Grouting process prediction and optimization control method, device, equipment and medium

Abstract

The invention belongs to the technical field of grouting, and provides a grouting process prediction and optimization control method, device, equipment and medium, and the method comprises the following steps: obtaining multi-source monitoring data of a transparent soil test device under a simulated crustal stress condition; feature extraction and neural network collaborative response modeling are performed based on multi-source monitoring data, so that collaborative response data of crustal stress-grouting parameter-slurry diffusion-soil deformation are obtained; constructing a three-dimensional dynamic digital twinborn model of the transparent soil grouting process based on the monitoring image and the collaborative response data; performing grouting process digital dynamic simulation and future moment diffusion form prediction on the three-dimensional dynamic digital twinborn model, generating optimization adjustment data of control parameters such as grouting pressure and grouting flow based on a prediction result, and further performing real-time parameter adjustment on a grouting system. And error identification and closed-loop correction are performed in combination with the updated multi-source monitoring data, so that the grouting process prediction accuracy and the grouting control efficiency are improved.

Description

Technical Field

[0001] This invention relates to the field of grouting technology, and in particular to a method, apparatus, equipment and medium for predicting and optimizing the grouting process. Background Technology

[0002] The transparent soil physical model and grouting test technology mainly involves constructing a visual porous medium model indoors, simulating the stress state of the actual strata under external loads, injecting grout into the transparent soil, and studying the transport law of the grout in the porous medium and the response characteristics of the soil through monitoring methods such as pressure, flow rate and images. This provides experimental basis for the design of engineering grouting parameters and the evaluation of reinforcement effects. However, existing transparent soil grouting tests rely heavily on operator experience for manual setting and adjustment of parameters such as grouting pressure and flow rate. This lack of adaptation to real-time responses to changes in ground stress, soil deformation, and grout diffusion patterns during the test results in poor repeatability and low control precision. Furthermore, existing ground stress simulation systems primarily focus on loading and maintaining a static stress state, lacking forward-looking prediction and dynamic control of the time-varying grouting process. These systems can only passively respond to monitoring results and cannot adjust control parameters in time before the grout diffusion deviates from the target morphology. In addition, the multi-source data acquired during the test, such as overlying stress, pore water pressure, grouting pressure, grout flow rate, and images, are independent and lack a unified framework for coupled analysis and intelligent modeling. This makes it difficult to deeply reveal the inherent coupling laws between "ground stress—grouting parameters—grout diffusion—soil deformation," thus limiting the ability to extract universal grouting mechanisms and optimize control strategies from the test results. Summary of the Invention

[0003] In order to at least solve one of the technical problems existing in the prior art, the present invention provides a method, apparatus, equipment and medium for predicting and optimizing the grouting process.

[0004] One aspect of the present invention provides a method for predicting and optimizing the grouting process, comprising:

[0005] S100: Acquire multi-source monitoring status data and transparent soil grouting process images of the transparent soil grouting test device under simulated in-situ stress conditions; Identify transparent soil grouting diffusion boundary region and soil deformation characteristics based on transparent soil grouting process images.

[0006] S200: Based on multi-source monitoring status data, feature extraction and nonlinear correlation mapping learning are performed to obtain ground stress-grouting parameter correlation data. Based on the ground stress-grouting parameter correlation data, multi-level collaborative response neural network learning is performed on grouting pressure parameters and grouting flow parameters to obtain collaborative response data of transparent soil grouting process.

[0007] S300: Based on the monitoring images of the transparent soil grouting process, the three-dimensional structural data of the transparent soil grouting area is obtained. Based on the collaborative response data of the transparent soil grouting process, the three-dimensional structural data of the transparent soil grouting area is dynamically rendered to obtain the dynamic rendering model of the transparent soil grouting process.

[0008] S400 performs digital dynamic simulation of the grouting process on the dynamic rendering model of transparent soil grouting process, obtains dynamic simulation data of grout diffusion, and dynamically adjusts the control parameters of the dynamic simulation data of grout diffusion based on the grout diffusion boundary area of ​​transparent soil and the preset grouting target shape, to obtain dynamic adjustment data of grouting pressure parameters and grouting flow rate parameters.

[0009] S500 performs adaptive grouting parameter compensation optimization based on dynamic adjustment data of grouting pressure and grouting flow parameters to obtain transient grouting compensation parameters. Based on the transient grouting compensation parameters, the transparent soil grouting system is adjusted in real time, and real-time adjustment operation status data is obtained.

[0010] S600 identifies error parameters in real-time adjustment operation data based on dynamic simulation data of grout diffusion to obtain grouting control error parameters; and performs dynamic balance control optimization of transparent soil grouting system based on grouting control error parameters to generate dynamic control parameters for transparent soil grouting process, so as to perform prediction and optimization control of transparent soil grouting process.

[0011] According to the grouting process prediction and optimization control method, S100 includes:

[0012] S110, to perform real-time monitoring of the transparent soil grouting test device under simulated in-situ stress conditions, and to acquire multi-source monitoring status data of the test device; the multi-source monitoring status data includes, but is not limited to, overlying stress parameters, pore water pressure parameters, grouting pressure parameters, and grouting flow rate parameters;

[0013] S120 applies the overburden stress, simulating in-situ stress, to the transparent soil model through a loading device, and collects and records the overburden stress in real time to obtain overburden stress time series data.

[0014] S130 uses pore water pressure sensors deployed inside and / or outside the transparent soil model to collect and record pore water pressure in real time, thereby obtaining pore water pressure time series data.

[0015] S140 uses a pressure sensor and a flow meter installed in the grouting pipeline to collect and record grouting pressure and grouting flow in real time, thereby obtaining grouting pressure time series data and grouting flow time series data.

[0016] S150, acquires monitoring image sequences of the transparent soil grouting process through imaging devices deployed on the sidewalls and / or top of the transparent soil model;

[0017] S160, preprocesses the monitoring image sequence of transparent soil grouting process, including but not limited to time synchronization, geometric calibration and noise filtering;

[0018] S170, based on the preprocessed monitoring image sequence, performs visual recognition of the grout diffusion front and soil displacement to extract the grout diffusion front contour line and soil deformation features; according to the grout diffusion front contour line, the monitoring image is segmented into regions to obtain the transparent soil grouting diffusion boundary region and soil deformation features.

[0019] According to the grouting process prediction and optimization control method described above, S200 includes:

[0020] S210, based on the overlying stress parameters and pore water pressure parameters, the historical time series data of grouting pressure parameters and grouting flow rate parameters are subjected to disturbance analysis to obtain the disturbance response data of grouting parameters under in-situ stress conditions.

[0021] S220, based on the disturbance response data of grouting parameters, nonlinear correlation mapping learning is performed on the overlying stress parameters, pore water pressure parameters, and grouting pressure parameters and grouting flow rate parameters to obtain the correlation data between ground stress and grouting parameters;

[0022] S230, the temporal evolution characteristics of the grouting diffusion boundary area and soil deformation characteristics of transparent soil are analyzed to obtain grouting diffusion-soil response characteristic data;

[0023] S240 uses a multi-level collaborative response neural network to learn the correlation data between ground stress and grouting parameters and the grouting diffusion and soil response characteristics data, thereby generating collaborative response data for the transparent soil grouting process.

[0024] According to the grouting process prediction and optimization control method, S300 includes:

[0025] S310, acquire monitoring image sequences of the transparent soil grouting process;

[0026] S320, perform spatial topological analysis of the grout diffusion area on the monitoring image sequence of the transparent soil grouting process to obtain spatial topological data of the grout diffusion area;

[0027] S330, based on the spatial topology data of the grouting diffusion area, performs three-dimensional morphological analysis to obtain the three-dimensional morphological data of the grout diffusion front;

[0028] S340: Using the three-dimensional morphological data of the grout diffusion front, the monitoring image sequence of the transparent soil grouting process is reconstructed in three dimensions to build a three-dimensional structural model of transparent soil grout diffusion.

[0029] S350, based on the collaborative response data of the transparent soil grouting process, performs dynamic parameter rendering on the three-dimensional structural model of transparent soil grouting diffusion, thereby constructing a dynamic rendering model of the transparent soil grouting process.

[0030] According to the grouting process prediction and optimization control method described above, S400 includes:

[0031] S410, Perform digital dynamic simulation of the grouting process on the dynamic rendering model of transparent soil grouting process to obtain dynamic simulation data of grout diffusion; the dynamic simulation data of grout diffusion includes, but is not limited to, grout diffusion range, diffusion front position and soil deformation response data at different time steps.

[0032] S420 uses time-series evolution analysis based on dynamic simulation data of grout diffusion to predict the grout diffusion morphology and diffusion influence range at future moments, thereby obtaining prediction data for the transparent soil grouting process.

[0033] S430, based on the diffusion boundary area of ​​transparent soil grouting and the preset grouting target shape, the deviation evaluation analysis of the predicted data of transparent soil grouting process is carried out to obtain diffusion deviation evaluation data.

[0034] S440 calculates the dynamic adjustment of grouting pressure and grouting flow parameters based on diffusion deviation assessment data, thereby generating dynamic adjustment data for grouting pressure and grouting flow parameters.

[0035] According to the grouting process prediction and optimization control method, S500 includes:

[0036] S510, based on diffusion deviation assessment data and dynamic adjustment data of grouting pressure parameters and grouting flow rate parameters, performs adaptive grouting parameter compensation optimization on transient grouting parameters to obtain transient grouting compensation parameters;

[0037] S520 performs optimal collaborative control decisions on the dynamic adjustment data of grouting pressure parameters and grouting flow parameters, as well as transient grouting compensation parameters, to obtain the optimal control parameters for the transparent soil grouting system.

[0038] S530 adjusts the parameters of the transparent soil grouting system in real time based on the optimal control parameters of the transparent soil grouting system, and obtains real-time adjustment operation status data.

[0039] According to the grouting process prediction and optimization control method described above, S600 includes:

[0040] S610: Acquire real-time adjustment and operation status data of the transparent soil grouting system, and perform time synchronization and data preprocessing on the real-time adjustment and operation status data and grout diffusion dynamic simulation data to obtain comparable measured operation data and simulation prediction data.

[0041] S620, based on the comparative analysis of actual measured data and simulated prediction data, calculates the deviation of parameters such as grouting diffusion range, diffusion front position, grouting pressure and grouting flow rate, so as to obtain grouting control error parameters including but not limited to diffusion deviation, pressure deviation and flow rate deviation.

[0042] S630: Based on the grouting control error parameters, a dynamic balance control optimization model for the transparent soil grouting process is established. The correction amounts of the grouting pressure parameters and grouting flow rate parameters are calculated to generate dynamic control parameters for the transparent soil grouting process, which can be used for subsequent transparent soil grouting process prediction and optimization control operations.

[0043] Another aspect of the present invention provides a grouting process prediction and optimization control device, comprising:

[0044] The first module is used to acquire multi-source monitoring status data of the transparent soil grouting test device under simulated in-situ stress conditions and images of the transparent soil grouting process, and to identify the grouting diffusion boundary region and soil deformation characteristics of the transparent soil based on the images of the transparent soil grouting process.

[0045] The second module is used to extract features and learn nonlinear correlation mapping based on multi-source monitoring status data to obtain ground stress-grouting parameter correlation data. Based on the ground stress-grouting parameter correlation data, a multi-level collaborative response neural network is used to learn grouting pressure parameters and grouting flow parameters to obtain collaborative response data of transparent soil grouting process.

[0046] The third module is used to obtain the three-dimensional structural data of the transparent soil grouting area based on the monitoring images of the transparent soil grouting process, and to perform dynamic parameter rendering on the three-dimensional structural data of the transparent soil grouting area based on the collaborative response data of the transparent soil grouting process to obtain the dynamic rendering model of the transparent soil grouting process.

[0047] The fourth module is used to perform digital dynamic simulation of the grouting process on the dynamic rendering model of transparent soil grouting process, obtain dynamic simulation data of grout diffusion, and dynamically adjust the control parameters of the dynamic simulation data of grout diffusion based on the grout diffusion boundary area of ​​transparent soil and the preset grouting target shape, so as to obtain dynamic adjustment data of grouting pressure parameters and grouting flow rate parameters.

[0048] The fifth module is used to perform adaptive grouting parameter compensation optimization based on the dynamic adjustment data of grouting pressure parameters and grouting flow parameters, obtain transient grouting compensation parameters, adjust the parameters of the transparent soil grouting system in real time according to the transient grouting compensation parameters, and obtain real-time adjustment operation status data.

[0049] The sixth module is used to identify error parameters in the real-time adjustment operation status data based on the dynamic simulation data of grout diffusion, and obtain the grouting control error parameters; based on the grouting control error parameters, the transparent soil grouting system is dynamically balanced and optimized to generate dynamic control parameters for the transparent soil grouting process, so as to perform the prediction and optimization control operation of the transparent soil grouting process.

[0050] Another aspect of the present invention provides an electronic device, including a processor and a memory;

[0051] The memory is used to store programs;

[0052] The processor executes the program to implement the method as described above.

[0053] This invention also discloses a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium and execute the computer instructions, causing the computer device to perform the methods described above.

[0054] The beneficial effects of this invention are as follows: Multi-source monitoring status data and transparent soil grouting process images under simulated geostress conditions are obtained through multi-source monitoring and boundary recognition, multi-source sensing and preprocessing. Boundary recognition and soil deformation feature extraction are performed on the images. Time synchronization, noise filtering, and geometric calibration are performed on the multi-source data and images to obtain preprocessed data and image sequences, providing reliable input for subsequent modeling. Through coupled feature modeling, geostress, grouting parameters, and grout diffusion response features are extracted. Nonlinear correlation mapping learning is performed to generate geostress-grouting parameter correlation data and collaborative response data, quantifying the coupling relationship. Through digital twin reconstruction, spatial topology analysis is performed on the preprocessed image sequences, and dynamic mapping rendering is performed based on the collaborative response data. The system visualizes the grouting diffusion front, soil deformation, and control parameters. Through predictive simulation and target optimization, it performs digital simulation on the twin model, assesses the deviation between the diffusion boundary and the preset target shape, and generates diffusion deviation assessment data and dynamic adjustment data for grouting parameters. By implementing control and transient compensation, it constructs an adaptive compensation optimization model for grouting parameters based on the adjustment data, solves for transient grouting compensation parameters, updates control parameters in real time, drives the grouting equipment adjustment, and obtains real-time operating status data. Through error assessment and closed-loop learning, it compares simulated data with real-time data, identifies grouting control errors, updates the geostress-grouting parameter correlation data and collaborative response data, corrects the optimization strategy, and outputs dynamic control parameters, achieving closed-loop optimization and dynamic equilibrium control. Attached Figure Description

[0055] Figure 1This is a schematic diagram of the grouting process prediction and optimization control flow according to an embodiment of the present invention.

[0056] Figure 2 This is a schematic diagram of the image recognition process for transparent soil grouting according to an embodiment of the present invention.

[0057] Figure 3 This is a schematic diagram of the collaborative response process of transparent soil grouting according to an embodiment of the present invention.

[0058] Figure 4 This is a schematic diagram of the dynamic rendering process of transparent soil grouting according to an embodiment of the present invention.

[0059] Figure 5 This is a schematic diagram of the dynamic adjustment data generation process according to an embodiment of the present invention.

[0060] Figure 6 This is a schematic diagram of the diffusion deviation assessment data generation process according to an embodiment of the present invention.

[0061] Figure 7 This is a schematic diagram of another dynamic adjustment data generation process according to an embodiment of the present invention.

[0062] Figure 8 This is a schematic diagram of the real-time adjustment and operation status data acquisition process according to an embodiment of the present invention.

[0063] Figure 9 This is a schematic diagram of the process for obtaining grouting parameter compensation data according to an embodiment of the present invention.

[0064] Figure 10 This is a schematic diagram of the process for obtaining the optimal control parameters of the transparent soil grouting system according to an embodiment of the present invention.

[0065] Figure 11 This is a schematic diagram of the operation flow for predicting and optimizing the grouting process of transparent soil according to an embodiment of the present invention.

[0066] Figure 12 This is a schematic diagram of the grouting process prediction and optimization control device according to an embodiment of the present invention. Detailed Implementation

[0067] The embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings. Throughout the description, the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions. In the following description, suffixes such as "module," "part," or "unit" used to denote elements are used only for the purpose of illustrative purposes and have no specific meaning in themselves. Therefore, "module," "part," or "unit" can be used interchangeably. Terms such as "first," "second," etc., are used only to distinguish technical features and should not be construed as indicating or implying relative importance, or implicitly indicating the number of indicated technical features, or implicitly indicating the sequential relationship of the indicated technical features. In the following description, the consecutive reference numerals for method steps are for ease of review and understanding. Adjusting the implementation order of steps, in conjunction with the overall technical solution of the present invention and the logical relationship between the various steps, will not affect the technical effect achieved by the technical solution of the present invention. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0068] refer to Figure 1 ,in Figure 1 This is a schematic diagram of the grouting process prediction and optimization control flow according to an embodiment of the present invention, which includes, but is not limited to, steps S100~S600:

[0069] S100 acquires multi-source monitoring status data and images of the transparent soil grouting test device under simulated in-situ stress conditions, and identifies the grouting diffusion boundary region and soil deformation characteristics based on the images of the transparent soil grouting process.

[0070] refer to Figure 2 The schematic diagram of the image recognition process for transparent soil grouting shown includes, but is not limited to, steps S110~S170:

[0071] S110 is used to monitor the grouting test device for transparent soil under simulated in-situ stress conditions in real time and obtain multi-source monitoring status data of the test device. The multi-source monitoring status data includes, but is not limited to, overlying stress parameters, pore water pressure parameters, grouting pressure parameters, and grouting flow rate parameters.

[0072] S120 applies the overburden stress, simulating in-situ stress, to the transparent soil model through a loading device, and collects and records the overburden stress in real time to obtain overburden stress time series data.

[0073] S130 uses pore water pressure sensors deployed inside and / or outside the transparent soil model to collect and record pore water pressure in real time, thereby obtaining pore water pressure time series data.

[0074] S140 uses a pressure sensor and a flow meter installed in the grouting pipeline to collect and record grouting pressure and grouting flow in real time, thereby obtaining grouting pressure time series data and grouting flow time series data.

[0075] S150, acquires monitoring image sequences of the transparent soil grouting process through imaging devices deployed on the sidewalls and / or top of the transparent soil model;

[0076] S160, preprocesses the monitoring image sequence of transparent soil grouting process, including but not limited to time synchronization, geometric calibration and noise filtering;

[0077] S170, based on the preprocessed monitoring image sequence, performs visual recognition of the grout diffusion front and soil displacement to extract the grout diffusion front contour line and soil deformation features; according to the grout diffusion front contour line, the monitoring image is segmented into regions to obtain the transparent soil grouting diffusion boundary region and soil deformation features.

[0078] In some embodiments, multiple sensors and imaging devices are deployed on the transparent soil grouting test device to acquire multi-source monitoring status data and images of the transparent soil grouting process under simulated geostress conditions: Overburden stress sensors are arranged on the loading plate or loading beam of the loading device to collect overburden stress signals under loading in real time, characterizing the geostress level of the transparent soil model and providing boundary conditions for analyzing the grouting response under geostress conditions; pore water pressure sensors are pre-embedded inside or at the bottom of the transparent soil model to collect pore water pressure signals in real time, reflecting the changing characteristics of the pore water pressure field during grouting and thus determining the soil seepage state and drainage conditions; pressure sensors and flow meters are connected in series on the grouting pipeline to acquire grouting pressure and grouting flow signals in real time, characterizing the grouting energy input intensity and grouting rate, thus providing a basis for controlling the grout injection process; high-definition cameras are installed on the sidewalls and / or top of the transparent soil model, with appropriate viewing angles along the transparent observation surface to capture and acquire images of the transparent soil in real time. Images of the grouting process in the transparent soil are generated, ensuring sufficient image resolution to clearly capture the internal brightness and dark variations and interface details. By processing and analyzing the image grayscale distribution, refractive texture changes, and color particle movement characteristics, the brightness / texture abrupt boundary of the grout diffusion front is identified, yielding the grout diffusion front contour. This contour is used to describe the position and morphology of the grout diffusion boundary at different time sections. By calculating the displacement of feature points, deformation of grid markers, or optical flow fields in consecutive image frames, the soil deformation field and displacement vector distribution are obtained, reflecting the deformation response of the transparent soil under grouting disturbance. The identified transparent soil grouting diffusion boundary region and soil deformation characteristics are correlated with multi-source monitoring data such as overlying stress, pore water pressure, grouting pressure, and grouting flow rate. This data serves as the input data foundation for subsequent collaborative modeling of geostress-grouting parameters-grout diffusion-soil deformation, construction of a 3D digital twin, and prediction and optimization control of the grouting process. This supports intelligent analysis and closed-loop control of the entire transparent soil grouting process.

[0079] S200 uses feature extraction and nonlinear correlation mapping learning based on multi-source monitoring status data to obtain ground stress-grouting parameter correlation data. Based on the ground stress-grouting parameter correlation data, a multi-level collaborative response neural network is used to learn grouting pressure parameters and grouting flow parameters to obtain collaborative response data of transparent soil grouting process.

[0080] In some embodiments, reference Figure 3 The schematic diagram of the collaborative response process for transparent soil grouting shown includes steps S210 to S240:

[0081] S210, based on the overlying stress parameters and pore water pressure parameters, the historical time series data of grouting pressure parameters and grouting flow rate parameters are subjected to disturbance analysis to obtain the disturbance response data of grouting parameters under in-situ stress conditions.

[0082] S220, based on the disturbance response data of grouting parameters, nonlinear correlation mapping learning is performed on the overlying stress parameters, pore water pressure parameters, and grouting pressure parameters and grouting flow rate parameters to obtain the correlation data between ground stress and grouting parameters;

[0083] S230, the temporal evolution characteristics of the grouting diffusion boundary area and soil deformation characteristics of transparent soil are analyzed to obtain grouting diffusion-soil response characteristic data;

[0084] S240 uses a multi-level collaborative response neural network to learn the correlation data between ground stress and grouting parameters and the grouting diffusion and soil response characteristics data, thereby generating collaborative response data for the transparent soil grouting process.

[0085] In some embodiments, multi-source time-series information on the grouting process under in-situ stress conditions is obtained by jointly analyzing historical time-series data of overlying stress parameters, pore water pressure parameters, and grouting pressure and flow rate parameters. Perturbation analysis of the aforementioned historical time-series data yields perturbation response data of grouting pressure and flow rate under different in-situ stresses and pore water pressures. This perturbation response data is used to characterize the sensitivity and response characteristics of in-situ stress changes to grouting conditions, thus providing a foundation for establishing a quantitative relationship between in-situ stress and grouting parameters. By performing nonlinear correlation mapping learning on overlying stress parameters, pore water pressure parameters, and grouting pressure and flow rate parameters based on the perturbation response data, in-situ stress-grouting parameter correlation data is obtained. This correlation data is used to characterize different in-situ stress levels and... The influence of the combined regulation of grouting pressure and grouting flow rate on the system state under pore water pressure conditions is investigated, thus providing a priori mapping for intelligent adjustment of grouting parameters. Temporal evolution characteristic analysis of the grouting diffusion boundary region and soil deformation characteristics in transparent soil is conducted to obtain grouting diffusion-soil response characteristic data. This data reflects the coupling process between grout diffusion morphology and soil deformation over time, providing temporal characteristic support for characterizing the "input parameter-medium response" relationship. The in-situ stress-grouting parameter correlation data and the grouting diffusion-soil response characteristic data are jointly input into a multi-level collaborative response neural network for learning and training, generating collaborative response data for the transparent soil grouting process. This collaborative response data comprehensively characterizes the overall coupling relationship between in-situ stress, pore water pressure, grouting parameters, grout diffusion, and soil deformation.

[0086] S300: Based on the monitoring images of the transparent soil grouting process, the three-dimensional structural data of the transparent soil grouting area is obtained. Based on the collaborative response data of the transparent soil grouting process, the three-dimensional structural data of the transparent soil grouting area is dynamically rendered to obtain a dynamic rendering model of the transparent soil grouting process.

[0087] In some embodiments, reference Figure 4The schematic diagram of the dynamic rendering process of transparent soil grouting shown includes, but is not limited to, steps S10~S350:

[0088] S310, acquire monitoring image sequences of the transparent soil grouting process;

[0089] S320, perform spatial topological analysis of the grout diffusion area on the monitoring image sequence of the transparent soil grouting process to obtain spatial topological data of the grout diffusion area;

[0090] S330, based on the spatial topology data of the grouting diffusion area, performs three-dimensional morphological analysis to obtain the three-dimensional morphological data of the grout diffusion front;

[0091] S340: Using the three-dimensional morphological data of the grout diffusion front, the monitoring image sequence of the transparent soil grouting process is reconstructed in three dimensions to build a three-dimensional structural model of transparent soil grout diffusion.

[0092] S350, based on the collaborative response data of the transparent soil grouting process, performs dynamic parameter rendering on the three-dimensional structural model of transparent soil grouting diffusion, thereby constructing a dynamic rendering model of the transparent soil grouting process.

[0093] In some embodiments, the present invention acquires a sequence of monitoring images of the transparent soil grouting process to obtain visual information at different time sections during the grouting process. The monitoring image sequence provides a temporal record of the grout diffusion morphology and soil structure changes within the transparent soil, which is used for subsequent spatial topology analysis and 3D modeling. By performing spatial topology analysis on the grout diffusion area of ​​the monitoring image sequence of the transparent soil grouting process, the connectivity, boundary morphology, and spatial distribution characteristics of the grout diffusion area on the plane are determined. The obtained spatial topology data of the grout diffusion area is used to describe the geometric framework and regional division of the diffusion area, providing basic data for 3D morphology analysis. By performing 3D morphology analysis based on the spatial topology data of the grout diffusion area, the position and outward expansion morphology of the grout diffusion front at different depths are inferred. The obtained 3D morphology data of the grout diffusion front is used to quantify the shape and evolution law of the grout diffusion front within the transparent soil in 3D space, providing a basis for constructing a 3D structure. The model provides accurate front boundary information. By utilizing the three-dimensional morphological data of the grout diffusion front to reconstruct the monitoring image sequence of the transparent soil grouting process in three dimensions, a three-dimensional structural model of transparent soil grout diffusion is constructed. The three-dimensional structural model provides a complete mapping of each location within the grouting area in terms of spatial coordinates, hierarchical relationships, and diffusion envelope, which is used to carry the spatial projection and fusion expression of multi-source monitoring status data. By performing dynamic parameter rendering on the three-dimensional structural model of transparent soil grout diffusion based on the collaborative response data of the transparent soil grouting process, the correlation data of ground stress and grouting parameters and the grout diffusion-soil response characteristics are mapped to each unit of the three-dimensional structural model, and a dynamic rendering model of the transparent soil grouting process is constructed. The generated dynamic rendering model is used to display the coupling relationship between the grout diffusion front, soil deformation, and control parameters in three-dimensional digital space, thereby providing a basic carrier for the subsequent digital dynamic simulation and optimization of grouting control parameters that integrates visualization and quantification.

[0094] S400 performs digital dynamic simulation of the grouting process using a dynamic rendering model of transparent soil grouting process, and obtains dynamic simulation data of grout diffusion. Based on the grout diffusion boundary region of transparent soil and the preset grouting target shape, the control parameters of the dynamic simulation data of grout diffusion are dynamically adjusted to obtain dynamic adjustment data of grouting pressure parameters and grouting flow rate parameters.

[0095] In some embodiments, reference Figure 5 The diagram showing the dynamic adjustment data generation process includes, but is not limited to, steps S410 to S440:

[0096] S410, to perform digital dynamic simulation of the grouting process on the dynamic rendering model of transparent soil grouting process, so as to obtain dynamic simulation data of grout diffusion; the dynamic simulation data of grout diffusion includes but is not limited to the grout diffusion range, diffusion front position and soil deformation response data at different time steps.

[0097] S420 uses time-series evolution analysis based on dynamic simulation data of grout diffusion to predict the grout diffusion morphology and diffusion influence range at future moments, thereby obtaining prediction data for the transparent soil grouting process.

[0098] S430, based on the diffusion boundary area of ​​transparent soil grouting and the preset grouting target shape, the deviation evaluation analysis of the predicted data of transparent soil grouting process is carried out to obtain diffusion deviation evaluation data.

[0099] In some embodiments, reference Figure 6 The schematic diagram shown below illustrates the data generation process for diffusion deviation assessment, which includes, but is not limited to, steps S431 to S433:

[0100] S431, Extract the grout diffusion front position data and diffusion radius data at the target time based on the predicted data of the transparent soil grouting process;

[0101] S432, compare and analyze the slurry diffusion front position data and diffusion radius data at the target time with the preset grouting target shape to obtain the original data of diffusion deviation;

[0102] S433 performs normalization processing and deviation quantification calculation on the original diffusion deviation data, including but not limited to comprehensive evaluation of diffusion radius deviation, diffusion morphology deviation and coverage deviation, thereby generating diffusion deviation assessment data.

[0103] S440 calculates the dynamic adjustment of grouting pressure and grouting flow parameters based on diffusion deviation assessment data, thereby generating dynamic adjustment data for grouting pressure and grouting flow parameters.

[0104] In some embodiments, reference Figure 7 The diagram shown illustrates another dynamic adjustment data generation process, which includes, but is not limited to, steps S441 to S443:

[0105] S441, based on the correlation data of ground stress-grouting parameters and the diffusion deviation assessment data, establish the control sensitivity relationship between grouting pressure parameters and grouting flow rate parameters on diffusion deviation, so as to obtain the control sensitivity data of grouting parameters;

[0106] S442, Based on the diffusion deviation assessment data and the grouting parameter control sensitivity data, a dynamic optimization model for grouting parameters is constructed, and the adjustment amounts of grouting pressure parameters and grouting flow rate parameters are calculated to obtain the grouting parameter adjustment amount data;

[0107] S443, superimposes the grouting parameter adjustment data onto the current grouting pressure parameter and grouting flow rate parameter to generate dynamic adjustment data for the grouting pressure parameter and grouting flow rate parameter.

[0108] In this embodiment, a dynamic rendering model of the transparent soil grouting process is used as a simulation platform. This model incorporates the physical processes of grout seepage, diffusion, and disturbance to the soil skeleton within the porous transparent soil medium during grouting. Numerical calculations and evolution simulations are performed on the grout volume content field, pressure field, and velocity field at different time steps to obtain dynamic simulation data of grout diffusion. This data describes the spatiotemporal distribution of grout diffusion range, diffusion front location, and soil deformation response under given geostress conditions and initial grouting parameters, thus providing a basis for the forward-looking adjustment of control parameters. Based on the transparent soil grouting diffusion boundary region and the preset grouting target shape, the dynamics of grout diffusion are analyzed. By comparing and analyzing the simulated data, the deviations between the simulated diffusion boundary and the target diffusion morphology in terms of diffusion radius, boundary shape, and coverage area at different time sections are identified. The control requirements for reducing or increasing the diffusion range and suppressing or enhancing the diffusion direction at each control moment are calculated, which are used to generate adjustment instructions for grouting pressure and grouting flow parameters. By mapping the above control requirements into pressure increase / decrease and flow rate increase / decrease, dynamic adjustment calculations are performed on the grouting pressure and grouting flow parameters to obtain dynamic adjustment data for the grouting pressure and grouting flow parameters. The dynamic adjustment data is used to indicate the pressure and flow rate setpoints to be used at each control moment during the grouting process that evolves over time.

[0109] S500 performs adaptive grouting parameter compensation optimization based on dynamic adjustment data of grouting pressure and grouting flow parameters to obtain transient grouting compensation parameters. Based on the transient grouting compensation parameters, the transparent soil grouting system is adjusted in real time, and real-time adjustment operation status data is obtained.

[0110] refer to Figure 8 , Figure 8 This is a schematic diagram of the real-time adjustment and operation status data acquisition process according to an embodiment of the present invention, which includes, but is not limited to, steps S510~S530:

[0111] S510, based on diffusion deviation assessment data and dynamic adjustment data of grouting pressure parameters and grouting flow rate parameters, performs adaptive grouting parameter compensation optimization on transient grouting parameters to obtain transient grouting compensation parameters;

[0112] In some embodiments, such as Figure 9 A schematic diagram of the process for obtaining grouting parameter compensation data, including but not limited to steps S511~S513:

[0113] S511. Based on the diffusion deviation assessment data, evaluation indicators such as diffusion radius deviation, diffusion morphology deviation, and coverage deviation are extracted, and each evaluation indicator is normalized to obtain normalized diffusion deviation data.

[0114] S512, an adaptive compensation optimization model for grouting parameters is constructed based on normalized diffusion deviation data. The adaptive compensation optimization model for grouting parameters takes minimizing diffusion deviation as the objective function and combines the adjustment constraints of grouting pressure parameters and grouting flow rate parameters to optimize the solution, thereby obtaining the grouting parameter compensation data.

[0115] S513, based on the grouting parameter compensation data, adaptively compensates and superimposes the current grouting pressure parameter and grouting flow rate parameter to generate transient grouting compensation parameters.

[0116] S520 performs optimal collaborative control decisions on the dynamic adjustment data of grouting pressure parameters and grouting flow parameters, as well as transient grouting compensation parameters, to obtain the optimal control parameters for the transparent soil grouting system.

[0117] like Figure 10 The schematic diagram shown illustrates the process for obtaining the optimal control parameters of the transparent soil grouting system, which includes, but is not limited to, steps S521~S523:

[0118] S521, normalize the dynamic adjustment data of grouting pressure parameters and grouting flow parameters and transient grouting compensation parameters to obtain normalized grouting parameter candidate data;

[0119] S522, a multi-objective collaborative control decision model is constructed based on normalized grouting parameter candidate data and collaborative response data of transparent soil grouting process. The multi-objective collaborative control decision model takes diffusion deviation, grouting stability and grouting energy consumption as decision objectives, and performs collaborative optimization of grouting pressure parameters and grouting flow rate parameters to obtain grouting parameter collaborative optimization result data.

[0120] S523, the optimal control parameters of the transparent soil grouting system are calculated based on the data of the collaborative optimization of grouting parameters.

[0121] S530 adjusts the parameters of the transparent soil grouting system in real time based on the optimal control parameters of the transparent soil grouting system, and obtains real-time adjustment operation status data.

[0122] In this embodiment, an adaptive grouting parameter compensation optimization algorithm is established. Using dynamic adjustment data of grouting pressure and flow parameters as input, the algorithm analyzes the magnitude and direction of diffusion deviation at different control moments. Combined with the response inertia and time-delay characteristics of the transparent soil grouting system under pressure and flow changes, predictive control and constraint optimization strategies are employed to solve for the required pressure and flow increments under the current operating conditions, thereby obtaining transient grouting compensation parameters. These transient grouting compensation parameters are used to superimpose fine compensation amounts on the original control commands, making the grouting input more consistent with the current diffusion control requirements. Based on the transient grouting compensation parameters, the control system adjusts the grouting pump outlet pressure setpoint, flow control valve opening, and control signals of related actuators in real time to update the actual working pressure and grouting flow of the transparent soil grouting system, causing the grout diffusion process to converge towards the preset target shape. During the execution of the above real-time parameter adjustments, the control system collects and records information such as the adjusted grouting pressure, grouting flow, overlying stress, pore water pressure, and synchronously acquired monitoring images of the transparent soil grouting process in real time, forming real-time adjustment operation status data to reflect the actual response of the system under adaptive compensation control.

[0123] The S600 identifies error parameters in real-time operational status data based on dynamic simulation data of grout diffusion, obtaining grouting control error parameters. Based on these error parameters, the transparent soil grouting system is dynamically balanced and optimized, generating dynamic control parameters for the transparent soil grouting process to perform predictive and optimized control operations.

[0124] In some embodiments, such as Figure 11 A schematic diagram of the prediction and optimization control process for transparent soil grouting, including but not limited to steps S610~S630:

[0125] S610: Acquire real-time adjustment and operation status data of the transparent soil grouting system, and perform time synchronization and data preprocessing on the real-time adjustment and operation status data and grout diffusion dynamic simulation data to obtain comparable measured operation data and simulation prediction data.

[0126] S620, based on the comparative analysis of actual measured data and simulated prediction data, calculates the deviation of parameters such as grouting diffusion range, diffusion front position, grouting pressure and grouting flow rate, so as to obtain grouting control error parameters including but not limited to diffusion deviation, pressure deviation and flow rate deviation.

[0127] S630: Based on the grouting control error parameters, a dynamic balance control optimization model for the transparent soil grouting process is established. The correction amounts of the grouting pressure parameters and grouting flow rate parameters are calculated to generate dynamic control parameters for the transparent soil grouting process, which can be used for subsequent transparent soil grouting process prediction and optimization control operations.

[0128] In this embodiment, by comparing and analyzing the dynamic simulation data of grout diffusion with the real-time adjusted operating status data, deviations in key parameters such as grout diffusion range, diffusion front position, grouting pressure, and grouting flow rate are identified, forming grouting control error parameters. These parameters quantify the difference between the actual operating state and the digital simulation prediction state of the transparent soil grouting system, providing a basis for subsequent control strategy correction. Based on the grouting control error parameters, a dynamic balance control optimization algorithm for the transparent soil grouting process is established. Under the premise of meeting the ground stress constraints and equipment safety operating conditions, the correction amounts for the grouting pressure and flow rate parameters are solved to obtain the dynamic control parameters for the transparent soil grouting process. These dynamic control parameters guide the control system to update and adjust the execution units such as the grouting pump outlet pressure setpoint and the flow control valve opening, gradually reducing diffusion deviation and pressure / flow rate deviations within a continuous control cycle. This maintains the grout diffusion morphology and soil deformation response within the target control range, thereby supporting the prediction and optimization control of the transparent soil grouting process and achieving dynamic balance and closed-loop fine control of the grouting process under simulated ground stress conditions.

[0129] Figure 12 This is a schematic diagram of a grouting process prediction and optimization control device according to an embodiment of the present invention. The device includes a first module 1210, a second module 1220, a third module 1230, a fourth module 1240, a fifth module 1250, and a sixth module 1260.

[0130] The system comprises three modules: The first module acquires multi-source monitoring data and images of the transparent soil grouting test device under simulated in-situ stress conditions, and identifies the grouting diffusion boundary region and soil deformation characteristics based on the grouting process images; the second module performs feature extraction and nonlinear correlation mapping learning based on the multi-source monitoring data to obtain in-situ stress-grouting parameter correlation data, and performs multi-level collaborative response neural network learning on grouting pressure and flow parameters based on the in-situ stress-grouting parameter correlation data to obtain collaborative response data of the transparent soil grouting process; the third module obtains three-dimensional structural data of the transparent soil grouting area based on the monitoring images of the transparent soil grouting process, and identifies the grouting diffusion boundary region and soil deformation characteristics based on the collaborative response data of the transparent soil grouting process. The first module performs dynamic parameter rendering on the three-dimensional structural data of the soil grouting area to obtain a dynamic rendering model of the transparent soil grouting process. The second module performs digital dynamic simulation of the grouting process on the dynamic rendering model of the transparent soil grouting process to obtain dynamic simulation data of grout diffusion. Based on the grout diffusion boundary area of ​​the transparent soil and the preset grouting target shape, the control parameters of the dynamic simulation data of grout diffusion are dynamically adjusted to obtain dynamic adjustment data of grouting pressure parameters and grouting flow rate parameters. The third module performs adaptive grouting parameter compensation optimization based on the dynamic adjustment data of grouting pressure parameters and grouting flow rate parameters to obtain transient grouting compensation parameters. Based on the transient grouting compensation parameters, the transparent soil grouting system is adjusted in real time, and real-time adjustment operation status data is obtained.

[0131] The sixth module is used to identify error parameters in the real-time adjustment operation status data based on the dynamic simulation data of grout diffusion, and obtain the grouting control error parameters; based on the grouting control error parameters, the transparent soil grouting system is dynamically balanced and optimized to generate dynamic control parameters for the transparent soil grouting process, so as to perform the prediction and optimization control operation of the transparent soil grouting process.

[0132] Exemplarily, with the cooperation of the first, second, third, fourth, fifth, and sixth modules in the device, the embodiment device can implement any of the aforementioned grouting process prediction and optimization control methods, namely, acquiring multi-source monitoring status data and transparent soil grouting process images of the transparent soil grouting test device under simulated in-situ stress conditions; identifying the transparent soil grouting diffusion boundary region and soil deformation characteristics based on the transparent soil grouting process images; performing feature extraction and nonlinear correlation mapping learning based on the multi-source monitoring status data to obtain in-situ stress-grouting parameter correlation data; performing multi-level collaborative response neural network learning on grouting pressure parameters and grouting flow rate parameters based on the in-situ stress-grouting parameter correlation data to obtain transparent soil grouting process collaborative response data; obtaining three-dimensional structural data of the transparent soil grouting area based on the transparent soil grouting process monitoring images; and performing dynamic parameter rendering on the three-dimensional structural data of the transparent soil grouting area based on the transparent soil grouting process collaborative response data to obtain... A dynamic rendering model of the transparent soil grouting process is obtained. The grouting process is then digitally simulated using this model to obtain dynamic simulation data of grout diffusion. Based on the grout diffusion boundary region and the preset grouting target shape, the control parameters of the dynamic simulation data are dynamically adjusted to obtain dynamic adjustment data for grouting pressure and flow rates. Adaptive grouting parameter compensation optimization is performed based on this dynamic adjustment data to obtain transient grouting compensation parameters. Real-time parameter adjustments are then made to the transparent soil grouting system according to these transient compensation parameters, and real-time adjustment operation status data is acquired. Error parameters are identified in the real-time adjustment operation status data based on the grout diffusion dynamic simulation data to obtain grouting control error parameters. Finally, dynamic balance control optimization is performed on the transparent soil grouting system based on these grouting control error parameters to generate dynamic control parameters for the transparent soil grouting process, enabling the execution of predictive and optimized control operations for the transparent soil grouting process.The beneficial effects of this invention are as follows: Multi-source monitoring status data and transparent soil grouting process images under simulated geostress conditions are obtained through multi-source monitoring and boundary recognition, multi-source sensing and preprocessing. Boundary recognition and soil deformation feature extraction are performed on the images. Time synchronization, noise filtering, and geometric calibration are performed on the multi-source data and images to obtain preprocessed data and image sequences, providing reliable input for subsequent modeling. Through coupled feature modeling, geostress, grouting parameters, and grout diffusion response features are extracted. Nonlinear correlation mapping learning is performed to generate geostress-grouting parameter correlation data and collaborative response data, quantifying the coupling relationship. Through digital twin reconstruction, spatial topology analysis is performed on the preprocessed image sequences, and dynamic mapping rendering is performed based on the collaborative response data. The system visualizes the grouting diffusion front, soil deformation, and control parameters. Through predictive simulation and target optimization, it performs digital simulation on the twin model, assesses the deviation between the diffusion boundary and the preset target shape, and generates diffusion deviation assessment data and dynamic adjustment data for grouting parameters. By implementing control and transient compensation, it constructs an adaptive compensation optimization model for grouting parameters based on the adjustment data, solves for transient grouting compensation parameters, updates control parameters in real time, drives the grouting equipment adjustment, and obtains real-time operating status data. Through error assessment and closed-loop learning, it compares simulated data with real-time data, identifies grouting control errors, updates the geostress-grouting parameter correlation data and collaborative response data, corrects the optimization strategy, and outputs dynamic control parameters, achieving closed-loop optimization and dynamic equilibrium control.

[0133] This invention also provides an electronic device, which includes a processor and a memory;

[0134] The memory stores the program;

[0135] The processor executes a program to perform the aforementioned grouting process prediction and optimization control method; the electronic device has the function of carrying and running the software system for grouting process prediction and optimization control provided in the embodiments of the present invention, such as a personal computer, minicomputer, main frame, workstation, network or distributed computing environment, standalone or integrated computer platform, or communicating with charged particle tools or other imaging devices, etc.

[0136] This invention also provides a computer-readable storage medium storing a program that is executed by a processor to implement the grouting process prediction and optimization control method described above.

[0137] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this invention are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented in the embodiments of this invention. Alternative embodiments are contemplated, in which the order of various operations is changed and sub-operations described as part of a larger operation are executed independently.

[0138] This invention also discloses a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium and execute the computer instructions, causing the computer device to perform the aforementioned grouting process prediction and optimization control method.

[0139] Furthermore, although the invention has been described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the described functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the invention. Rather, considering the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed in the embodiments of the invention, the actual implementation of the module will be understood within the scope of conventional skill of an engineer. Therefore, those skilled in the art can implement the invention as set forth in the claims using ordinary techniques without excessive experimentation. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the invention, which is determined by the full scope of the appended claims and their equivalents.

[0140] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0141] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can include, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0142] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0143] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0144] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0145] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

[0146] The above is a detailed description of the preferred embodiments of the present invention, but the present invention is not limited to the embodiments described. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention, and these equivalent modifications or substitutions are all included within the scope defined by the claims of this application.

Claims

1. A method for predicting and optimizing the grouting process, characterized in that, include: S100: Acquire multi-source monitoring status data and transparent soil grouting process images of the transparent soil grouting test device under simulated in-situ stress conditions; Identify transparent soil grouting diffusion boundary region and soil deformation characteristics based on transparent soil grouting process images. S200: Based on multi-source monitoring status data, feature extraction and nonlinear correlation mapping learning are performed to obtain ground stress-grouting parameter correlation data. Based on the ground stress-grouting parameter correlation data, multi-level collaborative response neural network learning is performed on grouting pressure parameters and grouting flow parameters to obtain collaborative response data of transparent soil grouting process. S300: Based on the monitoring images of the transparent soil grouting process, the three-dimensional structural data of the transparent soil grouting area is obtained. Based on the collaborative response data of the transparent soil grouting process, the three-dimensional structural data of the transparent soil grouting area is dynamically rendered to obtain the dynamic rendering model of the transparent soil grouting process. S400 performs digital dynamic simulation of the grouting process on the dynamic rendering model of transparent soil grouting process, obtains dynamic simulation data of grout diffusion, and dynamically adjusts the control parameters of the dynamic simulation data of grout diffusion based on the grout diffusion boundary area of ​​transparent soil and the preset grouting target shape, to obtain dynamic adjustment data of grouting pressure parameters and grouting flow rate parameters. S500 performs adaptive grouting parameter compensation optimization based on dynamic adjustment data of grouting pressure and grouting flow parameters to obtain transient grouting compensation parameters. Based on the transient grouting compensation parameters, the transparent soil grouting system is adjusted in real time, and real-time adjustment operation status data is obtained. S600 identifies error parameters in real-time adjustment and operation status data based on dynamic simulation data of grout diffusion to obtain grouting control error parameters. Based on the grouting control error parameters, the transparent soil grouting system is dynamically balanced and optimized to generate dynamic control parameters for the transparent soil grouting process, so as to perform predictive and optimized control operations for the transparent soil grouting process.

2. The grouting process prediction and optimization control method according to claim 1, characterized in that, S100 includes: S110, to perform real-time monitoring of the transparent soil grouting test device under simulated in-situ stress conditions, and to acquire multi-source monitoring status data of the test device; the multi-source monitoring status data includes, but is not limited to, overlying stress parameters, pore water pressure parameters, grouting pressure parameters, and grouting flow rate parameters; S120 applies the overburden stress, simulating in-situ stress, to the transparent soil model through a loading device, and collects and records the overburden stress in real time to obtain overburden stress time series data. S130 uses pore water pressure sensors deployed inside and / or outside the transparent soil model to collect and record pore water pressure in real time, thereby obtaining pore water pressure time series data. S140 uses a pressure sensor and a flow meter installed in the grouting pipeline to collect and record grouting pressure and grouting flow in real time, thereby obtaining grouting pressure time series data and grouting flow time series data. S150, acquires monitoring image sequences of the transparent soil grouting process through imaging devices deployed on the sidewalls and / or top of the transparent soil model; S160, preprocesses the monitoring image sequence of transparent soil grouting process, including but not limited to time synchronization, geometric calibration and noise filtering; S170, based on the preprocessed monitoring image sequence, performs visual recognition of the grout diffusion front and soil displacement to extract the grout diffusion front contour line and soil deformation features; according to the grout diffusion front contour line, the monitoring image is segmented into regions to obtain the transparent soil grouting diffusion boundary region and soil deformation features.

3. The grouting process prediction and optimization control method according to claim 1, characterized in that, S200 includes: S210, based on the overlying stress parameters and pore water pressure parameters, the historical time series data of grouting pressure parameters and grouting flow rate parameters are subjected to disturbance analysis to obtain the disturbance response data of grouting parameters under in-situ stress conditions. S220, based on the disturbance response data of grouting parameters, nonlinear correlation mapping learning is performed on the overlying stress parameters, pore water pressure parameters, and grouting pressure parameters and grouting flow rate parameters to obtain the correlation data between ground stress and grouting parameters; S230, the temporal evolution characteristics of the grouting diffusion boundary area and soil deformation characteristics of transparent soil are analyzed to obtain grouting diffusion-soil response characteristic data; S240 uses a multi-level collaborative response neural network to learn the correlation data between ground stress and grouting parameters and the grouting diffusion and soil response characteristics data, thereby generating collaborative response data for the transparent soil grouting process.

4. The grouting process prediction and optimization control method according to claim 1, characterized in that, The S300 includes: S310, acquire monitoring image sequences of the transparent soil grouting process; S320, perform spatial topological analysis of the grout diffusion area on the monitoring image sequence of the transparent soil grouting process to obtain spatial topological data of the grout diffusion area; S330, based on the spatial topology data of the grouting diffusion area, performs three-dimensional morphological analysis to obtain the three-dimensional morphological data of the grout diffusion front; S340: Using the three-dimensional morphological data of the grout diffusion front, the monitoring image sequence of the transparent soil grouting process is reconstructed in three dimensions to build a three-dimensional structural model of transparent soil grout diffusion. S350, based on the collaborative response data of the transparent soil grouting process, performs dynamic parameter rendering on the three-dimensional structural model of transparent soil grouting diffusion, thereby constructing a dynamic rendering model of the transparent soil grouting process.

5. The grouting process prediction and optimization control method according to claim 1, characterized in that, The S400 includes: S410, Perform digital dynamic simulation of the grouting process on the dynamic rendering model of transparent soil grouting process to obtain dynamic simulation data of grout diffusion; the dynamic simulation data of grout diffusion includes, but is not limited to, grout diffusion range, diffusion front position and soil deformation response data at different time steps. S420 uses time-series evolution analysis based on dynamic simulation data of grout diffusion to predict the grout diffusion morphology and diffusion influence range at future moments, thereby obtaining prediction data for the transparent soil grouting process. S430, based on the diffusion boundary area of ​​transparent soil grouting and the preset grouting target shape, the deviation evaluation analysis of the predicted data of transparent soil grouting process is carried out to obtain diffusion deviation evaluation data. S440 calculates the dynamic adjustment of grouting pressure and grouting flow parameters based on diffusion deviation assessment data, thereby generating dynamic adjustment data for grouting pressure and grouting flow parameters.

6. The grouting process prediction and optimization control method according to claim 1, characterized in that, The S500 includes: S510, based on diffusion deviation assessment data and dynamic adjustment data of grouting pressure parameters and grouting flow rate parameters, performs adaptive grouting parameter compensation optimization on transient grouting parameters to obtain transient grouting compensation parameters; S520 performs optimal collaborative control decisions on the dynamic adjustment data of grouting pressure parameters and grouting flow parameters, as well as transient grouting compensation parameters, to obtain the optimal control parameters for the transparent soil grouting system. S530 adjusts the parameters of the transparent soil grouting system in real time based on the optimal control parameters of the transparent soil grouting system, and obtains real-time adjustment operation status data.

7. The grouting process prediction and optimization control method according to claim 6, characterized in that, The S600 includes: S610: Acquire real-time adjustment and operation status data of the transparent soil grouting system, and perform time synchronization and data preprocessing on the real-time adjustment and operation status data and grout diffusion dynamic simulation data to obtain comparable measured operation data and simulation prediction data. S620, based on the comparative analysis of actual measured data and simulated prediction data, calculates the deviation of parameters such as grouting diffusion range, diffusion front position, grouting pressure and grouting flow rate, so as to obtain grouting control error parameters including but not limited to diffusion deviation, pressure deviation and flow rate deviation. S630: Based on the grouting control error parameters, a dynamic balance control optimization model for the transparent soil grouting process is established. The correction amounts of the grouting pressure parameters and grouting flow rate parameters are calculated to generate dynamic control parameters for the transparent soil grouting process, which can be used for subsequent transparent soil grouting process prediction and optimization control operations.

8. A grouting process prediction and optimization control device, characterized in that, include: The first module is used to acquire multi-source monitoring status data of the transparent soil grouting test device under simulated in-situ stress conditions and images of the transparent soil grouting process, and to identify the grouting diffusion boundary region and soil deformation characteristics of the transparent soil based on the images of the transparent soil grouting process. The second module is used to extract features and learn nonlinear correlation mapping based on multi-source monitoring status data to obtain ground stress-grouting parameter correlation data. Based on the ground stress-grouting parameter correlation data, a multi-level collaborative response neural network is used to learn grouting pressure parameters and grouting flow parameters to obtain collaborative response data of transparent soil grouting process. The third module is used to obtain the three-dimensional structural data of the transparent soil grouting area based on the monitoring images of the transparent soil grouting process, and to perform dynamic parameter rendering on the three-dimensional structural data of the transparent soil grouting area based on the collaborative response data of the transparent soil grouting process to obtain the dynamic rendering model of the transparent soil grouting process. The fourth module is used to perform digital dynamic simulation of the grouting process on the dynamic rendering model of transparent soil grouting process, obtain dynamic simulation data of grout diffusion, and dynamically adjust the control parameters of the dynamic simulation data of grout diffusion based on the grout diffusion boundary area of ​​transparent soil and the preset grouting target shape, so as to obtain dynamic adjustment data of grouting pressure parameters and grouting flow rate parameters. The fifth module is used to perform adaptive grouting parameter compensation optimization based on the dynamic adjustment data of grouting pressure parameters and grouting flow parameters, obtain transient grouting compensation parameters, adjust the parameters of the transparent soil grouting system in real time according to the transient grouting compensation parameters, and obtain real-time adjustment operation status data. The sixth module is used to identify error parameters in the real-time adjustment operation status data based on the dynamic simulation data of grout diffusion, and obtain the grouting control error parameters; based on the grouting control error parameters, the transparent soil grouting system is dynamically balanced and optimized to generate dynamic control parameters for the transparent soil grouting process, so as to perform the prediction and optimization control operation of the transparent soil grouting process.

9. An electronic device, characterized in that, Including the processor and memory; The memory is used to store programs; The processor executes the program to implement the grouting process prediction and optimization control method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The storage medium stores a program, which is executed by a processor to implement the grouting process prediction and optimization control method as described in any one of claims 1-7.

Images