1007/s00366-016-0483-9 Liu H, Zhang H Q, Liu B. 2014. A prediciton method for the deformation of deep foundation pit based on the particle swarm optimization neural network[J]. Journal of Jilin University: Earth Science Edition, 44 (5): 1609-1614. Liu R. 2020. Research on deformation characteristics of foundation pit in soil-rock combination strata based on HSS model[D]. Beijing: Beijing Jiaotong University. Lu Y F, Wang B Z, Fan W L, et al. 2019. Mechanical parameters inversion of dam body and foundation based on online SVR-ABAQUS[J]. Gansu Water Resources and Hydropower Technology, 55 (3): 15-19. Luo Z Y. 2018. Investigation on horizontal displacement of deep foundation pit of subway based on PSO-LSSVM models[D]. Bejing: China University of Geosciences(Beijing). Mao X. 2019. Back analysis of soil parameters of deep foundation pit based on LSSVM and GA algorithm and deformation prediction of retaining piles[D]. Chengdu: Chengdu University of Technology. Pang X C, Huang J J, Su D, et al. 2018. Experimental study on parameters of the hardening soil model for undisturbed granite residual soil in Shenzhen[J]. Rock and Soil Mechanics, 39 (11): 4079-4085. Qin S W, Miao Q, Zhang L S, et al. 2020. Finite element analysis on influence of excavation and support removal of foundation pit to surrounding environment[J]. Journal of Engineering Geology, 28 (5): 1106-1115. Ruan Y F, Yu D X, Yang J, et al. 2020. Inversion of mechanical parameters of reinforced soft soil around tunnel based on PSO-SVM[J]. Journal of Highway and Transportation Research and Development, 37 (6): 87-96. Sha Y H, Chen Z J, et al. 2017. Application of PSO-SVM algorithm in soil parameters inversion[J]. Site Investigation Science and Technology, (3): 45-49. Shi Y Z, Hua J B, Lian Y X, et al. 2018. Safety evaluation and protection measures to adjacent pipelines during deep excavation for metro construction[J]. Journal of Engineering Geology, 26 (4): 1043-1053. Shi Y Z, Lin S Z, Zhao H L. 2016. Soil's small strain paramrters sensitivity analysis of metro deep foundation pit excavation effect in Xiamen Area[J]. Journal of Engineering Geology, 24 (6): 1294-1301. Song C C. 2019. Numerical simulation of excavation deformation of a deep foundation pit based on MIDAS/GTS[J]. Journal of Heilongjiang University of Technology, 19 (4): 60-65. Su H Z, Wen Z P, Zhang S, et al. 2016. Method for choosing the optimal resource in back-analysis for multiple material parameters of a dam and its foundation[J]. Journal of Computing in Civil Engineering, 30(4): 4015060. doi: 10.1061/(ASCE)CP.1943-5487.0000537 Sun C, Xu C J. 2019. Influence of Excavation of a deep excavation on the surrounding environment[J]. Journal of Jilin University: Earth Science Edition, 49 (6): 1698-1705. Sun Q C, Li S J, Zhao H B, et al. 2019. Probabilistic back analysis of rock mechanical parameters based on displacement and relaxation depth[J]. Chinese Journal of Rock Mechanics and Engineering, 38 (9): 1884-1894. Wu C D, Zhang Y M, Tian L C, et al. 2017. Displacement back analysis of deep foundation pit for subway station based on modified neural network[J]. Bulletin of Science and Technology, 33 (1): 142-146. Xiao M Q, Liu H, Peng C S, et al. 2017. Back analysis of deep soft soil parameters based on neural network[J]. Chinese Journal of Underground Space and Engineering, 13 (1): 279-286. Xu S, An X, Qiao X D, et al. 2013. Multi-output least-squares support vector regression machines[J]. Pattern Recognition Letters, 34 (9): 1078-1084. doi: 10.1016/j.patrec.2013.01.015 Xu Z H, Wang W D. 2010. Selection of soil constitutive models for numerical analysis of deep excavations in close proximity to sensitive properies[J]. Rock and Soil Mechanies, 31(1): 258-264. Yang J, Hu D X, Wu Z R. 2006. Bayesian uncertainty inverse analysis method based on pome[J]. Journal of Zhejiang University(Engineering Science), 40 (5): 810-815. Zhang L F, Zhou G C. 2019. Parameters selection and sensitivity analysis of settlement of silt seawall based on hardened soil model[J]. Water Resources and Power, 37 (10): 85-87. Zhang Y X. 2019. Back analysis of soil parameters of deep foundation pit in haixiang with soft soil and dynamic prediction of foundation Pit excavation[D]. Chengdu: Southwest Jiaotong University. Zhao T, Liang Q G, Ai S J, et al. 2021. Study on numerical simulation of deep foundation Pit excavation in sandy cobble stratum[J]. Journal of Lanzhou Jiaotong University, 40 (1): 6-12. Zhou Y, Hu Y L. 2021. Calculation for displacement and internal force of pile anchor retaining structure based on improved increment method[J]. Journal of Engineering Geology, 29 (1): 229-236. Zhu H Q, Xi M X, Cui M, et al. 2017. Back analysis of parameters and settlement prediction of soft foundation based on BP neural network and genetic algorithm[J]. Journal of Nanchang Institute of Technology, 36 (3): 84-90. Zhu X Q, Gao Z H. 2018. An efficient gradient-based model selection algorithm for multi-output least-squares support vector regression machines[J]. Pattern Recognition Letters, 111 : 16-22. doi: 10.1016/j.patrec.2018.01.023 陈浩冲. 2017. 填海区淤泥的岩土参数反演及基坑变形预测研究[D]. 广州: 广州大学. 陈文玲, 王振刚, 魏美蓉. 2014. 锚杆排桩基坑支护效果及其对周围环境的影响[J]. 吉林大学学报(地球科学版), 44 (4): 1269-1275. https://www.cnki.com.cn/Article/CJFDTOTAL-CCDZ201404021.htm 豆红强, 王浩, 吴福宝, 等. 2018. 带多阳角的综合管廊垂直交叉节点深基坑的坑角效应分析[J]. 工程地质学报, 26 (6): 1657-1665. doi: 10.13544/j.cnki.jeg.2017-473 葛增杰, 李锡夔. 2000. 深基坑开挖工程多层土体物性参数识别的BP法[J]. 大连理工大学学报, 40 (3): 271-275. https://www.cnki.com.cn/Article/CJFDTOTAL-DLLG200003008.htm 郭子奇, 杨双锁, 李彦斌, 等. 2020. 基于PSO-BP神经网络的地铁盾构场地土体参数反演[J]. 太原理工大学学报, 51 (2): 171-176. https://www.cnki.com.cn/Article/CJFDTOTAL-TYGY202002003.htm 胡斌, 王新刚, 冯晓腊, 等. 2014. 武汉地铁某深基坑开挖对周边高架桥影响的分析预测与数值模拟研究[J]. 岩土工程学报, 36 (S2): 368-373. https://www.cnki.com.cn/Article/CJFDTOTAL-YTGC2014S2066.htm 胡建林, 孙利成, 崔宏环, 等. 2021. 修正莫尔库仑模型下的深基坑变形数值分析[J]. 辽宁工程技术大学学报(自然科学版), 40(2): 134-140. 胡瑞庚, 刘红军, 王兆耀, 等. 2020. 邻近建筑物的滨海土岩组合基坑支护结构变形分析[J]. 工程地质学报, 28 (6): 1368-1377. doi: 10.13544/j.cnki.jeg.2019-545 李爱国, 覃征, 鲍复民, 等. 2002. 粒子群优化算法[J]. 计算机工程与应用, (21): 1-3. https://www.cnki.com.cn/Article/CJFDTOTAL-JSGG200221000.htm 李连祥, 张永磊, 扈学波. 2016. 基于PLAXIS 3D有限元软件的某坑中坑开挖影响分析[J]. 地下空间与工程学报, 12(S1): 254-261. https://www.cnki.com.cn/Article/CJFDTOTAL-BASE2016S1040.htm 李冕, 徐阳, 张搏. 2020. 深基坑竖向支承系统的侧向刚度研究[J]. 工程地质学报, 28 (5): 1116-1122. doi: 10.13544/j.cnki.jeg.2020-430 李庄伟. 2015. 试析工程地质勘察在基坑设计和施工中的作用[J]. 低碳世界, (11): 95-96. 刘贺, 张弘强, 刘斌. 2014. 基于粒子群优化神经网络算法的深基坑变形预测方法[J]. 吉林大学学报(地球科学版), 44 (5): 1609-1614. https://www.cnki.com.cn/Article/CJFDTOTAL-CCDZ201405019.htm 刘蓉. 2020. 基于HSS模型的土岩组合地层基坑变形特性研究[D]. 北京: 北京交通大学. 卢远富, 汪宾舟, 樊文林, 等. 2019. 基于在线SVR-ABAQUS的坝体与坝基力学参数反演[J]. 甘肃水利水电技术, 55 (3): 15-19. https://www.cnki.com.cn/Article/CJFDTOTAL-GSSJ201903006.htm 罗志远. 2018. 基于PSO-LSSVM模型的地铁深基坑水平位移反分析研究[D]. 北京: 中国地质大学(北京). 毛翔. 2019. 基于LSSVM和GA算法的深基坑土体参数反演及支护桩变形预测[D]. 成都: 成都理工大学. 庞小朝, 黄俊杰, 苏栋, 等. 2018. 深圳地区原状花岗岩残积土硬化土模型参数的试验研究[J]. 岩土力学, 39 (11): 4079-4085. https://www.cnki.com.cn/Article/CJFDTOTAL-YTLX201811021.htm 秦胜伍, 苗强, 张领帅, 等. 2020. 基坑开挖与支撑拆除对周围环境影响的研究[J]. 工程地质学报, 28 (5): 1106-1115. doi: 10.13544/j.cnki.jeg.2020-275 阮永芬, 余东晓, 杨均, 等. 2020. PSO-SVM反演隧道周围加固软土的力学参数[J]. 公路交通科技, 37 (6): 87-96. https://www.cnki.com.cn/Article/CJFDTOTAL-GLJK202006011.htm 沙勇华, 陈志坚. 2017. PSO-SVM算法在土体参数反演中的应用[J]. 勘察科学技术, (3): 45-49. https://www.cnki.com.cn/Article/CJFDTOTAL-KCKX201703012.htm 施有志, 华建兵, 连宇新, 等. 2018. 地铁深基坑施工扰动下邻近管线安全评价及保护措施[J]. 工程地质学报, 26 (4): 1043-1053. doi: 10.13544/j.cnki.jeg.2017-295 施有志, 林树枝, 赵花丽. 2016. 地铁深基坑开挖效应土体小应变参数敏感性分析——以厦门地区为例[J]. 工程地质学报, 4 (6): 1294-1301. doi: 10.13544/j.cnki.jeg.2016.06.032 宋辰辰. 2019. 基于MIDAS/GTS对某深基坑开挖变形的数值模拟研究[J]. 黑龙江工业学院学报(综合版), 19 (4): 60-65. https://www.cnki.com.cn/Article/CJFDTOTAL-XBJX201904012.htm 孙超, 许成杰. 2019. 基坑开挖对周边环境的影响[J]. 吉林大学学报(地球科学版), 49 (6): 1698-1705. https://www.cnki.com.cn/Article/CJFDTOTAL-CCDZ201906016.htm 孙钱程, 李邵军, 赵洪波, 等. 2019. 基于位移和松弛深度的岩体参数概率反分析方法[J]. 岩石力学与工程学报, 38 (9): 1884-1894. https://www.cnki.com.cn/Article/CJFDTOTAL-YSLX201909016.htm 吴才德, 章玉明, 田领川, 等. 2017. 基于改进神经网络的地铁车站深基坑位移反分析[J]. 科技通报, 33 (1): 142-146. https://www.cnki.com.cn/Article/CJFDTOTAL-KJTB201701031.htm 肖明清, 刘浩, 彭长胜, 等. 2017. 基于神经网络的深厚软土地层参数反演分析[J]. 地下空间与工程学报, 13 (1): 279-286. https://www.cnki.com.cn/Article/CJFDTOTAL-BASE201701039.htm 徐中华, 王卫东. 2021. 敏感环境下基坑数值分析中土体本构模型的选择[J]. 岩土力学, 30(1): 258-264. https://www.cnki.com.cn/Article/CJFDTOTAL-YTLX201001045.htm 杨杰, 胡德秀, 吴中如. 2006. 基于最大熵原理的贝叶斯不确定性反分析方法[J]. 浙江大学学报(工学版), 40 (5): 810-815. https://www.cnki.com.cn/Article/CJFDTOTAL-ZDZC200605016.htm 张丽芬, 周谷城. 2019. 基于硬化土模型的淤泥质海堤沉降计算参数取值及灵敏度分析[J]. 水电能源科学, 37 (10): 85-87. https://www.cnki.com.cn/Article/CJFDTOTAL-SDNY201910022.htm 张亚西. 2019. 海相软土地质深基坑土体参数反演及基坑动态开挖预测[D]. 成都: 西南交通大学. 赵涛, 梁庆国, 艾胜军, 等. 2021. 砂卵石地层深基坑开挖数值模拟研究[J]. 兰州交通大学学报, 40 (1): 6-12. https://www.cnki.com.cn/Article/CJFDTOTAL-LZTX202101002.htm 周勇, 胡玉丽. 2021. 基于改进增量法的桩锚支护结构位移与内力计算[J]. 工程地质学报, 29 (1): 229-236. doi: 10.13544/j.cnki.jeg.2020-039 朱海琴, 习明星, 崔猛, 等. 2017. 基于BP神经网络和遗传算法的软基参数反演与沉降预测[J]. 南昌工程学院学报, 36 (3): 84-90. https://www.cnki.com.cn/Article/CJFDTOTAL-NCSB201703017.htm -
点击查看大图
图(6) / 表(10)
计量
- 文章访问数: 466
- HTML全文浏览量: 88
- PDF下载量: 50
- 被引次数: 0
