Intelligent grouting anti-seepage control system and method for fractured rock stratum

Abstract

The invention provides an intelligent grouting anti-seepage control system and method for a fractured rock stratum, and the method comprises the steps: carrying out the three-dimensional scanning detection of the fractured rock stratum through a sound wave CT technology, constructing the three-dimensional space information of the fractured rock stratum, recognizing the fracture presentation characteristics of the fractured rock stratum, carrying out the multi-index analysis of the fracture presentation characteristics through a preset clustering algorithm, and obtaining the fractured rock stratum. The method comprises the following steps: determining high, medium and low three-level grouting subareas, constructing and operating a grouting correlation model of the fractured rock stratum, obtaining a grouting demand corresponding to each level of grouting subarea, and controlling corresponding grouting equipment to perform grouting operation on the fractured rock stratum by using a specified grouting process. And meanwhile, the grouting effect of the grouting operation is restored and evaluated by utilizing the grouting correlation model, so that the defects that the traditional grouting construction depends on artificial experience, each link is disjointed, the construction precision is low, the effect feedback is lagged and the like are fundamentally overcome.

Description

Technical Field

[0001] This invention relates to the field of grouting and seepage prevention engineering technology for fractured rock strata, and particularly to an intelligent grouting and seepage prevention control system and method for fractured rock strata. Background Technology

[0002] In the construction of water conservancy and hydropower projects, transportation tunnels, and mining operations, seepage prevention treatment of fractured rock strata is a crucial step in ensuring the safety and stability of the project. Grouting technology, as the core method for seepage prevention treatment in fractured rock strata, directly affects the seepage resistance and service life of the project.

[0003] Current methods for grouting fractured rock formations rely heavily on manual experience for parameter setting and process control, which has many shortcomings: First, the accuracy of rock strata detection is insufficient. Traditional detection techniques are unable to accurately obtain the three-dimensional spatial information and fracture distribution characteristics of fractured rock strata, resulting in unreasonable grouting zoning. Second, the grouting parameters lack scientific basis and are mostly determined based on past engineering experience. They do not fully take into account the differences in geological conditions of different grouting zones, which can easily lead to problems of insufficient or excessive grouting. Third, the validity of historical data was not screened during the model construction process. Outdated or abnormal data can easily lead to large deviations in the constructed grouting correlation model, making it impossible to accurately guide construction. Fourth, the delayed detection of grouting effects makes it difficult to detect grouting defects in real time and adjust construction parameters accordingly, thus affecting the grouting's anti-seepage effect.

[0004] To address the aforementioned technical problems, this invention provides an intelligent grouting and seepage prevention control system and method for fractured rock strata. Summary of the Invention

[0005] This invention provides an intelligent grouting seepage prevention control system and method for fractured rock strata, which can overcome the defects of existing technologies in grouting seepage prevention construction for fractured rock strata, such as low detection accuracy, unreasonable zoning, poor model reliability, inaccurate construction control, and delayed effect detection. It provides an intelligent grouting seepage prevention control system for fractured rock strata, realizing intelligent and precise control of the entire process of grouting seepage prevention construction for fractured rock strata, and improving the grouting seepage prevention effect.

[0006] This invention provides an intelligent grouting and seepage prevention control system for fractured rock strata, comprising: The rock strata detection module is used to perform three-dimensional scanning detection of fractured rock strata using acoustic CT technology, and to construct three-dimensional spatial information of the fractured rock strata based on the reflection propagation time and wave velocity data of the fractured rock strata at different scanning frequencies. The partitioning module is used to identify the fracture presentation characteristics of the fractured rock layer in the three-dimensional spatial information, and to perform multi-index analysis on the fracture presentation characteristics using a preset clustering algorithm to determine the high, medium and low three-level grouting partitions. The model building module is used to construct a grouting association model of the fractured rock strata based on the historical grouting data, permeability coefficient, and grouting conditions corresponding to each level of grouting zone. The process execution module is used to run the grouting association model, obtain the grouting requirements corresponding to each grouting zone of the level, and control the corresponding grouting equipment to perform grouting operations on the fractured rock layer using the specified grouting process. The effect detection module is used to input the real-time water pressure information and real-time sound wave information of the grouting equipment during the grouting operation into the grouting association model, restore the grouting effect of the grouting operation, and evaluate it.

[0007] In one implementable manner, the rock strata detection module includes: The acoustic matching unit is used to deduce the known density corresponding to different rock strata regions in the fractured rock strata based on the fractured rock strata information uploaded by the user, and to deduce several estimated densities corresponding to the fractured rock strata based on the known density. Based on the acoustic sensitivity characteristics corresponding to each density, several scanning frequencies for this detection are determined. The scanning execution unit is used to control the acoustic CT device to perform dynamic scanning of the fractured rock layer according to the scanning frequency, and at the same time collect the preliminary scanning feedback signal of the fractured rock layer for each scanning acoustic wave, and construct the preliminary three-dimensional information of the fractured rock layer by combining the scanning trajectory of the acoustic CT device. The signal optimization unit is used to sample the initial scan three-dimensional information several times, identify the reflection propagation time data and wave velocity data corresponding to each sampling point in each initial scan feedback signal, and calibrate the reflection propagation time data and wave velocity data corresponding to the same sampling point using timestamps to obtain several sampling optimization information. The information reconstruction unit is used to overlay the sampling optimization information into each of the preliminary scan feedback signals, and at the same time, to interpolate and supplement the preliminary scan feedback signals according to the correlation law between rock density and wave velocity to obtain the corresponding optimized scan feedback signals, and to construct the three-dimensional spatial information of the fractured rock layer based on the optimized scan feedback signals.

[0008] In one implementable manner, the information reconstruction unit includes: The positioning processing subunit is used to identify the actual spatial location of each of the sampling optimization information in the fractured rock layer according to the scanning trajectory, and at the same time obtain the sampling point compactness corresponding to each of the actual spatial locations and determine the spatial lithological characteristics corresponding to each sampling point. The regularity analysis subunit is used to determine several interpolation supplement points of the initial scan information based on the distribution of the sampling points in the initial scan information, and to determine the relevant sampling points corresponding to each interpolation supplement point based on the correlation law between rock layer density and wave velocity and the spatial lithological characteristics corresponding to each sampling point. The data interpolation subunit is used to identify the numerical correlation weight between each interpolation supplement point and the corresponding related sampling point, determine the supplement value corresponding to each interpolation supplement point by combining the information value corresponding to each related sampling point, and use the supplement value to interpolate and supplement the interpolation supplement point to obtain the corresponding optimized scanning feedback signal. The information generation subunit constructs a voxel grid corresponding to each sampling point and each interpolation supplement point based on the optimized scanning feedback signal, arranges the voxel grid in space to generate a three-dimensional spatial structure, and inputs each optimized scanning feedback signal into the three-dimensional spatial structure to generate the three-dimensional spatial information of the fractured rock layer.

[0009] In one implementable manner, the partitioning module includes: The fracture identification unit is used to perform voxel slicing processing on the three-dimensional spatial information according to each preset specified slicing direction to obtain several spatial layer information corresponding to each preset specified slicing direction, and to identify the rock layer grayscale features and structural texture features corresponding to each spatial layer information respectively. The fracture extraction unit is used to perform comprehensive fracture identification on the grayscale features and structural texture features of the rock layer according to the information cross relationship between the spatial layering information corresponding to different preset slices, and to fuse the fracture identification results with connection relationship to determine several rock layer fractures of the fractured rock layer. The feature analysis unit is used to locate the fracture start point and fracture end point corresponding to each rock layer fracture using the spatial layering information, and at the same time identify the fracture aperture and fracture branch corresponding to each rock layer fracture, and generate the fracture presentation features of the fractured rock layer. The clustering analysis unit is used to optimize the parameters of the preset clustering algorithm according to the clustering criteria corresponding to each preset analysis index, and use the optimized preset clustering algorithm to perform clustering iteration on the fracture presentation characteristics to obtain the clustering result corresponding to each preset analysis index. The partitioning unit is used to divide the clustering results corresponding to each preset analysis index into three clustering partitions from high to low. The partitions are compared with the rock strata stability partitions in the engineering geological survey report of the fractured rock strata, and the boundaries of each partition are locally adjusted to obtain the high grouting partition, medium grouting partition and low grouting partition of the fractured rock strata.

[0010] In one implementable manner, the model building module includes: The data acquisition and processing unit is used to acquire historical grouting data, permeability coefficient data and grouting condition data corresponding to each grouting zone, clean each data, and perform outlier detection on the cleaned data to obtain the outlier corresponding to each cleaned data. Based on the outlier anomaly format corresponding to each outlier and the data attributes of the corresponding cleaned data, several data items to be optimized are determined for each cleaned data. The data optimization unit is used to find several valid optimized data values ​​corresponding to each data item to be optimized in the historical grouting data, the permeability coefficient data and the grouting condition data, and input each valid optimized data value into the corresponding data item to be optimized for optimization and verification, so as to obtain the valid data corresponding to each cleaning data. The model training unit is used to construct an initial grouting association model of the fractured rock layer based on the data relationship between different valid data, perform cross-validation training on the model parameters in the initial grouting association model, and generate training logs. The model verification unit is used to input the historical grouting data into the initial grouting association model to obtain several verification data, identify valid log information that matches the verification data in the training log, and modify the initial grouting association model using the valid log information to obtain the grouting association model of the fractured rock layer.

[0011] In one implementable manner, the process execution module includes: The demand analysis unit is used to run the grouting correlation model under different grouting speed, grouting pressure, grout water-cement ratio and grouting time as simulation conditions to obtain the grouting impact of each simulation condition on different grouting zones and determine the grouting demand corresponding to each grouting zone. The preparation guidance unit is used to generate equipment control instructions corresponding to each level of grouting zone according to the grouting requirements, adjust the opening of the cement storage equipment and water storage equipment to regulate the feeding rate, start the stirring device to mix the grout, collect the viscosity data of the grout in real time, and adjust the speed of the stirring device according to the viscosity data to obtain qualified grout. The execution supervision unit is used to inject the qualified grout into the grouting equipment to perform grouting operation on the fractured rock layer using the specified grouting process, collect the operating data of the grouting equipment in real time, identify the numerical deviation between the operating data and the equipment control command, and adjust the parameters of the grouting equipment using the numerical deviation; The grouting switching unit is used to collect the orifice pressure data of the previous grouting section after the grouting operation of the current grouting section is completed, and to determine whether the inter-section sealing quality of the previous grouting section is qualified based on the orifice pressure data. If so, the unit controls the grouting equipment to switch to the next grouting section for grouting operation.

[0012] In one implementable manner, the effect detection module includes: The real-time acquisition unit is used to acquire the real-time water pressure information of the grouting equipment and the real-time acoustic information of the fractured rock layer, respectively, and to remove the pipeline pressure fluctuation noise in the real-time water pressure information and the environmental interference noise in the real-time acoustic information to obtain the noise-reduced effective water pressure data and effective acoustic data. The effective water pressure data and effective acoustic data are aligned to the same time node to obtain aligned data. The effect restoration unit is used to input the alignment data into the grouting association model to simulate grouting, obtain the grout diffusion information and fracture filling degree of the fractured rock layer, generate a grouting visual image corresponding to each grouting moment, and evaluate the effect of each grouting visual image. The effect feedback unit is used to extract the key indicators that did not meet the standards in the effect evaluation, generate parameter adjustment suggestions, and display them when the effect evaluation shows that it is unqualified.

[0013] One feasible approach also includes: An information supplementation unit is used to evaluate the integrity of the fractured rock strata information. When the integrity of the fractured rock strata information is lower than a preset error threshold, a preset geological lithology database is invoked, and historical compactness data of the same type of rock strata in the same region are matched according to the geographical coordinates and stratigraphic age of the area where the fractured rock strata are located. The similarity between densities is estimated based on the historical density data, and historical density data with similarity reaching a preset standard are selected as supplementary data to compensate for the fractured rock strata information.

[0014] One feasible approach also includes: The deep screening unit is used to extract the collection time information corresponding to each historical grouting data, and analyze the time weight of historical data at different collection times in combination with the geological evolution law of fractured rock strata. Historical data with a time weight less than a preset weight threshold are removed.

[0015] This invention provides a method for intelligent grouting and seepage control in fractured rock formations, comprising: Step 1: Use acoustic CT technology to perform three-dimensional scanning detection on the fractured rock layer, and construct the three-dimensional spatial information of the fractured rock layer based on the reflection propagation time and wave velocity data of the fractured rock layer at different scanning frequencies; Step 2: Identify the fracture features of the fractured rock strata in the three-dimensional spatial information, and use a preset clustering algorithm to perform multi-index analysis on the fracture features to determine the high, medium and low grouting zones; Step 3: Based on the historical grouting data, permeability coefficient, and grouting conditions corresponding to each grouting zone, construct the grouting correlation model of the fractured rock strata; Step 4: Run the grouting association model to obtain the grouting requirements corresponding to each grouting zone of the specified level, and control the corresponding grouting equipment to perform grouting operations on the fractured rock layer using the specified grouting process; Step 5: Input the real-time water pressure information and real-time acoustic information of the grouting equipment during the grouting operation into the grouting association model to restore the grouting effect of the grouting operation and evaluate it.

[0016] The beneficial effects of this invention are as follows: To fundamentally overcome the shortcomings of traditional grouting construction, such as reliance on manual experience, disconnect between various stages, low construction precision, and delayed feedback, and to improve the accuracy and reliability of grouting construction and ensure the quality of seepage prevention projects, this invention first uses sonic CT technology to perform three-dimensional scanning detection of fractured rock strata. Combined with reflection propagation time and wave velocity data, three-dimensional spatial information is constructed to more comprehensively and accurately restore the basic characteristics of the internal structure and fracture distribution of the rock strata, providing high-quality and reliable data support for subsequent zoning. Then, based on the three-dimensional spatial information, the fracture characteristics are accurately identified. Through a preset clustering algorithm, multi-index comprehensive analysis is performed to achieve a scientific division of high, medium, and low-level grouting zones. The zoning results can accurately match the actual geological conditions of the fractured rock strata, providing a clear basis for subsequent differentiated grouting construction, improving the targeting and rationality of grouting construction, avoiding resource waste, and further relying on each level... A grouting correlation model is constructed based on historical grouting data, permeability coefficients, and grouting conditions corresponding to each grouting zone. This model quantitatively correlates geological conditions with grouting parameters, freeing the determination of grouting requirements from reliance on manual experience and better aligning with the actual geological characteristics of different zones. This provides scientific and precise parameter guidance for subsequent process execution, laying the foundation for precise construction. Finally, by running the grouting correlation model, the personalized grouting requirements of each level zone are obtained, thereby controlling the grouting equipment to execute the prescribed grouting process. This achieves standardization and automation of grouting construction, precisely controlling key construction parameters such as grout preparation, grouting pressure, and grouting duration. This effectively reduces human error, ensures the continuity and standardization of the construction process, and comprehensively improves the quality and efficiency of grouting construction. It can promptly detect construction defects such as insufficient grout diffusion and inadequate crack filling, and provides adjustment basis for the process execution module, enabling real-time monitoring and evaluation of grouting effects.

[0017] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings.

[0018] 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

[0019] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings: Figure 1 This is a schematic diagram of the composition of the intelligent grouting and seepage prevention control system for fractured rock strata in an embodiment of the present invention; Figure 2 This is a schematic diagram of the composition of the rock stratum detection module in the intelligent grouting and seepage prevention control system for fractured rock strata in an embodiment of the present invention; Figure 3 This is a schematic diagram illustrating the workflow of the intelligent grouting seepage prevention control method for fractured rock strata in an embodiment of the present invention. Detailed Implementation

[0020] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0021] Example 1: This example provides an intelligent grouting and seepage prevention control system for fractured rock strata, such as... Figure 1 As shown, it includes: The rock strata detection module is used to perform three-dimensional scanning detection of fractured rock strata using acoustic CT technology, and to construct three-dimensional spatial information of the fractured rock strata based on the reflection propagation time and wave velocity data of the fractured rock strata at different scanning frequencies. The partitioning module is used to identify the fracture presentation characteristics of the fractured rock layer in the three-dimensional spatial information, and to perform multi-index analysis on the fracture presentation characteristics using a preset clustering algorithm to determine the high, medium and low three-level grouting partitions. The model building module is used to construct a grouting association model of the fractured rock strata based on the historical grouting data, permeability coefficient, and grouting conditions corresponding to each level of grouting zone. The process execution module is used to run the grouting association model, obtain the grouting requirements corresponding to each grouting zone of the level, and control the corresponding grouting equipment to perform grouting operations on the fractured rock layer using the specified grouting process. The effect detection module is used to input the real-time water pressure information and real-time sound wave information of the grouting equipment during the grouting operation into the grouting association model, restore the grouting effect of the grouting operation, and evaluate it.

[0022] In this example, three-dimensional scanning detection refers to the process of using acoustic CT technology to scan and detect fractured rock layers from all directions and multiple angles, obtain acoustic response data at different locations of the rock layers, and achieve a comprehensive capture of the spatial distribution characteristics of the rock layers. In this example, the reflection propagation time represents the total time it takes for the sound waves emitted by the acoustic CT device to propagate through the fractured rock layer, be reflected by the rock layer interface, and return to the receiving device. In this example, the wave velocity data represents the speed at which sound waves propagate through fractured rock strata; In this example, the three-dimensional spatial information represents a three-dimensional digital model that reflects the spatial location, internal structure, and fracture distribution of fractured rock strata, based on the reflection propagation time and wave velocity data obtained from three-dimensional scanning detection. In this example, the fracture characteristics represent the specific properties and distribution of fractures in the fractured rock strata, including fracture aperture, extension length, branching, distribution density, and connectivity. In this example, multi-index analysis refers to an analytical method that takes multiple dimensions of parameters that exhibit the characteristics of fractures as the analysis object and combines them with preset evaluation criteria to comprehensively judge the priority of rock grouting needs. In this example, the permeability coefficient represents a parameter characterizing the water permeability of fractured rock strata, and its value directly reflects the seepage prevention performance of the rock strata. In this example, grouting conditions refer to various environmental and engineering factors that affect the grouting effect during the grouting construction process, including the initial moisture content of the rock strata, ambient temperature and humidity, and geological stability of the construction area. In this example, the grouting correlation model represents a quantitative correlation model between grouting parameters and grouting effects established by integrating historical grouting data, permeability coefficients, and grouting conditions corresponding to grouting zones of various levels. In this example, the grouting requirement represents the personalized construction parameter requirements for different levels of grouting zones, combined with the output of the grouting association model, including grouting pressure, grout water-cement ratio, grouting time, grouting volume, etc. In this example, the grouting process is defined as a standardized grouting operation procedure based on engineering specifications and grouting requirements, including grout preparation standards, grouting equipment operation specifications, grouting section division and switching procedures, etc. In this example, the real-time water pressure information represents the pressure data monitored in real time in the grouting equipment pipeline and grouting hole during the grouting operation, reflecting the grout diffusion status and pipeline patency. In this example, the real-time acoustic information represents the acoustic signals of the fractured rock strata and grouting area collected in real time during the grouting operation. Its changes can reflect the process and effect of the grout filling the cracks.

[0023] The working principle and beneficial effects of the above technical solution are as follows: To fundamentally overcome the shortcomings of traditional grouting construction, such as reliance on manual experience, disconnect between various stages, low construction accuracy, and delayed feedback, and to improve the accuracy and reliability of grouting construction and ensure the quality of seepage prevention projects, the following approach is first used: 3D scanning detection of fractured rock strata is performed using sonic CT technology. Combined with reflection propagation time and wave velocity data, 3D spatial information is constructed to more comprehensively and accurately restore the basic characteristics of the internal structure and fracture distribution of the rock strata, providing high-quality and reliable data support for subsequent zoning. Then, based on the 3D spatial information, the fracture characteristics are accurately identified. Through a preset clustering algorithm, multi-index comprehensive analysis is performed to achieve a scientific division of high, medium, and low-level grouting zones. The zoning results can accurately match the actual geological conditions of the fractured rock strata, providing a clear basis for subsequent differentiated grouting construction, improving the targeting and rationality of grouting construction, avoiding resource waste, and further relying on various... A grouting correlation model is constructed based on historical grouting data, permeability coefficients, and grouting conditions corresponding to different grouting zones. This model quantitatively correlates geological conditions with grouting parameters, freeing the determination of grouting requirements from reliance on manual experience and better aligning with the actual geological characteristics of different zones. This provides scientific and precise parameter guidance for subsequent process execution, laying the foundation for precise construction. Finally, by running the grouting correlation model, the personalized grouting requirements of each zone are obtained, thereby controlling the grouting equipment to execute the prescribed grouting process. This achieves standardization and automation of grouting construction, precisely controlling key construction parameters such as grout preparation, grouting pressure, and grouting duration. This effectively reduces human error, ensures the continuity and standardization of the construction process, and comprehensively improves the quality and efficiency of grouting construction. It can promptly detect construction defects such as insufficient grout diffusion and inadequate crack filling, and provides adjustment basis for the process execution module, enabling real-time monitoring and evaluation of grouting effects.

[0024] Example 2: Based on Example 1, the intelligent grouting and seepage prevention control system for fractured rock strata, the rock strata detection module, such as... Figure 2 As shown, it includes: The acoustic matching unit is used to deduce the known density corresponding to different rock strata regions in the fractured rock strata based on the fractured rock strata information uploaded by the user, and to deduce several estimated densities corresponding to the fractured rock strata based on the known density. Based on the acoustic sensitivity characteristics corresponding to each density, several scanning frequencies for this detection are determined. The scanning execution unit is used to control the acoustic CT device to perform dynamic scanning of the fractured rock layer according to the scanning frequency, and at the same time collect the preliminary scanning feedback signal of the fractured rock layer for each scanning acoustic wave, and construct the preliminary three-dimensional information of the fractured rock layer by combining the scanning trajectory of the acoustic CT device. The signal optimization unit is used to sample the initial scan three-dimensional information several times, identify the reflection propagation time data and wave velocity data corresponding to each sampling point in each initial scan feedback signal, and calibrate the reflection propagation time data and wave velocity data corresponding to the same sampling point using timestamps to obtain several sampling optimization information. The information reconstruction unit is used to overlay the sampling optimization information into each of the preliminary scan feedback signals, and at the same time, to interpolate and supplement the preliminary scan feedback signals according to the correlation law between rock density and wave velocity to obtain the corresponding optimized scan feedback signals, and to construct the three-dimensional spatial information of the fractured rock layer based on the optimized scan feedback signals.

[0025] In this example, the fractured rock strata information represents the basic geological information related to the target fractured rock strata uploaded by the user, including but not limited to rock strata type, stratigraphic distribution range, approximate location of known fractures, and some geological parameters obtained from previous explorations. It is the basis for the acoustic matching unit to deduce density and determine scanning frequency. In this example, the known density refers to the density-related parameters of a specific region in the fractured rock layer, which can be directly extracted from the user-uploaded information on fractured rock layers or clearly obtained through simple derivation, and characterizes the compactness of the rock layer particles in that region; In this example, the estimated density represents the estimated density of other undefined areas in the fractured rock layer, derived by the acoustic matching unit based on the known density and in combination with the stratigraphic continuity and lithological gradation of the fractured rock layer. In this example, the acoustic sensitivity characteristics represent the response characteristics of rock layers with different densities to sound waves of different frequencies, including the degree of sound wave propagation attenuation, reflection intensity, and propagation speed variation in the rock layers. In this example, dynamic scanning refers to the process by which the scanning execution unit controls the acoustic CT equipment to perform continuous and comprehensive scanning and detection of fractured rock strata according to a preset movement trajectory and scanning rhythm. In this example, the initial scan 3D information represents the 3D framework information that the scanning execution unit initially constructs, reflecting the approximate spatial outline and basic structure of the fractured rock strata, by combining the initial scan feedback signal collected during the dynamic scan process and the scan trajectory of the acoustic CT equipment. In this example, the preliminary scan feedback signal represents the original signal received by the equipment after the sound waves emitted by the acoustic CT device act on the fractured rock layer and are reflected and refracted at the rock layer interface. In this example, timestamp calibration means that the signal optimization unit adds a unified timestamp to the reflection propagation time data and wave velocity data corresponding to the same sampling point. Through time synchronization processing, the mismatch between the two types of data caused by the difference in data acquisition time is eliminated, ensuring that the core data of the same sampling point can be accurately matched. In this example, the interpolation supplementation represents the process by which the information reconstruction unit calculates supplementary data for blank areas in the initial scan three-dimensional information using mathematical interpolation methods, based on the correlation between rock density and wave velocity and existing sampling optimization information. In this example, the sampling optimization information represents the collection of reflection propagation duration data and wave velocity data corresponding to each sampling point extracted by the signal optimization unit after sampling the initial scan three-dimensional information. It is a high-quality core detection data after invalid data has been removed and deviations have been corrected.

[0026] The working principle and beneficial effects of the above technical solution are as follows: To improve the accuracy, completeness, and reliability of three-dimensional spatial information of fractured rock strata, the known and estimated densities are first derived from the fractured rock strata information uploaded by the user. The scanning frequency is then determined by combining the acoustic wave sensitivity characteristics corresponding to the density, achieving personalized adaptation of the scanning frequency. This avoids the defect of fixed-frequency scanning being unable to adapt to rock strata regions with different densities, ensuring that the scanning acoustic waves can effectively penetrate different rock strata regions and produce a clear response, improving the effectiveness and recognizability of the scanning signal. Then, based on the adapted scanning frequency, the acoustic CT equipment is controlled to perform dynamic scanning. The initial three-dimensional information is constructed by combining the scanning trajectory, enabling comprehensive and blind-spot-free detection of the fractured rock strata. Further, through multiple... The sampling process extracts reflection propagation time and wave velocity data from sampling points. Timestamps are used to calibrate two types of data from the same sampling point, effectively eliminating data deviations caused by asynchronous sampling. Valid sampling data is accurately selected, forming optimized sampling information. This improves the accuracy of core detection data and provides data assurance for the precision of information reconstruction. Finally, the optimized sampling information is overlaid onto the initial scan feedback signal, and interpolation is performed based on the correlation between rock density and wave velocity to fill in the blank areas of the initial scan data, improving the completeness of the scan information. This accurately reflects the spatial distribution and internal structure of the fractured rock layers, solving the problem of incomplete rock layer feature reconstruction due to data sparsity in traditional detection methods. This provides core data support for the precise work of subsequent modules.

[0027] Example 3: Based on Example 2, the information reconstruction unit of the intelligent grouting and seepage prevention control system for fractured rock strata includes: The positioning processing subunit is used to identify the actual spatial location of each of the sampling optimization information in the fractured rock layer according to the scanning trajectory, and at the same time obtain the sampling point compactness corresponding to each of the actual spatial locations and determine the spatial lithological characteristics corresponding to each sampling point. The regularity analysis subunit is used to determine several interpolation supplement points of the initial scan information based on the distribution of the sampling points in the initial scan information, and to determine the relevant sampling points corresponding to each interpolation supplement point based on the correlation law between rock layer density and wave velocity and the spatial lithological characteristics corresponding to each sampling point. The data interpolation subunit is used to identify the numerical correlation weight between each interpolation supplement point and the corresponding related sampling point, determine the supplement value corresponding to each interpolation supplement point by combining the information value corresponding to each related sampling point, and use the supplement value to interpolate and supplement the interpolation supplement point to obtain the corresponding optimized scanning feedback signal. The information generation subunit constructs a voxel grid corresponding to each sampling point and each interpolation supplement point based on the optimized scanning feedback signal, arranges the voxel grid in space to generate a three-dimensional spatial structure, and inputs each optimized scanning feedback signal into the three-dimensional spatial structure to generate the three-dimensional spatial information of the fractured rock layer.

[0028] In this example, the actual spatial location represents the real three-dimensional coordinate position in the target fractured rock layer corresponding to each sampled optimization information; In this example, spatial lithological characteristics represent the inherent properties of the rock strata corresponding to the actual spatial location of the sampling point, including rock strata type, grain size, degree of cementation, mineral composition, and other characteristics related to the physical properties of the rock strata. In this example, the interpolation supplementary points represent the regions and points in the initial scan data that are blank or missing, identified by the regularity analysis subunit based on the distribution of sampling points in the initial scan 3D information. In this example, the relevant sampling points represent, for each interpolation supplement point, effective sampling points selected from existing, location-processed sampling points that have similar lithology, similar density, and are spatially close to the interpolation supplement point, based on the correlation between rock density and wave velocity and spatial lithological characteristics. In this example, the numerical correlation weight represents the influence coefficient of the information value of each relevant sampling point on the supplementary value of the interpolation supplementary point. It is determined based on factors such as the spatial distance between the relevant sampling point and the interpolation supplementary point, lithological similarity, and density difference. The higher the correlation, the greater the weight. In this example, the voxel grid represents the basic three-dimensional pixel unit used to construct the three-dimensional spatial structure. Each voxel grid corresponds to a fixed spatial volume range, which can store the optimized scan feedback signal data within that range. In this example, the three-dimensional spatial structure represents a three-dimensional framework structure that is consistent with the spatial morphology of the target fractured rock strata, formed by arranging the voxel meshes corresponding to all sampling points and interpolation supplement points in an orderly manner according to their actual spatial positions.

[0029] The working principle and beneficial effects of the above technical solution are as follows: To ensure the accuracy and reliability of the entire grouting and seepage prevention control system, the actual spatial location of the sampling optimization information is first accurately locked through the scanning trajectory. At the same time, the density of the sampling points is obtained and the spatial lithological characteristics are determined, realizing the deep binding of core detection data with physical spatial location and rock layer properties. Then, based on the distribution of sampling points, interpolation supplement points are scientifically determined. Combining the correlation law between rock layer density and wave velocity and spatial lithological characteristics, relevant sampling points are matched to achieve the accuracy of interpolation supplementation. This avoids invalid calculations caused by blindly setting supplement points and ensures that the lithological and density characteristics of relevant sampling points and supplement points are consistent. Furthermore, supplementary values ​​are calculated by identifying numerical correlation weights and completing interpolation supplementation. Weights are allocated according to the correlation degree between relevant sampling points and supplementary points, making the supplementary values ​​more consistent with the actual characteristics of the rock layers. This effectively fills the blank areas of the initial scanning data and improves the integrity and continuity of the scanning feedback signal. Finally, a three-dimensional spatial structure is constructed using voxel mesh and the optimized scanning feedback signal is imported to realize the digital and visual reconstruction of the three-dimensional information of the fractured rock layer. This makes it convenient for subsequent modules to intuitively identify the distribution and development characteristics of fractures and improves the convenience of data application.

[0030] Example 4: Based on Example 1, the intelligent grouting and seepage prevention control system for fractured rock strata includes a zoning module comprising: The fracture identification unit is used to perform voxel slicing processing on the three-dimensional spatial information according to each preset specified slicing direction to obtain several spatial layer information corresponding to each preset specified slicing direction, and to identify the rock layer grayscale features and structural texture features corresponding to each spatial layer information respectively. The fracture extraction unit is used to perform comprehensive fracture identification on the grayscale features and structural texture features of the rock layer according to the information cross relationship between the spatial layering information corresponding to different preset slices, and to fuse the fracture identification results with connection relationship to determine several rock layer fractures of the fractured rock layer. The feature analysis unit is used to locate the fracture start point and fracture end point corresponding to each rock layer fracture using the spatial layering information, and at the same time identify the fracture aperture and fracture branch corresponding to each rock layer fracture, and generate the fracture presentation features of the fractured rock layer. The clustering analysis unit is used to optimize the parameters of the preset clustering algorithm according to the clustering criteria corresponding to each preset analysis index, and use the optimized preset clustering algorithm to perform clustering iteration on the fracture presentation characteristics to obtain the clustering result corresponding to each preset analysis index. The partitioning unit is used to divide the clustering results corresponding to each preset analysis index into three clustering partitions from high to low. The partitions are compared with the rock strata stability partitions in the engineering geological survey report of the fractured rock strata, and the boundaries of each partition are locally adjusted to obtain the high grouting partition, medium grouting partition and low grouting partition of the fractured rock strata.

[0031] In this example, the preset slicing direction refers to a fixed angle or orientation that is set in advance for voxel slicing of the three-dimensional spatial information of the fractured rock layer; In this example, the spatial layering information represents the set of rock strata spatial data corresponding to each slice obtained after voxel slicing the three-dimensional spatial information according to a preset slicing direction. Each layer of data corresponds to the cross-sectional information of the rock strata at a certain depth or orientation. In this example, the grayscale features of the rock strata represent the distribution characteristics of grayscale values ​​in different regions of the rock strata in the spatial stratification information. In this example, structural texture features represent the regular texture morphology features presented on the surface or inside of rock strata in spatial layering information, such as bedding texture, fracture extension texture, and grain distribution texture. In this example, the information cross relationship represents the correlation and complementarity between spatial layering information corresponding to different preset slice directions; In this example, fracture comprehensive identification refers to the process of combining spatial layering information from multiple slice directions, utilizing the cross-relationships between various information to integrate and analyze the grayscale characteristics and structural texture characteristics of rock strata, thereby accurately determining the existence, extension trajectory, and connectivity of fractures. In this example, rock strata fractures refer to cracks or voids that exist within the rock and are identified from fractured rock strata through fracture synthesis. In this example, the fracture initiation location represents the specific three-dimensional coordinate position of the starting end of each rock layer fracture in the three-dimensional space of the fractured rock layer; In this example, the fracture endpoint position represents the specific three-dimensional coordinate position of the termination end of each rock layer fracture in the three-dimensional space of the fractured rock layer. In this example, fracture aperture represents the width of the fracture in the rock strata; In this example, the fracture branches represent secondary fractures extending from the main fracture. The more branches there are, the more complex the fracture development is, and the higher the difficulty and requirements of grouting. In this example, the fracture feature representation is a comprehensive feature dataset that fully reflects the overall development state of fractures after integrating the core attributes such as the starting point, ending point, aperture, and branches of fractures in each rock stratum. In this example, clustering iteration represents the process by which the clustering analysis unit uses an optimized preset clustering algorithm to perform multiple cyclic clustering analyses on the characteristics of the cracks. Through feedback adjustments of the clustering results in each round, the clustering accuracy is gradually optimized, and finally a stable and accurate clustering result is obtained. In this example, local adjustment refers to the process by which the zoning determination unit, after comparing the three-level zoning obtained from clustering with the rock strata stability zoning in the engineering geological survey report, fine-tunes the zoning boundaries for local areas where the boundaries of the two do not coincide or the zoning ranges do not match.

[0032] The working principle and beneficial effects of the above technical solution are as follows: To significantly improve the targeting and rationality of grouting construction and avoid waste of grouting resources, firstly, voxel slicing is performed on the three-dimensional spatial information through multiple preset specified slicing directions. Simultaneously, the grayscale characteristics and structural texture characteristics of rock strata in each spatial layer are identified, achieving multi-dimensional and all-round capture of fracture features. Then, based on the information cross-relationship of spatial layering information in different slicing directions, comprehensive fracture identification is performed. At the same time, fracture identification results with connectivity are integrated, solving the problem of fragmented and discontinuous fractures in single-slice direction identification. This further accurately locates the starting and ending points of fractures and simultaneously identifies fracture aperture and branches. The algorithm generates core attributes and fracture characteristics, achieving the quantification and integration of fracture features and avoiding the problem of chaotic and disordered fracture features. Further optimization of algorithm parameters is achieved based on preset analysis indicators and clustering standards. The optimized clustering algorithm then iterates through the fracture characteristics, ensuring the relevance and accuracy of the clustering results. Finally, the clustering results are divided into three levels of partitions, which are compared and locally adjusted in conjunction with the rock strata stability partitions in the engineering geological survey report. This avoids the potential for pure algorithm clustering to deviate from actual geological conditions, ensuring that the final high, medium, and low grouting partition boundaries are precise and closely match the actual engineering situation, providing a practical and feasible partitioning basis for subsequent differentiated grouting construction.

[0033] Example 5: Based on Example 1, the intelligent grouting and seepage prevention control system for fractured rock strata includes a model construction module comprising: The data acquisition and processing unit is used to acquire historical grouting data, permeability coefficient data and grouting condition data corresponding to each grouting zone, clean each data, and perform outlier detection on the cleaned data to obtain the outlier corresponding to each cleaned data. Based on the outlier anomaly format corresponding to each outlier and the data attributes of the corresponding cleaned data, several data items to be optimized are determined for each cleaned data. The data optimization unit is used to find several valid optimized data values ​​corresponding to each data item to be optimized in the historical grouting data, the permeability coefficient data and the grouting condition data, and input each valid optimized data value into the corresponding data item to be optimized for optimization and verification, so as to obtain the valid data corresponding to each cleaning data. The model training unit is used to construct an initial grouting association model of the fractured rock layer based on the data relationship between different valid data, perform cross-validation training on the model parameters in the initial grouting association model, and generate training logs. The model verification unit is used to input the historical grouting data into the initial grouting association model to obtain several verification data, identify valid log information that matches the verification data in the training log, and modify the initial grouting association model using the valid log information to obtain the grouting association model of the fractured rock layer.

[0034] In this example, historical grouting data represents the construction data generated in past grouting projects of the same type in fractured rock strata corresponding to each grouting zone. In this example, the permeability coefficient data represents quantitative parameter data characterizing the water permeability of the fractured rock layer corresponding to each grouting zone; In this example, the grouting condition data represents the various environmental and engineering prerequisite conditions that affect the grouting construction effect corresponding to each level of grouting zone; In this example, outlier detection refers to the process by which the data acquisition and processing unit analyzes the cleaned historical data, identifies and filters out abnormal data (i.e., outliers) that deviate from the overall data distribution range and do not conform to the actual logic of the project. In this example, the outlier anomaly format represents the specific anomaly form or data characteristic presented by the outlier value; In this example, the data item to be optimized represents the data attributes of the acquisition and processing unit that combine the abnormal format of outliers with the corresponding cleaned data; In this example, optimization verification means that the data optimization unit substitutes the found valid optimized data values ​​into the data item to be optimized, and then verifies the rationality, accuracy and applicability of the optimized data by comparing it with the actual engineering standards, similar data characteristics or preset verification rules. In this example, multiple nonlinear regression is a data analysis technique used to analyze the nonlinear relationships between multiple independent variables and the dependent variable. In this example, the initial grouting correlation model represents the prototype of the model training unit, which is obtained through multivariate nonlinear regression analysis based on effective data from each level of zoning, and preliminarily characterizes the correlation between grouting parameters and geological conditions. In this example, cross-validation training means that the model training unit divides the effective data into training set and validation set, and performs model training and parameter validation by using different data subsets in multiple rounds. In this example, valid log information refers to log entries in the training logs generated during model training that match the validation data obtained by the model validation unit and reflect key information such as parameter adjustments, error changes, and data fitting effects during model training.

[0035] The working principle and beneficial effects of the above technical solution are as follows: To improve the intelligence level of the entire grouting and seepage prevention control system, historical data is first accurately collected for each grouting zone. Through dual processing of data cleaning and outlier detection, duplicate, erroneous, and abnormal data are effectively eliminated. Simultaneously, by combining outlier formats and data attributes, data items to be optimized are identified, achieving preliminary purification and problem localization of the original data. Then, effective optimized data values ​​are precisely found for the data items to be optimized and optimized and verified, achieving targeted repair and quality improvement of problematic data. Furthermore, multivariate nonlinear regression technology is used to conduct targeted regression analysis on the effective data of each zone, accurately capturing… By capturing the complex nonlinear correlation between grouting data and geological conditions, and combining cross-validation training to optimize model parameters, the model effectively avoids overfitting or underfitting. Finally, the initial model is validated using historical grouting data, and the model is corrected by matching effective log information. This effectively identifies parameter deviations in the initial model that do not match the actual project, and the root causes of the problems are traced and accurately corrected through log information, ensuring the reliability and practicality of the final output grouting correlation model. This avoids inaccurate construction parameters due to model deviations, thus effectively solving the core problems of inconsistent data quality, poor model adaptability to regional geological conditions, and difficulty in guaranteeing model reliability in the traditional model construction process.

[0036] Example 6: Based on Example 1, the intelligent grouting and seepage prevention control system for fractured rock strata, the process execution module includes: The demand analysis unit is used to run the grouting correlation model under different grouting speed, grouting pressure, grout water-cement ratio and grouting time as simulation conditions to obtain the grouting impact of each simulation condition on different grouting zones and determine the grouting demand corresponding to each grouting zone. The preparation guidance unit is used to generate equipment control instructions corresponding to each level of grouting zone according to the grouting requirements, adjust the opening of the cement storage equipment and water storage equipment to regulate the feeding rate, start the stirring device to mix the grout, collect the viscosity data of the grout in real time, and adjust the speed of the stirring device according to the viscosity data to obtain qualified grout. The execution supervision unit is used to inject the qualified grout into the grouting equipment to perform grouting operation on the fractured rock layer using the specified grouting process, collect the operating data of the grouting equipment in real time, identify the numerical deviation between the operating data and the equipment control command, and adjust the parameters of the grouting equipment using the numerical deviation; The grouting switching unit is used to collect the orifice pressure data of the previous grouting section after the grouting operation of the current grouting section is completed, and to determine whether the inter-section sealing quality of the previous grouting section is qualified based on the orifice pressure data. If so, the unit controls the grouting equipment to switch to the next grouting section for grouting operation.

[0037] In this example, the equipment control instructions represent a set of instructions generated by the preparation guidance unit based on the grouting requirements corresponding to each level of grouting zone, used to control the operation of grouting-related equipment; In this example, the opening degree adjustment of the feed rate means controlling the feeding speed of cement and water by adjusting the opening degree of the feed valves on the cement storage equipment and the water storage equipment; In this example, the numerical deviation represents the difference between the actual operating data of the grouting equipment collected by the execution supervision unit and the preset parameter value in the equipment control command output by the preparation guidance unit. In this example, the inter-segment sealing quality refers to the quality attributes such as the airtightness and firmness of the sealing structure between adjacent grouting segments after the current grouting segment has been completed in the segmented grouting construction.

[0038] The working principle and beneficial effects of the above technical solution are as follows: To improve the construction quality and efficiency of the entire grouting and seepage prevention project, a grouting correlation model is first run under multiple simulation conditions to analyze the impact of different parameters on grouting in each grade zone. Then, targeted equipment control commands are generated according to grouting requirements to precisely regulate the feed rate and stirring speed. Combined with real-time viscosity data, the grout preparation process is dynamically optimized, achieving standardized and precise preparation of qualified grout. Furthermore, during the grouting operation, equipment operation data is collected in real time to accurately identify numerical deviations and dynamically adjust equipment parameters, effectively avoiding deviations in construction parameters caused by equipment operation fluctuations and subtle changes in geological conditions. This ensures that the grouting operation strictly follows the prescribed grouting process, significantly improving the stability and accuracy of grouting construction. Finally, the quality of inter-section sealing is verified by orifice pressure data. Only after passing the verification can the process be switched to the next grouting section, achieving standardized and quality-controllable switching of grouting sections. This method avoids the leakage risks at the joints between sections caused by traditional direct switching, ensuring tight connections between each grouting section and further guaranteeing the seepage prevention integrity of the entire grouting area.

[0039] Example 7: Based on Example 1, the intelligent grouting and seepage prevention control system for fractured rock strata includes an effect detection module comprising: The real-time acquisition unit is used to acquire the real-time water pressure information of the grouting equipment and the real-time acoustic information of the fractured rock layer, respectively, and to remove the pipeline pressure fluctuation noise in the real-time water pressure information and the environmental interference noise in the real-time acoustic information to obtain the noise-reduced effective water pressure data and effective acoustic data. The effective water pressure data and effective acoustic data are aligned to the same time node to obtain aligned data. The effect restoration unit is used to input the alignment data into the grouting association model to simulate grouting, obtain the grout diffusion information and fracture filling degree of the fractured rock layer, generate a grouting visual image corresponding to each grouting moment, and evaluate the effect of each grouting visual image. The effect feedback unit is used to extract the key indicators that did not meet the standards in the effect evaluation, generate parameter adjustment suggestions, and display them when the effect evaluation shows that it is unqualified.

[0040] In this example, pipeline pressure fluctuation noise refers to the interference signal generated by factors related to non-real grouting pressure, such as unstable grout flow in the grouting pipeline, pipeline vibration, and equipment operation fluctuations, during the process of collecting real-time water pressure information of the grouting equipment. In this example, environmental interference noise refers to the interference sound wave signals generated by factors unrelated to the rock strata and grouting process, such as mechanical vibration at the construction site, personnel activities, and external natural environmental sounds, during the process of collecting real-time sound wave information of fractured rock strata. In this example, the effective water pressure data represents the water pressure data that truly reflects the core grouting status, such as the operating pressure of the grouting equipment and the grout diffusion pressure, after the real-time acquisition unit has processed the original real-time water pressure information to remove interference signals such as pipeline pressure fluctuation noise. In this example, the effective acoustic data represents the acoustic data that truly reflects the changes in the internal structure of the fractured rock strata and the process of grout filling the cracks after the real-time acquisition unit has processed the original real-time acoustic information to reduce noise and remove interference signals such as environmental noise. In this example, the same time node indicates that the real-time acquisition unit sets a unified time mark reference for the effective water pressure data and the effective acoustic wave data, so that the two types of data can correspond one-to-one in the time dimension. In this example, the grout diffusion information represents the core information reflecting the diffusion range, diffusion rate, and diffusion path of the grout within the fractured rock strata, obtained through simulation analysis using a grouting correlation model. In this example, the degree of fissure filling is represented by the simulation analysis obtained through the grouting correlation model, reflecting the degree to which the fissures in the fractured rock layer are filled by grout. In this example, the grouting visualization image representation effect restoration unit generates a three-dimensional visualization image that can intuitively present the distribution of grout inside the fractured rock layer and the state of fracture filling at different grouting times, based on grout diffusion information and the degree of fracture filling.

[0041] The working principle and beneficial effects of the above technical solution are as follows: To ensure the quality of the entire grouting and seepage prevention project at the level of construction effect control, and to achieve real-time, visual, and precise monitoring of the grouting effect, ensuring that grouting defects can be detected and rectified in a timely manner, the system firstly collects real-time water pressure information of the grouting equipment and real-time acoustic information of the fractured rock layer simultaneously. Pipeline pressure fluctuation noise and environmental interference noise are specifically eliminated, and the time nodes of the two types of data are aligned to effectively avoid noise interference with core detection data, ensuring that the output effective data truly reflects the actual grouting state. Then, the aligned data is input into the grouting association model for grouting simulation, accurately acquiring the grout diffusion and crack filling situation. The effect is intuitively presented and evaluated moment by moment through grouting visual images. Finally, when the effect evaluation is unqualified, the system quickly extracts the key indicators that did not meet the standards and generates parameter adjustment suggestions, realizing the rapid conversion of detection results into construction adjustments. This avoids the continuous expansion of grouting defects, allowing the process execution module to optimize construction parameters in a timely manner based on the suggestions, significantly improving the timeliness and pertinence of grouting defect rectification, and ensuring the final grouting and seepage prevention effect.

[0042] Example 8: Based on Example 2, the intelligent grouting and seepage prevention control system for fractured rock strata further includes: An information supplementation unit is used to evaluate the integrity of the fractured rock strata information. When the integrity of the fractured rock strata information is lower than a preset error threshold, a preset geological lithology database is invoked, and historical compactness data of the same type of rock strata in the same region are matched according to the geographical coordinates and stratigraphic age of the area where the fractured rock strata are located. The similarity between densities is estimated based on the historical density data, and historical density data with similarity reaching a preset standard are selected as supplementary data to compensate for the fractured rock strata information.

[0043] In this example, the preset error threshold is a pre-set critical standard value used to judge whether the integrity of the broken rock layer information uploaded by the user meets the standard. It is usually based on the proportion of missing information items, the number of missing key parameters, etc. In this example, geographic coordinates represent the spatial positioning data such as latitude, longitude, and altitude of the target fractured rock layer; In this example, the stratigraphic age refers to the geological age of the target fractured rock layer.

[0044] The working principle and beneficial effects of the above technical solution are as follows: By evaluating the completeness of the fractured rock strata information uploaded by users, the system can proactively identify key missing lithological parameters in the information. It then calls upon a preset geological lithology database, using the geographical coordinates and stratigraphic age of the fractured rock strata as the core matching conditions. This ensures that the matched data is historical density data of the same region and type of strata. By screening and estimating historical data with density similarity that meets preset standards as supplementary data, the system ensures that the supplementary data matches the density characteristics derived by the acoustic matching unit, avoiding the introduction of invalid data with poor compatibility. This achieves the accuracy of information supplementation and ensures the scientific validity of the subsequent acoustic matching unit's determination of the scanning frequency.

[0045] Example 9: Based on Example 5, the intelligent grouting and seepage prevention control system for fractured rock strata further includes: The deep screening unit is used to extract the collection time information corresponding to each historical grouting data, and analyze the time weight of historical data at different collection times in combination with the geological evolution law of fractured rock strata. Historical data with a time weight less than a preset weight threshold are removed.

[0046] The working principle and beneficial effects of the above technical solution are as follows: In order to ensure the effectiveness of information and avoid the impact of prominent data on the overall data, the acquisition time information of historical grouting data is extracted, and the time weight is analyzed in combination with the geological evolution law of fractured rock strata. Historical data with time weight less than the preset weight threshold are selectively removed. This effectively avoids the interference of outdated data that has become invalid due to geological evolution on model construction, avoids modeling bias introduced by poor data, and significantly improves the data quality of input model construction module.

[0047] Example 10: This invention provides a method for intelligent grouting and seepage control in fractured rock formations, such as... Figure 3 As shown, it includes: Step 1: Use acoustic CT technology to perform three-dimensional scanning detection on the fractured rock layer, and construct the three-dimensional spatial information of the fractured rock layer based on the reflection propagation time and wave velocity data of the fractured rock layer at different scanning frequencies; Step 2: Identify the fracture features of the fractured rock strata in the three-dimensional spatial information, and use a preset clustering algorithm to perform multi-index analysis on the fracture features to determine the high, medium and low grouting zones; Step 3: Based on the historical grouting data, permeability coefficient, and grouting conditions corresponding to each grouting zone, construct the grouting correlation model of the fractured rock strata; Step 4: Run the grouting association model to obtain the grouting requirements corresponding to each grouting zone of the specified level, and control the corresponding grouting equipment to perform grouting operations on the fractured rock layer using the specified grouting process; Step 5: Input the real-time water pressure information and real-time acoustic information of the grouting equipment during the grouting operation into the grouting association model to restore the grouting effect of the grouting operation and evaluate it.

[0048] In this example, three-dimensional scanning detection refers to the process of using acoustic CT technology to scan and detect fractured rock layers from all directions and multiple angles, obtain acoustic response data at different locations of the rock layers, and achieve a comprehensive capture of the spatial distribution characteristics of the rock layers. In this example, the reflection propagation time represents the total time it takes for the sound waves emitted by the acoustic CT equipment to propagate through the fractured rock layer, be reflected by the rock layer interface, and return to the receiving device. In this example, the wave velocity data represents the speed at which sound waves propagate through fractured rock strata; In this example, the three-dimensional spatial information represents a three-dimensional digital model that reflects the spatial location, internal structure, and fracture distribution of fractured rock strata, based on the reflection propagation time and wave velocity data obtained from three-dimensional scanning detection. In this example, the fracture characteristics represent the specific properties and distribution of fractures in the fractured rock strata, including fracture aperture, extension length, branching, distribution density, and connectivity. In this example, multi-index analysis refers to an analytical method that takes multiple dimensions of parameters that exhibit the characteristics of fractures as the analysis object and combines them with preset evaluation criteria to comprehensively judge the priority of rock grouting needs. In this example, the permeability coefficient represents a parameter characterizing the water permeability of fractured rock strata, and its value directly reflects the seepage prevention performance of the rock strata. In this example, grouting conditions refer to various environmental and engineering factors that affect the grouting effect during the grouting construction process, including the initial moisture content of the rock strata, ambient temperature and humidity, and geological stability of the construction area. In this example, the grouting correlation model represents a quantitative correlation model between grouting parameters and grouting effects established by integrating historical grouting data, permeability coefficients, and grouting conditions corresponding to grouting zones of various levels. In this example, the grouting requirement represents the personalized construction parameter requirements for different levels of grouting zones, combined with the output of the grouting association model, including grouting pressure, grout water-cement ratio, grouting time, grouting volume, etc. In this example, the grouting process is defined as a standardized grouting operation procedure based on engineering specifications and grouting requirements, including grout preparation standards, grouting equipment operation specifications, grouting section division and switching procedures, etc. In this example, the real-time water pressure information represents the pressure data monitored in real time in the grouting equipment pipeline and grouting hole during the grouting operation, reflecting the grout diffusion status and pipeline patency. In this example, the real-time acoustic signal refers to the acoustic signal collected in real time during the grouting operation of the fractured rock layer and the grouting area. Its changes can reflect the process and effect of the grout filling the cracks.

[0049] The working principle and beneficial effects of the above technical solution are as follows: To fundamentally overcome the shortcomings of traditional grouting construction, such as reliance on manual experience, disconnect between various stages, low construction accuracy, and delayed feedback, and to improve the accuracy and reliability of grouting construction and ensure the quality of seepage prevention projects, the following approach is first used: 3D scanning detection of fractured rock strata is performed using sonic CT technology. Combined with reflection propagation time and wave velocity data, 3D spatial information is constructed to more comprehensively and accurately restore the basic characteristics of the internal structure and fracture distribution of the rock strata, providing high-quality and reliable data support for subsequent zoning. Then, based on the 3D spatial information, the fracture characteristics are accurately identified. Through a preset clustering algorithm, multi-index comprehensive analysis is performed to achieve a scientific division of high, medium, and low-level grouting zones. The zoning results can accurately match the actual geological conditions of the fractured rock strata, providing a clear basis for subsequent differentiated grouting construction, improving the targeting and rationality of grouting construction, avoiding resource waste, and further relying on various... A grouting correlation model is constructed based on historical grouting data, permeability coefficients, and grouting conditions corresponding to different grouting zones. This model quantitatively correlates geological conditions with grouting parameters, freeing the determination of grouting requirements from reliance on manual experience and better aligning with the actual geological characteristics of different zones. This provides scientific and precise parameter guidance for subsequent process execution, laying the foundation for precise construction. Finally, by running the grouting correlation model, the personalized grouting requirements of each zone are obtained, thereby controlling the grouting equipment to execute the prescribed grouting process. This achieves standardization and automation of grouting construction, precisely controlling key construction parameters such as grout preparation, grouting pressure, and grouting duration. This effectively reduces human error, ensures the continuity and standardization of the construction process, and comprehensively improves the quality and efficiency of grouting construction. It can promptly detect construction defects such as insufficient grout diffusion and inadequate crack filling, and provides adjustment basis for the process execution module, enabling real-time monitoring and evaluation of grouting effects.

[0050] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. An intelligent grouting and seepage prevention control system for fractured rock strata, characterized in that, include: The rock strata detection module is used to perform three-dimensional scanning detection of fractured rock strata using acoustic CT technology, and to construct three-dimensional spatial information of the fractured rock strata based on the reflection propagation time and wave velocity data of the fractured rock strata at different scanning frequencies. The partitioning module is used to identify the fracture presentation characteristics of the fractured rock layer in the three-dimensional spatial information, and to perform multi-index analysis on the fracture presentation characteristics using a preset clustering algorithm to determine the high, medium and low three-level grouting partitions. The model building module is used to construct a grouting association model of the fractured rock strata based on the historical grouting data, permeability coefficient, and grouting conditions corresponding to each level of grouting zone. The process execution module is used to run the grouting association model, obtain the grouting requirements corresponding to each grouting zone of the level, and control the corresponding grouting equipment to perform grouting operations on the fractured rock layer using the specified grouting process. The effect detection module is used to input the real-time water pressure information and real-time sound wave information of the grouting equipment during the grouting operation into the grouting association model, restore the grouting effect of the grouting operation, and evaluate it.

2. The intelligent grouting and seepage prevention control system for fractured rock strata as described in claim 1, characterized in that, The rock strata detection module includes: The acoustic matching unit is used to deduce the known density corresponding to different rock strata regions in the fractured rock strata based on the fractured rock strata information uploaded by the user, and to deduce several estimated densities corresponding to the fractured rock strata based on the known density. Based on the acoustic sensitivity characteristics corresponding to each density, several scanning frequencies for this detection are determined. The scanning execution unit is used to control the acoustic CT device to perform dynamic scanning of the fractured rock layer according to the scanning frequency, and at the same time collect the preliminary scanning feedback signal of the fractured rock layer for each scanning acoustic wave, and construct the preliminary three-dimensional information of the fractured rock layer by combining the scanning trajectory of the acoustic CT device. The signal optimization unit is used to sample the initial scan three-dimensional information several times, identify the reflection propagation time data and wave velocity data corresponding to each sampling point in each initial scan feedback signal, and calibrate the reflection propagation time data and wave velocity data corresponding to the same sampling point using timestamps to obtain several sampling optimization information. The information reconstruction unit is used to overlay the sampling optimization information into each of the preliminary scan feedback signals, and at the same time, to interpolate and supplement the preliminary scan feedback signals according to the correlation law between rock density and wave velocity to obtain the corresponding optimized scan feedback signals, and to construct the three-dimensional spatial information of the fractured rock layer based on the optimized scan feedback signals.

3. The intelligent grouting and seepage prevention control system for fractured rock strata as described in claim 2, characterized in that, The information reconstruction unit includes: The positioning processing subunit is used to identify the actual spatial location of each of the sampling optimization information in the fractured rock layer according to the scanning trajectory, and at the same time obtain the sampling point compactness corresponding to each of the actual spatial locations and determine the spatial lithological characteristics corresponding to each sampling point. The regularity analysis subunit is used to determine several interpolation supplement points of the initial scan information based on the distribution of the sampling points in the initial scan information, and to determine the relevant sampling points corresponding to each interpolation supplement point based on the correlation law between rock layer density and wave velocity and the spatial lithological characteristics corresponding to each sampling point. The data interpolation subunit is used to identify the numerical correlation weight between each interpolation supplement point and the corresponding related sampling point, determine the supplement value corresponding to each interpolation supplement point by combining the information value corresponding to each related sampling point, and use the supplement value to interpolate and supplement the interpolation supplement point to obtain the corresponding optimized scanning feedback signal. The information generation subunit constructs a voxel grid corresponding to each sampling point and each interpolation supplement point based on the optimized scanning feedback signal, arranges the voxel grid in space to generate a three-dimensional spatial structure, and inputs each optimized scanning feedback signal into the three-dimensional spatial structure to generate the three-dimensional spatial information of the fractured rock layer.

4. The intelligent grouting and seepage prevention control system for fractured rock strata as described in claim 1, characterized in that, The partitioning module includes: The fracture identification unit is used to perform voxel slicing processing on the three-dimensional spatial information according to each preset specified slicing direction to obtain several spatial layer information corresponding to each preset specified slicing direction, and to identify the rock layer grayscale features and structural texture features corresponding to each spatial layer information respectively. The fracture extraction unit is used to perform comprehensive fracture identification on the grayscale features and structural texture features of the rock layer according to the information cross relationship between the spatial layering information corresponding to different preset slices, and to fuse the fracture identification results with connection relationship to determine several rock layer fractures of the fractured rock layer. The feature analysis unit is used to locate the fracture start point and fracture end point corresponding to each rock layer fracture using the spatial layering information, and at the same time identify the fracture aperture and fracture branch corresponding to each rock layer fracture, and generate the fracture presentation features of the fractured rock layer. The clustering analysis unit is used to optimize the parameters of the preset clustering algorithm according to the clustering criteria corresponding to each preset analysis index, and use the optimized preset clustering algorithm to perform clustering iteration on the fracture presentation characteristics to obtain the clustering result corresponding to each preset analysis index. The partitioning unit is used to divide the clustering results corresponding to each preset analysis index into three clustering partitions from high to low. The partitions are compared with the rock strata stability partitions in the engineering geological survey report of the fractured rock strata, and the boundaries of each partition are locally adjusted to obtain the high grouting partition, medium grouting partition and low grouting partition of the fractured rock strata.

5. The intelligent grouting and seepage prevention control system for fractured rock strata as described in claim 1, characterized in that, The model building module includes: The data acquisition and processing unit is used to acquire historical grouting data, permeability coefficient data and grouting condition data corresponding to each grouting zone, clean each data, and perform outlier detection on the cleaned data to obtain the outlier corresponding to each cleaned data. Based on the outlier anomaly format corresponding to each outlier and the data attributes of the corresponding cleaned data, several data items to be optimized are determined for each cleaned data. The data optimization unit is used to find several valid optimized data values ​​corresponding to each data item to be optimized in the historical grouting data, the permeability coefficient data and the grouting condition data, and input each valid optimized data value into the corresponding data item to be optimized for optimization and verification, so as to obtain the valid data corresponding to each cleaning data. The model training unit is used to construct an initial grouting association model of the fractured rock layer based on the data relationship between different valid data, perform cross-validation training on the model parameters in the initial grouting association model, and generate training logs. The model verification unit is used to input the historical grouting data into the initial grouting association model to obtain several verification data, identify valid log information that matches the verification data in the training log, and modify the initial grouting association model using the valid log information to obtain the grouting association model of the fractured rock layer.

6. The intelligent grouting and seepage prevention control system for fractured rock strata as described in claim 1, characterized in that, The process execution module includes: The demand analysis unit is used to run the grouting correlation model under different grouting speed, grouting pressure, grout water-cement ratio and grouting time as simulation conditions to obtain the grouting impact of each simulation condition on different grouting zones and determine the grouting demand corresponding to each grouting zone. The preparation guidance unit is used to generate equipment control instructions corresponding to each level of grouting zone according to the grouting requirements, adjust the opening of the cement storage equipment and water storage equipment to regulate the feeding rate, start the stirring device to mix the grout, collect the viscosity data of the grout in real time, and adjust the speed of the stirring device according to the viscosity data to obtain qualified grout. The execution supervision unit is used to inject the qualified grout into the grouting equipment to perform grouting operation on the fractured rock layer using the specified grouting process, collect the operating data of the grouting equipment in real time, identify the numerical deviation between the operating data and the equipment control command, and adjust the parameters of the grouting equipment using the numerical deviation; The grouting switching unit is used to collect the orifice pressure data of the previous grouting section after the grouting operation of the current grouting section is completed, and to determine whether the inter-section sealing quality of the previous grouting section is qualified based on the orifice pressure data. If so, the unit controls the grouting equipment to switch to the next grouting section for grouting operation.

7. The intelligent grouting and seepage prevention control system for fractured rock strata as described in claim 1, characterized in that, The effect detection module includes: The real-time acquisition unit is used to acquire the real-time water pressure information of the grouting equipment and the real-time acoustic information of the fractured rock layer, respectively, and to remove the pipeline pressure fluctuation noise in the real-time water pressure information and the environmental interference noise in the real-time acoustic information to obtain the noise-reduced effective water pressure data and effective acoustic data. The effective water pressure data and effective acoustic data are aligned to the same time node to obtain aligned data. The effect restoration unit is used to input the alignment data into the grouting association model to simulate grouting, obtain the grout diffusion information and fracture filling degree of the fractured rock layer, generate a grouting visual image corresponding to each grouting moment, and evaluate the effect of each grouting visual image. The effect feedback unit is used to extract the key indicators that did not meet the standards in the effect evaluation, generate parameter adjustment suggestions, and display them when the effect evaluation shows that it is unqualified.

8. The intelligent grouting and seepage prevention control system for fractured rock strata as described in claim 2, characterized in that, Also includes: An information supplementation unit is used to evaluate the integrity of the fractured rock strata information. When the integrity of the fractured rock strata information is lower than a preset error threshold, a preset geological lithology database is invoked, and historical compactness data of the same type of rock strata in the same region are matched according to the geographical coordinates and stratigraphic age of the area where the fractured rock strata are located. The similarity between densities is estimated based on the historical density data, and historical density data with similarity reaching a preset standard are selected as supplementary data to compensate for the fractured rock strata information.

9. The intelligent grouting and seepage prevention control system for fractured rock strata as described in claim 5, characterized in that, Also includes: The deep screening unit is used to extract the collection time information corresponding to each historical grouting data, and analyze the time weight of historical data at different collection times in combination with the geological evolution law of fractured rock strata. Historical data with a time weight less than a preset weight threshold are removed.

10. A method for intelligent grouting and seepage prevention control in fractured rock strata, characterized in that, include: Step 1: Use acoustic CT technology to perform three-dimensional scanning detection on the fractured rock layer, and construct the three-dimensional spatial information of the fractured rock layer based on the reflection propagation time and wave velocity data of the fractured rock layer at different scanning frequencies; Step 2: Identify the fracture features of the fractured rock strata in the three-dimensional spatial information, and use a preset clustering algorithm to perform multi-index analysis on the fracture features to determine the high, medium and low grouting zones; Step 3: Based on the historical grouting data, permeability coefficient, and grouting conditions corresponding to each grouting zone, construct the grouting correlation model of the fractured rock strata; Step 4: Run the grouting association model to obtain the grouting requirements corresponding to each grouting zone of the specified level, and control the corresponding grouting equipment to perform grouting operations on the fractured rock layer using the specified grouting process; Step 5: Input the real-time water pressure information and real-time acoustic information of the grouting equipment during the grouting operation into the grouting association model to restore the grouting effect of the grouting operation and evaluate it.

Images