摘要
针对盾构掘进过程中无法全面动态感知地质信息引发的难以精确预测地面沉降问题,提出了一种融入动态地层识别的地面沉降预测方法,该方法基于XGBoost动态地层识别模型,利用盾构施工参数对地层变动情况进行反向推演,明晰了地层变动时施工参数的变化规律;通过基于BP-SVR的地面沉降预测融合模型最终得到距开挖面不同距离处的地面沉降量与地层情况、掘进参数的内在关联关系,从而实现了复杂地层自适应的地面沉降量准确预测。在某地铁施工区间590环数据验证下,所提的地面沉降预测方法相比传统预测方法具有更高的预测精度。
The geological information cannot be fully dynamically perceived in the shield tunneling process,which makes it difficult to accurately predict the ground settlement. To solve this problem,one kind of dynamical stratum identification model using the adaptive complex stratum changes is proposed in this paper. This method is based on the extreme gradient boosting( XGBoost) using shield construction parameters to implement the inverse deduction of stratum changes. In this way,the changing rule of construction parameters can be clarified when the stratum changes. The fusion model of error back propagation algorithm( BP) and support vector regression( SVR) for ground settlement prediction is formulated to obtain the intrinsic relationship of the ground settlement at different distances from the initial excavation face,stratum conditions and parameters of shield driving. The proposed method is validated by the 590-ring data of a metro construction. Compared with the traditional method,it can achieve higher prediction accuracy.
引文
[1] FANG Y,HE C,NAZEM A,et al. Surface settlement prediction for EPB shield tunneling in sandy ground[J].KSCE Journal of Civil Engineering, 2017, 21(7):2908-2918.
[2] SHI CH H,CAO CH Y,LEI M F. An analysis of the ground deformation caused by shield tunnel construction combining an elastic half-space model and stochastic medium theory[J]. KSCE Journal of Civil Engineering,2017,21(5):1933-1944.
[3] KAVVADAS M, LITSAS D, VAZAIOS L, et al.Development of a 3D finite element model for shield EPB tunnelling[J]. Tunnelling and Underground Space Technology,2017,65:22-34.
[4] LIANG R ZH,WU W B,YU F,et al. Simplified method for evaluating shield tunnel deformation due to adjacent excavation[J]. Tunnelling and Underground Space Technology,2018,71:94-105.
[5] OCAK L,SEKER S E. Calculation of surface settlements caused by EPBM tunneling using artificial neural network, SVM, and Gaussian processes[J].Environmental Earth Sciences,2013,70(3):1263-1276.
[6]高攀科,谢永利.隧道软弱围岩的改进BP神经网络位移反分析[J].郑州大学学报(工学版),2013,34(1):23-26.GAO P K, XIE Y L. Displacement back analysis of tunnels in soft and weak rocks based on improved BP neural network method[J]. Journal of Zhengzhou University(Engineering Science),2013,34(1):23-26.
[7] XIONG X W,MENG ZH C. Forecasting method of the deformation of soft rock roadways based on time series'analysis and BP neural networks and its application[J].Journal of Transport Science Engineering,2012,28(2):53-60,100.
[8] YAO B ZH,YANG CH Y,YU B,et al. Applying support vector machines to predict tunnel surrounding rock displacement[J]. Applied Mechanics and Materials,2010,29:1717-1721.
[9] WANG F,GOU B C,ZHANG Q L,et al. Evaluation of ground settlement in response to shield penetration using numerical and statistical methods:a metro tunnel construction case[J]. Structure and Infrastructure Engineering,2016,12(9):1024-1037.
[10] MAHDEVARI S,HAGHIGHAT H S,TORABI S R. A dynamically approach based on SVM algorithm for prediction of tunnel convergence during excavation[J].Tunnelling and Underground Space Technology,2013,38:59-68.
[11] KOHESTANI V R,BAZARGANLARI M R,MARNANI J A. Prediction of maximum surface settlement caused by earth pressure balance shield tunneling using random forest[J]. Journal of AI and Data Mining,2017,5(1):127-135.
[12] 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,2016:785-794.
[13] ZHOU X W,XIA Y M,XUE J. Neural network strata identification based on tunneling parameters of shield machine[C]. International Conference on Intelligent Robotics and Applications,2009:392-401.
[14]熊鹏文,林虹,宋爱国,等.基于随机森林回归的手臂末端力的软测量方法[J].仪器仪表学报,2017,38(10):2400-2406.XIONG P W, LIN H, SONG AI G, et al. Soft measurement method of end-of-arm force based on random forest regression[J]. Chinese Journal of Scientific Instrument,2017,38(10):2400-2406.
[15] YAO D J,YANG J,ZHAN X J. Feature selection algorithm based on random forest[J]. Journal of Jilin University,2014,44(1):137-141.