基于集成学习的超大型沉井基础下沉倾斜程度预测

doi:10.13722/j.cnki.jrme.2022.0631

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (1443 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要沉井基础广泛应用于各类大型构筑物建设中，其下沉倾斜程度是下沉姿态最重要的指标之一，准确预测下沉倾斜程度有利于确保沉井安全平稳下沉以及预防潜在施工风险。基于bagging和boosting两种集成学习机制，分别采用随机森林算法和XGBoost框架建立沉井下沉倾斜程度预测模型，利用沉井底部结构应力监测数据，预测下沉过程中沉井基础顺桥向高差与横桥向高差。依托常泰长江大桥主塔超大型沉井基础下沉工程，验证本文提出预测模型的可靠性。之后，将本文预测模型与其他单一机器学习算法模型进行对比，并分析模型重要参数对预测精度的影响。结果表明：本文预测模型可以准确预测沉井下沉过程中的顺桥向高差和横桥向高差，能够合理确定沉井下沉倾斜程度；本文模型的预测精度高于其他单一机器学习模型，模型运行速度快、实用性强，且模型预测精度随基学习器个数和最大树深度的增大而提高。研究成果实现沉井下沉倾斜程度实时预测，可为类似的大型沉井下沉监控提供重要参考。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	董学超1
	2
	郭明伟1
	2
	王水林1
	2
	蒋凡3

关键词 ：基础工程, 沉井基础, 倾斜预测, 集成学习, 随机森林, 梯度提升树, 常泰长江大桥

Abstract：Open caisson foundations are widely used in the construction of various large structures，and the inclination of an open caisson is one of the most important indexes of its sinking attitude. Accurate prediction of the inclination is conducive to ensuring the sinking safety and steady of the open caisson and preventing potential construction risks. Based on two ensemble learning techniques，bagging and boosting，the random forest algorithm and XGBoost framework are applied for the inclination prediction modeling. The monitoring data of the structural stress at the bottom of the open caisson are used to predict the longitudinal height difference and transverse height difference. The reliability of the prediction model was verified by applying it to the super-sized open caisson foundation of the main bridge pylon in the Changtai Yangtze River Bridge Project，and the proposed model was compared with the prediction models applying other single machine learning algorithms. Then，the important parameters of the ensemble learning model were analyzed to study their influence on prediction accuracy. The results show that the prediction model in this paper can accurately predict the longitudinal height difference and transverse height difference and reasonably determine the inclination of the open caisson foundation. With fast operating speed and strong practicability，the proposed model has higher prediction accuracy than other single machine learning models. In addition，the prediction accuracy increases with the number of base learners and the maximum tree depth. The research results achieve the real-time prediction of the inclination of the open caisson foundation during the sinking process，which can provide an important reference for the monitoring of similar foundations.

Key words： foundation engineering open caisson foundation inclination prediction ensemble learning random forest gradient boosting decision tree Changtai Yangtze River Bridge

引用本文:

董学超1，2，郭明伟1，2，王水林1，2，蒋凡3. 基于集成学习的超大型沉井基础下沉倾斜程度预测[J]. 岩石力学与工程学报, 2023, 42(S1): 3812-3822.
DONG Xuechao1，2，GUO Mingwei1，2，WANG Shuilin1，2，JIANG Fan3. Inclination prediction of a super-sized open caisson foundation during sinking process based on ensemble learning. , 2023, 42(S1): 3812-3822.

链接本文:

http://rockmech.whrsm.ac.cn/CN/10.13722/j.cnki.jrme.2022.0631 或 http://rockmech.whrsm.ac.cn/CN/Y2023/V42/IS1/3812

[2]	李军堂，秦顺全，张瑞霞. 桥梁深水基础的发展和展望[J]. 桥梁建设，2020，50(3)：17-24.(LI Juntang，QIN Shunquan，ZHANG Ruixia. Developments and prospects of deep water foundations for bridge[J]. Bridge Construction，2020，50(3)：17-24.(in Chinese))
[5]	李孟豪. 沉井下沉过程中刃脚承载力空间分布特性研究[硕士学位论文][D]. 成都：西南交通大学，2019.(LI Menghao. Study on spatial distribution stress of foot blade during caisson sinking in water[M. S. Thesis][D]. Chengdu：Southwest Jiaotong University，2019.(in Chinese))
[12]	YAN X，ZHAN W，HU Z，et al. Field study on deformation and stress characteristics of large open caisson during excavation in deep marine soft clay[J]. Advances in Civil Engineering，2021，2020：7656068.
[15]	龚维明，朱建民，穆保岗，等. 南京长江四桥北锚碇沉井首次降排水下沉研究[J]. 岩土工程学报，2010，32(增2)：537-540.(GONG Weiming，ZHU Jianming，MU Baogang，et al. Dewater sinking of north anchorage caisson of Fourth Nanjing Yangtze River Bridge[J]. Chinese Journal of Geotechnical Engineering，2010，32(Supp.2)：537-540.(in Chinese))
[22]	李明亮，李克钢，秦庆词，等. 岩爆烈度等级预测的机器学习算法模型探讨及选择[J]. 岩石力学与工程学报，2021，40(增1)：2 806- 2 816.(LI Mingliang，LI Kegang，QIN Qingci，et al. Discussion and selection of machine learning algorithm model for rockburst intensity grade prediction[J]. Chinese Journal of Rock Mechanics and Engineering，2021，40(Supp.1)：2 806-2 816.(in Chinese))
[10]	LAI F W，LIU S Y，LI Y L，et al. A new installation technology of large diameter deeply-buried caissons：Practical application and observed performance[J]. Tunnelling and Underground Space Technology，2022，125：104507.
[20]	吴志军，方立群，翁磊，等. 基于TBM掘进性能的岩体分级及可掘性等级感知识别方法[J]. 岩石力学与工程学报，2022，41(增1)： 2 684-2 699.(WU Zhijun，FANG Liqun，WENG Lei，et al. A classification and boreability perception and recognition method for rock mass based on TBM tunneling performance[J]. Chinese Journal of Rock Mechanics and Engineering，2022，41(Supp.1)：2 684-2 699.(in Chinese))
[25]	KE Y，DAI Y T，XU M L，et al. Tunnel surface settlement forecasting with ensemble learning[J]. Sustainability，2022，12(1)：232.
[30]	周小雄，龚秋明，殷丽君，等. 基于BLSTM-AM模型的TBM稳定段掘进参数预测[J]. 岩石力学与工程学报，2020，39(增2)：3 505- 3 515.(ZHOU Xiaoxiong，GONG Qiuming，YIN Lijun，et al. Predicting boring parameters of TBM stable stage based on BLSTM network combined with attention mechanism[J]. Chinese Journal of Rock Mechanics and Engineering，2020，39(Supp.2)：3 505-3 515.(in Chinese))
[32]	秦顺全，徐伟，陆勤丰，等. 常泰长江大桥主航道桥总体设计与方案构思[J]. 桥梁建设，2020，50(3)：1-10.(QIN Shunquan，XU Wei，LU Qinfeng，et al. Overall design and concept development for main navigational channel bridge of Changtai Changjiang River Bridge[J]. Bridge Construction，2020，50(3)：1-10.(in Chinese))
[35]	郭明伟，董学超，沈孔健，等. 超大沉井基础取土下沉端阻力变化规律研究[J]. 岩石力学与工程学报，2021，40(增1)：2 976-2 985. (GUO Mingwei，DONG Xuechao，SHEN Kongjian，et al. Study on the variation of the bottom resistance during sinking stage of super large caisson foundation[J]. Chinese Journal of Rock Mechanics and Engineering，2021，40(Supp.1)：2 976-2 985.(in Chinese))
[3]	施洲，刘东东，纪锋，等. 超大型沉井基础的施工风险评估[J]. 西南交通大学学报，2021，56(6)：1 241-1 249.(SHI Zhou，LIU Dongdong，JI Feng，et al. Construction risk assessment of super-large open caisson foundation[J]. Journal of Southwest Jiaotong University，2021，56(6)：1 241-1 249.(in Chinese))
[6]	褚晶磊. 沉井动态下沉侧摩阻力空间分布大型模型试验研究[硕士学位论文][D]. 成都：西南交通大学，2019.(CHU Jinglei. Large scale model test study on spatial distribution of side friction of caisson during dynamic sinking[M. S. Thesis][D]. Chengdu：Southwest Jiaotong University，2019.(in Chinese))
[13]	陈培帅. 深厚淤泥层大型陆上沉井施工控制技术研究[博士学位论文][D]. 西安：长安大学，2021.(CHEN Peishuai. Research on key technology of large land caisson in deep silt overburden[Ph D. Thesis][D]. Xi?an：Chang?an University，2021.(in Chinese))
[16]	董晓朋. 超深大沉井施工期间结构内力试验研究[硕士学位论文][D]. 成都：西南交通大学，2018.(DONG Xiaopeng. Experimental research on structural internal force of the ultra-deep and large caisson during construction[M. S. Thesis][D]. Chengdu：Southwest Jiaotong University，2018.(in Chinese))
[23]	周志华. 机器学习[M]. 北京：清华大学出版社，2016：171-196. (ZHOU Zhihua. Machine learning[M]. Beijing：Tsinghua University Press，2020：171-196.(in Chinese))
[26]	刘德军，戴庆庆，左建平，等. 基于Stacking集成算法的岩爆等级预测研究[J]. 岩石力学与工程学报，2022，41(增1)：2 915-2 926. (LIU Dejun，DAI Qingqing，ZUO Jianping，et al. Research on rockburst grade prediction based on stacking integrated algorithm[J]. Chinese Journal of Rock Mechanics and Engineering，2022，41(Supp.1)：2 915-2 926.(in Chinese))
[33]	李小珍，李星星，舒晓峰，等. 常泰长江大桥主桥风-车-线-桥耦合分析[J]. 桥梁建设，2021，51(3)：17-24.(LI Xiaozhen，LI Xingxing，SHU Xiaofeng，et al. Analysis of wind-train-track-bridge interaction for main bridge of Changtai Changjiang River Bridge[J]. Bridge Construction，2021，51(3)：17-24.(in Chinese))
[1]	段良策，殷奇. 沉井设计与施工[M]. 上海：同济大学出版社，2006：1-10.(DUAN Liangce，YIN Qi. Design and construction of caissons[M]. Shanghai：Tongji University Press，2006：1-10.(in Chinese))
[8]	李今保，姜涛，石先旺，等. 某旋流池沉井施工及失稳倾斜原因分析及处理[J]. 工业建筑，2012，42(9)：167-172.(LI Jinbao，JIANG Tao，SHI Xianwang，et al. The caisson construction of a swirl pool and its instability tilt analysis and treatment[J]. Industrial Construction，2012，42(9)：167-172.(in Chinese))
[18]	MAHMOODZADEH A，MOHAMMADI M，IBRAHIM H H，et al. Machine learning forecasting models of disc cutters life of tunnel boring machine[J]. Automation in Construction，2021，128：103779.
[28]	DOU J，YUNUS A P，BUI D T，et al. Improved landslide assessment using support vector machine with bagging，boosting，and stacking ensemble machine learning framework in a mountainous watershed，Japan[J]. Landslides，2019，39(4)：641-658.
[4]	穆保岗，朱建民，龚维明. 大型沉井设计、施工及监测[M]. 北京：中国建筑工业出版社，2015：1-21.(MU Baogang，ZHU Jianmin，GONG Weiming. Design，construction and monitoring of large open caissons[M]. Beijing：China Architecture and Building Press，2015：1-21.(in Chinese))
[7]	张治成，邓燕羚，郑锋利，等. 深厚软土地区大型沉井突沉行为分析[J]. 地下空间与工程学报，2020，16(3)：933-943.(ZHANG Zhicheng，DENG Yanling，ZHENG Fengli，et al. Analysis on sudden sinking behaviors of massive open caisson in deep-thick soft clay area[J]. Chinese Journal of Underground Space and Engineering，2020，16(3)：933-943.(in Chinese))
[9]	LI J，CHEN S X，YU F，et al. Mechanics and deformation characteristics of an oversized inclined caisson foundation when being reused[J]. Ocean Engineering，2022，248：110780.
[11]	ROYSTON R，SHEIL B B，BYRNE B W. Monitoring the construction of a large-diameter caisson in sand[J]. Proceedings of the Institution of Civil Engineers-Geotechnical Engineering，2020，175(3)：1-17.
[14]	徐鹏飞，李耀良，徐伟. 压入式沉井施工对环境影响的现场监测研究[J]. 岩土力学，2014，35(4)：1 084-1 094.(XU Pengfei，LI Yaoliang，XU Wei. Field measurement and analysis of influence of jacked open caisson construction on environments[J]. Rock and Soil Mechanics，2014，35(4)：1 084-1 094.(in Chinese))
[17]	邱锡鹏. 神经网络与深度学习[M]. 北京：机械工业出版社，2020：4-22.(QIU Xipeng. Neural networks and deep learning[M]. Beijing：China Machine Press，2020：4-22.(in Chinese))
[19]	XU C，LIU X L，WANG E Z，et al. Prediction of tunnel boring machine operating parameters using various machine learning algorithms[J]. Tunnelling and Underground Space Technology，2021，109：103699.
[21]	汤志立，徐千军. 基于9种机器学习算法的岩爆预测研究[J]. 岩石力学与工程学报，2020，39(4)：773-781.(TANG Zhili，XU Qianjun. Rockburst prediction based on nine machine learning algorithms[J]. Chinese Journal of Rock Mechanics and Engineering，2020，39(4)：773-781.(in Chinese))
[24]	仉文岗，唐理斌，陈福勇，等. 基于4种超参数优化算法及随机森林模型预测TBM掘进速度[J]. 应用基础与工程科学学报，2021，29(5)：1 186-1 200.(ZHANG Wengang，TANG Libin，CHEN Fuyong，et al. Prediction for TBM penetration rate using four hyperparameter optimization methods and random forest model[J]. Journal of Basic Science and Engineering，2021，29(5)：1 186-1 200.(in Chinese))
[27]	LV L，CHEN T，DOU J，et al. A hybrid ensemble-based deep-learning framework for landslide susceptibility mapping[J]. International Journal of Applied Earth Observation and Geoinformation，2022，108：102713.
[29]	CHEN T，GUESTRIN C. Xgboost：A scalable tree boosting system[C]// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York：Association for Computing Machinery，2016：785-794.
[31]	巫崇智. 基于XGBoost与LightGBM模型的土体不排水抗剪强度预测研究[硕士学位论文][D]. 重庆：重庆大学，2020.(WU Chongzhi. Soil undrained shear strength prediction based on XGBoost and LightGBM model[M. S. Thesis][D]. Chongqing：Chongqing University，2020.(in Chinese))
[34]	秦顺全，谭国宏，陆勤丰，等. 超大沉井基础设计及下沉方法研究[J]. 桥梁建设，2020，50(5)：1-9.(QIN Shunquan，TAN Guohong，LU Qinfeng，et al. Research on design and sinking methods for super- large caisson foundation[J]. Bridge Construction，2020，50(5)：1-9.(in Chinese))