Time Series Prediction on Settlement of Metro Tunnels Adjacent to Deep Foundation Pit by Clustering Monitoring Data

被引:5
作者
Zhang, Qi [1 ,2 ]
Ma, Yanning [1 ]
Zhang, Bin [1 ]
Tian, Longgang [1 ]
Zhang, Guozhu [3 ]
机构
[1] Southeast Univ, Sch Civil Engn, Nanjing 211189, Peoples R China
[2] China Univ Min & Technol, State Key Lab Geomech & Deep Underground Engn, Xuzhou 221116, Peoples R China
[3] Southeast Univ, Sch Transportat, Nanjing 211189, Peoples R China
基金
国家重点研发计划; 中国国家自然科学基金;
关键词
Settlement of metro tunnels; Improved data clustering method; Time series prediction; Adjacent to the deep foundation pit; Gaussian Mixture model; SIMILARITY SEARCH; ALGORITHM;
D O I
10.1007/s12205-023-0274-y
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
High requirements are put forward for the settlement control of metro tunnel to ensure the normal and safe operation of adjacent metro line during the process of deep foundation pit construction. Monitoring and predicting could constantly monitor the settlement of the tunnel and make safety early-warning, and massive data to be processed is collected by sensors in this process. In the study, an improved clustering method based on Gaussian mixture model (GMM) is proposed to deal with a large amount of monitoring data. Four initial eigenvalues are defined and the initial core points of clustering are selected by grouping monitoring sensors based on the characteristics of the project site and sensors. An improved method is utilized to the metro tunnel of Metro Line 9 near Xujiahui station. Compared with the traditional clustering method, the improved method has more reliable results, and reduces the operation time by 57.9%. Representative monitoring sensors are selected from each cluster to predict based on Long Short-Term Memory (LSTM) neural network. The prediction results well agree with the measured value and the prediction accuracy is reaching to 99.3%. Compared with other sensor selection ways, the data of representative sensors exhibits good representativeness and effectiveness. Finally, the prediction result after data update is more consistent with the monitoring data than the prediction result without data update. Increasing the data update frequency improves the accuracy of the prediction results in practical engineering application.
引用
收藏
页码:2180 / 2190
页数:11
相关论文
共 35 条
[1]   A hierarchical Gamma Mixture Model-based method for estimating the number of clusters in complex data [J].
Azhar, Muhammad ;
Huang, Joshua Zhexue ;
Masud, Md Abdul ;
Li, Mark Junjie ;
Cui, Laizhong .
APPLIED SOFT COMPUTING, 2020, 87 (87)
[2]   MODEL-BASED GAUSSIAN AND NON-GAUSSIAN CLUSTERING [J].
BANFIELD, JD ;
RAFTERY, AE .
BIOMETRICS, 1993, 49 (03) :803-821
[3]   A Hybrid Feature Selection-multidimensional LSTM Framework for Deformation Prediction of Super High Arch Dams [J].
Cao, Enhua ;
Bao, Tengfei ;
Li, Hui ;
Xie, Xiang ;
Yuan, Rongyao ;
Hu, Shaopei ;
Wang, Wenjun .
KSCE JOURNAL OF CIVIL ENGINEERING, 2022, 26 (11) :4603-4616
[4]   Prediction of shield tunneling-induced ground settlement using machine learning techniques [J].
Chen, Renpeng ;
Zhang, Pin ;
Wu, Huaina ;
Wang, Zhiteng ;
Zhong, Zhiquan .
FRONTIERS OF STRUCTURAL AND CIVIL ENGINEERING, 2019, 13 (06) :1363-1378
[5]   DP-GMM clustering-based ensemble learning prediction methodology for dam deformation considering spatiotemporal differentiation [J].
Chen, Wenlong ;
Wang, Xiaoling ;
Cai, Zhijian ;
Liu, ChangXin ;
Zhu, YuShan ;
Lin, Weiwei .
KNOWLEDGE-BASED SYSTEMS, 2021, 222
[6]  
[崔粟晋 Cui Sujin], 2018, [仪器仪表学报, Chinese Journal of Scientific Instrument], V39, P147
[7]   Maximum likelihood estimation of stochastic differential equations with random effects driven by fractional Brownian motion [J].
Dai, Min ;
Duan, Jinqiao ;
Liao, Junjun ;
Wang, Xiangjun .
APPLIED MATHEMATICS AND COMPUTATION, 2021, 397
[8]   Investigation of the long-term settlement of a cut-and-cover metro tunnel in a soft deposit [J].
Di, Honggui ;
Zhou, Shunhua ;
Xiao, Junhua ;
Gong, Quanmei ;
Luo, Zhe .
ENGINEERING GEOLOGY, 2016, 204 :33-40
[9]   On the optimality of the simple Bayesian classifier under zero-one loss [J].
Domingos, P ;
Pazzani, M .
MACHINE LEARNING, 1997, 29 (2-3) :103-130
[10]   Unsupervised learning of finite mixture models [J].
Figueiredo, MAT ;
Jain, AK .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2002, 24 (03) :381-396