A spatiotemporal deep learning method for excavation-induced wall deflections

Data-driven approaches such as neural networks are increasingly used for deep excavations due to the growing amount of available monitoring data in practical projects.However,most neural network models only use the data from a single monitoring point and neglect the spatial relationships between multiple monitoring points.Besides,most models lack flexibility in providing predictions for multiple days after monitoring activity.This study proposes a sequence-to-sequence(seq2seq)two-dimensional(2D)convolutional long short-term memory neural network(S2SCL2D)for predicting the spatiotemporal wall deflections induced by deep excavations.The model utilizes the data from all monitoring points on the entire wall and extracts spatiotemporal features from data by combining the 2D convolutional layers and long short-term memory(LSTM)layers.The S2SCL2D model achieves a long-term prediction of wall deflections through a recursive seq2seq structure.The excavation depth,which has a significant impact on wall deflections,is also considered using a feature fusion method.An excavation project in Hangzhou,China,is used to illustrate the proposed model.The results demonstrate that the S2SCL2D model has superior prediction accuracy and robustness than that of the LSTM and S2SCL1D(one-dimensional)models.The prediction model demonstrates a strong generalizability when applied to an adjacent excavation.Based on the long-term prediction results,practitioners can plan and allocate resources in advance to address the potential engineering issues.

A modified back analysis method for deep excavation with multi-objective optimization procedure

Real-time prediction of excavation-induced displacement of retaining pile during the deep excavation process is crucial for construction safety.This paper proposes a modified back analysis method with multi-objective optimization procedure,which enables a real-time prediction of horizontal displacement of retaining pile during construction.As opposed to the traditional stage-by-stage back analysis,time series monitoring data till the current excavation stage are utilized to form a multi-objective function.Then,the multi-objective particle swarm optimization (MOPSO) algorithm is applied for parameter identification.The optimized model parameters are immediately adopted to predict the excavation-induced pile deformation in the continuous construction stages.To achieve efficient parameter optimization and real-time prediction of system behavior,the back propagation neural network (BPNN) is established to substitute the finite element model,which is further implemented together with MOPSO for automatic operation.The proposed approach is applied in the Taihu tunnel excavation project,where the effectiveness of the method is demonstrated via the comparisons with the site monitoring data.The method is reliable with a prediction accuracy of more than 90%.Moreover,different optimization algorithms,including non-dominated sorting genetic algorithm (NSGA-II),Pareto Envelope-based Selection Algorithm II (PESA-II) and MOPSO,are compared,and their influences on the prediction accuracy at different excavation stages are studied.The results show that MOPSO has the best performance for high dimensional optimization task.

Rockburst criterion and evaluation method for potential rockburst pit depth considering excavation damage effect

Excavation-induced disturbances in deep tunnels will lead to deterioration of rock properties and formation of excavation damaged zone(EDZ).This excavation damage effect may affect the potential rockburst pit depth.Taking two diversion tunnels of Jinping II hydropower station for example,the relationship between rockburst pit depth and excavation damage effect is first surveyed.The results indicate that the rockburst pit depth in tunnels with severe damage to rock masses is relatively large.Subsequently,the excavation-induced damage effect is characterized by disturbance factor D based on the Hoek-Brown criterion and wave velocity method.It is found that the EDZ could be further divided into a high-damage zone(HDZ)with D=1 and weak-damage zone(WDZ),and D decays from one to zero linearly.For this,a quantitative evaluation method for potential rockburst pit depth is established by presenting a three-element rockburst criterion considering rock strength,geostress and disturbance factor.The evaluation results obtained by this method match well with actual observations.In addition,the weakening of rock mass strength promotes the formation and expansion of potential rockburst pits.The potential rockburst pit depth is positively correlated with HDZ and WDZ depths,and the HDZ depth has a significant contribution to the potential rockburst pit depth.

Similar simulation device for unloading effect of deep roadway excavation and its application

The unloading effect of the excavation of deep roadways has been considerably studied, but most research methods have been limited to numerical simulations and field measurements. Only a few have adopted experimental methods for similar simulations. On the basis of the theory of mechanics,the testing system is designed considering initial geostress and dynamic unloading. The system includes an impact unloading gear and in-situ stress loading equipment, and a designed three-link structure and the impact hammer can effectively realize the dynamic excavation of roadways.Meanwhile, a cyclic excavation similar simulation experiment on a deep roadway is conducted in a laboratory. The testing system and the relevant monitoring facilities are utilized, and the unloading effect inside the surrounding rock under the cyclic dynamic excavation is studied. Results show that the cyclic dynamic excavation causes significant unloading only in the nearby rock mass, and the unloading indicators show nonlinear changes.Moreover, when the lateral pressure coefficient is 1.2,the damage is concentrated on both roadsides due to the excavation unloading. Meanwhile, the damage gradually decays as the span increases.

Prediction of Rock Burst with Deep Mining Excavation in Linglong Gold Mine

To predict rock burst in deep mining excavation in Linglong gold mine, systematical laboratory tests of mechanical properties of rock, in situ stress measurement and 3-D FEM analysis on energy distribution in rock mass surrounding deep mining rooms were carried out. According to various prediction criteria of rock burst, it is concluded that rock burst is liable to occur during deep mining excavation in the mine.

A case study on behaviors of composite soil nailed wall with bored piles in a deep excavation

A complete case of a deep excavation was explored. According to the practical working conditions, a 3D non-linear finite element procedure is used to simulate a deep excavation supported by the composite soil nailed wall with bored piles in soft soil. The modified cam clay model is employed as the constitutive relationship of the soil in the numerical simulation. Results from the numerical analysis are fitted well with the field data, which indicate that the research approach used is reliable. Based on the field data and numerical results of the deep excavation supported by four different patterns of the composite soil nailed wall, the significant corner effect is founded in the 3D deep excavation. If bored piles or soil anchors are considered in the composite soil nailed wall, they are beneficial to decreasing deformations and internal forces of bored piles, cement mixing piles, soil anchors, soil nailings and soil around the deep excavation. Besides, the effects due to bored piles are more significant than those deduced from soil anchors. All mentioned above prove that the composite soil nailed wall with bored piles is feasible in the deep excavation.

A post-peak dilatancy model for soft rock and its application in deep tunnel excavation

The dilation angle is the most commonly used parameter to study nonlinear post-peak dilatancy(PPD)behavior and simulate surrounding rock deformation;however,simplified or constant dilatancy models are often used in numerical calculations owing to their simple mathematical forms.This study developed a PPD model for rocks(rock masses)based on the Alejanoe-Alonso(A-A)dilatancy model.The developed model comprehensively reflects the influences of confining pressure(σ_(3))and plastic shear strain(γ^(p)),with the advantages of a simple mathematical form,while requiring fewer parameters and demonstrating a clear physical significance.The overall fitting accuracy of the PPD model for 11 different rocks was found to be higher than that of the A-A model,particularly for Witwatersrand quartzite and jointed granite.The applicability and reliability of the PPD model to jointed granites and different scaled Moura coals were also investigated,and the model was found to be more suitable for the soft and large-scale rocks,e.g.deep rock mass.The PPD model was also successfully applied in studying the mechanical response of a circular tunnel excavated in strain-softening rock mass,and the developed semi-analytical solution was compared and verified with existing analytical solutions.The sensitivities of the rock dilatancy to γ^(p) and σ_(3) showed significant spatial variabilities along the radial direction of the surrounding rock,and the dilation angle did not exhibit a monotonical increasing or decreasing law from the elasticeplastic boundary to the tunnel wall,thereby presenting the σ3-or γ^(p)-dominated differential effects of rock dilatancy.Tunnel deformation parabolically or exponentially increased with increasing in situ stress(buried depth).The developed PPD model is promising to conduct refined numerical and analytical analyses for deep tunneling,which produces extensive plastic deformation and exhibits significant nonlinear post-peak behavior.

Design adaptations in a large and deep urban excavation: Case study

In this paper, design, re-design, and performance of a long-standing very deep excavation, which was originally planned to depth of 38 m, are presented. Over-digging was not planned in the original design,thus the reassessment was performed. Two main topics were followed: deepening to increase the maximum depth of an existent excavation from 38 m to 42.5 m, and feasibility for upgrading a predesigned support system from temporary to permanent support system. The geological investigations in the project site illustrated a type of stiff and cemented coarse-grained alluvium. An observational approach with additional geotechnical investigations and in situ tests was applied. Back analyses of stability of an unsupported access ramp, as well as deformation monitoring of walls, were used in order to review geotechnical design parameters that represent the full-scale behavior of the ground. Additional nails and soldier piles together with building mat foundation were implemented as a complementary lateral support in the retaining system. From an engineering point of view, by assuming a corrosion rate of 0.065 mm/a for existent rebars, according to chemical and electrical resistivity tests, the long-term performance of the revised retaining system was verified by static and pseudo-dynamic ultimate limit state analyses. Performance monitoring during the construction shows that the measured deformation is in the lower limit of the prediction.

Deterministic and probabilistic analysis of great-depth braced excavations:A 32 m excavation case study in Paris

The Fort d’Issy-Vanves-Clamart(FIVC)braced excavation in France is analyzed to provide insights into the geotechnical serviceability assessment of excavations at great depth within deterministic and probabilistic frameworks.The FIVC excavation is excavated at 32 m below the ground surface in Parisian sedimentary basin and a plane-strain finite element analysis is implemented to examine the wall deflections and ground surface settlements.A stochastic finite element method based on the polynomial chaos Kriging metamodel(MSFEM)is then proposed for the probabilistic analyses.Comparisons with field measurements and former studies are carried out.Several academic cases are then conducted to investigate the great-depth excavation stability regarding the maximum horizontal wall deflection and maximum ground surface settlement.The results indicate that the proposed MSFEM is effective for probabilistic analyses and can provide useful insights for the excavation design and construction.A sensitivity analysis for seven considered random parameters is then implemented.The soil friction angle at the excavation bottom layer is the most significant one for design.The soil-wall interaction effects on the excavation stability are also given.

Analytical procedure for massive water-sealing barriers used in deep excavations considering seepage effect and its application

This paper presents an analytical procedure for massive water-sealing barriers(MWSBs)that are made of partially overlapped jet-grouting columns used for deep excavations,in which two crucial factors of the permeability and strength of jet-grouted materials are considered.Subsequently,a calculation example is analyzed and discussed.Results show that“tension failure”mechanism is a major concern for the structural failure during a design of MWSBs.The maximum allowable seepage discharge is a crucial index for the design of MWSBs,which has a significant influence on determining the design parameters of MWSBs.Compared with the design procedure for MWSBs that is proposed in this paper,the design parameters of MWSBs determined by the stability equilibrium and seepage stability equilibrium approaches are conservative due to the fact that it fails to consider the permeability or strength of jet-grouted materials that makes a contribution to the structural safety.Based on the proposed design method,the ranges of both the thickness and depth of MWSBs for a case history of subway excavation in Fuzhou,China were determined.Finally,field pumping test results showed that the water-tightness performance of MWSBs performed at site was quite well.

PREDICTION AND CONTROL OF ROCKBURST DURING DEEP EXCAVATION OF A GOLD MINE IN CHINA

The studies of prediction and control of rockburst are presented during deep excavation in a gold mine in China. Firstly,the stress-relief method is used to obtain a vast amount of data about initial geostress. Secondly,3D FEM analyses of large scale are performed to find out the law of geostress distribution at various excavation levels of the mining area. At the same time,as an equally important measure,six typical kinds of rock blocks are sampled for the experimental study of rockburst tendency. According to the synthesized results of the theoretical and testing results,the methods of brittleness coefficient,brittle index and stress,and so on,are adopted. Finally,the evaluation on the possibility of rockbursts is given that may take place at the deep mining area and some effective measures are put forward to prevent and control the rockburst.

Deformation Control of Deep Excavation Pit and Numerical Simulation with Finite Element Method

The authors firstly introduce deformation control of deep excavation pit indetail, and then put forward new conceptions such as: effective coefficient of excavation pit,effective area, ineffective area and critical line, and also put forward the referential criteria ofdeformation control. The System of Optimization Design with Deformation Control of Deep ExcavationPit and Numerical Simulation with Finite Element Method (SDCDEFEM) is also briefly introduced.Factors influencing deformation of excavation pit are analyzed by the system. The measured andsimulated data of maximum deformations (settlement, displacement and upheaval) and their positionsare analyzed and discussed. The statistic formula estimating maximum deformations and theirpositions was gained, and economical-effective measures of deformation control were brought forward.

Lessons learnt from a deep excavation for future application of the observational method

This paper draws lessons learnt from a comprehensive case study in overconsolidated clay. Apart from the introduction of the case study, including field measurements, the paper draws on the observations and a three-dimensional（3 D） numerical analysis to discuss the implications of observations in the application of the observational method（OM） in the context of the requirements of EUROCODE 7（EC7）.In particular, we focus on corner effects and time-dependent movements and provide initial guidance on how these could be considered. Additionally, we present the validation of a new set of parameters to check that it provides a satisfactory compliance with EC7 as a set of design parameters. All these findings and recommendations are particularly important for those who want to use the OM in similar future projects.

Construction Technology and Safety Risk Control Measures of Deep Foundation Pit Excavation

Deep foundation pit excavation is a basic and key step involved in modern building construction.In order to ensure the construction quality and safety of deep foundation pits,this paper takes a project as an example to analyze deep foundation pit excavation technology,including the nature of this construction project,the main technical measures in the construction of deep foundation pit,and the analysis of the safety risk prevention and control measures.The purpose of this analysis is to provide scientific reference for the construction quality and safety of deep foundation pits.

A rigid true triaxial apparatus for analyses of deformation and failure features of deep weak rock under excavation stress paths

The squeezing scenario in deep weak rock tunnels can hinder underground construction.However,due to the limitations of test technologies at hand,the real excavation stress path cannot be mimicked in the laboratory.Thus,the large deformation mechanism of deep weak rocks still remains unclear.For this,a true triaxial apparatus(TTA)to investigate the mechanical responses of deep weak rock under excavation stress paths in field and reveal the squeezing mechanism of deep tunnels is assembled and developed at Northeastern University,China.The apparatus can perform instantaneous unloading in s3 direction based on electromagnetism technology.In addition,uniform loading and deformation measurements can be carried out based on the proposed linked interlocking clamp and antifriction device,even if the sample has a strong dilatation deformation performance.Next,a bore trepanning is designed to capture noiseless acoustic emission(AE)signals for deep weak rock at a low threshold.Finally,two tests were are conducted using this instrument to preliminarily understand the failure and deformation features of deep weak rock based on fractured marble.The results show that the complete stressestrain curves of fractured marble have the characteristics of low strengths and large deformations,and the larger deformation and the more serious failure occur when the fractured marble enters the post-peak state after excavation.The results show that the developed apparatus is likely to be applicable for deep weak rock engineering.

Deep Foundation Pit Excavations Adjacent to Disconnected Piled Rafts: A Review on Risk Control Practice

Foundation pit excavation engineering is an old subject full of decision making. Yet, it still deserves further research due to the associated high failure cost and the complexity of the geological conditions and/or the surrounding existing infrastructure around it. This article overviews the risk control practice of foundation pit excavation projects in close proximity to existing disconnected piled raft. More focus is given to geotechnical aspects. The review begins with achievements to ensure excavation performance requirements, and follows to discuss the complex soil structure interaction involved among the fundamental components: the retaining wall, mat, piles, cushion, and the soil. After bringing consensus points to practicing engineers and decision makers, it then suggests possible future research directions.

Research on Robotized Advance Support and Supporting Time for Deep Fully Mechanized Excavation Roadway

To keep coal workers away from the hazardous area with frequent accidents such as the roof fall and rib spalling in an underground coalmine,we put forward the solution with robotized self-moving anchor-supporting unit.The existing research shows that the surrounding rock of the roadway has self-stability,and the early or late support is not conducive to the safe and reliable support of the roadway,so there is a problem of support opportunity.In order to study the supporting effect and the optimal supporting time of the above solution,we established the mechanical coupling model of surrounding rock and advance support,and investigated the surrounding rock deformation and advance support pressure distribution under different reserved roof subsidence by using the numerical simulation software FLAC3D.The results show that the deformation of surrounding rock increases and finally tends to a stable level with the increase of pre settlement of roadway roof,and when the pre settlement of roof is between 8-15 mm,the vertical pressure of the top beam of advance support reaches the minimum value,about 0.58 MPa.Based on the above research,we put forward the optimum supporting time in roadway excavation,and summarized the evaluation method based on the mechanical coupling model of surrounding rock-advance support.

Predicting excavation damage zone depths in brittle rocks

During the construction of an underground excavation, damage occurs in the surrounding rock mass due in large part to stress changes. While the predicted damage extent impacts profile selection and support design, the depth of damage is a critical aspect for the design of permeability sensitive excavations, such as a deep geological repository(DGR) for nuclear waste. Review of literature regarding the depth of excavation damage zones(EDZs) indicates three zones are common and typically related to stress induced damage. Based on past developments related to brittle damage prediction using continuum modelling, the depth of the EDZs has been examined numerically. One method to capture stress induced damage in conventional engineering software is the damage initiation and spalling limit(DISL) approach. The variability of depths predicted using the DISL approach has been evaluated and guidelines are suggested for determining the depth of the EDZs around circular excavations in brittle rock masses. Of the inputs evaluated, it was found that the tensile strength produces the greatest variation in the depth of the EDZs. The results were evaluated statistically to determine the best fit relation between the model inputs and the depth of the EDZs. The best correlation and least variation were found for the outer EDZ and the highly damaged zone(HDZ) showed the greatest variation. Predictive equations for different EDZs have been suggested and the maximum numerical EDZ depths, represented by the 68% prediction interval, agreed well with the empirical evidence. This suggests that the numerical limits can be used for preliminary depth prediction of the EDZs in brittle rock for circular excavations.

An intelligent procedure for updating deformation prediction of braced excavation in clay using gated recurrent unit neural networks

This paper aims to establish an intelligent procedure that combines the observational method with the existing deep learning technique for updating deformation of braced excavation in clay.The gated recurrent unit(GRU) neural network is adopted to formulate the forecast model and learn the potential rules in the field observations using the Nesterov-accelerated Adam(Nadam) algorithm.In the proposed procedure,the GRU-based forecast model is first trained based on the field data of previous and current stages.Then,the field data of the current stage are used as input to predict the deformation response of the next stage via the previously trained GRU-based forecast model.This updating process will loop up till the end of the excavation.This procedure has the advantage of directly predicting the deformation response of unexcavated stages based on the monitoring data.The proposed intelligent procedure is verified on two well-documented cases in terms of accuracy and reliability.The results indicate that both wall deflection and ground settlement are accurately predicted as the excavation proceeds.Furthermore,the advantages of the proposed intelligent procedure compared with the Bayesian/o ptimization updating are illustrated.

Collapse of a Deep Excavated Foundation Pit in the Soft Soils by 3-D FEM

In view of the collapse of a deep excavated foundation pit of the Xianghu subway underground station in Hangzhou of China,the main features of the accident are analyzed,and the induced factors of the accident are summarized. Then,a 3-D FEM analysis model is created to demonstrate the soil-support structures interaction system,and the effect of the main factors,such as the volume replacement ratio of the bottom soil reinforcing,the asymmetric ground overload,the embedded depth of the diaphragm wall,the shear strength of the bottom soils disturbed by the construction,and the excessive excavation of the bottom soil,are analyzed and compared. The results show that the ineffective original reinforcement plan for the bottom soft soil is the most prominent factor for the accident,and the disturbance effect of the deep excavation on the shear strength of the bottom soft soil is another significant factor for the accident. Meanwhile,if the reinforcement of the bottom soft soil is canceled,an appropriate extension of the diaphragm retaining walls to the under lying harder soil layer can also effectively prevent the collapse of the deep excavated foundation pit. In addition,the partly excessive excavation in the process has a great influence on the axial force of the most nearby horizontal support but few effect on the stability of the diaphragm wall. Thus,the excessive excavation of the bottom soils should not be the direct inducing factor for the accident. To the asymmetric ground overload,it should be the main factor inducing the different damage conditions of the diaphragm walls on different sides. According to the numerical modeling and actual engineering accident condition,the development process of the accident is also identified.