A method for analyzing influence of railway tunnel construction on urban groundwater

Abstract

The application discloses a kind of railway tunnel construction influence analysis methods of city underground water, belong to railway tunnel construction field, comprising the following steps: S1, multi-source data acquisition and pretreatment;S2, construct geology-hydrology-construction-remote sensing multidimensional feature vector, and extract groundwater disturbance index;S3, establish stress-seepage-heat conduction three-field coupling model;S4, based on three-field coupling model analysis three-field coupling effect, and output the comprehensive risk grade of tunnel construction influence on groundwater;S5, utilize GIS spatial analysis function fusion comprehensive risk grade, combined with real-time data realizes groundwater influence spatial visualization and hierarchical early warning;S6, real-time update the geological parameters of three-field coupling model, and search optimal construction parameter combination.The above-mentioned railway tunnel construction influence analysis methods of city underground water, significantly improve the scientificity and engineering practicability of railway tunnel construction influence analysis of city underground water.

Description

Technical Field

[0001] This invention relates to the field of railway tunnel construction technology, and in particular to a method for analyzing the impact of railway tunnel construction on urban groundwater. Background Technology

[0002] With the acceleration of urbanization, railway tunnel projects are increasingly penetrating densely populated urban areas, and the impact of construction disturbance on urban groundwater systems has become a key issue for project safety and environmental protection. Traditional analysis methods suffer from the following technical bottlenecks:

[0003] 1. Insufficient Accuracy of Multi-Source Data Fusion: Existing technologies mainly rely on single data sources (such as borehole exploration or InSAR (Synthetic Aperture Radar Interferometry) monitoring), making it difficult to comprehensively reflect the multidimensional impact of tunnel construction on groundwater. Traditional borehole sampling density is low (typically one borehole every 50-100m), making it difficult to capture the spatial variation of rock mass damage and permeability coefficients. Permeability coefficient estimation based on Standard Penetration Test (SPT) can have an error of ±30%, and it cannot reflect abrupt changes in permeability caused by blasting damage. Furthermore, existing InSAR displacement calculation methods (such as PS-InSAR) are affected by atmospheric delay and thermal noise, resulting in significant errors in extracting construction disturbance signals. For example, in a subway tunnel project, traditional filtering methods mistakenly identified atmospheric disturbances as construction settlement, leading to misjudgment of risks.

[0004] 2. Insufficient Intelligent Recognition of Tunnel Face Conditions: The degree of weathering (WD) and groundwater condition (GC) of the tunnel face are key factors affecting the seepage field. Early methods relied on manual geological logging, which was time-consuming and susceptible to subjective experience. Later, methods based on point cloud clustering or region growing were developed for structural surface recognition, but these require manual parameter setting and have poor robustness. For example, the DBSCAN-based clustering algorithm has a misclassification rate exceeding 15% in areas with dense fractures.

[0005] 3. Incomplete Multiphysics Coupling Modeling: Existing models do not fully consider the multiphysics interaction effects of construction disturbances. For example, the stress-seepage coupling is simplified: the elastoplastic model based on the Mohr-Coulomb criterion ignores the impact of damage on permeability. In a railway tunnel project, the permeability reduction in the blast damage zone (actually reduced to 1 / 5 of the original rock) was not considered, resulting in a seepage flow prediction error of over 50%. Missing Temperature Effects: Changes in pore water pressure caused by tunnel construction heat sources (such as heat generated by mechanical friction) are not included in the analysis. Theoretical studies show that a 5°C increase in temperature can increase seepage flow by 12%–18%, but existing models generally ignore this effect. Ignoring Dynamic Damage Evolution: The spatiotemporal evolution of the damage factor (D) is not coupled with the seepage field in real time, failing to reflect the dynamic changes in permeability caused by support lag.

[0006] 4. The existing risk assessment system has the following defects: (1) Static index system: Risk classification based on a single parameter (such as seepage threshold) cannot reflect the coupling effect of multiple factors. In a certain tunnel project, the seepage flow did not exceed the threshold, but stress concentration led to sudden water inrush, exposing the limitations of traditional methods. (2) Weak spatial analysis capability: The integration of GIS (Geographic Information System) and BIM (Building Information Model) is limited to static layer overlay and lacks dynamic risk field simulation. For example, in a certain subway project, the risk superposition effect of fault intersection area was not identified in time, resulting in the delay of emergency plan. (3) Insufficient real-time performance: The monitoring data and model update cycle is long (usually in days), and it is impossible to capture the instantaneous risk changes during the construction process. The seepage flow of a certain tunnel surged three times within 1 hour after blasting, but the existing system failed to issue a timely warning.

[0007] 5. Traditional construction parameter adjustment relies on experience and does not form a closed loop of "monitoring-analysis-optimization", which has the following defects: (1) Lack of parameter sensitivity analysis: The optimization of support pressure and excavation rate lacks quantitative basis. In a certain tunnel project, blindly increasing the support pressure led to a 20% increase in cost, but the risk was reduced by less than 10%. (2) Poor dynamic adaptability: Changes in geological conditions during construction (such as sudden faulting) cannot trigger automatic parameter adjustment. In a certain railway tunnel, the over-excavation increased by 30% due to the failure to adjust the blasting parameters in time, which aggravated the groundwater disturbance. (3) Insufficient data credibility: The risk of monitoring data tampering (such as false alarms due to sensor failure) affects optimization decisions.

[0008] In summary, the core shortcomings of existing technologies lie in insufficient fusion of multi-source data, incomplete physical process modeling, static risk assessment, and reliance on experience for construction optimization. These problems result in insufficient accuracy in analyzing the impact of railway tunnel construction on urban groundwater, making it difficult to meet the dual requirements of engineering safety and environmental protection. Summary of the Invention

[0009] The purpose of this invention is to provide a method for analyzing the impact of railway tunnel construction on urban groundwater. By using intelligent fusion of multimodal data, deep learning feature enhancement, coupled modeling of thermo-hydraulic-mechanical fields, integrated early warning of GIS-BIM-blockchain, and digital twin optimization, this method systematically solves the above-mentioned technical bottlenecks and significantly improves the scientific nature and engineering applicability of the analysis method.

[0010] To achieve the above objectives, this invention provides a method for analyzing the impact of railway tunnel construction on urban groundwater, comprising the following steps:

[0011] S1. Multi-source data acquisition and preprocessing to construct a multi-dimensional spatiotemporal dataset containing surface fissures, geological and hydrological data, and construction disturbances;

[0012] S2. Integrate the preprocessed multi-source data through a multi-dimensional feature fusion algorithm to construct a geological-hydrological-construction-remote sensing multi-dimensional feature vector, and use the improved RNPC-net model to identify the working face status and extract groundwater disturbance indicators.

[0013] S3. Based on the elastoplastic damage theory and seepage mechanics, a stress-seepage-heat conduction three-field coupling model is established, and the boundary conditions of the stress-seepage-heat conduction three-field coupling model are set based on the groundwater disturbance index.

[0014] S4. Analyze the three-field coupling effect based on the three-field coupling model, and output the comprehensive risk level of the impact of tunnel construction on groundwater based on the comprehensive risk assessment model;

[0015] S5. Utilize GIS spatial analysis functions to integrate comprehensive risk levels and combine real-time data to achieve spatial visualization and graded early warning of groundwater impacts;

[0016] S6. The geological parameters of the three-field coupled model are updated in real time using the extended Kalman filter algorithm. Combined with digital twin technology, a virtual mapping of the construction process is constructed, and the optimal combination of construction parameters is searched to form a monitoring-analysis-optimization closed-loop control.

[0017] Therefore, the beneficial effects of the above-mentioned method for analyzing the impact of railway tunnel construction on urban groundwater in this invention are as follows:

[0018] 1. Multi-source data acquisition and preprocessing: solves the problem of traditional single data source, improves data fusion accuracy, can capture the spatial variation of rock mass damage and permeability coefficient, and reduces the error in extracting construction disturbance signals;

[0019] 2. A multi-dimensional feature fusion algorithm and an improved RNPC-net model are used to identify the working face condition, and the probability distribution of the weathering level and groundwater condition of the working face is output, which improves the intelligence and accuracy of the working face condition identification and reduces the time consumption of manual recording and the influence of subjective experience.

[0020] 3. Based on the elastoplastic damage theory and seepage mechanics, a stress-seepage-heat conduction three-field coupling model is established, which considers the temperature effect of construction heat source, the spatiotemporal evolution of damage factors and the real-time coupling of seepage field, solves the problem of incomplete multi-physics coupling modeling in traditional models, and improves the prediction accuracy of seepage flow and other parameters.

[0021] 4. Construct a comprehensive risk assessment model, output a comprehensive risk level based on multiple risk indicators, establish a risk-measure mapping relationship, solve the problems of traditional static indicator system and weak spatial analysis capability, and reflect the coupling effect of multiple factors;

[0022] 5. Utilize GIS spatial analysis functions to integrate comprehensive risk levels, and combine BIM and Unity3D platforms to achieve spatial visualization and hierarchical early warning of groundwater impacts, thereby improving the timeliness of risk response and the ability to simulate dynamic risk fields;

[0023] 6. The extended Kalman filter algorithm is used to update the geological parameters of the model in real time. Combined with digital twin technology, a virtual mapping of the construction process is constructed and the optimal combination of construction parameters is searched to form a closed-loop control of monitoring, analysis and optimization. This solves the problem of traditional construction parameter adjustment relying on experience, realizes dynamic parameter optimization, improves construction efficiency and safety, and reduces costs.

[0024] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0025] Figure 1 This is a flowchart illustrating the method for analyzing the impact of railway tunnel construction on urban groundwater according to the present invention. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of the embodiments of the present invention and are not intended to limit the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of this application. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout.

[0027] It should be noted that the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, such as a process, method, system, product, or server that includes a series of steps or units, not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such process, method, product, or device.

[0028] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0029] like Figure 1 As shown, a method for analyzing the impact of railway tunnel construction on urban groundwater includes the following steps:

[0030] S1. Multi-source data acquisition and preprocessing to construct a multi-dimensional spatiotemporal dataset containing surface fissures, geological and hydrological data, and construction disturbances;

[0031] Step S1 specifically includes the following steps:

[0032] S11. Acquire multi-source data: Obtain C-band remote sensing data from Sentinel-1A / B satellites via EGMS to obtain surface fracture data; simultaneously acquire borehole data, geological survey reports, groundwater level monitoring data, permeability coefficient test results, and pore water pressure distribution data to form geological and hydrological data; and acquire construction process parameters and tunnel face images to form construction disturbance data.

[0033] In step S11, the borehole data is acquired as follows: boreholes are arranged every 50m-100m along the tunnel axis, and the borehole depth penetrates 10m-20m below the tunnel floor. Rock core samples are collected and lithological classification is performed to obtain lithological distribution data.

[0034] Simultaneously, the number of blows N for a penetration of 30 cm was obtained using a standard penetration test. SPT The effective internal friction angle of the rock mass was estimated by combining the DeMello empirical formula.

[0035]

[0036] Construction process parameters include TBM tunneling parameters and blasting parameters. TBM tunneling parameters include cutterhead torque M. t Propulsion speed v p and shield pressure P shield Blasting parameters include the charge amount Q per hole. b , center of explosion distance r b blasting time interval and ground vibration velocity v b .

[0037] S12. Multi-source data preprocessing:

[0038] For remote sensing data: First, based on the orbital geometry parameters of the Sentinel-1 satellite, the LOS displacement sequences of the ascending and descending orbit data are projected onto the vertical direction to eliminate radar incidence angle θ bias. Then, valid monitoring points are retained through coherence thresholding, and the corrected vertical displacement sequence d is output. vert :

[0039]

[0040] In the formula, d LOS This represents the original LOS displacement time series;

[0041] Then, effective monitoring points are screened using a coherence threshold, and principal component analysis-independent component analysis (PCA-ICA) is used to separate the construction disturbance component and the natural settlement component in the displacement signal, extracting the construction disturbance displacement sequence d. excav ;

[0042] For borehole data: particle size was tested using sieving and sedimentation methods to obtain clay content, and then the permeability coefficient K = K0·10 was initially estimated based on the clay content. -3 K0 represents the baseline permeability coefficient related to clay content. Finally, the initially estimated permeability coefficient K is calibrated through a water pressure test to obtain the anisotropic permeability coefficient tensor K for each layer. i The formula for calculating the permeability coefficient K is as follows:

[0043] Simultaneously, the degree of fracture development was analyzed based on borehole CT images, and damage factors were defined. L fracture and L core The lengths of the surface cracks and the core are represented respectively, and then ordinary kriging interpolation is used to generate a three-dimensional damage factor field D(x,y,z).

[0044] S2. Integrate the preprocessed multi-source data through a multi-dimensional feature fusion algorithm to construct a geological-hydrological-construction-remote sensing multi-dimensional feature vector, and use the improved RNPC-net model to identify the working face status and extract groundwater disturbance indicators.

[0045] Step S2 specifically includes the following steps:

[0046] S21. Construct a multi-dimensional feature vector integrating geology, hydrology, construction, and remote sensing:

[0047] S211, Based on the corrected vertical displacement sequence d excav Given the tunnel diameter R and burial depth z0, calculate the settlement characteristic parameters, including the volume loss rate V. L And the slot width d;

[0048] The volume loss rate V was calculated based on the Gaussian sedimentation model. L :

[0049]

[0050] In the formula, V s This indicates the volume of the settling tank, and ω(x) represents the vertical displacement distribution function of the surface settlement trough, and ω max ω represents the maximum surface subsidence. max =max(d excav ), l i Indicates the distance to the inflection point of the settling trough, where x represents the horizontal coordinate; A t This represents the cross-sectional area of ​​the tunnel, and R represents the tunnel diameter;

[0051] Calculate the slot width d using the following formula:

[0052]

[0053] In the formula, i represents the inflection point distance; z0 represents the tunnel depth;

[0054] S212. Constructing the Feature Vector: Integrating geological and hydrological data, construction data, remote sensing data, and surface fracture distribution data, we obtain the feature matrix F = [K]. i ,n,D,v p M t V L ,d,ω max ], where n represents the surface porosity;

[0055] S213. The min-max normalization method is used to map each eigenvalue in the feature matrix to the interval [0,1] to obtain the normalized feature matrix F. norm ;

[0056] S22. Identifying the working face: Constructing an improved RNPC-net model and utilizing preprocessed working face images, 3D coordinates, and feature matrix F norm Train the improved RNPC-net model until convergence, and output the weathering grade probability distribution P(WD) and the groundwater state probability distribution P(GC):

[0057] The improved RNPC-net model adopts a three-branch hybrid feature extraction module, which includes a two-dimensional image convolution branch with ResNet50 as the backbone, a three-dimensional point cloud processing branch, and a fully connected branch for construction parameters. It also integrates multi-source data input through an adaptive weight-assisted classifier.

[0058] The cross-entropy loss function is defined as follows:

[0059]

[0060] In the formula, : represents the loss value; y s P represents the label vector; s S represents the probability distribution; S represents the total number of categories; s represents the category index.

[0061] S23. Extract groundwater disturbance indicators, including the weathering composite index WI and the groundwater activity intensity index GI.

[0062] Among them, the weathering comprehensive index WI is calculated based on the weathering grade probability distribution P(WD):

[0063]

[0064] In the formula, w k P(WD) represents the weight; k) represents the predicted probability of the kth weathering level, where k = 1, 2, 3, 4 represent unweathered, slightly weathered, moderately weathered, and strongly weathered, respectively;

[0065] The groundwater state probability distribution P(GC) is mapped to a numerical index to construct the groundwater activity intensity index GI:

[0066] GI=4P(FW)+3P(DW)+2P(DP)+P(DR);

[0067] In the formula, P(FW), P(DW), P(DP) and P(DR) represent the probability of water gushing from the working face, the probability of water dripping from the working face, the probability of water dripping in a line from the working face, and the probability of the working face drying out, respectively.

[0068] S3. Based on the elastoplastic damage theory and seepage mechanics, a stress-seepage-heat conduction three-field coupling model is established, and the boundary conditions of the stress-seepage-heat conduction three-field coupling model are set based on the groundwater disturbance index.

[0069] Step S3 specifically includes the following steps:

[0070] S31. Elastic-plastic damage stress field modeling:

[0071] S311. Invert damage zone parameters, including the blast damage radius and the anisotropic material parameter matrix [E]. d ,v d The radius of the blast damage was estimated using the following empirical formula and calibrated in conjunction with the acoustic test results to determine the extent of the damage zone:

[0072]

[0073] In the formula, R d Indicates the geometric parameters of the damaged area; k b Indicates the geological correction factor;

[0074] Anisotropic material parameter matrix [E d ,v d The elastic modulus E of the damaged area in the figure d The calculation formula is as follows:

[0075] E d =E0(1-D);

[0076] In the formula, W0 represents the elastic modulus of the original rock;

[0077] Poisson's ratio v d The calculation formula is as follows:

[0078] v d =v0+0.1D;

[0079] In the formula, v0 represents the Poisson's ratio of the original rock;

[0080] S312, Radial effective stress σ' in the elastic zone er and tangential effective stress σ' eθ :

[0081]

[0082]

[0083] In the formula, P0 represents the original rock stress; r represents the tunnel inner wall stress; R i Indicates the inner radius of the tunnel;

[0084] Based on the Mohr-Coulomb criterion, the effective radial stress σ' in the plastic zone is derived. pr and tangential effective stress σ' pθ :

[0085]

[0086] In the formula, This indicates the cohesion in the plastic zone, and c p Indicates the cohesive force in the plastic zone; This represents the earth pressure coefficient in the plastic zone, and R p Indicates the radius of the plastic zone; This represents the friction angle within the plastic zone, and η represents the damage reduction factor;

[0087] S32. Construct a seepage equation considering temperature effects and set boundary conditions to obtain the pore water pressure distribution cloud map and seepage flow rate Q. The expression of the seepage equation is as follows:

[0088]

[0089] In the formula, v represents the seepage velocity vector; μ represents the dynamic viscosity of water; P w ρ represents pore water pressure; g represents gravitational acceleration; h represents hydraulic head; β represents the coefficient of thermal expansion; and T represents the temperature field distribution.

[0090] The boundary conditions are as follows: tunnel inner wall r = R i Pore ​​water pressure P w =P wi P wi Represents the water pressure inside the tunnel; far field r = R w Time P w =P w0 R w P represents the radius of influence of seepage. w0Indicates the initial pore water pressure;

[0091] The formula for calculating the seepage flow rate Q is as follows:

[0092]

[0093] In the formula, H represents the thickness of the aquifer.

[0094] S4. Analyze the three-field coupling effect based on the three-field coupling model, and output the comprehensive risk level of the impact of tunnel construction on groundwater based on the comprehensive risk assessment model;

[0095] Step S4 specifically includes the following steps:

[0096] S41. Calculation of total stress using coupled stress field and seepage field:

[0097] σ r =σ′ r +P w , σ θ =σ′ θ +P w ;

[0098] In the formula, σ r and σ θ These represent the total radial stress and the total tangential stress, respectively; σ' r and σ' θ Let σ' represent the radial stress and tangential stress of the stress field, respectively, and σ' r =σ' er +σ' pr , σ' θ =σ' eθ +=σ′ pθ ;

[0099] S42. Introduce a construction heat source, calculate the temperature distribution using the heat conduction equation, and correct the seepage parameters:

[0100]

[0101] In the formula, μ(T) represents the dynamic viscosity of water after temperature correction, and μ(T) = μ0exp(-k T (T-T0)), μ0 represents the dynamic viscosity of the reference water, k T The temperature coefficient is represented by T and T0, which represent the real-time temperature and the initial temperature, respectively.

[0102] S43. Set the risk indicators as water inrush risk, settlement risk, and compression risk, among which water inrush risk Settlement risk Squeeze risk Q th and d th Both are set thresholds, rqd Represents rock quality indicators; yields a single risk factor vector [RI] Q ,RI d ,SPI];

[0103] S44. Constructing the Comprehensive Risk Index (CRI):

[0104] CRI = ω Q RI Q +ω d RI d +ω SPI SPI;

[0105] In the formula, ω Q ω d and ω SPI Both represent weights, and ω Q +ω d +ω SPI =1;

[0106] S45. Based on the Comprehensive Risk Index (CRI), risks are classified into low risk, medium risk, and high risk, and a risk-measure mapping relationship is established.

[0107] S5. Utilize GIS spatial analysis functions to integrate comprehensive risk levels and combine real-time data to achieve spatial visualization and graded early warning of groundwater impacts;

[0108] Step S5 specifically includes the following steps:

[0109] S51. Convert geological parameters, three-field coupling model analysis results, and real-time monitoring data into ESRIShapefile format and project them onto the UTM coordinate system.

[0110] S52. Create thematic layers of geological layers, stress fields, and seepage fields in ArcGIS Pro;

[0111] S53. Use the inverse distance weighting method to interpolate discrete risk points to generate a continuous risk surface:

[0112]

[0113] In the formula, R(x,y,z) represents the continuous risk value at the three-dimensional spatial coordinates (x,y,z); d i Represents the spatial distance between the predicted point and the i-th discrete risk monitoring point; CRI i I represents the comprehensive risk index of the i-th discrete risk monitoring point; I represents the total number of discrete risk monitoring points.

[0114] S54. Based on the tunnel geometric parameters, construction process parameters, and the analysis results of the three-field coupling model, a BIM tunnel model is constructed, and the BIM tunnel model and comprehensive risk level data are imported into the Unity 3D platform to realize the dynamic correlation display between construction progress and risk evolution.

[0115] S55. Set graded early warning rules: Level 1 early warning conditions: Comprehensive risk index CRI≥0.7 and surface subsidence rate>1mm / day, triggering a red warning and automatically activating the emergency grouting plan;

[0116] Level II warning conditions: 0.4≤CRI<0.7 or settlement rate>0.5mm / day, triggering a yellow warning and prompting an increase in monitoring frequency.

[0117] S6. The geological parameters of the three-field coupled model are updated in real time using the extended Kalman filter algorithm. Combined with digital twin technology, a virtual mapping of the construction process is constructed, and the optimal combination of construction parameters is searched to form a monitoring-analysis-optimization closed-loop control.

[0118] Step S6 specifically includes the following steps:

[0119] S61. Use extended Kalman filtering to update the geological parameters of the three-field coupled model in real time, and output the updated damage factor D. new and permeability coefficient K new ;

[0120] Define the state vector x = [D, K] i ], observation vector Q represents the measured value of vertical displacement on the Earth's surface. meas To represent the measured seepage flow rate, the following state equation and observation equation are established:

[0121] x k+1 =f(x) k )+w k ;

[0122] z k =h(x k )+v k ;

[0123] In the formula, x k+1 and x k Let f(·) represent the predicted state vector value at time k+1 and the estimated state vector value at time k, respectively; let f(·) represent the state transition function; w k Indicates state noise; z k The vector at time k represents the observation vector; h(·) represents the observation function; v k Indicates observation noise;

[0124] The state estimate is calculated iteratively using the extended Kalman filter algorithm:

[0125]

[0126] In the formula, and Let K represent the optimal estimate of the state vector at time k and the predicted state at time k based on the estimate at time k-1, respectively; k Indicates Kalman gain, and P k|k-1 This represents the covariance matrix of the state prediction at time k based on the estimate at time k-1. The covariance matrix representing the observation noise;

[0127] S62, Update the damage factor D new and permeability coefficient K new Substitute the three-field coupling model described in step S3 into the recalculated stress field, seepage field, and risk index;

[0128] S63. Compare the recalibration results with the measured data, calculate the root mean square error to evaluate the accuracy of the three-field coupling model. If the root mean square error is >5%, return to step S61 to perform the second calibration process.

[0129] S64. Optimize construction parameters;

[0130] S641. Constructing a digital twin model: Develop a digital twin of tunnel construction based on the Unity platform, integrate BIM tunnel model and real-time monitoring data, and realize a 1:1 virtual mapping of the construction process;

[0131] S642. Employing a near-end strategy optimization algorithm, the optimal parameter combination is searched with the objective of minimizing the Comprehensive Risk Index (CRI). and These represent the optimal support pressure and the optimal excavation rate, respectively.

[0132] Simulation Experiment

[0133] Experimental conditions: Software platform: COMSOL Multiphysics 6.0, coupled seepage field-stress field-temperature field module. Geological model: Strata: Divided into 3 layers, simulating typical urban loose sedimentary layers. Groundwater: Initial water level depth 5m, porosity 0.25, permeability coefficient decreases with depth. Tunnel: Diameter 8m, depth 20m, excavated using TBM, support lags behind the excavation face by 10m. Boundary conditions: Top is a free surface, bottom is a fixed water head boundary (water level depth 30m). Gradient pore water pressure is applied to the tunnel excavation face to simulate the change in permeability coefficient caused by construction disturbance (permeability coefficient increases by 1-3 times in the disturbed zone).

[0134] Table 1. Stratigraphic Parameters

[0135]

[0136] Based on the above conditions, the impact of tunnel construction on urban groundwater was analyzed using the method described in this invention and the traditional method (single Gaussian permeability model, ignoring stress-seepage coupling, and assuming the permeability coefficient is constant).

[0137] Table 2 Comparison of seepage flow

[0138]

[0139] It can be seen that the error between the predicted seepage flow rate and the measured value of the present invention is 8.5%, while the error of the traditional method is 22.3%, indicating that the three-field coupling model described in the present invention significantly improves the accuracy.

[0140] Furthermore, the traditional method predicts a maximum drawdown of 3.2m with an influence radius of 50m. The present invention predicts a maximum drawdown of 2.8m with an influence radius of 42m, which is more consistent with the on-site monitoring (drawdown of 2.9m and radius of 40m), thus proving the effectiveness of the present invention.

[0141] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the technical solutions of the present invention, and these modifications or equivalent substitutions cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for analyzing the impact of railway tunnel construction on urban groundwater, characterized in that: Includes the following steps: S1. Multi-source data acquisition and preprocessing to construct a multi-dimensional spatiotemporal dataset containing surface fissures, geological and hydrological data, and construction disturbances; S2. Integrate the preprocessed multi-source data through a multi-dimensional feature fusion algorithm to construct a geological-hydrological-construction-remote sensing multi-dimensional feature vector, and use the improved RNPC-net model to identify the working face status and extract groundwater disturbance indicators. S3. Based on the elastoplastic damage theory and seepage mechanics, a stress-seepage-heat conduction three-field coupling model is established, and the boundary conditions of the stress-seepage-heat conduction three-field coupling model are set based on the groundwater disturbance index. S4. Analyze the three-field coupling effect based on the three-field coupling model, and output the comprehensive risk level of the impact of tunnel construction on groundwater based on the comprehensive risk assessment model; S5. Utilize GIS spatial analysis functions to integrate comprehensive risk levels and combine real-time data to achieve spatial visualization and graded early warning of groundwater impacts; S6. The geological parameters of the three-field coupled model are updated in real time using the extended Kalman filter algorithm. Combined with digital twin technology, a virtual mapping of the construction process is constructed, and the optimal combination of construction parameters is searched to form a monitoring-analysis-optimization closed-loop control. Step S2 specifically includes the following steps: S21. Construct a multi-dimensional feature vector integrating geology, hydrology, construction, and remote sensing: S211, Based on the corrected vertical displacement sequence and tunnel diameter and burial depth Calculate the settlement characteristic parameters, including the volume loss rate. and slot width ; Calculation of volume loss rate based on Gaussian sedimentation model : ； In the formula, This indicates the volume of the settling tank, and , Let represent the vertical displacement distribution function of the surface settlement trough, and , This represents the maximum surface subsidence. , Indicates the distance to the inflection point of the settling trough. Indicates the horizontal coordinate; This represents the cross-sectional area of ​​the tunnel, and , Indicates the tunnel diameter; Calculate the slot width using the following formula : ； In the formula, Indicates the distance to the inflection point; Indicates the tunnel depth; S212. Constructing Feature Vectors: Integrating geological and hydrological data, construction data, remote sensing data, and surface fracture distribution data to obtain the feature matrix. , Indicates surface porosity; Represents the anisotropic permeability tensor of each layer; Indicates the loss factor; Indicates the speed of propulsion; Indicates the cutter head torque; S213. Use the min-max normalization method to map each eigenvalue in the feature matrix to... The interval is used to obtain the normalized feature matrix. ; S22. Identifying the working face: Constructing an improved RNPC-net model and utilizing preprocessed working face images, 3D coordinates, and feature matrices. Train the improved RNPC-net model until convergence, and output the weathering level probability distribution. and groundwater state probability distribution : The improved RNPC-net model adopts a three-branch hybrid feature extraction module, which includes a two-dimensional image convolution branch with ResNet50 as the backbone, a three-dimensional point cloud processing branch, and a fully connected branch for construction parameters. It also integrates multi-source data input through an adaptive weight-assisted classifier. The cross-entropy loss function is defined as follows: ； In the formula, Indicates the loss value; Represents a label vector; Represents the probability distribution; Indicates the general category; Indicates a category index; S23. Extract groundwater disturbance indicators, including the comprehensive weathering index. and groundwater activity intensity index ; Among them, based on the probability distribution of weathering level Calculating the comprehensive weathering index : ； In the formula, Indicates weight; Indicates the first Predicted probability of weathering grade These represent unweathered, slightly weathered, moderately weathered, and strongly weathered, respectively. and the probability distribution of groundwater state Mapping to numerical indicators to construct a groundwater activity intensity index : ； In the formula, , , and These represent the probabilities of water gushing from the working face, water dripping from the working face, water dripping in a line from the working face, and the working face drying out, respectively. Step S3 specifically includes the following steps: S31, Elastic-plastic damage stress field modeling: S311. Invert damage zone parameters, including the blast damage radius and the anisotropic material parameter matrix. The radius of the blast damage was estimated using the following empirical formula and calibrated in conjunction with the acoustic test results to determine the extent of the damage zone: ； In the formula, Indicates the geometric parameters of the damaged area; Indicates the geological correction factor; Anisotropic material parameter matrix elastic modulus of the damaged area The calculation formula is as follows: ； In the formula, This indicates the elastic modulus of the original rock. Poisson's ratio The calculation formula is as follows: ； In the formula, This represents the Poisson's ratio of the original rock. S312, Radial effective stress in the elastic zone and tangential effective stress : ； ； In the formula, Indicates the stress in the original rock; Indicates the inner wall of the tunnel; Indicates the inner radius of the tunnel; Based on the Mohr-Coulomb criterion, the effective radial stress in the plastic zone is derived. and tangential effective stress : ； ； In the formula, This indicates the cohesion in the plastic zone, and , Indicates the cohesive force in the plastic zone; This represents the earth pressure coefficient in the plastic zone, and ; Indicates the radius of the plastic zone; This represents the friction angle within the plastic zone, and , Indicates the damage reduction factor; S32. Construct a seepage equation considering temperature effects and set boundary conditions to obtain the pore water pressure distribution cloud map and seepage flow rate. The seepage equation is expressed as follows: ； In the formula, Represents the seepage velocity vector; Indicates the dynamic viscosity of water; Indicates pore water pressure; Indicates the density of water; Represents gravitational acceleration; Indicates the water head height; Indicates the coefficient of thermal expansion; Indicates the temperature field distribution; The boundary conditions are as follows: tunnel inner wall Pore ​​water pressure , Indicates water pressure inside the tunnel; far field hour , Indicates the radius of influence of seepage. Indicates the initial pore water pressure; seepage flow The calculation formula is as follows: ； In the formula, Indicates the thickness of the aquifer; This represents the preliminary estimated permeability coefficient.

2. The method for analyzing the impact of railway tunnel construction on urban groundwater according to claim 1, characterized in that: Step S1 specifically includes the following steps: S11. Acquire multi-source data: Obtain C-band remote sensing data from Sentinel-1 A / B satellites via EGMS to obtain surface fracture data; simultaneously acquire borehole data, geological survey reports, groundwater level monitoring data, permeability coefficient test results, and pore water pressure distribution data to form geological and hydrological data; and acquire construction process parameters and tunnel face images to form construction disturbance data. S12. Multi-source data preprocessing: For remote sensing data: First, based on the orbital geometry parameters of the Sentinel-1 satellite, the LOS displacement sequences of the ascending and descending orbit data are projected onto the vertical direction to eliminate the radar incidence angle. Deviations are identified, and valid monitoring points are selected and retained using a coherence threshold. The corrected vertical displacement sequence is then output. : ； In the formula, This represents the original LOS displacement time series; Then, effective monitoring points are screened using a coherence threshold, and principal component analysis-independent component analysis (PCA-ICA) is used to separate the construction disturbance component and the natural settlement component in the displacement signal, thereby extracting the construction disturbance displacement sequence. ; For borehole data: particle size was tested using sieving and sedimentation methods to obtain clay content, and then the permeability coefficient was initially estimated based on the clay content. , This represents the baseline permeability coefficient related to clay content, and the initially estimated permeability coefficient is finally calibrated through a pressure water test. Obtain the anisotropic permeability tensor of each layer. : Simultaneously, the degree of fracture development was analyzed based on borehole CT images, and damage factors were defined. , and The surface fracture length and core length are represented respectively, and then a three-dimensional damage factor field is generated using ordinary kriging interpolation. .

3. The method for analyzing the impact of railway tunnel construction on urban groundwater according to claim 2, characterized in that: In step S11, the borehole data is acquired as follows: boreholes are arranged every 50m-100m along the tunnel axis, and the borehole depth penetrates 10m-20m below the tunnel floor. Rock core samples are collected and lithological classification is performed to obtain lithological distribution data. Simultaneously, the number of blows to a penetration of 30cm was obtained using the standard penetration test. The effective internal friction angle of the rock mass was estimated by combining the De Mello empirical formula. : ； Construction process parameters include TBM tunneling parameters and blasting parameters. TBM tunneling parameters include cutterhead torque. Speed ​​of advancement and shield pressure Blasting parameters include the charge amount per hole. , explosion center distance blasting interval and ground vibration velocity .

4. The method for analyzing the impact of railway tunnel construction on urban groundwater according to claim 3, characterized in that: Step S4 Specifically, the following steps are included: S41. Calculation of total stress using coupled stress field and seepage field: ； In the formula, and These represent the total radial stress and the total tangential stress, respectively. and Let represent the radial stress and tangential stress of the stress field, respectively. , ; S42. Introduce a construction heat source, calculate the temperature distribution using the heat conduction equation, and correct the seepage parameters: ； In the formula, This represents the dynamic viscosity of water after temperature correction, and , Indicates the dynamic viscosity of reference water. Indicates the temperature coefficient. and These represent the real-time temperature and the initial temperature, respectively. S43. Set the risk indicators as water inrush risk, settlement risk, and compression risk, among which water inrush risk Settlement risk Squeeze out risks , and All of these are set thresholds. Indicates rock quality indicators; Obtain a single risk factor vector ; S44. Constructing a comprehensive risk index : ； In the formula, , and Both represent weights, and ; S45, Based on Comprehensive Risk Index Risks are categorized into low, medium, and high risks, and a risk-measure mapping relationship is established.

5. The method for analyzing the impact of railway tunnel construction on urban groundwater according to claim 4, characterized in that: Step S5 specifically includes the following steps: S51. Convert geological parameters, three-field coupling model analysis results, and real-time monitoring data into ESRI Shapefile format and project them onto the UTM coordinate system. S52. Create thematic layers of geological layers, stress fields, and seepage fields in ArcGIS Pro; S53. Use the inverse distance weighting method to interpolate discrete risk points to generate a continuous risk surface: ； In the formula, Representing three-dimensional spatial coordinates Continuous risk value at the location; Indicates the prediction point and the first Spatial distance between discrete risk monitoring points; Indicates the first The comprehensive risk index of a discrete risk monitoring point; This represents the total number of discrete risk monitoring points; S54. Based on the tunnel geometric parameters, construction process parameters, and the analysis results of the three-field coupling model, a BIM tunnel model is constructed, and the BIM tunnel model and comprehensive risk level data are imported into the Unity 3D platform to realize the dynamic correlation display between construction progress and risk evolution. S55. Setting Tiered Early Warning Rules: Level 1 Early Warning Conditions: Comprehensive Risk Index Furthermore, if the surface subsidence rate is greater than 1 mm / day, a red alert is triggered, and the emergency grouting plan is automatically activated. Level II warning conditions: If the settling rate is greater than 0.5 mm / day, a yellow alert will be triggered, prompting an increase in monitoring frequency.

6. The method for analyzing the impact of railway tunnel construction on urban groundwater according to claim 5, characterized in that: Step S6 specifically includes the following steps: S61. The geological parameters of the three-field coupled model are updated in real time using extended Kalman filtering, and the updated damage factor is output. and permeability coefficient ; Define state vector Observation vector , This represents the measured value of vertical displacement on the Earth's surface. To represent the measured seepage flow rate, the following state equation and observation equation are established: ； ； In the formula, and They represent The predicted state vector at time t and State vector estimate at time t; Represents the state transition function; Indicates state noise; express The observation vector at time; Represents the observation function; Indicates observation noise; The state estimate is calculated iteratively using the extended Kalman filter algorithm: ； In the formula, and They represent The optimal estimate of the state vector at time step and based on Time estimation Predicted state value at any given time; Indicates Kalman gain, and , Indicates based on Time estimation The covariance matrix of the state prediction at time step. The covariance matrix representing the observation noise; S62, Update the damage factor and permeability coefficient Substitute the three-field coupling model described in step S3 into the recalculated stress field, seepage field, and risk index; S63. Compare the recalibration results with the measured data, calculate the root mean square error to evaluate the accuracy of the three-field coupling model. If the root mean square error is >5%, return to step S61 to perform the second calibration process. S64. Optimize construction parameters; S641. Constructing a digital twin model: Develop a digital twin of tunnel construction based on the Unity platform, integrate BIM tunnel model and real-time monitoring data, and realize a 1:1 virtual mapping of the construction process; S642. Employ a near-end strategy optimization algorithm to minimize the overall risk index. To achieve the goal, search for the optimal combination of parameters. , and These represent the optimal support pressure and the optimal excavation rate, respectively.

Images