|
|
Reliability analysis of post-construction settlement of DMC composite foundation and design optimization |
Wei-hang CHEN1( ),Qiang LUO1,2,Teng-fei WANG1,2,*( ),Wen-sheng ZHANG1,Liang-wei JIANG1,2 |
1. School of Civil Engineering, Southwest Jiaotong University, Chengdu 610031, China 2. MOE Key Laboratory of High-Speed Railway Engineering, Chengdu 610031, China |
|
|
Abstract The stochastic nature of the model was used to characterize the uncertainty of soil parameters based on the random transformation of an artificial neural network architecture incorporating Monte Carlo Dropout (ANN_MCD) in order to address the issue that using deterministic analysis method is risky to control the post-construction settlement of ground improved by deep mixed columns (DMCs). The predictions were performed efficiently for post-construction settlement of ground improved by DMCs considering the uncertainty of soil parameters by combining the finite element simulations with a surrogate model. The probability distribution of post-construction settlement with different combinations of pile length, pile diameter, pile spacing and cushion thickness was obtained. The limit value of the post-construction settlement was determined from the target reliability index for serviceability limit state, and linked to the cost of ground improvement based on the nonlinear mapping. The structural design optimization was finally conducted by considering the benefit–cost ratio. The uncertainty of modified Cam-Clay model parameters can be derived from the plasticity index Ip of soft clay with ANN_MCD-based model, with the 95% prediction interval matching closely with the experimental data. The ANN-based model with a separated input layer can individually extract features from soil and structural parameters, avoiding a redundant architecture of ANN and achieving efficient and precise predictions for post-construction settlement of DMC composite foundation. The relationship between post-construction settlement and the lowest construction cost can be fitted by a Logistic curve. The threshold of benefit-cost ratio corresponds to the maximum curvature point of the Logistic curve, and the optimized design should be on the side of cost lower than Cv (highly cost-effective).
|
Received: 12 November 2021
Published: 25 October 2022
|
|
Fund: 国家自然科学基金资助项目(52078435, 41901073);四川省科技计划资助项目(2021YJ0001) |
Corresponding Authors:
Teng-fei WANG
E-mail: chenweihang@my.swjtu.edu.cn;w@swjtu.edu.cn
|
DMC复合地基工后沉降可靠性分析及设计优化
针对确定性分析方法进行水泥土搅拌桩(DMC)复合地基工后沉降控制存在一定风险的问题,基于Monte Carlo dropout神经网络(ANN_MCD)架构的随机变换,利用模型输出随机性表征土体参数的不确定性. 结合有限元与代理模型,开展考虑土体参数不确定性的DMC复合地基工后沉降高效计算,获得不同桩长、桩径、桩间距、垫层厚度参数组合下的工后沉降概率分布. 以路基正常使用极限状态下的目标可靠指标,确定工后沉降界限值,建立沉降与地基处理成本的非线性映射关系,结合成本效能指标进行结构设计优化. 研究表明,ANN_MCD模型可以依据地基软黏土塑性指数Ip,推演修正剑桥模型参数的不确定性,预测参数的95%置信区间与试验值吻合良好. 利用土体与结构参数独立进行特征提取的双输入层ANN代理模型,可以有效地避免网络结构冗余,实现DMC复合地基工后沉降S的高效高精度预测. S与最低建造成本符合Logistic曲线形式,成本效能分界值Cv位于曲率最大点,设计优化方案应位于成本≤Cv的高效费比区.
关键词:
深度学习,
DMC复合地基,
工后沉降,
可靠性分析,
设计优化
|
|
[1] |
DANG C C, DANG L C. Numerical investigation on the stability of soil-cement columns reinforced riverbank [C]// Information Technology in Geo-Engineering. Switzerland: Springer, 2020.
|
|
|
[2] |
WIJERATHNA M, LIYANAPATHIRANA D S, LEO C J Analytical solution for the consolidation behavior of deep cement mixed column-improved ground[J]. International Journal of Geomechanics, 2017, 17 (9): 04017065
doi: 10.1061/(ASCE)GM.1943-5622.0000954
|
|
|
[3] |
陈昌富, 邱琳淇, 毛凤山, 等 基于加权扰动共生生物搜索算法桩网复合地基优化设计[J]. 岩土力学, 2019, 40 (11): 4477- 4485 CHEN Chang-fu, QIU Lin-qi, MAO Feng-shan, et al Design optimization of pile-net composite foundation based on perturbation-weighted symbiotic organisms search (PWSOS) algorithm[J]. Rock and Soil Mechanics, 2019, 40 (11): 4477- 4485
|
|
|
[4] |
CHIKAHIRO Y, ARIO I, PAWLOWSKI P, et al Optimization of reinforcement layout of scissor-type bridge using differential evolution algorithm[J]. Computer-Aided Civil and Infrastructure Engineering, 2019, 34 (6): 523- 538
doi: 10.1111/mice.12432
|
|
|
[5] |
李顺群, 张建伟, 夏锦红 原状土的剑桥模型和修正剑桥模型[J]. 岩土力学, 2015, 36 (Supple.2): 215- 220 LI Shun-qun, ZHANG Jian-wei, XIA Jin-hong An improvement on Cam-clay model and modified Cam-clay model for intact soil[J]. Rock and Soil Mechanics, 2015, 36 (Supple.2): 215- 220
doi: 10.16285/j.rsm.2015.S2.028
|
|
|
[6] |
陈建峰, 孙红, 石振明, 等 修正剑桥渗流耦合模型参数的估计[J]. 同济大学学报: 自然科学版, 2003, 31 (5): 544- 548 CHEN Jian-feng, SUN Hong, SHI Zhen-ming, et al Estimation of parameters of modified Cam-clay model coupling Biot theory[J]. Journal of Tongji University: Natural Science, 2003, 31 (5): 544- 548
|
|
|
[7] |
KATSUHIKO A, HIDEKI O, KEISUKE K, et al Application of back-analysis to several test embankments on soft clay deposits[J]. Soil and Foundations, 1986, 26 (2): 60- 72
doi: 10.3208/sandf1972.26.2_60
|
|
|
[8] |
AKIO N, TAKESHI X, OSAMU K Constitutive parameters estimated by plasticity index[J]. Journal of Geotechnical Engineering, 1988, 114 (7): 844- 858
doi: 10.1061/(ASCE)0733-9410(1988)114:7(844)
|
|
|
[9] |
GAL Y, GHAHRAMANI Z. Dropout as a Bayesian approximation: representing model uncertainty in deep learning [C]// International Conference on Machine Learning. New York: MIT Press, 2016: 1050-1069.
|
|
|
[10] |
ZHANG P, YIN Z Y, JIN Y F Bayesian neural network-based uncertainty modelling: application to soil compressibility and undrained shear strength prediction[J]. Canadian Geotechnical Journal, 2021, 59 (4): 546- 557
|
|
|
[11] |
ZHANG P, JIN Y F, YIN Z Y Machine learning–based uncertainty modelling of mechanical properties of soft clays relating to time-dependent behavior and its application[J]. International Journal for Numerical and Analytical Methods Geomechanics, 2021, 45 (11): 1588- 1602
doi: 10.1002/nag.3215
|
|
|
[12] |
张天龙, 曾鹏, 李天斌, 等 基于主动学习径向基函数的边坡系统可靠度分析[J]. 岩土力学, 2020, 41 (9): 3098- 3108 ZHANG Tian-long, ZENG Peng, LI Tian-bin, et al System reliability analyses of slopes based on active-learning radial basis function[J]. Rock and Soil Mechanics, 2020, 41 (9): 3098- 3108
doi: 10.16285/j.rsm.2019.1695
|
|
|
[13] |
毛凤山, 陈昌富, 朱世民 代理模型方法及其在岩土工程中的应用综述[J]. 地基处理, 2020, 31 (4): 295- 306 MAO Feng-shan, CHEN Chang-fu, ZHU Shi-min Surrogate model method and its application in geotechnical engineering[J]. Chinese Journal of Ground Improvement, 2020, 31 (4): 295- 306
|
|
|
[14] |
DANG L C, DANG C C, KHABBAZ H. Modelling of columns and fibre-reinforced load-transfer platform- supported embankments [C]// Ground Improvement, 2020, 173(4): 197-215.
|
|
|
[15] |
ANGGRAINI V, ASADI A, HUAT B B K, et al Performance of chemically treated natural fibres and lime in soft soil for the utilisation as pile-supported Earth platform[J]. International Journal of Geosynthetics and Ground Engineering, 2015, 1 (3): 1- 14
|
|
|
[16] |
CHAI J C, SHRESTHA S, HINO T, et al 2D and 3D analyses of an embankment on clay improved by soil−cement columns[J]. Computers and Geotechnics, 2015, 68: 28- 37
doi: 10.1016/j.compgeo.2015.03.014
|
|
|
[17] |
JELUŠIČ P, ŽLENDER B Optimal design of piled embankments with basal reinforcement[J]. Geosynthetics International, 2018, 25 (2): 150- 163
doi: 10.1680/jgein.17.00039
|
|
|
[18] |
邓永锋, 洪振舜, 刘松玉, 等 搅拌桩复合地基平面模拟的简化方法探讨[J]. 岩土力学, 2005, 26 (Supple.1): 209- 212 DENG Yong-feng, HONG Zhun-shun, LIU Song-yu, et al A planar simplified method for three-dimension cement-soil mixing piles composite foundation with FEM numerical analysis[J]. Rock and Soil Mechanics, 2005, 26 (Supple.1): 209- 212
doi: 10.16285/j.rsm.2005.s1.050
|
|
|
[19] |
CHEN C, MAO F, ZHANG G, et al. Settlement-based cost optimization of geogrid-reinforced pile-supported foundation[J]. Geosynthetics International, 2021, 28 (5): 541- 557
doi: 10.1680/jgein.21.00002
|
|
|
[20] |
国家铁路局. 铁路工程结构可靠性设计统一标准: GB 50216—2019 [S]. 北京: 中国计划出版社, 2019.
|
|
|
[21] |
浙江省住房和城乡建设厅. 复合地基技术规范: GB/T 50783—2012 [S]. 北京: 中国计划出版社, 2012.
|
|
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
|
Shared |
|
|
|
|
|
Discussed |
|
|
|
|