Multi-field coupling driven urban underground space grouting intelligent regulation and control method and platform

Abstract

The application discloses a multi-field coupling driven urban underground space grouting intelligent regulation and control method and platform, relates to the technical field of grouting intelligent regulation and control, and comprises the following steps: collecting geological exploration data of a target grouting space, and constructing a three-dimensional geological model; horizontally cutting the three-dimensional geological model into P layers of horizontal geological slices; performing multi-field coupling grouting analysis to obtain a first layer of grouting strategy; during the execution of an underground space grouting simulation process, performing parameter updating of a second layer of horizontal geological slices, outputting second layer updated data structure; outputting a hierarchical grouting regulation and control strategy; and executing grouting intelligent regulation and control of the target grouting space. The application solves the technical problem that the existing urban underground space grouting regulation and control lacks multi-field coupling analysis and hierarchical intelligent optimization, and the grouting efficiency is low, achieves the intelligent regulation and control of urban underground space grouting, and improves the grouting efficiency.

Description

Technical Field

[0001] This invention relates to the field of intelligent grouting control technology, specifically to a method and platform for intelligent control of grouting in urban underground spaces driven by multi-field coupling. Background Technology

[0002] In the development of urban underground space, grouting technology is a key means to ensure geological stability and engineering safety. However, existing technologies for underground space grouting often lack a systematic consideration of the coupling effects of multiple physical fields, making it difficult to accurately match the grouting requirements under different geological conditions. For example, traditional methods typically use uniform grouting parameters without dynamically adjusting them based on lithological characteristics such as the permeability coefficient, fracture density, and stress state of the strata, resulting in low grouting efficiency and uneven grout distribution. Furthermore, existing technologies lack analysis of the mutual influence of different strata during the grouting process, making it difficult to formulate multi-level grouting strategy control, thus failing to meet the requirements of complex urban underground space development.

[0003] Existing technologies for grouting control in urban underground spaces lack multi-field coupling analysis and layered intelligent optimization, resulting in low grouting efficiency. Summary of the Invention

[0004] This application provides a multi-field coupling driven intelligent control method and platform for grouting in urban underground space, which is used to address the technical problem of low grouting efficiency caused by the lack of multi-field coupling analysis and hierarchical intelligent optimization in the control of grouting in urban underground space in the prior art.

[0005] In view of the above problems, this application provides a method and platform for intelligent control of grouting in urban underground space driven by multi-field coupling.

[0006] The first aspect of this application provides a multi-field coupled-driven intelligent control method for grouting in urban underground spaces, the method comprising:

[0007] S1: Collect geological exploration data of the target grouting space and construct a three-dimensional geological model; S2: Horizontally divide the three-dimensional geological model into P-layer horizontal geological slices; S3: After calling the first-layer slice data structure of the first-layer horizontal geological slice, perform multi-field coupled grouting analysis on the first-layer slice data structure to obtain the first-layer grouting strategy; S4: During the underground space grouting simulation of the first-layer horizontal geological slice using the first-layer grouting strategy, update the parameters of the second-layer horizontal geological slice based on the predicted field variable increment based on the physical field coupling effect, and output the second-layer updated data structure; S5: Iterate through S3-S4 until the P-layer horizontal geological slice, and output the hierarchical grouting control strategy; S6: Use the hierarchical grouting control strategy to perform intelligent grouting control of the target grouting space along the P-layer horizontal geological slice.

[0008] A second aspect of this application provides a multi-field coupled intelligent control platform for grouting in urban underground spaces, the platform comprising:

[0009] The system includes the following modules: a 3D geological model construction module for collecting geological exploration data of the target grouting space and constructing a 3D geological model; a model segmentation module for horizontally segmenting the 3D geological model into P-layer horizontal geological slices; a grouting analysis module for calling the first-layer slice data structure of the first-layer horizontal geological slice and performing multi-field coupled grouting analysis on the first-layer slice data structure to obtain the first-layer grouting strategy; a parameter update module for updating the parameters of the second-layer horizontal geological slice based on the predicted field variable increments during the underground space grouting simulation of the first-layer horizontal geological slice using the first-layer grouting strategy, and outputting the second-layer updated data structure; a grouting control strategy output module for iteratively executing the grouting analysis module and parameter update module until the P-layer horizontal geological slice, and outputting the hierarchical grouting control strategy; and a grouting intelligent control module for performing intelligent grouting control of the target grouting space along the P-layer horizontal geological slice using the hierarchical grouting control strategy.

[0010] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0011] S1: Collect geological exploration data of the target grouting space and construct a three-dimensional geological model; S2: Horizontally divide the three-dimensional geological model into P-layer horizontal geological slices; S3: After calling the first-layer slice data structure of the first-layer horizontal geological slice, perform multi-field coupled grouting analysis on the first-layer slice data structure to obtain the first-layer grouting strategy; S4: During the underground space grouting simulation of the first-layer horizontal geological slice using the first-layer grouting strategy, update the parameters of the second-layer horizontal geological slice based on the predicted field variable increments according to the physical field coupling effect, and output the second-layer updated data structure; S5: Iterate through S3-S4 until the P-layer horizontal geological slice, and output the hierarchical grouting control strategy; S6: Use the hierarchical grouting control strategy to perform intelligent grouting control of the target grouting space along the P-layer horizontal geological slice. This achieves the technical effect of intelligent control of urban underground space grouting and improves grouting efficiency. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 A flowchart illustrating the intelligent control method for grouting in urban underground space driven by multi-field coupling provided in this application embodiment;

[0014] Figure 2 A schematic diagram of the structure of the intelligent control platform for grouting in urban underground space driven by multi-field coupling provided in the embodiments of this application.

[0015] Figure labeling: 3D geological model construction module 10, model segmentation module 20, grouting analysis module 30, parameter update module 40, grouting control strategy output module 50, grouting intelligent control module 60. Detailed Implementation

[0016] This application provides a multi-field coupling driven intelligent control method and platform for grouting in urban underground spaces, which addresses the technical problem of low grouting efficiency caused by the lack of multi-field coupling analysis and hierarchical intelligent optimization in the control of grouting in urban underground spaces in existing technologies.

[0017] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0018] Example 1, as Figure 1 As shown, this application provides a multi-field coupled intelligent control method for grouting in urban underground spaces, the method comprising:

[0019] S1: Collect geological exploration data of the target grouting space and construct a three-dimensional geological model.

[0020] Specifically, core samples from the target grouting space are obtained using geological drilling equipment to analyze lithological distribution. Geophysical exploration methods such as seismic wave reflection and electromagnetic methods are used to collect stratigraphic physical parameters such as porosity, permeability coefficient, and fracture development. Geostress field distribution and groundwater temperature data are obtained using geostress measuring instruments and temperature sensors. After preprocessing the collected multidimensional data, including denoising and normalization, the data is imported into Petrel 3D geological modeling software. Kriging interpolation is used to spatially interpolate the discrete data. Combined with geostatistical methods, a 3D geological model is constructed, including stratigraphic structure, lithological characteristics, permeability field, stress field, and temperature field. The resolution of each grid cell in the model is set to 0.5–2 m according to the subsequent slicing and layering requirements, ensuring that the model accurately reflects geological characteristics and provides basic data support for dynamic allocation of slice thickness and multi-field coupling analysis.

[0021] S2: The three-dimensional geological model is horizontally divided into P-layer horizontal geological slices.

[0022] Specifically, a vertical feature sequence consisting of lithology, permeability coefficient, and fracture density is first extracted from the 3D geological model. This sequence is then divided into K lithological sub-features using a sampling scale of 1 / K of the model's vertical depth. By calculating the coefficients of variation of permeability and fracture density within each sub-feature interval (taking the maximum of both as the stratigraphic coefficient of variation), corresponding slice thickness parameters are matched to form a slice thickness sequence that dynamically changes with geological features. Finally, the 3D model is horizontally segmented into P-layer geological slices according to this sequence. Larger slice thicknesses (e.g., 5–10 m) are used in areas with homogeneous lithology and low stratigraphic coefficients of variation, while areas with well-developed fractures or drastic changes in permeability are subdivided to 1–3 m. This ensures spatial consistency of multi-field coupling features within each slice, providing accurate geological units for subsequent layered grouting strategy analysis.

[0023] S3: After calling the first layer slice data structure of the first layer horizontal geological slice, the first layer grouting strategy is obtained by performing multi-field coupled grouting analysis on the first layer slice data structure.

[0024] Specifically, the slice data structure of the first-layer horizontal geological slice is invoked to extract parameters such as average permeability coefficient, maximum fracture density, minimum principal stress, and average groundwater temperature. The minimum principal stress is used to match the first grouting pressure, ensuring effective penetration without damaging the formation. Based on the average permeability coefficient and maximum fracture density, a first grouting formula, consisting of grout type, viscosity, and water-cement ratio, is matched to adapt to the rock formation's permeability characteristics. The average permeability coefficient is used to determine the baseline grouting rate, which is then adjusted using a coupling correction coefficient calculated based on the maximum fracture density and minimum principal stress to obtain the first grouting rate. Finally, the above parameters and the average groundwater temperature are used as constraints to retrieve the first curing time from the database. Through multi-field parameter coupling analysis, a first-layer grouting strategy incorporating grouting pressure, formula, rate, and curing time is formed, achieving precise matching between geological conditions and grouting parameters.

[0025] S4: During the underground space grouting simulation of the first layer horizontal geological slice using the first layer grouting strategy, the parameters of the second layer horizontal geological slice are updated based on the predicted field variable increments according to the physical field coupling effect, and the second layer updated data structure is output.

[0026] Specifically, when performing underground space grouting simulation on the first horizontal geological slice using the first-layer grouting strategy, COMSOL Multiphysics multi-field coupled simulation software was used to construct a coupled model including the Darcy flow equation, the elasticity equilibrium equation, and the heat conduction equation. This model simulated the dynamic interaction of stress, seepage, and temperature fields during grouting pressure (first grouting pressure), grout penetration (based on the first grouting formula), and curing heat release (combined with the first curing time). After the simulation, the pore water pressure increment (accuracy ±0.1MPa) and stress tensor increment (resolution 10) were obtained through the data extraction module. -3 MPa), temperature increment (error ±0.5℃), and change in permeability (accurate to 10). -10 An incremental set of field variables, such as permeability coefficients (m / s), is input into a pre-constructed set of interlayer physical transfer functions (including stress-seepage transfer functions and heat conduction layered superposition functions based on Biot consolidation theory). Matrix operations are used to quantify the cross-layer physical field coupling effect, resulting in an updated set of field variables. Finally, based on this updated set, parameters such as the original permeability coefficient and geostress components in the second-layer slice data structure are iteratively corrected (using gradient descent with a convergence threshold of 1%). The output is a second-layer updated data structure containing interlayer coupling effects, providing accurate geological parameters with spatiotemporal evolution characteristics for subsequent grouting strategy analysis.

[0027] S5: Iterate through S3-S4 until the Pth layer of horizontal geological slices are sliced, and output the layer grouting control strategy.

[0028] Specifically, after completing the first-layer grouting strategy analysis and the second-layer data structure update, the process enters an iterative cycle: For the i-th horizontal geological slice (i starts from 2), the updated data structure of the i-th layer, corrected by the previous grouting simulation, is called. Multi-field parameters such as the average permeability coefficient and maximum fracture density of this layer are extracted. The multi-field coupling analysis process of S3 is repeated to match the grouting pressure, formula, speed, and curing time of the i-th layer, forming the grouting strategy for the i-th layer. Subsequently, this strategy is used to perform grouting simulation on the i-th layer. The incremental set of field variables, such as pore water pressure increment, is extracted through multi-field coupling simulation. After calculation using the interlayer physical transfer function set, the parameters of the i+1-th slice data structure are updated. This cycle continues until the P-th slice. After completing the grouting strategy analysis for the P-th layer, the iteration terminates. The grouting strategies of each layer are integrated according to the slice order into a hierarchical grouting control strategy covering the geological characteristics of the P-th layer and the interlayer physical field coupling effect. This strategy includes the grouting parameter sequence of each layer and cross-layer influence correction rules, providing a systematic execution plan for intelligent grouting control.

[0029] S6: Using the hierarchical grouting control strategy, intelligent grouting control is performed along the horizontal geological slice of layer P to control the grouting in the target grouting space.

[0030] Specifically, the output hierarchical grouting control strategy is translated into specific grouting execution commands, and grouting operations are performed sequentially from the first layer to the Pth layer along the horizontal geological slice of layer P. During the grouting process, sensors deployed in the grouting holes collect data in real time, such as grouting pressure, grouting volume, grout temperature, and formation displacement, and transmit this data to the intelligent control platform. Based on the parameter requirements in each layer's grouting strategy (such as grouting pressure, formula, speed, and curing time), the platform uses a PID control algorithm to dynamically adjust equipment such as the grouting pump flow rate and grout mixing device to ensure that the actual grouting parameters match the strategy. Simultaneously, based on the interlayer physical field coupling effect, the impact of the current layer's grouting on the geological parameters of the next layer is monitored in real time. If the increment of field variables exceeds a preset threshold (such as an increase in pore water pressure exceeding 0.5 MPa), the grouting strategy for the next layer is automatically corrected, forming a closed-loop control of monitoring-control-correction. Ultimately, this achieves multi-field coupling-driven intelligent control of the target grouting space, ensuring the grouting effect and the achievement of geological optimization goals.

[0031] In one possible implementation, step S2 further includes:

[0032] Vertical lithological feature sequences were extracted from the three-dimensional geological model.

[0033] The slice thickness sequence is dynamically assigned based on the longitudinal lithological characteristic sequence.

[0034] The three-dimensional geological model is horizontally segmented according to the slice thickness sequence to obtain the P-layer horizontal geological slice.

[0035] Specifically, when extracting the vertical lithological feature sequence from the three-dimensional geological model, geological parameters such as lithological type (e.g., sandstone, claystone), permeability coefficient, fracture density, and porosity are collected at depth points along the vertical depth direction of the model at preset sampling intervals (e.g., 0.5–2 meters). The discrete point data are then fitted into a continuous vertical profile curve using a spatial interpolation algorithm, forming a complete vertical lithological feature sequence that reflects the vertical changes of the strata. This sequence covers the distribution of lithology and physical field parameters of the entire strata from the surface to the target grouting depth, providing basic data support for the subsequent dynamic allocation of slice thickness.

[0036] When dynamically allocating slice thickness sequences based on the vertical lithological feature sequence, the vertical depth of the 3D geological model is first used as 1 / K as the sampling segmentation scale, dividing the vertical lithological feature sequence into K vertical lithological sub-features. For each sub-feature, the permeability coefficient and fracture density values ​​of multiple discrete grid points are extracted from its feature interval. The mean and standard deviation of the two sets of data are calculated respectively. The permeability variation coefficient and fracture variation coefficient are obtained by dividing the mean by the standard deviation, and the maximum value of the two is taken as the stratigraphic variation coefficient of the sub-feature. Based on the K stratigraphic variation coefficients, the corresponding K slice thickness parameters are matched (for example, when the stratigraphic variation coefficient is >0.5, a slice thickness of 1-3 meters is matched; when the variation coefficient is ≤0.5, a slice thickness of 5-10 meters is matched), finally forming a slice thickness sequence that dynamically changes with geological features. This ensures that larger slice thicknesses are used in areas with homogeneous lithology, and smaller slice thicknesses are used in areas with developed fractures or drastic parameter fluctuations, to adapt to the accuracy requirements of subsequent multi-field coupling analysis.

[0037] When horizontally segmenting a 3D geological model based on the slice thickness sequence, the process begins at the top of the model and proceeds layer by layer horizontally according to the thickness parameters corresponding to each layer in the slice thickness sequence. For example, if the first parameter of the slice thickness sequence is 5 meters, the first horizontal slice is cut 5 meters down from the top of the model, resulting in the first horizontal geological slice. Then, according to the next thickness parameter (e.g., 3 meters), the second slice is cut 3 meters down from the bottom of the first slice, and so on. During the segmentation process, the layering function of the 3D modeling software precisely controls the spatial position and thickness of each slice, ensuring that the upper and lower interfaces of each slice are parallel to the horizontal plane. Ultimately, the 3D geological model is completely segmented into P layers of horizontal geological slices. Each slice retains geological data such as lithological characteristics, permeability coefficient, fracture density, and geostress field of the corresponding depth range in the original model, forming an independent slice data structure. This provides accurate spatial geological units for subsequent multi-field coupled grouting analysis of each layer.

[0038] In one possible implementation, step S2 further includes:

[0039] The vertical depth of the three-dimensional geological model is 1 / K as the sampling segmentation scale.

[0040] The longitudinal lithological feature sequence is divided into K longitudinal lithological sub-features using the sampling segmentation scale.

[0041] Calculate K stratigraphic variation coefficients based on the K vertical lithological sub-characteristics.

[0042] After matching K slice thickness parameters with the K stratigraphic variation coefficients, slice layering is set based on the K slice thickness parameters, and the slice thickness sequence is output.

[0043] Specifically, when using 1 / K of the vertical depth of the 3D geological model as the sampling segmentation scale, the total depth of the model in the vertical direction is first determined, and then this depth value is divided into K equal parts. The depth value of each part is the sampling segmentation scale. For example, if the vertical depth of the 3D geological model is 100 meters, and K = 20 is set, then the sampling segmentation scale is 100 meters × 1 / 20 = 5 meters, that is, every 5 meters is used as a sampling unit to segment the vertical lithological feature sequence. This scale, by dividing the vertical depth of the model proportionally, ensures that each segmented vertical lithological sub-feature interval has a unified depth benchmark, which facilitates subsequent statistical analysis and coefficient of variation calculation of geological parameters within each interval, thereby providing a standardized sampling unit for dynamically allocating slice thickness.

[0044] When dividing the longitudinal lithological feature sequence into K longitudinal lithological sub-features using the aforementioned sampling segmentation scale, a fixed depth interval of 1 / K of the longitudinal depth of the three-dimensional geological model is used (e.g., when the model depth is 100 meters and K=20, the interval is 5 meters). Starting from the top of the model, the longitudinal lithological feature sequence is divided equidistantly along the vertical depth direction according to this interval. The starting depth of each segment is successively 0, 1 / K×H, 2 / K×H… (H is the total depth of the model), and the ending depth is correspondingly 1 / K×H, 2 / K×H, 3 / K×H…, thus forming K continuous and non-overlapping longitudinal lithological sub-feature intervals. Each sub-feature interval contains a complete sequence of geological parameters such as lithology type, permeability coefficient, and fracture density for that depth segment, providing an independent feature analysis unit for subsequent calculation of stratigraphic variation coefficients and dynamic allocation of slice thickness.

[0045] When calculating the K stratigraphic variation coefficients based on the K vertical lithological sub-features, for each vertical lithological sub-feature, the permeability coefficient and fracture density values ​​of multiple discrete grid points within its feature interval are first extracted (for example, at least 20 grid points are selected for each sub-feature). The mean and standard deviation of the two sets of data are then calculated. The permeability variation coefficient is obtained by dividing the mean permeability coefficient by the standard deviation of the permeability coefficient, and the fracture variation coefficient is obtained by dividing the mean fracture density by the standard deviation of the fracture density. The two values ​​are compared, and the maximum value is taken as the stratigraphic variation coefficient corresponding to that sub-feature. This process is repeated to complete the calculation of the K vertical lithological sub-features, forming K stratigraphic variation coefficients that characterize the degree of fluctuation in stratigraphic parameters. This provides a quantitative basis for subsequent matching of slice thickness parameters, where a larger variation coefficient indicates a more drastic change in geological characteristics at that depth.

[0046] After matching K slice thickness parameters based on the K stratigraphic variation coefficients, slice stratification is set based on the K slice thickness parameters. When outputting the slice thickness sequence, a mapping relationship model between stratigraphic variation coefficients and slice thickness (such as a piecewise function or neural network model) is established. Each stratigraphic variation coefficient is substituted into the model to match the corresponding slice thickness parameter. For example, when the stratigraphic variation coefficient is greater than 0.6, a slice thickness of 1–3 meters is matched; when the stratigraphic variation coefficient is between 0.3 and 0.6, a slice thickness of 3–5 meters is matched; when the stratigraphic variation coefficient is less than 0.3, a slice thickness of 5–10 meters is matched. Then, according to the depth order of vertical lithological sub-characteristics, the K slice thickness parameters are arranged sequentially to set slice stratification, ensuring that the variation range of adjacent slice thickness parameters is within a reasonable range and avoiding abrupt changes. Finally, the set K slice thickness parameters are combined sequentially into a slice thickness sequence and output. This sequence is used to guide the horizontal segmentation of the three-dimensional geological model, so that the geological features within each horizontal geological slice after segmentation have relative consistency, to meet the accuracy requirements of subsequent multi-field coupled grouting analysis.

[0047] In one possible implementation, step S2 further includes:

[0048] Multiple permeability coefficient values ​​and multiple fracture density values ​​of multiple discrete grid points are extracted from the feature interval of the first longitudinal lithological sub-characteristics.

[0049] After calculating the average and standard deviation of the multiple permeability coefficient values, the permeability variation coefficient is output by dividing the average by the standard deviation.

[0050] After calculating the average and standard deviation of the multiple fracture density values, the fracture variation coefficient is output by dividing the average by the standard deviation.

[0051] The maximum value of the permeability variation coefficient and the fracture variation coefficient is taken as the first formation variation coefficient.

[0052] Specifically, when extracting permeability coefficient and fracture density values ​​from multiple discrete grid points within the feature interval of the first longitudinal lithology sub-feature, the depth interval corresponding to the sub-feature is first located (determined by the 1 / K sampling segmentation scale of the longitudinal depth of the 3D geological model). Then, within this interval, at least 20 discrete grid points are uniformly selected according to a preset spatial grid precision (e.g., 1m × 1m). Using the data query function of the 3D geological model, the permeability coefficient (unit: 10) of each grid point is extracted in batches. -10 The raw data of permeability coefficient (m / s) and fracture density (unit: fracture / m) are used to form the permeability coefficient dataset and fracture density dataset of this sub-feature, providing a quantitative basis for subsequent calculation of formation variation coefficient.

[0053] When calculating the average and standard deviation of multiple permeability coefficient values, first extract the permeability coefficient values ​​(unit: 10) of all discrete grid points from the first vertical lithology sub-characteristic interval. -10 The arithmetic mean is obtained by summing the values ​​of each data point (m / s) and dividing by the number of data points. Then, the squared difference between each data point and the mean is calculated, summed, divided by the number of data points, and the square root is taken to obtain the standard deviation. A division operation is performed with the mean as the numerator and the standard deviation as the denominator. The resulting dimensionless value is the permeability variation coefficient. This coefficient quantifies the dispersion of the permeability coefficient, reflecting the fluctuation range of formation permeability characteristics, and provides a key parameter for subsequent comparison with the fracture variation coefficient and for determining the formation variation coefficient.

[0054] To calculate the average and standard deviation of multiple fracture density values, the fracture density values ​​(unit: fractures / m) of all discrete grid points extracted from the first vertical lithology sub-characteristic interval are first summed, and then divided by the number of data points to obtain the arithmetic mean. Next, the squared difference between each data point and the average is calculated, summed, divided by the number of data points, and the square root is taken to obtain the standard deviation. A division operation is performed with the average as the numerator and the standard deviation as the denominator. The resulting dimensionless value is the fracture variation coefficient. This coefficient quantifies the dispersion of fracture density, reflects the heterogeneity of formation fracture development, and provides a key quantitative indicator for subsequent comparison with the permeability variation coefficient and for determining the formation variation coefficient.

[0055] The calculated permeability variation coefficient and fracture variation coefficient are compared numerically, and the larger value is selected as the first stratigraphic variation coefficient. This coefficient comprehensively reflects the maximum fluctuation of geological parameters within the first vertical lithological sub-characteristic interval, providing a key basis for dynamically matching slice thickness parameters according to the degree of stratigraphic variation. This ensures that a smaller slice thickness is used in areas with drastic changes in geological characteristics to meet the accuracy requirements of multi-field coupled grouting analysis.

[0056] In one possible implementation, step S3 further includes:

[0057] The average permeability coefficient, maximum fracture density, minimum principal stress, and average groundwater temperature were extracted from the first layer of sliced ​​structural data.

[0058] The minimum principal stress is used as the stress condition to match the first grouting pressure.

[0059] The average permeability coefficient and maximum fracture density are used as lithological conditions to match the first grouting formula, wherein the first grouting formula consists of a first grout type, a first grout viscosity, and a first grout water-cement ratio.

[0060] The first grouting speed is obtained by using the average permeability coefficient, maximum fracture density and minimum principal stress for parameter coupling matching.

[0061] Using the first grouting pressure, the first grouting formula, the first grouting speed, and the average temperature of groundwater as multivariate search constraints, the first curing time is obtained. The first curing time, the first grouting pressure, the first grouting formula, and the first grouting speed constitute the grouting strategy for the first layer.

[0062] Specifically, when extracting the average permeability coefficient, maximum fracture density, minimum principal stress, and average groundwater temperature from the first layer of slice structural data, the permeability coefficient, fracture density, principal stress, and temperature data of all discrete grid points within the slice are first obtained through the data query function of the three-dimensional geological model. Then, the arithmetic mean of the permeability coefficient data is taken to obtain the average permeability coefficient. The maximum value is extracted from the fracture density data as the maximum fracture density. The minimum value is selected from the principal stress data as the minimum principal stress. The arithmetic mean of the temperature data is taken to obtain the average groundwater temperature. In this way, the key geological parameters and physical field parameters of the slice are extracted, providing basic data for subsequent grouting strategy analysis.

[0063] When using the minimum principal stress as the stress condition to match the first grouting pressure, first establish a mapping relationship model between the minimum principal stress and the grouting pressure (such as a linear function or nonlinear fitting model). Then, substitute the minimum principal stress value extracted from the first layer slice structure data into the model. By calculating or looking up a pre-generated stress-grouting pressure comparison table, the first grouting pressure is matched to ensure that the pressure value is between the formation initiation splitting pressure and the safe grouting pressure. This allows the grout to effectively penetrate and diffuse without causing formation rupture, thus providing reasonable pressure parameters for the grouting operation of the first layer of horizontal geological slices.

[0064] When using average permeability coefficient and maximum fracture density as the basis for matching the first grouting formula to lithological conditions, a matching database of lithological parameters and grout properties is first established. This database contains the optimal grout type, viscosity, and water-cement ratio combinations corresponding to different permeability coefficient and fracture density ranges. Then, the average permeability coefficient (unit: 10) extracted from the first layer slice structure data is used. -10 The maximum fracture density (unit: fractures / m) and maximum crack density (unit: fractures / m) are input into the database. The corresponding first grout type (such as cement-based grout, chemical grout), first grout viscosity (unit: mPa·s) and first grout water-cement ratio are retrieved through fuzzy matching algorithm to form the first grouting formula adapted to the lithological characteristics of the slice, ensuring that the grout has good injectability and consolidation effect under the formation conditions.

[0065] When the first grouting velocity is obtained by parameter coupling matching using the average permeability coefficient, maximum fracture density, and minimum principal stress, the specific implementation method is as follows: First, using the average permeability coefficient as the core parameter, a pre-generated permeability coefficient-reference grouting velocity comparison table is consulted (e.g., when the average permeability coefficient is 5×10). -10When the grouting speed is m / s, the corresponding reference grouting speed is 15 L / min. The reference grouting speed is then obtained. Next, a mapping relationship is established between the maximum fracture density, the minimum principal stress, and the coupling grouting correction coefficient. For example, the correction coefficient is increased by 0.1 for every 1 fracture / m increase in maximum fracture density, and decreased by 0.05 for every 1 MPa increase in minimum principal stress. The coupling grouting correction coefficient is then calculated. Finally, the reference grouting speed is multiplied by the coupling grouting correction coefficient to obtain the first grouting speed. For example, if the reference grouting speed is 15 L / min and the correction coefficient is 1.2, the first grouting speed is 15 × 1.2 = 18 L / min, thus achieving precise control of the grouting speed.

[0066] When retrieving the first curing time using the first grouting pressure, first grouting formula, first grouting speed, and average groundwater temperature as multivariate search constraints, a multidimensional database containing the correspondence between the above parameters and curing time is first constructed. The database includes pre-set curing time data for different combinations of grouting pressure, grout type, viscosity, water-cement ratio, grouting speed, and temperature. Then, the extracted first grouting pressure (e.g., 5 MPa), first grouting formula (e.g., cement-based grout, viscosity 15 mPa·s, water-cement ratio 0.6), first grouting speed (e.g., 18 L / min), and average groundwater temperature (e.g., 20℃) are input into the database. A multidimensional indexing algorithm is then used to quickly locate the matching curing time (e.g., 45 minutes). Finally, the first curing time, together with the first grouting pressure, first grouting formula, and first grouting speed, constitutes the first-layer grouting strategy. This strategy integrates the influence of pressure, formula, speed, and temperature parameters on the curing process, providing a complete parameter combination scheme for the grouting operation of the first-layer horizontal geological slice, ensuring that the grouting effect meets design requirements.

[0067] In one possible implementation, step S3 further includes:

[0068] The average permeability coefficient is used as the dominant characteristic of the grouting speed to match the output benchmark grouting speed.

[0069] The coupling grouting correction coefficient is obtained by matching the maximum fracture density and the minimum principal stress.

[0070] The first grouting speed is obtained by correcting the reference grouting speed using the coupling grouting correction coefficient.

[0071] Specifically, when matching the output benchmark grouting speed with the average permeability coefficient as the dominant characteristic of the grouting speed, a mapping table between the permeability coefficient and the benchmark grouting speed is first established. For example, when the average permeability coefficient is 3×10... -10 The corresponding baseline grouting rate at m / s is 10 L / min, 5 × 10 -10 When m / s corresponds to 15L / min, the reference grouting speed can be obtained by consulting this table.

[0072] When obtaining the coupled grouting correction coefficient by matching the maximum fracture density and the minimum principal stress, a quantitative relationship model between the two and the correction coefficient is first established. For example, it is set that for every increase of 1 fracture / m in the maximum fracture density, the correction coefficient increases by 0.15, and for every increase of 1 MPa in the minimum principal stress, the correction coefficient decreases by 0.1. Then, the actual maximum fracture density (e.g., 3 fractures / m) and minimum principal stress (e.g., 5 MPa) are extracted from the first layer slice structure data and substituted into the model for calculation. If the initial correction coefficient is 1, the maximum fracture density increases the correction coefficient by 0.45 (3 × 0.15), and the minimum principal stress decreases the correction coefficient by 0.5 (5 × 0.1), finally obtaining a coupled grouting correction coefficient of 0.95. This coefficient is used to correct the baseline grouting rate to adapt to the degree of fracture development and stress state of the formation.

[0073] When correcting the baseline grouting rate using a coupled grouting correction coefficient, the coefficient is first calculated using the maximum fracture density and minimum principal stress. Then, this correction coefficient is multiplied by the baseline grouting rate to obtain the first grouting rate. For example, if the baseline grouting rate is 15 L / min and the coupled grouting correction coefficient is 1.2, the first grouting rate is 15 × 1.2 = 18 L / min. This process quantifies the influence of formation fracture development and stress state on the grouting rate, achieving precise adjustment of the baseline grouting rate. This ensures that the obtained first grouting rate better matches the actual formation conditions, guaranteeing the effectiveness and safety of the grouting operation.

[0074] In one possible implementation, step S4 further includes:

[0075] After performing a multi-field coupled simulation of the underground space grouting process on the first-layer horizontal geological slice using the first-layer grouting strategy, the field variable increment set is extracted, wherein the field variable increment includes pore water pressure increment, stress tensor increment, temperature increment and permeability coefficient change.

[0076] A pre-constructed set of inter-layer physical transfer functions is used, and cross-layer superposition correction is performed by synchronizing the incremental set of field variables to the set of inter-layer physical transfer functions to obtain the updated set of field variables.

[0077] The second-layer slice data structure is corrected using the field variable update set to obtain the second-layer update data structure.

[0078] Specifically, after performing a multi-field coupled simulation of the underground space grouting process on the first horizontal geological slice using the first-layer grouting strategy, the incremental set of field variables was extracted from the simulation results. Among these, the pore water pressure increment reflects the change in formation water pressure caused by grouting, the stress tensor increment reflects the change in formation stress state, the temperature increment originates from the chemical reaction of the grouting material or the thermal effect of fluid flow, and the change in permeability coefficient represents the change in formation permeability due to grouting. These incremental data comprehensively characterize the impact of grouting operations on the multi-physics environment of the first slice, providing a quantitative basis for subsequent parameter updates for the second slice.

[0079] A pre-constructed set of inter-layer physical transfer functions is used. This set contains mathematical models describing the transfer relationships of physical field variables between different stratigraphic slices, such as the transmission and superposition laws of variables like pore water pressure, stress, temperature, and permeability coefficient. The set of incremental field variables extracted from the first-layer grouting simulation (including increments in pore water pressure, stress tensor, temperature, and permeability coefficient) is input into the inter-layer physical transfer function set. Through the calculation and processing of the function set, the incremental field variables are superimposed and corrected across layers, thus obtaining an updated set of field variables that comprehensively considers the influence of upper-layer grouting. This provides accurate input parameters for the data structure correction of the second-layer slice.

[0080] When correcting the data structure of the second-layer slice using the field variable update set, the update set, which includes increments in pore water pressure, stress tensor, temperature, and permeability coefficient, is fused parameter by parameter with the original data structure of the second-layer slice. By superimposing the incremental values ​​from the field variable update set onto the corresponding original parameters—for example, adding the pore water pressure increment to the original pore water pressure value and the stress tensor increment to the original stress tensor value—the data structure of the second-layer slice is corrected. This yields a comprehensive updated data structure that reflects the influence of upper-layer grouting, providing more accurate data support for subsequent grouting strategy analysis of the second-layer slice based on actual geological conditions.

[0081] Example 2, based on the same inventive concept as the multi-field coupled driven intelligent control method for urban underground space grouting in the foregoing examples, such as... Figure 2 As shown, this application provides a multi-field coupled intelligent control platform for grouting in urban underground spaces. The platform and method embodiments in this application are based on the same inventive concept. The platform includes:

[0082] The 3D geological model construction module 10 is used to collect geological exploration data of the target grouting space and construct a 3D geological model.

[0083] The model segmentation module 20 is used to horizontally segment the three-dimensional geological model into P-layer horizontal geological slices.

[0084] The grouting analysis module 30 is used to call the first layer slice data structure of the first layer horizontal geological slice, and then perform multi-field coupled grouting analysis on the first layer slice data structure to obtain the first layer grouting strategy.

[0085] The parameter update module 40 is used to update the parameters of the second layer of horizontal geological slices based on the predicted field variable increments according to the physical field coupling effect during the underground space grouting simulation of the first layer of horizontal geological slices using the first layer grouting strategy, and output the second layer update data structure.

[0086] Grouting control strategy output module 50 is used to iteratively execute the grouting analysis module-parameter update module until the P-th layer horizontal geological slice, and output the layer grouting control strategy.

[0087] The grouting intelligent control module 60 is used to perform intelligent grouting control of the target grouting space along the horizontal geological slice of the P layer using the hierarchical grouting control strategy.

[0088] Furthermore, the platform is also used to implement the following functions:

[0089] The vertical lithological feature sequence is extracted from the three-dimensional geological model; the slice thickness sequence is dynamically allocated according to the vertical lithological feature sequence; the three-dimensional geological model is horizontally segmented according to the slice thickness sequence to obtain the horizontal geological slice of layer P.

[0090] Furthermore, the platform is also used to implement the following functions:

[0091] The sampling segmentation scale is 1 / K of the vertical depth of the three-dimensional geological model. The vertical lithological feature sequence is divided into K vertical lithological sub-features using the sampling segmentation scale. K stratigraphic variation coefficients are calculated based on the K vertical lithological sub-features. K slice thickness parameters are matched based on the K stratigraphic variation coefficients. Slice layering is set based on the K slice thickness parameters, and the slice thickness sequence is output.

[0092] Furthermore, the platform is also used to implement the following functions:

[0093] Multiple permeability coefficient values ​​and multiple fracture density values ​​are extracted from multiple discrete grid points within the characteristic range of the first vertical lithological sub-characteristics. After calculating the average value and standard deviation of the multiple permeability coefficient values, the permeability variation coefficient is output by dividing the average value by the standard deviation. After calculating the average value and standard deviation of the multiple fracture density values, the fracture variation coefficient is output by dividing the average value by the standard deviation. The maximum value of the permeability variation coefficient and the fracture variation coefficient is compared and taken as the first formation variation coefficient.

[0094] Furthermore, the platform is also used to implement the following functions:

[0095] The average permeability coefficient, maximum fracture density, minimum principal stress, and average groundwater temperature are extracted from the first layer of sliced ​​structural data. The minimum principal stress is used as a stress condition to match the first grouting pressure. The average permeability coefficient and maximum fracture density are used as lithological conditions to match the first grouting formula, wherein the first grouting formula consists of a first grout type, a first grout viscosity, and a first grout water-cement ratio. The average permeability coefficient, maximum fracture density, and minimum principal stress are used for parameter coupling matching to obtain the first grouting rate. The first grouting pressure, the first grouting formula, the first grouting rate, and the average groundwater temperature are used as multivariate search constraints to retrieve the first curing time. The first curing time, the first grouting pressure, the first grouting formula, and the first grouting rate constitute the first layer grouting strategy.

[0096] Furthermore, the platform is also used to implement the following functions:

[0097] Using the average permeability coefficient as the dominant characteristic of grouting speed, a benchmark grouting speed is matched and output; the maximum fracture density and minimum principal stress are used to match and obtain a coupling grouting correction coefficient; the benchmark grouting speed is corrected using the coupling grouting correction coefficient to obtain the first grouting speed.

[0098] Furthermore, the platform is also used to implement the following functions:

[0099] After performing a multi-field coupled simulation of the underground space grouting process on the first-layer horizontal geological slice using the first-layer grouting strategy, an incremental set of field variables is extracted. The incremental field variables include pore water pressure increment, stress tensor increment, temperature increment, and permeability coefficient change. An interlayer physical transfer function set is pre-constructed, and cross-layer superposition correction is performed by synchronizing the incremental set of field variables to the interlayer physical transfer function set to obtain an updated set of field variables. The updated set of field variables is then used to correct the data structure of the second-layer slice to obtain the updated data structure of the second layer.

[0100] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0101] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0102] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application intends to include such modifications and variations.

Claims

1. A multi-field coupling driven urban underground space grouting intelligent regulation and control method, characterized in that, The method includes: S1: Collect geological exploration data of the target grouting space and construct a three-dimensional geological model; S2: Horizontally divide the three-dimensional geological model into P-layer horizontal geological slices; S3: After calling the first layer slice data structure of the first layer horizontal geological slice, the first layer grouting strategy is obtained by performing multi-field coupled grouting analysis on the first layer slice data structure. S4: During the underground space grouting simulation of the first layer horizontal geological slice using the first layer grouting strategy, the parameters of the second layer horizontal geological slice are updated based on the predicted field variable increments according to the physical field coupling effect, and the second layer updated data structure is output. S5: Iterate through S3-S4 until the Pth layer of horizontal geological slice, and output the hierarchical grouting control strategy; S6: Using the hierarchical grouting control strategy, intelligent grouting control is performed along the horizontal geological slice of layer P to control the grouting in the target grouting space.

2. The multi-field coupling driven urban underground space grouting intelligent regulation method of claim 1, wherein The method of horizontally segmenting the three-dimensional geological model into P-layer horizontal geological slices includes: Extract the vertical lithological feature sequence from the three-dimensional geological model; The slice thickness sequence is dynamically assigned based on the longitudinal lithological characteristic sequence; The three-dimensional geological model is horizontally segmented according to the slice thickness sequence to obtain the P-layer horizontal geological slice.

3. The multi-field coupling driven urban underground space grouting intelligent regulation method of claim 2, wherein The method for dynamically allocating slice thickness sequences based on the longitudinal lithological characteristic sequence includes: The vertical depth of the three-dimensional geological model is used as the sampling segmentation scale (1 / K). The longitudinal lithological feature sequence is divided into K longitudinal lithological sub-features using the sampling segmentation scale. Calculate K stratigraphic variation coefficients based on the K vertical lithological sub-characteristics; After matching K slice thickness parameters with the K stratigraphic variation coefficients, slice layering is set based on the K slice thickness parameters, and the slice thickness sequence is output.

4. The multi-field coupling driven urban underground space grouting intelligent regulation method of claim 3, wherein The method for calculating K stratigraphic variation coefficients based on the K vertical lithological sub-characteristics includes: Multiple permeability coefficient values ​​and multiple fracture density values ​​of multiple discrete grid points are extracted from the feature interval of the first longitudinal lithological sub-characteristics. After calculating the average and standard deviation of the multiple permeability coefficient values, the permeability variation coefficient is output by dividing the average by the standard deviation; After calculating the average and standard deviation of the multiple fracture density values, the fracture variation coefficient is output by dividing the average by the standard deviation; The maximum value of the permeability variation coefficient and the fracture variation coefficient is taken as the first formation variation coefficient.

5. The multi-field coupling driven urban underground space grouting intelligent regulation method of claim 1, wherein After calling the first-layer slice data structure of the first-layer horizontal geological slice, the first-layer grouting strategy is obtained by performing multi-field coupled grouting analysis on the first-layer slice data structure. The method includes: The average permeability coefficient, maximum fracture density, minimum principal stress, and average groundwater temperature were extracted from the first layer of sliced ​​structural data. The minimum principal stress is used as the stress condition to match the first grouting pressure; The average permeability coefficient and maximum fracture density are used as lithological conditions to match the first grouting formula, wherein the first grouting formula consists of a first grout type, a first grout viscosity and a first grout water-cement ratio; The first grouting speed is obtained by using the average permeability coefficient, maximum fracture density and minimum principal stress for parameter coupling matching. The first grouting pressure, the first grouting formula, the first grouting speed and the average groundwater temperature are taken as multivariate search constraints to search for a first solidification time, and the first solidification time, the first grouting pressure, the first grouting formula and the first grouting speed constitute the first layer grouting strategy.

6. The multi-field coupling driven urban underground space grouting intelligent regulation method of claim 5, wherein The average permeability coefficient, the maximum fracture density and the minimum principal stress are used for parameter coupling matching to obtain a first grouting speed, and the method comprises the following steps: The average permeability coefficient is taken as a grouting speed dominant feature to match and output a reference grouting speed; The maximum fracture density and the minimum principal stress are used for matching to obtain a coupling grouting correction coefficient; The reference grouting speed is corrected by using the coupling grouting correction coefficient to obtain the first grouting speed.

7. The multi-field coupling driven urban underground space grouting intelligent regulation method according to claim 1, characterized in that, In the process of executing the underground space grouting simulation of the first layer horizontal geologic slice by using the first layer grouting strategy, parameter updating of a second layer horizontal geologic slice is performed based on a physical field coupling effect prediction field variable increment to output a second layer updated data structure, and the method comprises the following steps: After the multi-field coupling simulation of the underground space grouting process of the first layer horizontal geologic slice is performed by using the first layer grouting strategy, a field variable increment set is extracted, wherein the field variable increment comprises a pore water pressure increment, a stress tensor increment, a temperature increment and a permeability coefficient change amount; A set of interlayer physical transfer functions is pre-constructed, and cross-layer superposition correction is performed by synchronizing the field variable increment set to the set of interlayer physical transfer functions to obtain a field variable updated set; The second layer updated data structure is obtained by correcting a second layer slice data structure by using the field variable updated set.

8. The urban underground space grouting intelligent regulation and control platform driven by multi-field coupling, characterized in that, The platform is used to implement the multi-field coupling driven urban underground space grouting intelligent regulation and control method of any one of claims 1-7, and the platform comprises: A three-dimensional geologic model construction module is used to collect geologic exploration data of a target grouting space to construct a three-dimensional geologic model; A model slicing module is used to horizontally slice the three-dimensional geologic model into P layer horizontal geologic slices; A grouting analysis module is used to obtain a first layer grouting strategy by performing multi-field coupling grouting analysis on a first layer slice data structure of a first layer horizontal geologic slice after the first layer slice data structure is called; A parameter updating module is used to perform parameter updating of a second layer horizontal geologic slice based on a physical field coupling effect prediction field variable increment to output a second layer updated data structure in the process of executing the underground space grouting simulation of the first layer horizontal geologic slice by using the first layer grouting strategy; A grouting regulation and control strategy output module is used to iteratively execute the grouting analysis module-parameter updating module until the P layer horizontal geologic slice to output a layer-level grouting regulation and control strategy; A grouting intelligent regulation and control module is used to execute grouting intelligent regulation and control of the target grouting space along the P layer horizontal geologic slice by using the layer-level grouting regulation and control strategy.

Images