Comparison of machine learning methods for ground settlement prediction with different tunneling datasets

This study integrates different machine learning(ML) methods and 5-fold cross-validation(CV) method to estimate the ground maximal surface settlement(MSS) induced by tunneling.We further investigate the applicability of artificial intelligent(AI) based prediction through a comparative study of two tunnelling datasets with different sizes and features.Four different ML approaches,including support vector machine(SVM),random forest(RF),back-propagation neural network(BPNN),and deep neural network(DNN),are utilized.Two techniques,i.e.particle swarm optimization(PSO) and grid search(GS)methods,are adopted for hyperparameter optimization.To assess the reliability and efficiency of the predictions,three performance evaluation indicators,including the mean absolute error(MAE),root mean square error(RMSE),and Pearson correlation coefficient(R),are calculated.Our results indicate that proposed models can accurately and efficiently predict the settlement,while the RF model outperforms the other three methods on both datasets.The difference in model performance on two datasets(Datasets A and B) reveals the importance of data quality and quantity.Sensitivity analysis indicates that Dataset A is more significantly affected by geological conditions,while geometric characteristics play a more dominant role on Dataset B.

Effectiveness of predicting tunneling-induced ground settlements using machine learning methods with small datasets

Prediction of tunneling-induced ground settlements is an essential task,particularly for tunneling in urban settings.Ground settlements should be limited within a tolerable threshold to avoid damages to aboveground structures.Machine learning(ML)methods are becoming popular in many fields,including tunneling and underground excavations,as a powerful learning and predicting technique.However,the available datasets collected from a tunneling project are usually small from the perspective of applying ML methods.Can ML algorithms effectively predict tunneling-induced ground settlements when the available datasets are small?In this study,seven ML methods are utilized to predict tunneling-induced ground settlement using 14 contributing factors measured before or during tunnel excavation.These methods include multiple linear regression(MLR),decision tree(DT),random forest(RF),gradient boosting(GB),support vector regression(SVR),back-propagation neural network(BPNN),and permutation importancebased BPNN(PI-BPNN)models.All methods except BPNN and PI-BPNN are shallow-structure ML methods.The effectiveness of these seven ML approaches on small datasets is evaluated using model accuracy and stability.The model accuracy is measured by the coefficient of determination(R2)of training and testing datasets,and the stability of a learning algorithm indicates robust predictive performance.Also,the quantile error(QE)criterion is introduced to assess model predictive performance considering underpredictions and overpredictions.Our study reveals that the RF algorithm outperforms all the other models with the highest model prediction accuracy(0.9)and stability(3.0210^(-27)).Deep-structure ML models do not perform well for small datasets with relatively low model accuracy(0.59)and stability(5.76).The PI-BPNN architecture is proposed and designed for small datasets,showing better performance than typical BPNN.Six important contributing factors of ground settlements are identified,including tunnel depth,the distance between tunnel face and surface monitoring points(DTM),weighted average soil compressibility modulus(ACM),grouting pressure,penetrating rate and thrust force.

Prediction of surface settlement caused by synchronous grouting during shield tunneling in coarse-grained soils:A combined FEM and machine learning approach

This paper presents a surrogate modeling approach for predicting ground surface settlement caused by synchronous grouting during shield tunneling process.The proposed method combines finite element simulations with machine learning algorithms and introduces an intelligent optimization algorithm to invert geological parameters and synchronous grouting variables,thereby predicting ground surface settlement without conducting numerous finite element analyses.Two surrogate models based on the random forest algorithm are established.The first is a parameter inversion surrogate model that combines an artificial fish swarm algorithm with random forest,taking into account the actual number and distribution of complex soil layers.The second model predicts surface settlement during synchronous grouting by employing actual cover-diameter ratio,inverted soil parameters,and grouting variables.To avoid changes to input parameters caused by the number of overlying soil layers,the dataset of this model is generated by the finite element model of the homogeneous soil layer.The surrogate modeling approach is validated by the case history of a large-diameter shield tunnel in Beijing,providing an alternative to numerical computation that can efficiently predict surface settlement with acceptable accuracy.

Calculation of maximum surface settlement induced by EPB shield tunnelling and introducing most effective parameter

This study aims to predict ground surface settlement due to shallow tunneling and introduce the most affecting parameters on this phenomenon.Based on data collected from Shanghai LRT Line 2 project undertaken by TBM-EPB method,this research has considered the tunnel's geometric,strength,and operational factors as the dependent variables.At first,multiple regression(MR) method was used to propose equations based on various parameters.The results indicated the dependency of surface settlement on many parameters so that the interactions among different parameters make it impossible to use MR method as it leads to equations of poor accuracy.As such,adaptive neuro-fuzzy inference system(ANFIS),was used to evaluate its capabilities in terms of predicting surface settlement.Among generated ANFIS models,the model with all input parameters considered produced the best prediction,so as its associated R^2 in the test phase was obtained to be 0.957.The equations and models in which operational factors were taken into consideration gave better prediction results indicating larger relative effect of such factors.For sensitivity analysis of ANFIS model,cosine amplitude method(CAM) was employed; among other dependent variables,fill factor of grouting(n) and grouting pressure(P) were identified as the most affecting parameters.

LS-SVM and Monte Carlo methods based reliability analysis for settlement of soft clayey foundation

A method which adopts the combination of least squares support vector machine（LS-SVM） and Monte Carlo（MC） simulation is used to calculate the foundation settlement reliability.When using LS-SVM,choosing the training dataset and the values for LS-SVM parameters is the key.In a representative sense,the orthogonal experimental design with four factors and five levels is used to choose the inputs of the training dataset,and the outputs are calculated by using fast Lagrangian analysis continua（FLAC）.The decimal ant colony algorithm（DACA） is also used to determine the parameters.Calculation results show that the values of the two parameters,and δ2 have great effect on the performance of LS-SVM.After the training of LS-SVM,the inputs are sampled according to the probabilistic distribution,and the outputs are predicted with the trained LS-SVM,thus the reliability analysis can be performed by the MC method.A program compiled by Matlab is employed to calculate its reliability.Results show that the method of combining LS-SVM and MC simulation is applicable to the reliability analysis of soft foundation settlement.

基于多域物理信息神经网络的复合地层隧道掘进地表沉降预测

复合地层中盾构掘进诱发地表沉降的准确预测是隧道工程安全建设与施工决策的关键问题。基于隧道施工诱发地层变形机制构建隧道收敛变形与掘进位置的联系,并将其耦合至深度神经网络(deep neural network,简称DNN)框架,建立了预测盾构掘进诱发地层变形的物理信息神经网络(physics-informed neural network,简称PINN)模型。针对隧道上覆多个地层的地质特征,提出了多域物理信息神经网络(multi-physics-informed neural network,简称MPINN)模型,实现了在统一的框架内对不同地层的物理信息分区域表达。结果表明:MPINN模型高度还原了有限差分法的计算结果,可以准确预测复合地层中隧道开挖诱发的地表沉降;由于融入了物理机制,MPINN模型对隧道施工诱发地表沉降的问题具有普适性,可应用于不同地质和几何条件下隧道诱发地表沉降的预测;基于工程实测数据,提出的MPINN模型准确预测了监测断面的地表沉降曲线,可为复合地层下盾构掘进过程中地表沉降的预测预警提供参考。

基于改进最小二乘支持向量机组合模型的深基坑沉降变形预测

为了提高深基坑沉降变形预测精度,及时为深基坑支护施工提供指导,提出一种改进最小二乘支持向量机组合模型;通过引入自适应噪声完备集合经验模态分解方法分解原始深基坑沉降变形数据,并结合粒子群优化算法和遗传算法对最小二乘支持向量机进行参数寻优,对分解的数据分别训练、预测后再叠加,得到最终预测结果;应用所提出模型对济南市某深基坑的累积沉降量进行预测,同时与其他模型对比,验证所提出模型的实用性和优越性。结果表明:所提出模型预测深基坑累积沉降量的平均相对误差为0.035%,均方误差为0.0809 mm^(2),均方根误差为0.2838 mm,所提出模型的准确性远优于其他模型的;自适应噪声完备集合经验模态分解方法的引入更有利于在深基坑沉降变形预测方面发挥最小二乘支持向量机的优势。

基于SSA-SVM的巷道顶板空顶沉降量预测模型

为解决煤矿深部井巷工程巷道掘进顶板空顶期沉降量的预测问题,引入人工智能的支持向量机(SVM)工具,结合麻雀搜索优化算法(SSA),提出基于SSA-SVM的巷道顶板空顶沉降量预测模型。以内蒙古长城五矿深部地下巷道掘进过程的顶板空顶期位移量数据作为样本集合,选择单轴抗压强度(UCS)、岩石完整性(RQD)、地应力、巷道宽跨比、空顶时间、人为采动6项影响因素,通过适用性、相关性和归类一致性评价对数据的综合影响权重进行归纳整理。将十折交叉验证的准确率作为适应度函数,对不同种群数量的SSA-SVM预测模型展开训练和测试,通过误差相关系数(RMSE、MAPE、R^(2))、ROC曲线、AUC±Std、运行时间以及标准偏差率η等5方面来选择种群数量最优参数模型,并将该模型应用于1902S回风巷进行巷道掘进顶板空顶期的沉降量预测,同巷道实际矿压监测数据进行比较。研究结果表明:当种群数量为90时,SSA-SVM模型预测性能较好,训练样本的RMSE为0.0165,MAPE为22.54%,R^(2)为0.8295;测试样本的RMSE为0.0156,MAPE为22.37%,R^(2)为0.8490;真实度AUC达到最大0.8467,离散度Std最小为0.0115;运行时间最短为8.7239 s;标准偏差率维持在0.12%。在1902S回风巷现场应用中,预测值与实际值没有出现较大偏差,维持在线性拟合y=0.90x和y=1.10x范围内,误差相关系数与AUC±Std均符合试验精度要求,该模型的预测效果能够对后续的支护设计及补强支护作业提供重要的指导。

Prediction of shield tunneling-induced ground settlement using machine learning techniques

Predicting the tunneling-induced maximum ground surface settlement is a complex problem since the settlement depends on plenty of intrinsic and extrinsic factors.This study investigates the efficiency and feasibility of six machine learning(ML)algorithms,namely,back-propagation neural network,wavelet neural network,general regression neural network(GRNN),extreme learning machine,support vector machine and random forest(RF),to predict tunneling?induced settlement.Field data sets including geological conditions,shield operational parameters,and tunnel geometry collected from four sections of tunnel with a total of 3.93 km are used to build models.Three indicators,mean absolute error,root mean absolute error,and coefficient of determination the(7?2)are used to demonstrate the performance of each computational model.The results indicated that ML algorithms have great potential to predict tunneling-induced settlement,compared with the traditional multivariate linear regression method.GRNN and RF algorithms show the best performance among six ML algorithms,which accurately recognize the evolution of tunneling-induced settlement.The correlation between the input variables and settlement is also investigated by Pearson correlation coefficient.

基于SSA-ELM算法的基坑地表沉降预测

针对传统的极限学习机算法(ELM)在进行深基坑的地表沉降预测时易陷入局部极小、网络结构中参数选取不准确及预测精度不佳等问题,提出了一种基于麻雀搜索算法(SSA)优化极限学习机算法的基坑地表沉降预测模型。根据麻雀搜索算法收敛速度快、寻优能力与稳定性较强等特点,对极限学习机算法中的连接权值与阈值进行优化,并将优化后的模型应用于基坑的地表沉降预测。将麻雀搜索算法优化后的极限学习机算法(SSA-ELM)与ELM、 GA-ELM、 PSO-ELM算法进行预测精度对比,结果表明:SSA-ELM算法的预测精度高于ELM、 GA-ELM、 PSO-ELM算法,且其稳定性更强,在基坑的地表沉降预测方面效果更好,实现了提高预测精度的目的,具有一定的可行性和实用性。

机器学习预测盾构掘进地表沉降的研究进展及展望

针对采用机器学习方法预测盾构掘进地表沉降的研究,围绕预测模型的输入参数、预测目标、算法选取和超参数智能优化4个方面的研究进展开展系统综述,总结出当前研究中亟需解决的关键问题,并展望该领域的未来发展方向。研究表明:1)结合隧道几何参数、地层参数和盾构操作参数等信息进行沉降预测是当前主流的研究方向;2)沉降预测前需根据预测目标选取合适的模型和输入参数;3)通过超参数智能算法优化模型参数以提升预测精度。然而,现阶段的研究仍面临着诸多挑战:1)预测模型普遍缺乏特征自主识别能力且易发生过拟合;2)对海量数据的挖掘与分析尚不深入;3)尚未构建基于多源异构数据集的强鲁棒性模型;4)对地表沉降发展过程的预测研究相对匮乏。最后,展望盾构隧道智能掘进领域中需重点攻克的难题。

双线盾构隧道开挖引起既有铁路路基沉降及盾构掘进参数研究:工程案例

为揭示盾构掘进参数对既有铁路路基沉降的影响规律,本文依托北京地铁16号线丰益桥南站至丰台站双线盾构隧道下穿既有铁路线路工程进行案例分析。将盾构掘进过程分为盾构穿越前、盾构穿越中和盾构穿越后三个阶段。实测数据表明,路基沉降在盾构穿越前逐渐增大,在盾构穿越过程中急剧增大,在盾构穿越后趋于稳定。将盾构管片及时封闭成环,施作补偿注浆、二次注浆,有利于控制路基沉降。此外,盾构掘进参数对控制路基沉降具有至关重要的作用。研究结果表明:盾构掘进速度越快引起的路基沉降越大,继而引起较大的土仓压力,并伴随刀盘扭矩和盾构总推力的骤减;由于盾构过程中出土量易于控制,因此其对路基沉降影响不大;然而,如果同步注浆量控制不当,将导致既有路基向上隆起。本研究为盾构开挖下穿多条既有铁路线路引起的路基变形控制以及盾构掘进参数设置提供参考和指导。

Machine learning-based prediction of soil compression modulus with application of ID settlement

The compression modulus(Es)is one of the most significant soil parameters that affects the compressive deformation of geotechnical systems,such as foundations.However,it is difficult and sometime costly to obtain this parameter in engineering practice.In this study,we aimed to develop a non-parametric ensemble artificial intelligence(AI)approach to calculate the Es of soft clay in contrast to the traditional regression models proposed in previous studies.A gradient boosted regression tree(GBRT)algorithm was used to discern the non-linear pattern between input variables and the target response,while a genetic algorithm(GA)was adopted for tuning the GBRT model's hyper-parameters.The model was tested through 10-fold cross validation.A dataset of 221 samples from 65 engineering survey reports from Shanghai infrastructure projects was constructed to evaluate the accuracy of the new model5 s predictions.The mean squared error and correlation coefficient of the optimum GBRT model applied to the testing set were 0.13 and 0.91,respectively,indicating that the proposed machine learning(ML)model has great potential to improve the prediction of Es for soft clay.A comparison of the performance of empirical formulas and the proposed ML method for predicting foundation settlement indicated the rationality of the proposed ML model and its applicability to the compressive deformation of geotechnical systems.This model,however,cannot be directly applied to the prediction of Es in other sites due to its site specificity.This problem can be solved by retraining the model using local data.This study provides a useful reference for future multi-parameter prediction of soil behavior.

基于Stacking集成学习的盾构掘进地表沉降预测方法

为提高盾构施工中地表最终沉降预测模型的准确性和泛化性,结合主成分分析(PCA)和多层堆叠集成算法(Multi-layer Stacking)提出PCA-Stacking盾构掘进地表沉降预测方法。该方法利用PCA算法对盾构掘进过程中产生的大量数据进行处理,以减少特征维度并提取关键信息;此外,通过多层Stacking算法将多个异质模型进行融合,在提高模型预测性能的同时避免子模型间的优化比选。依托上海市北横通道超大直径盾构隧道工程,对盾构工程中的多源数据进行处理,对比PCA处理前后Stacking模型的性能,并将PCA-Stacking模型与RF、XGBoost模型进行对比。研究结果表明:1)PCA处理前后,Stacking模型的R 2分别为0.792和0.831,PCA对Stacking模型性能有一定提高;2)超参数优化后,RF和XGBoost的R 2分别为0.748和0.612,其性能弱于未进行超参数优化的PCA-Stacking;3)PCA-Stacking模型对地表隆起、沉降变化高度都具有良好的预测能力;4)在盾构掘进地表沉降预测方面,异质子模型的PCA-Stacking算法优于同质子模型的集成算法。

基于粒子群优化极限学习机的隧道地表沉降预测

为了提高地表沉降预测的精度和速度,提出了一种改进的极限学习机模型用于预测地表沉降。引入粒子群算法优化极限学习机的权值和阈值,提高极限学习机的预测效果。以济南轨道交通4号线燕山立交桥站为例,进行模型实证分析,利用改进的极限学习机进行盾构隧道地表沉降预测,并与传统的极限学习机模型进行对比。经过粒子群算法改进的极限学习机模型MSE降低了22%,RMSE降低了28%,MAPE降低了5.3%,验证了经粒子群算法改进后的极限学习机具有较好的预测精度和预测速度。对改进的极限学习机进行了泛化能力实证,验证了该模型具有较好的泛化能力。

基于IAO-LSSVM模型的基坑周围建筑物沉降预测:以深圳华强南站地铁基坑为例

针对当前基坑开挖引发建筑物沉降预测模型存在精度不足、收敛速度慢、易陷入局部最优等缺点,提出了一种基于改进天鹰算法(improved aquila optimizer, IAO)优化最小二乘支持向量机(least squares support vector machine, LSSVM)的建筑物沉降预测模型。利用Tent混沌映射提高天鹰算法的种群多样性水平,再通过自适应权重强化算法的全阶段寻优能力;引入IAO算法优化LSSVM的正则化参数和核函数宽度,构建基于IAO-LSSVM的建筑物沉降预测模型,并将该预测模型在深圳华强南某地铁基坑工程中进行了验证。结果表明:该沉降预测模型相比于传统预测模型精度更高、收敛更快、跳出局部最优域的能力强;该模型预测值与实际沉降监测值吻合度较高,其误差在5%左右,更适合预测城市中地铁基坑开挖引起的周围建筑物沉降。

SVM时序模型预测基坑工程稳定性的应用

预测基坑开挖会引起的周边地表沉降及支护结构的竖向位移,文中依托青岛某地铁车站基坑工程,对现场监测数据进行预处理,采用SVM的时间序列预测模型对深基坑地表沉降及桩顶竖向位移进行预测,对预测结果进行处理分析并通过RMSE、MAE、MBE、R2来衡量模型的预测精度。结果表明,SVM模型在预测深基坑变形方面具有一定潜力,但仍需进一步改进和优化。

基于GA-SVM模型的软土路基沉降预测

为实现软土地质条件下公路路基的沉降预测,提出了一种基于遗传算法优化支持向量机的路基沉降预测模型。采用支持向量机算法构建了软土路基沉降预测的基本模型,用遗传算法对模型超参数进行了调优,以公路沉降观测点的监测数据为样本建立了GA-SVM的路基沉降预测模型。结果表明:遗传算法可以有效提高支持向量机对沉降数据的拟合精度;GA-SVM沉降预测模型对10个验证集样本的平均误差和均方根误差分别为0.001 5 mm、0.015 5 mm;未来10期观测点位的路基结构趋于稳定,稳定后的平均预测沉降量约为0.03 mm/d。

不均匀沉降灾害特征分析及变形预测研究

文中结合现场调查成果,分析了不均匀灾害的发育特征,再通过变形预测评价灾害发展趋势。分析结果表明,据现场调查,灾害区可划分为3个变形区,变形特征较为显著,均暂时处于欠稳定-基本稳定状态,若在极端降雨条件下,均存在失稳可能,危害程度大。同时,变形预测得到JC16~JC18的后续变形速率介于0.33~0.57 mm/期,具有较大的增加趋势,即其累计变形还会增加,需尽快开展其不均匀防治研究。

管带机经过煤矿采空区的设计要点

近年来采空区的沉降问题给管带机的设计布置和安全稳定运行带来极大的困扰。本文通过分析某管带机输送项目的失败原因并结合新建项目,着重介绍了管带机在经过煤矿采空区时沉降柱的设计要点。