Surface Subsidence Prediction Research Articles

A novel combined intelligent algorithm prediction model for the tunnel surface settlement

To ensure the safety and stability of the shield tunnel construction process, the ground settlement induced by the shield construction needs to be effectively predicted. In this paper, a prediction method combining empirical mode decomposition (EMD), chaotic adaptive sparrow search algorithm (CASSA), and extreme learning machine (ELM) is proposed. First, the EMD is used to decompose the settlement sequence into trend vectors and fluctuation vectors to fully extract the effective information of the sequence; Second, the sparrow search algorithm is improved by introducing Cubic chaotic mapping to initialize the population and adaptive factor to optimize the searcher’s position formula, and the chaotic adaptive sparrow search algorithm is proposed; Finally, the CASSA-ELM prediction model is constructed by using CASSA to find the optimal values of weights and thresholds in the extreme learning machine. The fluctuation components and trend components decomposed by EMD are predicted one by one, and the prediction results are superimposed and reconstructed to obtain the predicted final settlement. Taking a shield interval in Jiangsu, China as an example, the meta-heuristic algorithm-optimized ELM model improves the prediction accuracy by 10.70% compared with the traditional ELM model. The combined EMD-CASSA-ELM prediction model can greatly improve the accuracy and speed of surface settlement prediction, and provide a new means for safety monitoring in shield tunnel construction. Intelligent prediction methods can predict surface subsidence more automatically and quickly, becoming a new development trend.

Prediction of Surface Settlement in Shield-Tunneling Construction Process Using PCA-PSO-RVM Machine Learning

Surface settlement is one of the key engineering issues during shield construction process. In order to accurately predict surface settlement, this paper proposes a new machine learning method based on relevance vector machine (RVM), principal component analysis (PCA), and particle swarm optimization (PSO). Taking Beijing Metro Line 6 as a case study, the PCA-PSO-RVM model is used to make the prediction and compared with the prediction results of the RVM model using the same samples. In order to evaluate the reliability of the model, three evaluation indexes including mean relative error (MRE), root mean square error (RMSE), and Theil inequality coefficient (TIC) were calculated, and sensitivity analysis was carried out on them. The results show that the minimum relative error between PCA-PSO-RVM and the actual value is only 0.06%. The calculated MRE, RMSE, and TIC are 0.17%, 0.0714 mm, and 0.027%, respectively, which shows that PCA-PSO-RVM model has higher prediction accuracy, smaller deviations, and higher reliability compared with the three other models. Through sensitivity analysis, it is found that the weighted average internal friction angle (φ) has the most significant impact on the surface settlement, which should be focused on in relevant research.

Prediction of Mine Subsidence Based on InSAR Technology and the LSTM Algorithm: A Case Study of the Shigouyi Coalfield, Ningxia (China)

The accurate prediction of surface subsidence induced by coal mining is critical to safeguarding the environment and resources. However, the precision of current prediction models is often restricted by the lack of pertinent data or imprecise model parameters. To overcome these limitations, this study proposes an approach to predicting mine subsidence that leverages Interferometric Synthetic Aperture Radar (InSAR) technology and the long short-term memory network (LSTM). The proposed approach utilizes small baseline multiple-master high-coherent target (SBMHCT) interferometric synthetic aperture radar technology to monitor the mine surface and applies the long short-term memory (LSTM) algorithm to construct the prediction model. The Shigouyi coalfield in Ningxia Province, China was chosen as a study area, and time series ground subsidence data were obtained based on Sentinel-1A data from 9 March 2015 to 7 June 2016. To evaluate the proposed approach, the prediction accuracies of LSTM and Support Vector Regression (SVR) were compared. The results show that the proposed approach could accurately predict mine subsidence, with maximum absolute errors of less than 2 cm and maximum relative errors of less than 6%. The findings demonstrate that combining InSAR technology with the LSTM algorithm is an effective and robust approach for predicting mine subsidence.

Prediction and Application of Surface Settlement of Shallow Buried Tunnels Taking into Account Strata Slip Cracks

The empirical formula is one of the traditional methods used for predicting ground deformation settlement caused by tunnel excavation. Due to its rationality and simplicity, the Peck formula is widely used for predicting surface subsidence. However, due to its limitations, it is necessary to modify it when predicting surface settlement caused by tunnel excavation in different strata. In this paper, a correction formula for the width coefficient of a tunnel surface settlement slot is derived from the Peck formula by taking into account the theory of strata slip cracks. Values are calculated using the correction formula and compared with measured data to verify the effectiveness of the correction formula. The main conclusions are: (1) The position corresponding to the width of the settlement in the Peck curve is the point where the formation is most prone to slip cracking. (2) In the general shallow buried case, the settlement groove width coefficient K and the internal friction angle φ of the ground satisfy the formula K = 1/tan(45° + φ/2 + a) + b, and the values of parameters a and b reflect the average values of the geometric properties of the tunnel based on the measured data. (3) The prediction of the correction formula is consistent with the measured data, and thus the correction formula can be applied to problems related to the stability of shallow buried tunnels.

Predictions of ground surface settlement for shield tunnels in sandy cobble stratum based on stochastic medium theory and empirical formulas

This paper focuses on the prediction of ground surface settlement induced by shield tunnelling in sandy cobble stratum. Based on the stochastic medium theory, an analytical solution to predict the surface settlement is developed considering the difference between soil and tunnel volume loss. Then, the effects of tunnel geometries, influence angle and volume loss on the characteristics of surface settlement are discussed. Through back analysis, a total of 103 groups of field monitoring data of surface settlement induced by shield tunnelling in sandy cobble stratum are examined to investigate the statistical characteristics of the maximum settlement, settlement trough width and volume loss. An empirical prediction is presented based on the results of back analysis. Finally, the analytical solution and empirical expression are validated by the comparisons with the results of model tests and field monitoring. Results show that the soil at ground surface has an overall dilative response for most of the shield tunnelling in sandy cobble stratum. In addition, the developed analytical solution is applicable and reasonable for surface settlement prediction. Meanwhile, the proposed empirical formula also shows good performance in some cases, providing an approach or a reference for engineering designers to preliminarily evaluate the surface settlement.

Strata Movement Characteristics in Underground Coal Gasification (UCG) under Thermal Coupling and Surface Subsidence Prediction Methods

As a green, safe, and efficient method of coal development, underground coal gasification (UCG) technology has gradually moved from the experimental stage to the industrial production stage. This technology plays one of the key roles in the sustainable development of resources and energy. However, underground mining will inevitably lead to strata movement and surface subsidence, which will have certain impacts on the surface environment and buildings. Currently, limited research results on strata movement and surface subsidence under high-temperature environments hardly support the further development of the UCG technology. Hence, this study aims at the key problems of UCG strata movement and surface subsidence prediction. The study established a numerical model to analyze the effects of thermal stress and coal–rock burnt on strata movement and surface subsidence. Results show that coal–rock burnt caused by high temperature has greatly changed the characteristics of UCG strata movement and surface subsidence and is the main controlling factor for aggravating the strata movement and surface subsidence of UCG. The coordinated deformation calculation method of the UCG cavity roof-coal pillar-floor is formed. Moreover, the cooperative subsidence space is regarded as the mining space. A prediction model of surface subsidence based on continuous-discrete medium theory is also established using the probability integral method. The reliability of the predicted model is proved by comparing the measured value with the predicted value.

Real-time online prediction of surface settlement considering spatiotemporal characteristics during foundation excavation

The accurate prediction of surface settlement induced by foundation excavation is challenging owing to complex spatiotemporal characteristics. To address this challenge, a real-time online prediction model comprising input, offline, and online modules was proposed. Grey relation analysis was employed to extract effective spatial coupling variables to improve the quality of the data in the input module; a long short-term memory network was trained to capture temporal nonlinearity in the offline module; and a statistical process control cloud platform was embedded to realize online updating when predicting residual anomalies in the online module. The model was verified using a time series dataset from a metro foundation project and outperformed other existing models with high accuracy. Our results could help managers to control settlement in a timely manner to prevent disasters. Clarifying the spatial coupling scale to improve the quality of input data of the model is left for future work.

An innovative and simple approach for predicting tunnelling-induced ground movements semi-analytically

ABSTRACT A semi-analytical elastic solution for predicting tunnelling-induced ground movements in clayey media is presented in this study. This study modelled the non-uniform ground movements (or non-uniform ground loss) around the tunnel cavity using the Gaussian distribution function. A new approach is proposed to model the tunnel peripheral displacements other than the simplistic trigonometric functions. It is shown that by modelling the ground loss in an elliptical fashion, (i) better prediction of ground surface settlements is obtained compared to the circular ground loss in some cases, while (ii) in other cases, circular ground loss gives better predictions. This indicates that both these approaches should be used to predict the ground surface settlements. Further, the ground displacements observed in East-West Metro, Kolkata, are discussed as a case study. The semi-analytically obtained displacements give good conformity with the observed field measurements in East-West Metro. This solution is much simpler to follow and can be easily employed in a code compared to the complex variable method or airy stress function method.

IoT-assisted feature learning for surface settlement prediction caused by shield tunnelling

The surface settlement caused by shield tunnelling may lead to collapse disaster, threatening the safety of ground and underground structures. Therefore, the prediction of surface settlement has attracted much attention, but the problem has not been well solved. Based on the Internet of Things and data driven method, this paper constructs a data model to predict the surface settlement on the basis of fully considering the time–space relationship of surface settlement caused by shield tunnelling. Then, based on this model, the convolutional neural network is used to learn time series features, the attention mechanism is used to realize feature interaction between parameters, and the tensorized long-term and short-term memory network are used to complete feature fusion between rings. A tensorized long-term and short-term memory network based on convolution feature adaptive interaction (TLCFAI) is proposed. Taking the tunnelling process of 10303 rings in 13 shield tunnel sections in Changzhou, China as an example, TLCFAI is obviously better than the other 9 typical algorithms, and the prediction effect is good. The research shows that this paper provides a relatively complete method and technical means for the prediction of surface settlement caused by shield tunnelling from the construction of data model to feature learning algorithm.

Experimental research on the influence of different factors on the behaviour of broken coal and rock particles during compaction

Broken coal-rock masses are a major part of the goaf. The breaking of coal and rock particles in the compaction process affects various aspects including control of strata motion, prediction of surface subsidence, and backfill mining. Therefore, isotropic compaction experiments on broken coal-rock mass were carried out by utilising the loading part of the seepage test system for coal-rock mass to analyse influences of particle strength, particle size, mixed type, stress, and loading and unloading times on breakage of particles in the compaction process. The test results show that the crushing behaviour of coal and rock particles in the compaction process can be divided into three stages: the structural re-arrangement and crushing of particles under a low stress, particle breakage under moderate stress, and compression of particles under a high stress. The reduction rate of porosity decreases with the increase of particle strength and increase of loading and unloading times, increases with the increase of particle size, has nothing to do with two mix types of coal-rock mass after compaction. Under the same stress unloading conditions, the recovery amounts of particles from compression deformation were similar, which was not related to unloading times. Research results is significant to those analysing overlying strata motion, predicting surface subsidence, optimising the material ratio for backfill mining, etc.

Spatial-temporal fusion network for maximum ground surface settlement prediction during tunnel excavation

The maximum ground surface settlement prediction is a complex problem as the settlement depends on plenty of intrinsic and extrinsic factors. To obtain the approximate range of the settlement, a hybrid prediction dataset including the geological and construction parameters is built using spatial and temporal series according to the sampling methods. The settlement prediction task is transformed into a multi-modal and multi-variate series prediction task. Hence, a spatial-temporal fusion network (STF-Network) is proposed. The spatial-temporal fusion mechanism is firstly designed to establish the spatial-temporal fusion map, which makes spatial and temporal series interact earlier. Then, the 3D residual unit structure is designed to capture the features of temporal series and spatial-temporal fusion map, and two fully-connected layers are established to capture the spatial structural information. Finally, the final output is merged by the three components. The experimental results for STF-Network demonstrate the superiority over state-of-the-art methods.

Research on Ground Surface Settlement of Curved Pipe Jacking Based on Numerical Simulation

The construction disturbance caused by pipe jacking is an index that must be strictly controlled in the project. With the wide application of curved pipe jacking in urban underground construction, predicting its ground surface settlement characteristics has become an increasingly important research topic. Based on finite element numerical simulation, a three-dimensional model of curved pipe jacking was established to simulate the construction stage. Compared with the straight pipe jacking, the normal component of jacking force is set in the outer tunnel of the curved pipe jacking to simulate the extrusion of the outer soil caused by the corner of the pipe joint, and the surface settlement characteristics of the curved pipe jacking are explored by changing the pressure value. The research results show that the surface settlement of the curved pipe jacking conforms to the normal distribution as a whole. Compared with the linear pipe jacking, the surface settlement is not symmetrical about the design axis of the tunnel. With the increase of the pressure outside the tunnel, the maximum settlement value of the surface and the difference between the two sides of the axis increase. Compared with the Peck formula, the width of the settling tank of the curved pipe jacking is larger, the convergence rate outside the width of the settling tank is slower, and the settlement trend is more in line with the Verruijt formula. The calculation formula is modified by axis offset distance and ovalization coefficient and modified formula can better reflect the measured engineering data. The research results can provide guidance and reference for the prediction and control of surface settlement of curved pipe jacking.

Prediction of Surface Subsidence of Deep Foundation Pit Based on Wavelet Analysis

Predicting surface settlement in deep foundation pit engineering plays a central role in the safety of foundation pit construction. Recently, static or dynamic methods are usually applied to predict ground settlement in deep foundation pit projects. In this work, we propose a model combining wavelet noise reduction and radial basis neural network (XW-RBF) to reduce noise interference in monitoring data. The results show that the XW-RBF model predicts an average relative error of 0.77 and a root average square error of 0.13. The prediction performance is better than the original data prediction results with noise structure and has higher prediction accuracy. The noise data caused by the interference of construction and the surrounding environment in the original data can be removed via the wavelet noise reduction method, with the discreteness of the original data reducing by 30%. More importantly, our results show that the XW-RBF model can reflect the law of data change to predict the future data trend with high credibility. The findings of this study indicate that the XW-RBF model could optimize the deep foundation pit settlement prediction model for high accuracy during the prediction, which inspires the potential application in deep foundation pit engineering.

Urban surface deformation monitoring and prediction by integrating SBAS-InSAR and Elman neural network

The existing prediction methods have complex model application, high requirements for data parameters, and are limited to the prediction of a single observation point. To address this problem, this paper proposes a deep learning-based surface subsidence prediction method. Taking Hefei City of China as the research area, the time-series surface deformation results of this area are obtained by using SBAS-InSAR, and then the SFLA intelligent algorithm and Elman neural network model are combined to predict the surface deformation of key urban areas, and the prediction results are compared and analyzed.The experimental results show that the prediction model proposed in this paper can not only accurately predict a single deformation point, but also predict regional land subsidence, and can be used for auxiliary decision-making of urban spatial planning, early warning of geological hazards and hazard mitigation.

Prediction of maximum ground surface settlement induced by shield tunneling using XGBoost algorithm with golden-sine seagull optimization

In order to avoid damage during shield tunnel construction to adjacent buildings on the ground, it is of paramount importance to precisely predict the Maximum Surface Settlement (MSS) deformation induced by shield tunneling under the surface. In this paper, a hybrid algorithm model incorporating the Extreme Gradient Boosting (XGBoost) with the Golden-sine Seagull Optimization Algorithm (GSOA) is proposed, namely the GSOA-XGBoost model. A total of 323 datasets including torque, penetration rate, thrust, cutterhead rotation speed, slurry pressure, grouting pressure, cover depth, and distance between cutting face and monitored section are taken as input parameters, and the corresponding measured MSS deformation is adopted as the output parameter. This dataset is employed to train the MSS prediction algorithm model. The analysis results indicate that the proposed GSOA-XGBoost hybrid algorithm model is much superior to other models in terms of accuracy, stability and computation time, and strong correlations are discovered between the predicted and measured settlements. Our model can predict the MSS deformation caused by shield tunnel construction with higher reliability, strong robustness and fault-tolerant capacity, and greatly reduces the engineering risk. Simultaneously, the consistency of the slurry pressure and grouting pressure values is calculated by the SOA-XGBoost and the grid search method, which demonstrates the feasibility and rationality of proposed hybrid algorithm model.

Prediction of Surface Subsidence Based on PSO-BP Neural Network

The traditional settlement monitoring has the problems of small monitoring range and low adaptability of settlement prediction model; Based on SBAS-InSAR technology and PSO-BP neural network algorithm, this paper constructs a PSO-BP settlement prediction model based on Sentinel-1A data. Take Jinan(E116°8’, N36°8’)the regional monitoring data is a data sample set. The algorithm proposed in this paper is compared with typical algorithms such as SVM. The results show that the MAE of 30 points predicted by this algorithm is 0.17, which is better than six typical algorithms such as SVM. This algorithm can be used as an effective means to provide early warning of surface subsidence.

Research Findings on the Application of the Arch Structure Model in Coal Mining, a Review

Studying the movement law and failure mechanism of overburden is important to underground safety production, aquifer protection, surface subsidence and ecological protection. A commonly used model, the arch structure model, for studying overburden movement is systematically reviewed in this paper. First, the arch structure in the mining field is divided into an unconsolidated layer arch, beam arch (hinged arch), and overburden arch according to arching medium. On this basis, the research progress and existing problems of these three arch structure models are discussed according to the research means, including theoretical modeling, numerical simulation, similar simulation, and field measurements. The application of the arch structure model focuses on the prediction and prevention of mining pressure and surface subsidence, and there are relatively few means to actively regulate overburden arch. Thus, three control methods of the arch structure in underground coal mining are proposed: the preset arch structure method before coal mining, process control arch methods during coal mining, and end reinforcement control arch methods after coal mining. Finally, the main research focus on the arch structure model in the future is discussed.

Predictive Models to Evaluate the Interaction Effect of Soil-Tunnel Interaction Parameters on Surface and Subsurface Settlement

Nowadays, the need for subway tunnels has increased considerably with urbanization and population growth in order to facilitate movements. In urban areas, subway tunnels are excavated in shallow depths under densely populated areas and soft ground. Its associated hazards include poor ground conditions and surface settlement induced by tunneling. Various sophisticated variables influence the settlement of the ground surface caused by tunneling. The shield machine's operational parameters are critical due to the complexity of shield-soil interactions, tunnel geometry, and local geological parameters. Since all elements appear to have some effect on tunneling-induced settlement, none stand out as particularly significant; it might be challenging to identify the most important ones. This paper presents a new model of an artificial neural network (ANN) based on the partial dependency approach (PDA) to optimize the lack of explainability of ANN models and evaluate the sensitivity of the model response to tunneling parameters for the prediction of ground surface and subsurface settlement. For this purpose, 239 and 104 points for monitoring surface and subsurface settlement, respectively, were obtained from line Y, the west bond of Crossrail tunnels in London. The parameters of the ground surface, the trough, and the tunnel boring machine (TBM) were used to categorize the 12 potential input parameters that could impact the maximum settlement induced by tunneling. An ANN model and a standard statistical model of multiple linear regression (MLR) were also used to show the capabilities of the ANN model based on PDA in displaying the parameter's interaction impact. Performance indicators such as the correlation coefficient (R2), root mean square error (RMSE), and t-test were generated to measure the prediction performance of the described models. According to the results, geotechnical engineers in general practice should attend closely to index properties to reduce the geotechnical risks related to tunneling-induced ground settlement. The results revealed that the interaction of two parameters that have different effects on the target parameter could change the overall impact of the entire model. Remarkably, the interaction between tunneling parameters was observed more precisely in the subsurface zone than in the surface zone. The comparison results also indicated that the proposed PDA-ANN model is more reliable than the ANN and MLR models in presenting the parameter interaction impact. It can be further applied to establish multivariate models that consider multiple parameters in a single model, better capturing the correlation among different parameters, leading to more realistic demand and reliable ground settlement assessments. This study will benefit underground excavation projects; the experts could make recommendations on the criteria for settlement control and controlling the tunneling parameters based on predicted results. Doi: 10.28991/CEJ-2022-08-11-05 Full Text: PDF

Time series monitoring and prediction of coal mining subsidence based on multitemporal InSAR technology and GSM-HW model

The surface subsidence caused by coal mining will cause serious environmental problems, and an effective monitoring and prediction system is indispensable. Aiming at this phenomenon, a mining subsidence monitoring and dynamic prediction model combining time series stacking differential interferometric synthetic aperture radar (TSS-DInSAR) technology, small baseline subset InSAR technology (SBAS-InSAR), and golden section method-Holt–Winters (GSM-HW) model was proposed. First, based on the nine scene images of Sentinel-1A satellite in the study area, the time series subsidence of 811 work-face in Guobei coal mine from April 5 to July 10, 2021, was obtained using TSS-DInSAR and SBAS-InSAR monitoring technologies, respectively. Then, the original training samples of the GSM-HW model were generated by combining the cumulative surface subsidence results monitored by TSS-DInSAR and SBAS-InSAR, and the monitoring and prediction of surface subsidence were realized using this model. The experimental results show that the application of TSS-DInSAR and SBAS-InSAR monitoring technology to the impact of surface mining in mining areas has certain reliability, and the GSM-HW prediction model can make up for the deficiency of a single HW model in parameter optimization. The maximum fitting accuracy and prediction accuracy of the model for the 10 monitoring pilot sites are 96.9% and 98.4%, respectively, which can provide a reference for the design of surface monitoring and prediction system in the mining area.

Numerical Study on Stratigraphic and Structural Deformation Patterns Considering Surface Load with Pile-Beam-Arch Method Construction

Due to soil disturbance during the construction of metro stations, the initial stress of the stratum is modified, leading to ground settlement within a particular range, fracturing the surrounding buildings and even causing significant ground deformation and building collapse. This paper employed the Pile-Beam-Arch method to assemble the Daguanying Station of Beijing Metro Line 7 as the engineering background. The numerical calculation method was used to study the regulations of ground settlement and structural deformation throughout the construction stage. Meanwhile, the effect of surface loading was taken into account and surface settlement control strategies were suggested. Finally, the Stochastic medium theory was used to predict surface settlement. It was evident from the study’s findings that the pilot tunnels excavation and the arches installation accounted for 67% and 23.1% of the total surface settlement, respectively, and produced the most surface settlement. Surface settlement can be significantly reduced by utilizing grouting reinforcement technology and the pilot tunnels excavation approach of “upper first, then lower and side first, then middle”. The structure was much less stressed during the pre-construction stage, with the maximum principal stress ranging from 1 to 5 MPa; after construction was finalized, the maximum principal stress reached 14.203 MPa, concentrating mostly in the middle column part, which was the consequence of the combined action of the upper load and the lower soil uplift. Additionally, there was a linear relationship between the surface load and ground settlement. The bottom slab and the middle column were situated where the structure’s most unfavorable components were concentrated. The conclusions of the surface settlement prediction demonstrated that there were discrepancies between the theoretical calculation and the simulated; thus, the prediction results were more conservative. The study results can serve as a reference for construction sites.