Prediction of high-embankment settlement combining joint denoising technique and enhanced GWO-v-SVR method

Reliable long-term settlement prediction of a high embankment relates to mountain infrastructure safety.This study developed a novel hybrid model(NHM)that combines a joint denoising technique with an enhanced gray wolf optimizer(EGWO)-n-support vector regression(n-SVR)method.High-embankment field measurements were preprocessed using the joint denoising technique,which in-cludes complete ensemble empirical mode decomposition,singular value decomposition,and wavelet packet transform.Furthermore,high-embankment settlements were predicted using the EGWO-n-SVR method.In this method,the standard gray wolf optimizer(GWO)was improved to obtain the EGWO to better tune the n-SVR model hyperparameters.The proposed NHM was then tested in two case studies.Finally,the influences of the data division ratio and kernel function on the EGWO-n-SVR forecasting performance and prediction efficiency were investigated.The results indicate that the NHM suppresses noise and restores details in high-embankment field measurements.Simultaneously,the NHM out-performs other alternative prediction methods in prediction accuracy and robustness.This demonstrates that the proposed NHM is effective in predicting high-embankment settlements with noisy field mea-surements.Moreover,the appropriate data division ratio and kernel function for EGWO-n-SVR are 7:3 and radial basis function,respectively.

Deformation prediction model of concrete face rockfill dams based on an improved random forest model

The unique structure and complex deformation characteristics of concrete face rockfill dams(CFRDs)create safety monitoring challenges.This study developed an improved random forest(IRF)model for dam health monitoring modeling by replacing the decision tree in the random forest(RF)model with a novel M5'model tree algorithm.The factors affecting dam deformation were preliminarily selected using the statistical model,and the grey relational degree theory was utilized to reduce the dimensions of model input variables.Finally,a deformation prediction model of CFRDs was established using the IRF model.The ten-fold cross-validation method was used to quantitatively analyze the parameters affecting the IRF algorithm.The performance of the established model was verified using data from three specific measurement points on the Jishixia dam and compared with other dam deformation prediction models.At point ES-10,the performance evaluation indices of the IRF model were superior to those of the M5'model tree and RF models and the classical support vector regression(SVR)and back propagation(BP)neural network models,indicating the satisfactory performance of the IRF model.The IRF model also outperformed the SVR and BP models in settlement prediction at points ES2-8 and ES4-10,demonstrating its strong anti-interference and generalization capabilities.This study has developed a novel method for forecasting and analyzing dam settlements with practical significance.Moreover,the established IRF model can also provide guidance for modeling health monitoring of other structures.

Predicting and validating the load-settlement behavior of large-scale geosynthetic-reinforced soil abutments using hybrid intelligent modeling

Settlement prediction of geosynthetic-reinforced soil(GRS)abutments under service loading conditions is an arduous and challenging task for practicing geotechnical/civil engineers.Hence,in this paper,a novel hybrid artificial intelligence(AI)-based model was developed by the combination of artificial neural network(ANN)and Harris hawks’optimisation(HHO),that is,ANN-HHO,to predict the settlement of the GRS abutments.Five other robust intelligent models such as support vector regression(SVR),Gaussian process regression(GPR),relevance vector machine(RVM),sequential minimal optimisation regression(SMOR),and least-median square regression(LMSR)were constructed and compared to the ANN-HHO model.The predictive strength,relalibility and robustness of the model were evaluated based on rigorous statistical testing,ranking criteria,multi-criteria approach,uncertainity analysis and sensitivity analysis(SA).Moreover,the predictive veracity of the model was also substantiated against several large-scale independent experimental studies on GRS abutments reported in the scientific literature.The acquired findings demonstrated that the ANN-HHO model predicted the settlement of GRS abutments with reasonable accuracy and yielded superior performance in comparison to counterpart models.Therefore,it becomes one of predictive tools employed by geotechnical/civil engineers in preliminary decision-making when investigating the in-service performance of GRS abutments.Finally,the model has been converted into a simple mathematical formulation for easy hand calculations,and it is proved cost-effective and less time-consuming in comparison to experimental tests and numerical simulations.

A computational method for post-construction settlement of high-speed railway bridge pile foundation considering soil creep effect

Based on reasonable assumptions that simplified the calculational model,a simple and practical method was proposed to calculate the post-construction settlement of high-speed railway bridge pile foundation by using the Mesri creep model to describe the soil characteristics and the Mindlin-Geddes method considering pile diameter to calculate the vertical additional stress of pile bottom.A program named CPPS was designed for this method to calculate the post-construction settlement of a high-speed railway bridge pile foundation.The result indicates that the post-construction settlement in 100 years meets the requirements of the engineering specifications,and in the first two decades,the post-construction settlement is about 80% of its total settlement,while the settlement in the rest eighty years tends to be stable.Compared with the measured settlement after laying railway tracks,the calculational result is closed to that of the measured,and the results are conservative with a high computational accuracy.It is noted that the method can be used to calculate the post-construction settlement for the preliminary design of high-speed railway bridge pile foundation.

A simplified method for prediction of embankment settlement in clays

The prediction of embankment settlement is a critically important issue for the serviceability of subgrade projects,especially the post-construction settlement.A number of methods have been proposed to predict embankment settlement;however,all of these methods are based on a parameter,i.e.the initial time point.The difference of the initial time point determined by different designers can de?nitely induce errors in prediction of embankment settlement.This paper proposed a concept named"potential settlement"and a simpli?ed method based on the in situ data.The key parameter"b"in the proposed method was veri?ed using theoretical method and?eld data.Finally,an example was used to demonstrate the advantages of the proposed method by comparing with other methods and the observation data.

Settlement Prediction of Dredger Fill with the Optimal Combination Model

Post-construction settlement has gained increasing attention because it frequently causes engineering problems. A combined model is a commonly used prediction model that overcomes the difficulty of a single model( i. e., cannot reflect various regulations of settlement at some stages or the entire process). In this study,the correlation coefficient,maximum error values,and other values were obtained according to the fitting and predicted results of a single model. The coefficient of variation was then introduced to determine the weight of each model forming the combination. The proposed model was used to fit and predict for settlement and overcome the issue of utilizing a single model while determining the weight. The fitting predictive effect was also analyzed using the settlement fitting precision results. The fitting precision of optimizing the combination model is high. The predicted data of the post-construction settlement are closer to the calculated value of the settlement monitoring data. Moreover,the proposed model has good practicability,does not require the interval data of settlement,and restricts the model number. Thus,this model can be applied in the engineering field.

Settlement Prediction for Buildings Surrounding Foundation Pits Based on a Stationary Auto-regression Model

To ensure the safety of buildings surrounding foundation pits, a study was made on a settlement monitoring and trend prediction method. A statistical testing method for analyzing the stability of a settlement monitoring datum has been discussed. According to a comprehensive survey, data of 16 stages at operating control point, were verified by a standard t test to determine the stability of the operating control point. A stationary auto-regression model, AR(p), used for the observation point settlement prediction has been investigated. Given the 16 stages of the settlement data at an observation point, the applicability of this model was analyzed. Settlement of last four stages was predicted using the stationary auto-regression model AR (1); the maximum difference between predicted and measured values was 0.6 mm, indicating good prediction results of the model. Hence, this model can be applied to settlement predictions for buildings surrounding foundation pits.

Settlement prediction model of slurry suspension based on sedimentation rate attenuation

This paper introduces a slurry suspension settlement prediction model for cohesive sediment in a still water environment. With no sediment input and a still water environment condition, control forces between settling particles are significantly different in the process of sedimentation rate attenuation, and the settlement process includes the free sedimentation stage, the log-linear attenuation stage, and the stable consolidation stage according to sedimentation rate attenuation. Settlement equations for sedimentation height and time were established based on sedimentation rate attenuation properties of different sedimentation stages. Finally, a slurry suspension settlement prediction model based on slurry parameters was set up with a foundation being that the model parameters were determined by the basic parameters of slurry. The results of the settlement prediction model show good agreement with those of the settlement column experiment and reflect the main characteristics of cohesive sediment. The model can be applied to the prediction of cohesive soil settlement in still water environments.

Shield Excavation Analysis: Ground Settlement & Mechanical Responses in Complex Strata

This study delves into the effects of shield tunneling in complex coastal strata, focusing on how this constructionmethod impacts surface settlement, the mechanical properties of adjacent rock, and the deformation of tunnelsegments. It investigates the impact of shield construction on surface settlement, mechanical characteristics ofnearby rock, and segment deformation in complex coastal strata susceptible to construction disturbances. Utilizingthe Fuzhou Binhai express line as a case study, we developed a comprehensive numerical model using theABAQUS finite element software. The model incorporates factors such as face force, grouting pressure, jack force,and cutterhead torque. Its accuracy is validated against field monitoring data from engineering projects. Simulationswere conducted to analyze ground settlement and mechanical changes in adjacent rock and segments acrossfive soil layers. The results indicate that disturbances are most significant near the excavation zone of the shieldmachine, with a prominent settlement trough forming and stabilizing around 2.0–3.0 D from the excavation. Theexcavation face compresses the soil, inducing lateral expansion. As grouting pressure decreases, the segmentexperiences upward buoyancy. In mixed strata, softer layers witness increased cutting, intensifying disturbancesbut reducing segment floatation. These findings offer valuable insights for predicting settlements, ensuring segmentand rock safety, and optimizing tunneling parameters.

Analysis and Prediction of Foundation Settlement of High-Rise Buildings under Complex Geological Conditions

Based on an example of a project in Tangshan, the high-rise buildings are built in karst area and mined out affected area which is treated by high pressure grouting, and foundation is adopted the form of pile raft foundation. By long-term measured settlement of high-rise buildings, It is found that foundation settlement is linear increase with the increase of load before the building is roof-sealed, and the settlement increases slowly after the building is roof-sealed, and the curve tends to converge, and the foundation consolidation is completed. The settlement of the foundation is about 80% - 84% of the total settlement before the building is roof-sealed.Three layer BP neural network model is used to predict the settlement in the karst area and mined affected area.Compared with the measured data, the relative difference of the prediction is 0.91% - 2.08% in the karst area, and is 0.95% - 2.11% in mined affected area. The prediction results of high precision can meet the engineering requirements.

基于InSAR-COMSOL的露天矿边坡稳定性分析及形变预测

露天矿地表形变特征的快速、准确分析及形变趋势精准预测是推进矿山绿色安全生产的重要保障。针对当前形变监测技术存在的时空采样率低、成本高,预测模型参数难确定等问题,以东鞍山露天铁矿为工程背景,提出了一种融合短基线子集干涉测量(SBAS-InSAR)技术和COMSOL有限元模拟的边坡稳定性分析和形变预测一体化方法。首先,利用SBAS-InSAR技术处理2018年5月—2020年6月获取的62景Sentinel-1A升轨SAR数据,获取了该区域2 a内地表形变时间序列,分析了其形变时空演化特征。然后,采用COMSOL Multiphysics软件模拟外界强降雨影响下的典型沉降区域边坡稳定性状况,探讨了坡体损伤裂化规律及形变机理。基于此,利用粒子群算法(PSO)优化长短期时间记忆(LSTM)网络,搭建了形变时序预测最优模型,开展典型沉降区的形变时序预测,并引入平均绝对误差和均方根误差作为预测精度评价指标。结果表明:矿区西部沉降相对严重,年均沉降速率高达47.8 mm/a,形变速率与区域降雨量存在显著相关性。相较于传统形变预测模型,PSO-LSTM模型的2种误差至少降低了14%和36%,且能够有效反映采区地表形变波动趋势,为滑坡灾前预警提供了新思路。

基于迭代协同克里金反演的非均质地基固结沉降预测研究

目前地基固结沉降反演预测多是以土体均质或分层假设为前提,然而天然地基水文、力学参数具有空间变异性是客观事实。鉴于此,提出了一种基于迭代协同克里金的非均质地基土体参数反演方法,据此开展了利用沉降和超孔隙水压力观测数据反演非均质地基土参数的数值试验研究,并结合敏感度分析解释了不同类型观测数据对非均质地基参数反演解析度的影响机制。结果表明:此方法反演的参数场是最优无偏估计;同时采用沉降和超孔隙水压力观测数据反演刻画非均质地基比单独采用沉降或超孔压数据反演刻画的非均质地基解析度更高,用于地基固结沉降预测效果也更好;不同类型观测信息对不同参数反演刻画解析度高低与观测信息对参数敏感度数量级呈正相关关系。

高铁桥墩沉降的通用渐进分解长期预测网络模型

高铁桥墩不均匀沉降是导致轨道不平顺的潜在原因之一,准确预测桥墩沉降对于确保铁路建设和运营的可靠性和安全性具有重要意义。目前,常规时间序列领域的多数预测模型仅在预处理良好且没有缺失的数据集上进行测试,而在高铁桥墩沉降的真实场景中,沉降数据相较于其他领域存在观测频次少且不等时距,以及沉降规律复杂多变的问题,造成长期预测困难。为此,本文提出一种高铁桥墩沉降的通用渐进分解长期预测网络(GPDLPnet),摒弃传统的预处理思想,将预处理过程嵌入网络结构,在网络训练过程中实现渐进预处理。首先,GPDLPnet在每轮迭代中利用改进对角掩码自注意力模块分析沉降数据中的缺失模式。然后,通过改进完全自适应噪声集合经验模态分解模块将沉降数据分解并重构为高频、低频和趋势子分量,将子分量作为BiLSTM-RSA-Resnet预测模块的特征输入。最后,输出递归预测结果,从而实现高铁桥墩沉降的长期预测。结合实际工程数据,将数据划分为高频观测和低频观测两类典型的观测模式进行试验,在3~4个月的预测中GPDLPnet均表现出良好的预测性能,并在精度指标上优于其他7种模型。

囊袋式注浆对盾构下穿高速铁路路基沉降的控制效果

高铁路基的沉降变形是影响运营安全的重要因素,盾构下穿既有高铁线路施工可诱发高铁路基沉降变形。为有效控制高铁路基沉降,基于数值模拟探究了囊袋式注浆作为高铁路基沉降主动控制措施的有效性。结果表明:注浆囊袋对其周围土体的影响具有局部性,地层等效塑性应变随注浆体埋深的增加而增大,且塑性区厚度通常小于注浆囊袋膨胀厚度的3.0倍。囊袋的埋设深度和膨胀直径对路基抬升整治范围有影响,囊袋埋设越浅其膨胀后对路基抬升的影响效果越明显,且路基表层的隆起变形曲线符合高斯方程。提出了盾构下穿高铁路基时囊袋式注浆控制措施下路基沉降预测模型,可指导盾构下穿高铁路基的沉降控制。

基于协同降噪与IGWO-SVR的高填方路基沉降预测

高填方路基沉降影响山岭重丘区重载铁路运营安全。为克服实测沉降数据掺杂随机噪声、现有预测模型适用性差的不足,提出基于协同降噪算法与IGWO-SVR模型的沉降预测方法。运用互补集合经验模态分解法(CEEMD)与小波包变换法(WPT)对含噪沉降数据进行协同降噪处理;提出基于佳点集初始化均布、非线性收敛控制与自身历史最优记忆位置更新的改进灰狼优化(IGWO)算法,并结合支持向量回归模型(SVR),构建IGWO-SVR沉降预测模型。进一步地,利用大准铁路工点及现有文献研究成果,验证IGWO-SVR模型的优越性。结果表明:协同降噪法可有效消除原数据中噪声项的干扰波动;在小样本数据集上,IGWO-SVR模型较传统沉降预测模型与现有文献所述预测模型,具有更高的预测精度与稳定性。研究成果为重载铁路高填方路基沉降预测提供了新途径。

基于SSA-BP的深基坑地表变形预测研究

文中采用麻雀搜索算法优化BP神经网络,对深圳市某在建地铁车站深基坑周围地表沉降监测点进行变形预测。通过对基坑地表变形监测点DBC16-4的118期监测数据进行训练学习,并与粒子群算法优化BP神经网络、遗传算法优化BP神经网络和标准BP神经网络横向对比,验证了训练效果。结果表明,麻雀搜索算法对BP神经网络权重寻优速度较快,收敛精度更高,麻雀搜索算法优化BP神经网络模型预测平均相对误差仅为1.72%,拟合精度较其他算法更高,预测效果良好。

西南某机场跑道沉降预测模型

机场道面沉降,严重影响机场安全运行。准确预测跑道工后沉降,对机场的建设与运行极为重要。以西南某机场跑道沉降变形的观测数据为依据,分别用双曲线模型、对数模型、指数模型以及灰色预测模型,对跑道沉降进行预测和对比分析,解决了小样本数下曲线预测精度较低及灰色模型对非线性预测准确度差等问题,提高了预测的精度;同时通过BP神经网络对组合预测模型的残差进行修正,最大限度地提高模型预测的精度和效果,为地基沉降预测提供借鉴。

滨海软土地基二次堆载预压固结沉降研究

滨海软土往往工程性质较差,一次堆载预压通常达不到设计要求而需要进行二次堆载预压。本文通过现场原位试验和室内试验,对二次堆载预压2年后的地基软土开展物理力学性质研究,并将试验获得的土体参数用于规范法和数值模拟,对地基未来20年的沉降进行预测。结果表明,二次堆载预压2年后,部分软土层力学参数提升显著,但淤泥层力学参数未见明显改善,地基承载力未达到设计要求,后续仍有较大的沉降变形。同时,对比规范法和研究开始前18个月沉降规律发现,经过二次堆载预压后的地基,数值模拟采用弹塑性模型能更准确地预测后续沉降,二次堆载预压20年后地基最大的沉降量可达1 m,位于12号钻孔位置处,其次是18号钻孔位置处,沉降量为0.9 m,10号钻孔位置处沉降量为0.8 m,并且沉降主要集中在淤泥层中。

西安湿陷性黄土地区狭长深基坑变形分析

为了探究西安地铁车站深基坑开挖过程中桩体侧移、地表沉降等时空演变规律,以西安地区某地铁车站深基坑为工程背景,同时收集了该地区2#、3#、4#线20个狭长基坑的实测数据,并对其进行统计分析。结果表明:地铁基坑围护结构最大侧移δhm=0.04%H~0.10%H(H为开挖深度),平均值为0.06%H,最大侧移位置深度为0.7H;地表最大沉降值δvm=0.036%H~0.116%H,主要影响区在1.4H范围以内;高斯函数模型可以预测西安地区的地表沉降,其影响范围为3.5H;在特定范围内,提高支护桩的刚度和插入比可以有效控制基坑变形。研究结果可为西安市其他地铁车站基坑支护结构的设计与施工提供借鉴。

SBAS-InSAR技术融合CNN-LSTM模型的矿区开采沉陷监测与预测

针对传统矿区开采沉陷监测方法耗费人力财力和预测预警模型较少的问题,研究提出一种基于短基线集合成孔径雷达干涉测量(Small Baseline Subset-Interferometry Synthetic Aperture Radar,SBAS-InSAR)技术和卷积神经网络(Convolutional Neural Networks,CNN)与长短期记忆网络(Long Short-Term Memory,LSTM)相结合的矿区开采沉陷监测预测方法。首先,利用SBAS-InSAR技术对建新煤矿进行矿区开采沉陷监测,获取了该矿区的年平均沉降速率和累计沉降值。用GNSS监测数据与SBAS-InSAR结果进行对比验证,其拟合效果较好。其次,在此基础上利用CNN-LSTM模型预测后6期沉降数据,其结果与CNN和LSTM预测结果进行对比。研究显示,CNN-LSTM模型的平均绝对误差(S_(MAE))和均方根误差(S_(RMSE))比单一的CNN和LSTM分别至少降低了44.8%和40.6%,其决定系数均高于98%。最后,进一步预测前6期和中6期沉降数据,验证了CNN-LSTM预测模型在时间上的一致性。因此,SBAS-InSAR融合CNN-LSTM模型在类似矿山开采沉陷监测和预测中有较好的应用前景。