Settlement Prediction Methods Research Articles

A multi-fidelity deep operator network (DeepONet) for fusing simulation and monitoring data: Application to real-time settlement prediction during tunnel construction

Ground settlement prediction during mechanized tunneling is of paramount importance and remains a challenging research topic. Typically, two paradigms are existing: a physics-driven approach utilizing numerical simulation models for prediction, and a data-driven approach employing machine learning techniques to learn mappings between influencing factors and the settlement. To integrate the advantages of both approaches and to assimilate the data from different sources, we propose a multi-fidelity deep operator network (DeepONet) framework, leveraging the recently developed operator learning methods. The presented framework comprises of two components: a low-fidelity subnet that captures the fundamental ground settlement patterns obtained from finite element simulations, and a high-fidelity subnet that learns the nonlinear correlation between numerical models and real engineering monitoring data. A pre-processing strategy for causality is adopted to consider the spatio-temporal characteristics of the settlement during tunnel excavation. The results show that the proposed method can effectively capture the physical information provided by the numerical simulations and accurately fit measured data (R2 around 0.9) as well. Notably, even when dealing with very limited noisy monitoring data (with a 50% error), the proposed model remains robust, achieving satisfactory results with R2>0.8. In comparison, the R2 score obtained by pure simulation-based prediction is only 0.2. The utilization of transfer learning significantly reduces the training time from 20 min to within 30 s, showcasing the potential of our method for real-time settlement prediction during tunnel construction.

Numerical simulation for vibration-induced settlement and permanent deformation accumulation in permafrost subgrades of the Qinghai-Tibet Railway

Train-induced vibrations critically influence permafrost subgrade deformation. This study used ABAQUS secondary development to establish a finite element model of vibration-induced settlement for permafrost subgrades in the Qinghai-Tibet Railway (QTR) based on a cumulative plastic strain model. A numerical simulation method for cumulative vibration-induced settlement prediction considering seasonality, vibration frequency, train types, and global warming was proposed. The scientificity of the simulation was verified by monitoring data. Then, the influences of embankment height, ice-rich permafrost thickness, and initial mean annual ground temperature (MAGT) of the site on cumulative vibration-induced settlement and permanent deformation accumulation in permafrost subgrades were analysed. The study further quantitatively evaluated cumulative dynamic and static deformation in the DK1136 section under various global warming conditions. The results indicate that cumulative vibration-induced settlement primarily occurs near the ice-rich permafrost layer and is significantly influenced by ground temperature. Permanent deformation accumulation increases with increasing embankment height, ice-rich permafrost thickness and initial MAGT of the site. Permanent deformation accumulation primarily results from thaw consolidation of the permafrost layer, with vibration-induced settlement contributing approximately 20 %. For permafrost regions, an optimal railway embankment height of 3–3.5 m and effective mitigation of settlement issues involve lowering the ground temperature and the embankment weight. These findings provide essential insights for subgrade challenges in permafrost regions.

Bayesian updating for ground surface settlements of shield tunneling

Accurate prediction of ground surface settlements induced by shield construction is of great significance for ensuring the safety of shield construction. This paper proposes a ground surface settlement prediction method for shield tunneling based on Bayesian updating. The sequential observation data during the advance of excavation is utilized to update the key soil parameters, leading to a more accurate settlement prediction for the subsequent excavation stages. Response surfaces are constructed to replace the finite element model as the forward models for higher computational efficiency. A tunnel excavation project in Hangzhou, China, is selected to illustrate the effectiveness of the proposed method. The shield excavation face passes through four soil layers, and two soil parameters (i.e., Young’s modulus and friction angle) of these soil layers are selected as random variables to be updated. The results show that the soil parameters can be effectively updated based on the observation data at multiple points and various excavation stages. The predictions of ground surface settlements are improved by using the updated soil parameters. The prediction accuracy of the proposed method increases as more stages of observation data are sequentially obtained and incorporated.

Batch Settling and Low-Pressure Consolidation Behaviors of Dredged Mud Slurry: Steady-State Evaluation and Mechanism Study

Since the exploration of the characteristics of dredged mud slurry during batch settlement and low-pressure consolidation (less than 100 kPa) is still insufficient, the determination of the optimal time to start the vacuum preloading method (VPM) on dredged-fill foundations is still empirically oriented (due to a lack of enough scientific basis). To further explore the characteristics of dredged mud slurry during batch settlement and low-pressure consolidation, samples from typical dredged-fill land projects were obtained and used to conduct batch sedimentation model experiments and low-pressure (less than 100 kPa) consolidation tests. The results of experiments and analyses showed the following: (1) the clay (d < 0.005 mm) content is a main factor affecting the batch settlement and consolidation characteristics of dredged mud slurry, which is not conducive to the consolidation effect of dredged-fill foundations. (2) For dredged mud slurry whose clay content is within 40% to 60%, the cumulative change rate of the average porosity ratio of 60% to 75% is suitable for evaluating the steady state of its batch sedimentation process, i.e., the optimal starting time of VPM. Finally, based on the experimental analyses, a settlement prediction method that considers both the batch sedimentation and the low-pressure consolidation processes was developed and validated.

Research on Subsidence Prediction Method of Water-Conducting Fracture Zone of Overlying Strata in Coal Mine Based on Grey Theory Model

The development height and settlement prediction of water-conducting fracture zones caused by coal seam mining play an important role in the stability of overburden aquifers and the safety of roadways. Based on the engineering geological data of the J60 borehole in the Daliuta Coal Mine and the mining conditions of the 2−2 coal seam, China, this study established a similar material test model of mining overburden. The deformation characteristics of overlying strata in the mining process of coal seam were studied by using distributed optical fiber sensing technology, and the development height of water flowing fractured zone was determined. According to the equidistant sampling characteristics of Brillouin optical time domain reflection technology and the principle of the grey theory model, the settlement prediction model of the water-conducting fracture zone was established. By analyzing and comparing the prediction accuracy of the GM (1, 1) model, grey progressive model, and metabolic model, the optimal method for settlement prediction of the water-conducting fracture zone was discussed. The results show that, for the metabolic model, with the increase in the number of test sets and the decrease in the number of prediction sets, the mean square error ratio c and the small error probability p of the prediction accuracy evaluation parameters display a downward trend. The accuracy is related to the sudden change in the settlement of the water-conducting fracture zone caused by the breaking of the key stratum of the overlying rock. The optimal time of test sets selected for the best settlement prediction model is 7~8, and that of prediction sets selected is 5~6. For the GM (1, 1) model and the grey progressive model, the prediction accuracy of mining overburden subsidence is grade 4, which is not suitable for settlement prediction of water-flowing fractured zones.

An improved creep correction factor for footings on sand using macro-element simulations

In many settlement prediction methods, the creep settlement of shallow foundations on sand is either disregarded or accounted for using time correction factors that lack a reliable basis. These existing settlement correction factors for creep have mainly been derived from a restricted number of long-term settlement measurements and do not consider the influence of factors such as the load level, rate of load application and properties of the soil below the foundation. In this study, a newly proposed one-dimensional elasto-viscoplastic macro-element was used to investigate the factors influencing the time-dependent behaviour of shallow foundations on sand. The safety factor of the foundation, the creep characteristics of the soils and the duration of load application were found to have important effects on the post-construction settlement development. The simulation results were used to develop an enhanced settlement correction factor for creep, which takes into account the identified factors. The improved settlement correction factor was found to be comparable to existing ones when the safety factor of the foundation is 3. The effectiveness of the proposed settlement correction factor is demonstrated using creep settlement measurements from one field footing test and two case histories.

Surface Subsidence Prediction Method for Backfill Mining in Shallow Coal Seams with Hard Roofs for Building Protection

The mining of shallow coal seams with hard roofs poses a threat to surface structures. In order to ensure the protection of these buildings, backfill mining is increasingly used in these types of coal seams. However, due to the lack of appropriate surface subsidence prediction methods, there are concerns about whether backfill mining can meet the requirements of building protection. In this study, through numerical simulation and physical experiments, the movement characteristics of the strata and surface were studied in the backfill mining of a shallow coal seam with a hard roof. Our results indicate that the backfilling ratio significantly influences strata movement and surface subsidence. As the backfilling ratio increases, the surface deformation in the backfill under the hard roof of the shallow coal seam transitions from discontinuous to continuous. When the backfilling ratio exceeds 60%, the deformation characteristics of the overburden and surface align with the probability integral method model. Consequently, a novel surface subsidence prediction method for backfill mining in shallow coal seams under hard roofs is proposed. This method was successfully applied at Yungang Mine, validating its effectiveness. These research findings have significant practical implications for the design of backfill mining in shallow coal seams under hard roofs.

Study on Ground Settlement Patterns and Prediction Methods in Super-Large-Diameter Shield Tunnels Constructed in Composite Strata

This study focuses on investigating the surface settlement characteristics induced by the construction of a super-large-diameter shield tunnel in composite strata. By utilizing a combination of field monitoring and numerical simulation analysis, the surface settlement patterns encountered during the construction process in horizontally distributed typical soil–rock composite strata were summarized based on the 16.03 m super-large-diameter shield tunnel project in the southerly extension of He’ping Avenue in Wuhan. In addition, the collected data were used to enhance the Peck empirical formula. The results of the study show the following: (1) Significant non-uniform settlement occurs along the tunneling direction when the shield machine passes through soil–rock composite strata. The range of non-uniform settlement is approximately 3.1 times the tunnel diameter (D) in soil sections and 1.9 times the tunnel diameter (D) in rock sections. (2) The impact of composite strata on the maximum settlement is greater than its effect on the settlement trough width, with a larger impact within the soil sections compared to the rock sections. (3) The Peck correction formula, which takes into account the distance between the monitoring cross-section and the composite interface, provides more accurate predictions than the original Peck empirical formula.

Prediction of ground subsidence by shield tunneling using ensemble learning

This study addresses a significant issue related to shield construction, namely the impact of shield construction parameters on ground subsidence. Shield tunnels, owing to their concealed construction, often lead to ground subsidence, causing severe disruptions to ground facilities, potential collapse, and consequent casualties and property loss. Most calculation methods for ground subsidence have a delay, making it difficult to predict ground subsidence in advance based on construction parameters. Therefore, this study collates over 1500 cases of shield construction in China and summarises the impact mechanisms of shield construction on ground subsidence through a detailed study of natural factors, engineering geology, types of structures, and types of construction parameters. Based on the influence law of the data, this study establishes three intelligent prediction methods to forecast ground subsidence. To select the hyperparameters in the models more effectively, a Bayesian optimisation algorithm was utilised. Through a comparative analysis of the models, a subsidence prediction method that is more in line with the construction characteristics and exhibits high accuracy was determined. The findings of this study serve as a valuable resource for predicting ground subsidence resulting from shield construction, enabling timely adjustments to construction parameters and the implementation of preventive measures to mitigate excessive subsidence.

Study on surface subsidence prediction method of shallow coal seam backfill-strip mining under the hard roof

Study on surface subsidence prediction method of shallow coal seam backfill-strip mining under the hard roof

Analysis of instantaneous surface settlement of tunnel construction in composite stratum based on semi-analytical method

It is important for shield tunneling safety to predict and control the instantaneous surface settlement. Particularly, the complex geological condition can make accurate prediction more difficult. To adapt to the stratum distribution, a semi-analytical method is established by introducing the finite layer method into tunnel mechanical analysis. Firstly, based on the elastic solution of the finite layer method, the horizontal flexibility coefficient of tunneling and the surface settlement are obtained by applying effective thrust to the excavation face. Secondly, two influencing factors are analyzed, including the penetration of shield tunneling and the Poisson ratio of geotechnical parameter. The relationship formula between the measured value and the theoretical value of the maximum settlement is derived through data fitting. Finally, the settlement prediction method of tunneling is proved to be practical, which provide a new ideal for the mechanical analysis of tunnels in composite strata.

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.

Analysis of instantaneous surface settlement during tunnel construction in composite stratum

It is important for shield tunnelling safety to predict and control the instantaneous surface settlement. Particularly, the complex geological condition can make accurate prediction more difficult. To adapt to the stratum distribution, a semi-analytical method is established by introducing the finite layer method into tunnel mechanical analysis. Firstly, based on the elastic solution of the finite layer method, the horizontal flexibility coefficient of tunnelling and the surface settlement are obtained by applying effective thrust to the excavation face. Secondly, two influencing factors are analyzed, including the penetration of shield tunnelling and the Poisson ratio of geotechnical parameter. The relationship formula between the measured value and the theoretical value of the maximum settlement is derived through data fitting. Finally, the settlement prediction method of tunnelling is proved to be practical, which provide a new ideal for the mechanical analysis of tunnels in composite strata.

Settlement Prediction Method of Extra-Large Diameter Tunnels in Soft Rock Strata

This research was undertaken to predict the result of vault settlement during the excavation of super-large-span tunnels in soft rock strata, which are prone to deformation and hard to predict aftermaths. Numerical simulation was applied to tackle with vault problems during excavation of super-large-span soft rock tunnels such as proneness to deformation and hard prediction on vault settlement. As a result, a model for continuous prediction of vault settlement as the tunnel face keeps advancing was proposed, with influencing factors such as excavation span and tunnel depth taken into consideration, and put forward the optimization of super-large-span variable-section tunnels construction scheme. The results show that the vault settlement becomes fast at the beginning of the excavation because its surrounding rocks are characterized by weakness, incompleteness, and poor stability. At the initial stage of excavation, the varying tunnel depth had a greater impact on vault settlement, indicating that the primary support has to be enhanced at the beginning of the excavation of a vault with weak surrounding rocks. As the excavation of pilot tunnels proceeds, the high-stress zone transfers to the deep part of the surrounding rocks. The tunnel vault settlement model is capable of rapidly predicting the vault settlement at locations other than the observation points. The final settlement amount is affected by the excavation span, the tunnel depth, and the basic mechanical parameters of surrounding rocks. The key to the construction of a super-large-span and variable cross-section tunnel lies in the cross-section varying parts where the stress is concentrated, thus requiring reinforcement and frequent monitoring. The research methods and analysis may provide basic data and technical means for the control of the vault settlement of large-span tunnels in soft rock strata.

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.

Numerical Investigation and Prediction of Side-By-Side Tunneling Effects on Buried Pipelines

With the fast development of underground space engineering, it is inevitable for buried pipelines to be crossed by twin tunnels. Previous studies mainly focused on the single-tunneling effects on pipelines. To emphasize the twin-tunneling effects on buried pipelines, we first examined the effectiveness of the ground settlement prediction method under twin-tunneling conditions. Then, the estimated ground settlement boundary condition was applied to the beam-on-spring finite element model. The numerical results show that with the decrease in tunnel depth and twin tunnel space, the values and positions of the maximum ground settlement and longitudinal pipe bending behavior both changed significantly. The biased distance of the maximum settlement position and the distance to the inflection point of the final ground settlement curve can be obtained by curve fitting. Based on that, a semi-empirical prediction method for the longitudinal pipe bending strain was proposed. The predicted values matched quite well with the numerical results, which can thus provide a quick and effective structural safety and integrity assessment approach for buried pipelines subjected to twin-tunneling conditions.

Land Subsidence Time Series Prediction Method Based on LSTM-AMSGD

Accurate prediction of geological subsidence is of great importance for geological hazard risk assessment. Various existing prediction models do not take into account the time correlation between geological subsidence, and the prediction effect lacks practical significance. In this paper, an LSTM-AMSGD-based land subsidence prediction method is proposed. Firstly, the high-precision time series inversion results of large-area land surface deformation are obtained by the small baseline interference technique with multiple principal image coherent targets. Secondly, a recurrent neural network (LSTM-AMSGD) is used as the network architecture. The final cumulative subsidence prediction error is within 0.3 mm, and the single-step prediction of more than 400,000 observation points can be completed in 126s. Therefore, the LSTM-AMSGD model in this paper is effective for the prediction of geological subsidence.

Prediction of Post-Construction Settlement of Road Embankment on Soft Soil Deposits

Organic soils are often considered problematic soils around the world due to several reasons. Excessive settlement is one of the main concerns when constructing infrastructure on soft grounds with organic soil deposits. Ground improvement is mainly carried out on the sub surfaces that lack the strength and stability to bear the structure to be constructed and undergo large settlement during operation. Different soft-ground treatment methods must be applied based on the soil properties to reduce the expected settlements during construction and operation periods. In this context, it is essential to know the behaviour of the subsurface after the ground improvement process. This study mainly investigates the accuracy of the settlement prediction methods during the post-construction stage of the Colombo-Katunayake Expressway Project in Sri Lanka. Settlement prediction was done for the Defect Liability Period using the hyperbolic method, the Mesri method and the Ladd method. A comparison of the predicted settlement with the measured field settlement was done to assess the accuracy of the settlement prediction methods. The comparison showed that the hyperbolic method was more accurate and convenient for predicting the settlement of the embankment. KEYWORDS: Soft ground treatment methods; Preloading; consolidation settlement; Asaoka method; hyperbolic method

ANN-Based Dynamic Prediction of Daily Ground Settlement of Foundation Pit Considering Time-Dependent Influence Factors

Accurately and dynamically predicting ground settlements during the construction of foundation pits is pivotal to the understanding of the potential risk of foundation pits and, therefore, enables constructors to take timely and effective actions to ensure the construction safety of foundation pits. Existing settlement prediction methods mainly focus on the prediction of the maximum ground settlements based on static influence factors, such as soil properties and the geometry of foundation pits. However, these methods are unable to be applied to the prediction of daily ground settlements in a direct way because daily ground settlements can be affected by many time-dependent influence factors, and an accurate prediction of daily ground settlements should take into consideration such factors. To address this problem, this paper proposes an artificial neural network-based daily ground settlement prediction method, where both static and time-dependent influence factors, as well as previous settlement monitoring data, are considered in the optimum artificial neural network. The proposed method is validated using data collected from a real cut-and-cover highway tunnel project in western Hangzhou, China. The results demonstrate that time-dependent influence factors and previous settlement monitoring data play vital roles in establishing an optimum artificial neural network for the accurate prediction of daily ground settlement.

Prediction of Coal Mining Subsidence Based on Machine Learning Probability Theory

Geological disasters such as subsidence caused by mining have been continuously affecting people’s production and life. Therefore, how to predict the occurrence of geological disasters such as mining subsidence is an urgent technical problem. The study of mining subsidence prediction can effectively guide the safe production of mining area, and it is of great practical significance. Probability theory is a discipline used to express uncertainty. It provides methods and axioms to quantify and deduce uncertainty, which allows us to reason when uncertainty exists. This paper mainly studies the prediction process of mining subsidence based on machine learning probability theory. In this paper, the mining subsidence problem is studied. The main research contents are as follows: through the research and analysis of the mining subsidence prediction method, the probability integral method is determined as the theoretical basis for the study. The mining parameters are obtained from the three-dimensional geological body model of the mining area, and the prediction parameters are calculated by the least square fitting. This paper makes a detailed plan for the overall design of mining subsidence prediction module, adopts the form of independent research and development and joint development with the existing software, designs five submodules according to the design objectives, principles, and functional needs of the module, and studies the application of mining subsidence prediction module. In this study, it is found that the predicted data of the maximum settlement value appear at the 23rd point, and the maximum value is 1567 mm, which is completely consistent with the change trend of the measured value. The settlement value is calculated from the edge position of the working face to the position where the chariot gradually increases, which conforms to the change law of surface movement and settlement.