基于智能优化算法的深大基坑施工反分析

左自波; 黄玉林; 吴小建

doi:10.11779/CJGE2017S2032

基于智能优化算法的深大基坑施工反分析 English Version

左自波^{1, 2},
黄玉林^{1, 2},
吴小建^{1, 2}

1. 上海建工集团工程研究总院,上海 201114;
2. 上海建工集团股份有限公司,上海200080

基金项目: 国家重点研发计划项目（2017YFC0805500）; 上海市“科技创新行动计划”社会发展领域项目（16DZ1201600）; 上海建工重点科研项目（14GLXX-05）

详细信息

作者简介:
左自波(1986- ),男,陕西安康人,硕士,工程师,主要从事土木工程数字化建造技术研究。E-mail：zuozibo@foxmail.com。

计量
- 文章访问数: 0302
- HTML全文浏览量: 0
- PDF下载量: 0228
出版历程
- 收稿日期: 2017-08-01
- 发布日期: 2017-12-19

Back analysis of construction of large deep excavations using intelligent optimization algorithm

ZUO Zi-bo^{1, 2},
HUANG Yu-lin^{1, 2},
WU Xiao-jian^{1, 2}

1. General Engineering Institute of Shanghai Construction Group, Shanghai 201114, China;
2. Shanghai Construction Group Co., Ltd., Shanghai 200080, China

摘要

摘要: 引入人工智能技术,提出了一种基于神经网络的Nelder-Mead改进加速算法,建立了基于监测结果的深大基坑动态施工反馈分析方法。以93383 m²超大基坑工程为案例,进行了三维有限元参数反演分析,预测了基坑后续开挖围护结构水平位移、支撑轴力、管沟位移。结果表明：与Nelder-Mead算法比较,采用所建立的方法的收敛速度快,迭代次数减少了最大达86.9％;预测结果与实测结果吻合较好。
- 基坑 /
- 反分析 /
- 三维FEM模拟 /
- Nelder-Mead算法 /
- 神经网络
Abstract: By introducing the artificial intelligence technology, on improved Nelder-Mead acceleration algorithm based on the neural network is proposed to obtain better optimization results. A back analysis method for construction of large deep excavations using field observations is established. 3D numerical simulation analyses using the intelligent optimization technique are performed to forecast the horizontal deformation of the wall, axial force of the supports and displacement of the adjacent energy supply pipelines at later stages based on the background of excavation with an area of 93383. The results show that the convergence of the calculation is faster using the proposed method, and the number of iterations decreases by up to 86.9% compared with that of the Nelder-Mead algorithm. The predicted results are in good agreement with the monitoring data.
- excavation /
- back analysis /
- three-dimensional finite element simulation /
- Nelder-Mead algorithm /
- neural network

HTML全文

参考文献(8)

[1]	侯学渊, 刘国彬, 黄院雄. 城市基坑工程发展的几点看法[J]. 施工技术, 2000, 29(1): 5-7. (HOU Xue-yuan, LIU Guo-bin, HUANG Yuan-xiong. Several views on the development of urban foundation work[J]. Construction Technology, 2000, 29(1): 5-7. (in Chinese))
[2]	HASHASH Y M A, LEVASSEUR S, OSOULI A, et al. Comparison of two inverse analysis techniques for learning deep excavation response[J]. Computers and Geotechnics, 2010(37): 323-333.
[3]	邓子胜. 基于径向基神经网络的深基坑非线性位移反分析[J]. 岩土工程学报, 2005, 27(5): 554-557. (DENG Zi-sheng. Nonlinear displacement back-analysis for deep excavation based on radial basis neural network[J]. Chinese Journal of Geotechnical Engineering, 2005, 27(5): 554-557. (in Chinese))
[4]	JUANG C H, LUO Z, ATAMTURKTUR S, et al. Bayesian updating of soil parameters for braced excavations using field observations[J]. Journal of Geotechnical and Geoenvironmental Engineering, ASCE, 2013, 139(3): 395-406.
[5]	MURAKAMI A. The role of Kalman filtering in an inverse analysis of elasto-plastic material[J]. Proceedings of the Japan Academy, 2002, 78(B): 250-255.
[6]	贾善坡, 陈卫忠, 谭贤君, 等．大岗山水电站地下厂房区初始地应力场Nelder-Mead 优化反演研究[J]. 岩土力学, 2008, 29(9): 2341-2348. (JIA Shan-po, CHEN Wei-zhong, TAN Xian-jun, et al. Nelder-Mead algorithm for inversion analysis of in-situ stress field of underground powerhouse area of Dagangshan Hydropower Station[J]. Rock and Soil Mechanics, 2008, 29(9): 2341-2348. ( in Chinese))
[7]	彭军龙, 张学民, 阳军生, 等. 地铁深基坑支护的遗传神经网络位移反分析[J]. 岩土力学, 2007, 28(10): 2118-2122. (PENG Jun-long, ZHANG Xue-min, YANG Jun-sheng, et al. Displacement back analysis of deep foundation pit for metro based on genetic algorithm and neural network[J]. Rock and Soil Mechanics, 2007, 28(10): 2118-2122. (in Chinese))
[8]	OBRZUD R F, TRUTY A, VULLIET L. Numerical modeling and neural networks to identify model parameters from piezocone tests: Ⅱ Multi-parameter identification from piezocone data[J]. International Journal for Numerical and Analytical Methods in Geomechanics, 2012, 36(6):743-779.

施引文献

资源附件(0)

计量

文章访问数:
HTML全文浏览量: 0
PDF下载量:
被引次数: 0

基于智能优化算法的深大基坑施工反分析 English Version

作者简介: 左自波(1986- ),男,陕西安康人,硕士,工程师,主要从事土木工程数字化建造技术研究。E-mail：zuozibo@foxmail.com。

计量

出版历程

Back analysis of construction of large deep excavations using intelligent optimization algorithm

计量

出版历程

目录

作者简介:
左自波(1986- ),男,陕西安康人,硕士,工程师,主要从事土木工程数字化建造技术研究。E-mail：zuozibo@foxmail.com。