A road grouting control method, system, device and medium

Abstract

The application belongs to the technical field of road maintenance, and discloses a road grouting control method, system, device and medium. The method first collects geological radar, pipeline detection and geological survey data of a target area, generates a construction planning graph containing grouting hole position coordinates and design parameter ranges; drills holes according to the planning, lays out distributed optical fibers and pore water pressure and pH sensors, and constructs a multi-scale monitoring network. During grouting construction, monitoring data is collected in real time, input into a pre-trained inversion model to generate a slurry three-dimensional probability field and a front pressure; the pipeline spacing, pore water pressure and pH changes are calculated respectively to obtain macroscopic and microscopic risk indexes. According to the double risk indexes, grouting pressure and slurry ratio control instructions are dynamically generated, and the intelligent grouting equipment executes the operation. After grouting is completed, the soil density is evaluated through the optical fiber vibration signal frequency spectrum attenuation rate, and the seepage and chemical change conditions are determined in combination with the sensor data, so that the grouting construction quality and operation safety are effectively improved.

Description

Technical Field

[0001] This application relates to the technical field of road maintenance, and in particular to a road grouting control method, system, equipment and medium. Background Technology

[0002] As the core of transportation infrastructure, the stability of the road's foundation structure directly affects its service life and driving safety. With the rapid development of my country's transportation industry, the continuous increase in heavy traffic volume, increasingly complex geological conditions, and the long-term impact of environmental factors, road foundations commonly exhibit defects such as uneven settlement, cracks, voids, and subgrade frost heave, seriously threatening road operational safety and shortening road lifespan. Grouting reinforcement technology, with its advantages of convenient construction, controllable cost, and significant reinforcement effects, has become a core method for repairing and reinforcing road foundation defects. By injecting specific grout into the foundation, it can effectively fill soil voids, consolidate loose soil, and improve the bearing capacity of the foundation, thereby enhancing the overall stability of the road structure.

[0003] However, in practical engineering applications, traditional road grouting construction still has many drawbacks: the separation of geological survey and pipeline detection data before construction leads to a lack of precision in grouting hole design, easily resulting in blind drilling and grouting, which not only wastes resources such as grout and manpower, but may also damage underground pipelines and cause safety accidents; monitoring methods during construction are limited, mostly focusing on basic parameters such as grouting pressure and flow rate, leaving the grouting process in an "invisible and uncontrollable" state. Therefore, it is difficult to meet the high requirements for grouting construction quality and safety in urban roads and heavy-duty roads. Summary of the Invention

[0004] To improve the quality and safety of grouting construction, this application provides a road grouting control method, system, equipment, and medium.

[0005] Firstly, this application provides a method for controlling road grouting, employing the following technical solution: A method for controlling road grouting, comprising: Collect ground-penetrating radar data, pipeline detection data, and geological survey data of the target area to generate a construction planning map that includes the coordinates of grouting hole locations and the range of design parameters; Based on the construction plan, boreholes were drilled on site, and a distributed fiber optic acoustic sensor network, pore water pressure sensor, and pH sensor were deployed to form a multi-scale monitoring network. During the grouting process, distributed optical fiber vibration data and microscopic sensor data are acquired in real time and input into a pre-trained inversion model to dynamically generate a three-dimensional probability field of grout distribution and grout front pressure. The minimum distance between the slurry and the pipeline is calculated based on the three-dimensional probability field, and the changes in pore water pressure and pH are calculated based on the microscopic sensor data, generating macroscopic risk index and microscopic risk index respectively. Based on the macro risk index and the micro risk index, dynamic decisions are made and real-time pressure control commands and grout ratio adjustment commands are generated for each grouting hole; the intelligent grouting equipment executes the real-time pressure control commands and grout ratio adjustment commands to complete the grouting operation; After grouting, the soil density is assessed based on the attenuation rate of the distributed optical fiber vibration signal spectrum before and after grouting, and the continuous seepage and chemical changes are confirmed based on the recovery of microscopic sensor data.

[0006] By adopting the above technical solutions, ground-penetrating radar, pipeline detection, and geological exploration data are deeply integrated. The generated construction planning map accurately locates the grouting holes and clarifies the parameter range, avoiding resource waste and construction risks caused by blind drilling and grouting from the outset. During construction, a multi-scale monitoring system composed of a distributed fiber optic acoustic sensor network and micro-sensors enables real-time perception of all dimensions from macroscopic grout diffusion to microscopic soil environment changes. Combined with a pre-trained inversion model, it can dynamically reconstruct the three-dimensional morphology of grout distribution and frontal pressure, making the previously invisible grouting process visible and quantifiable. Furthermore, the dynamic decision-making mechanism based on macroscopic and microscopic risk indices can adjust the grouting pressure and grout ratio in real time according to changes in the distance between the grout and the pipeline, pore water pressure, and pH value. This ensures the effectiveness of grouting reinforcement while minimizing disturbance to surrounding pipelines and the soil environment, effectively avoiding problems such as grout cross-hole formation, pipeline damage, and soil seepage that are common in traditional grouting construction. After grouting is completed, the soil density is assessed by the spectral attenuation rate, and the seepage and chemical changes are confirmed by combining sensor data. This forms a complete closed loop from pre-construction planning and construction control to post-construction acceptance, improving the efficiency and quality of road grouting construction.

[0007] Optionally, generating a construction planning drawing that includes the coordinates of grouting hole locations and the range of design parameters specifically includes: Based on the aforementioned ground-penetrating radar data, pipeline detection data, and geological exploration data, a digital twin model is constructed that includes a soil mechanical parameter field, a pipeline vector network, and a three-dimensional boundary of the target repair area. Based on the digital twin model, with the optimization objectives of minimum drilling cost, minimum grouting material cost and minimum risk to adjacent pipelines, multi-objective path planning is carried out under the conditions of satisfying regional coverage constraints, pipeline avoidance constraints and construction constraints, and a construction planning map containing grouting hole coordinates and design parameter range is generated. The deployment of pore water pressure sensors and pH sensors specifically includes: Based on the pipeline vulnerability index and spatial distance in the pipeline vector network, pore water pressure sensors and pH sensors are deployed near high-risk pipelines.

[0008] By adopting the above technical solutions, during the construction planning phase, a digital twin model constructed based on multi-source geological data is used to achieve three-dimensional visualization and fusion of soil mechanical properties, pipeline distribution, and repair area boundaries. Based on this, multi-objective path planning, while considering drilling costs, grouting material costs, and pipeline risks, adheres to construction constraints such as area coverage and pipeline avoidance. The generated grouting hole coordinates and design parameter ranges not only achieve comprehensive coverage of the target area at the lowest cost but also avoid potential threats to pipelines from the source, achieving an optimal balance between construction efficiency and cost control. Based on the pipeline vulnerability index and spatial distance, pore water pressure sensors and pH sensors are deployed directionally, precisely focusing monitoring resources around high-risk pipelines. This allows for real-time capture of subtle changes in the soil environment and timely early warning at the initial stage of risk development.

[0009] Optionally, the steps for generating a construction planning drawing that includes the coordinates of grouting hole locations and the range of design parameters specifically include: Define the orientation of the grouting hole and the designed grouting volume as decision variables; An optimization function is constructed with the total drilling cost, total grouting material cost and pipeline proximity risk as the objective. The proximity risk of a single borehole to a single pipeline is characterized by the product of the pipeline vulnerability index in the pipeline vector network and the negative exponential function of the spatial distance between the two. The distance from any point within the target repair area to the nearest grouting hole is set to be no greater than the effective grouting radius, and the spatial distance between any grouting hole and any pipeline in the pipeline vector network is set to be no less than the minimum safe distance as a hard constraint. A multi-objective optimization algorithm was used to solve the problem, resulting in a set of Pareto optimal solutions. Slurry diffusion simulations were then performed to verify each candidate solution. Based on the verification results, the final solution is selected from the Pareto optimal solution set, and the construction planning diagram is output.

[0010] By adopting the above technical solution, the constructed optimization function integrates the total drilling cost, total grouting material cost, and pipeline proximity risk in a weighted manner. Pipeline proximity risk is characterized by a negative exponential function of pipeline vulnerability index and spatial distance, reflecting both the differences in vulnerability among different pipelines and accurately quantifying the impact of distance on risk, thus providing a scientific basis for balancing cost and risk. The established hard constraints ensure that grouting operations can fully cover the target repair area while completely avoiding direct threats to pipelines from a spatial distance perspective, laying a solid foundation for construction safety. A multi-objective optimization algorithm is used to obtain the Pareto optimal solution set, providing the construction party with multiple alternatives that balance cost and safety. Further verification through grout diffusion simulation further ensures the feasibility and effectiveness of the selected solutions, avoiding the problem of disconnect between theoretical planning and actual construction.

[0011] Optionally, the steps of dynamically making decisions and generating real-time pressure control commands and grout ratio adjustment commands for each grouting hole specifically include: When any of the aforementioned micro-risk indices exceeds the emergency risk threshold, an emergency stop or depressurization command is generated, and the emergency sealing grouting process is triggered. When the macro risk index exceeds the macro threshold or any of the micro risk indices exceeds the optimized risk threshold, the real-time optimization controller is activated. The optimized risk threshold is less than the emergency risk threshold. The real-time optimization controller aims to minimize the weighted sum of the macro risk index and the micro risk index while maximizing the filling efficiency. It uses the pressure of each grouting hole and the water-cement ratio of the grout as optimization variables, solves the problem within the pressure range allowed by the equipment and the formation, and outputs the optimized pressure and proportion instruction set. When both the macro risk index and any of the micro risk indices are below the optimized risk threshold, grouting shall continue according to the design parameters in the construction plan.

[0012] By adopting the above technical solutions, in extreme cases where the micro-risk index exceeds the emergency risk threshold, emergency stop, pressure reduction commands, and barrier grouting procedures are directly triggered. This allows for rapid action at the moment a risk is imminent, minimizing the occurrence of serious safety accidents such as grout leakage and pipeline damage, thus establishing a final, solid line of defense for construction safety. When the macro-risk index exceeds the macro threshold or the micro-risk index exceeds the optimized risk threshold, a real-time optimization controller is activated. Aiming to balance risk and filling efficiency, the grouting pressure and water-cement ratio are dynamically adjusted within the limits allowed by the equipment and the geological formation. This approach avoids overly conservative adjustments that could affect construction progress while promptly controlling risks within a safe range, achieving a dynamic balance between safety and efficiency. When all risk indices are within the safe range, grouting continues using the original design parameters, ensuring construction stability and efficiency and avoiding unnecessary adjustments that could disrupt the construction schedule.

[0013] Optionally, the emergency sealing grouting process specifically includes: If an emergency risk is triggered during the main grouting process, a fast-setting inert isolation grout is immediately injected into the high-risk pipeline adjacent area corresponding to the microscopic sensor that exceeds the standard at a pressure lower than that of the main grouting. The readings of the pore water pressure sensors deployed in the adjacent area of ​​the high-risk pipeline are monitored in real time. When the readings continue to decrease and stabilize within the safe threshold range within a set time window, it is determined that an emergency sealing barrier has been formed. The high-risk pipeline adjacent area is included in the main grouting adaptive control closed loop, and a micro-risk early warning threshold is enabled for the high-risk pipeline adjacent area that is below the optimized risk threshold.

[0014] By adopting the above technical solution, during the main grouting process, inert isolation grout is injected into the adjacent area of ​​high-risk pipelines that are highly vulnerable and close to the grouting holes. This is equivalent to building a physical buffer barrier between the high-risk pipelines and the grouting area, effectively preventing the main grout from spreading towards the pipeline and avoiding direct contact or penetration of the grout into the surrounding soil. This reduces the risk of grout squeezing and corrosion of the pipeline from the source. Simultaneously, real-time monitoring of pore water pressure sensor readings determines whether the physical barrier has initially formed, ensuring the reliability of the protective measures. Furthermore, incorporating the adjacent area of ​​the high-risk pipeline into the main grouting adaptive control closed loop and setting a lower micro-risk early warning threshold further strengthens the dynamic control of this area. Once subtle anomalies occur in the soil environment, the control mechanism can be triggered promptly, allowing for earlier intervention compared to conventional areas, providing a more robust safety guarantee for high-risk pipelines.

[0015] Optionally, the steps for assessing soil compaction based on the attenuation rate of the distributed optical fiber vibration signal spectrum before and after grouting specifically include: The root mean square amplitude of the background vibration signal in a specific frequency band of the target repair area before grouting is extracted as the reference value. The root mean square amplitude of the vibration signal in the same area and frequency band after grouting was completed was extracted as the posterior value. Calculate the regional average attenuation rate based on the baseline value and the posterior value; The average attenuation rate of the region is compared with the preset density level threshold to output the quantitative evaluation result of soil density.

[0016] By adopting the above technical solution, the root mean square amplitude of the background vibration signal in a specific frequency band of the target repair area before grouting is extracted as a benchmark value, establishing a reliable reference standard for subsequent comparative evaluation. After grouting, the root mean square amplitude of the vibration signal in the same area and frequency band is extracted as a posterior value. By calculating the regional average attenuation rate, the change in soil density is transformed into a quantifiable numerical indicator, making the soil reinforcement effect, which was originally difficult to judge intuitively, clearly visible. The quantitative evaluation results output after comparing the regional average attenuation rate with the preset density level threshold can not only accurately reflect the overall soil density of the target area, but also avoid the evaluation bias caused by the limitations of traditional sampling inspection, achieving a comprehensive evaluation of the grouting repair area.

[0017] Optionally, the road grouting control method further includes: The sensing data, inversion results, control command sequence, and final effect evaluation data of a single grouting project are packaged and stored in the case database throughout the entire cycle. Historical data from the case database is periodically retrieved to retrain and update the parameters of the inversion model and the risk index generation related model. The updated model will be applied to path planning and real-time control in subsequent projects.

[0018] Secondly, this application provides a road grouting control system, which adopts the following technical solution: A road grouting control system, comprising: The data acquisition and modeling module is used to collect ground-penetrating radar data, pipeline detection data and geological survey data of the target area, and generate a construction planning map that includes the coordinates of grouting hole locations and the range of design parameters. The on-site deployment and monitoring module is used to drill holes on-site according to the construction plan and deploy a distributed fiber optic acoustic sensor network, a pore water pressure sensor, and a pH sensor to form a multi-scale monitoring network to acquire distributed fiber optic vibration data and micro-sensor data in real time. The grout dynamic inversion module is used to receive the distributed optical fiber vibration data and microscopic sensor data during the grouting construction process, and input them into the pre-trained inversion model to dynamically generate the three-dimensional probability field of grout distribution and grout front pressure. The multi-scale risk assessment module is used to calculate the minimum distance between the slurry and the pipeline based on the three-dimensional probability field, and to calculate the pore water pressure change and pH change based on the microscopic sensor data, thereby generating macroscopic risk index and microscopic risk index respectively. The intelligent decision-making and control instruction generation module is used to dynamically make decisions and generate real-time pressure control instructions and grout ratio adjustment instructions for each grouting hole based on the macro risk index and the micro risk index. The intelligent grouting execution module is used to control the intelligent grouting equipment to execute the real-time pressure control command and the grout ratio adjustment command to complete the grouting operation; The effect evaluation module is used to assess the soil compaction based on the attenuation rate of the distributed optical fiber vibration signal spectrum before and after grouting, and to confirm the continuous seepage and chemical changes based on the recovery of microscopic sensor data.

[0019] Thirdly, this application provides a computer device that adopts the following technical solution: A computer device includes a memory, a processor, and a computer program stored in the memory, the processor executing the computer program to implement the road grouting control method as described in the first aspect.

[0020] Fourthly, this application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium storing a computer program capable of being loaded by a processor and executing the road grouting control method as described in the first aspect.

[0021] In summary, this application includes at least one of the following beneficial technical effects: A closed-loop management system is constructed to cover the entire process, including intelligent planning before construction, real-time monitoring and dynamic control at multiple scales during construction, and quantitative evaluation of the spectrum after construction. Relying on digital twins, sensor monitoring and intelligent inversion models, the grouting process is visualized and quantified, which completely solves the problems of blind drilling and injection in traditional grouting and difficulty in accurately judging the reinforcement effect, thereby improving construction efficiency and the accuracy of soil compaction assessment.

[0022] By implementing multi-objective optimization planning, graded risk threshold control, and grouting protection for high-risk pipelines, the project effectively avoids risks such as grout cross-flow, pipeline damage, soil seepage, and chemical disturbance while optimizing the cost of drilling and grouting materials. This achieves a synergistic balance between grouting reinforcement effect, construction safety, and cost control. Attached Figure Description

[0023] Figure 1 This is a first flowchart of an embodiment of the method of this application; Figure 2 This is a second flowchart of an embodiment of the method of this application; Figure 3 This is a third flowchart of an embodiment of the method of this application; Figure 4 This is the fourth flowchart of an embodiment of the method of this application. Detailed Implementation

[0024] To make the purpose, technical solution, and advantages of this application clearer, the following description is provided in conjunction with the appendix. Figures 1-4 The present application will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the application.

[0025] The first embodiment of this application discloses a method for controlling road grouting. (Refer to...) Figure 1 The road grouting control method includes S110-S160: S110 collects ground-penetrating radar data, pipeline detection data, and geological survey data of the target area, and generates a construction planning map that includes the coordinates of grouting hole locations and the range of design parameters. S120 involves drilling on-site according to the construction plan and deploying a distributed fiber optic acoustic sensor network, pore water pressure sensor, and pH sensor to form a multi-scale monitoring network. S130 acquires distributed optical fiber vibration data and microscopic sensor data in real time during grouting construction, and inputs them into a pre-trained inversion model to dynamically generate a three-dimensional probability field of grout distribution and grout front pressure. S140 calculates the minimum distance between the slurry and the pipeline based on a three-dimensional probability field, and calculates the changes in pore water pressure and pH based on microscopic sensor data, generating macroscopic risk index and microscopic risk index respectively. S150 dynamically makes decisions and generates real-time pressure control commands and grout ratio adjustment commands for each grouting hole based on macro and micro risk indices; the intelligent grouting equipment executes the real-time pressure control commands and grout ratio adjustment commands to complete the grouting operation; S160 After grouting, the soil density is assessed based on the attenuation rate of the distributed optical fiber vibration signal spectrum before and after grouting, and the continuous seepage and chemical changes are confirmed based on the recovery of microscopic sensor data.

[0026] S110, generating a construction planning drawing that includes the coordinates of grouting hole locations and the range of design parameters, specifically includes: Based on ground-penetrating radar data, pipeline detection data, and geological survey data, a digital twin model is constructed, which includes a soil mechanical parameter field, a pipeline vector network, and a three-dimensional boundary of the target repair area. Based on the digital twin model, with the optimization objectives of minimizing drilling cost, minimizing grouting material cost, and minimizing adjacent pipeline risk, multi-objective path planning is performed under the conditions of satisfying regional coverage constraints, pipeline avoidance constraints, and construction constraints, generating a construction planning map that includes grouting hole coordinates and design parameter ranges.

[0027] In S120, the installation of pore water pressure sensors and pH sensors specifically includes: Based on the pipeline vulnerability index and spatial distance in the pipeline vector network, pore water pressure sensors and pH sensors are deployed near high-risk pipelines.

[0028] Reference Figure 2 Furthermore, the steps for generating a construction planning drawing that includes the coordinates of grouting hole locations and the range of design parameters specifically include S210-S250: S210, define the position of the grouting hole and the designed grouting volume as decision variables; S220 constructs an optimization function with the total drilling cost, total grouting material cost and pipeline proximity risk as the objective. The proximity risk of a single borehole to a single pipeline is characterized by the product of the pipeline vulnerability index in the pipeline vector network and the negative exponential function of the spatial distance between the two. S230 sets a hard constraint that the distance from any point in the target repair area to the nearest grouting hole is no greater than the effective grouting radius, and the spatial distance between any grouting hole and any pipeline in the pipeline vector network is no less than the minimum safe distance. S240 was solved using a multi-objective optimization algorithm to obtain a set of Pareto optimal solutions, and slurry diffusion simulation was performed to verify each candidate scheme. S250: Based on the verification results, select the final solution from the Pareto optimal solution set and output the construction planning diagram.

[0029] Specifically, for step S110, a high-frequency ground-penetrating radar (GPR) instrument is used to perform a comprehensive scan of the target repair area. The detection depth and scanning interval are set according to the soil conditions, and raw GPR data, including parameters such as reflected wave amplitude and propagation time, are collected. Simultaneously, an underground pipeline detector, combining electromagnetic induction and grounding methods, is used to detect underground pipelines within the area. The detection range covers the target repair area and the surrounding safety margin, accurately collecting data such as pipeline burial depth, diameter, material, and direction to construct the raw dataset of the pipeline vector network. Furthermore, borehole exploration is employed, with exploration holes laid out in a grid pattern within the target repair area. The hole depth is consistent with the grouting design depth, and soil samples are collected at set intervals. Laboratory tests are used to determine the soil's unit weight, cohesion, internal friction angle, porosity, and other mechanical parameters, forming a geological exploration dataset.

[0030] The three types of data mentioned above are imported into BIM modeling software and a digital twin platform. Data redundancy and errors are eliminated through data fusion algorithms. Specifically, the soil mechanical parameter field is spatially interpolated using the Kriging interpolation method to generate a continuous three-dimensional mechanical parameter distribution field. The pipeline vector network is calibrated and topologically constructed using GIS technology to clarify the connection relationships and spatial locations between pipelines. The three-dimensional boundary of the target repair area is outlined using CAD software and corrected by combining the stratigraphic interface data detected by ground-penetrating radar. Finally, a digital twin model containing the soil mechanical parameter field, pipeline vector network, and three-dimensional boundary of the target repair area is constructed to ensure that the model can accurately reflect the actual geological and pipeline conditions on site.

[0031] Based on the constructed digital twin model, the orientation of the grouting holes and the designed grouting volume are identified as core decision variables. The orientation of the grouting holes is defined using the local plane coordinate system, including plane coordinates and elevation, with the hole inclination angle strictly controlled within allowable limits. The designed grouting volume is determined based on the soil porosity, solidified volume, and grout loss coefficient of the target repair area, calculated using the formula Q = K × V × n, where Q is the designed grouting volume, K is the grout loss coefficient, V is the solidified volume of the target repair area calculated from the three-dimensional boundary in the digital twin model, and n is the soil porosity. The principle for allocating the grouting volume per hole is also clearly defined, with reasonable allocation based on the location of the grouting holes and differences in soil mechanical parameters to ensure grouting uniformity.

[0032] A multi-objective optimization function is constructed, with the weighted sum of total drilling cost, total grouting material cost, and pipeline proximity risk as the optimization objective. The weight coefficients are set according to the project priority.

[0033] The total drilling cost is determined based on the number of grouting holes and the drilling depth per hole; the total grouting material cost is determined based on the designed total grouting volume and the unit price of the grout. The core of pipeline proximity risk calculation is the proximity risk of a single hole to a single pipeline, which is represented as the product of the pipeline vulnerability index in the pipeline vector network and the negative exponential function of the spatial distance between the two. The pipeline vulnerability index is determined based on the pipeline material, service life, and pressure rating, and then normalized; the negative exponential function of the spatial distance is set as... ,in This is the normalized pipeline vulnerability index. The attenuation coefficient is determined based on the soil type, and d is the straight-line spatial distance between the grouting hole and the pipeline. For example, the normalized vulnerability index of a steel gas pipeline... The spatial distance between the grouting hole and the pipeline is d=2m. The single hole poses a risk to the vicinity of the pipeline. .

[0034] The total pipeline proximity risk is the sum of the proximity risks of all individual boreholes to all pipelines. Finally, after normalizing the total drilling cost, total grouting material cost, and total pipeline proximity risk, the target value of the optimization function is obtained by weighted summation.

[0035] Two hard constraints are set to ensure the safety and effectiveness of grouting construction. The first constraint is that the distance from any point in the target repair area to the nearest grouting hole is not greater than the effective grouting radius. The effective grouting radius is determined through field tests based on the grout type, grouting pressure, and soil permeability, ensuring that all points in the repair area are covered by grout. The second constraint is that the spatial distance between any grouting hole and any pipeline in the pipeline vector network is not less than the minimum safe distance. The minimum safe distance is determined based on the pipeline type and follows industry standards. The grouting hole positions are verified in the digital twin model. If the minimum safe distance is not met, the planar coordinates of the grouting hole need to be adjusted to ensure that all grouting holes meet both constraints.

[0036] The NSGA-III multi-objective optimization algorithm is used to solve the optimization function. To address the uncertainty in the dimensionality of decision variables caused by variations in the number of grouting holes, a variable-length encoding strategy is employed for population initialization and genetic operations. Algorithm constraints are incorporated into the algorithm's fitness function, penalizing candidate solutions that do not meet the constraints.

[0037] After solving the problem, a set of Pareto optimal solutions was obtained. Each candidate solution included core parameters such as the number of grouting holes, their orientation coordinates, and the designed grouting volume. Subsequently, each candidate solution underwent grout diffusion simulation verification. Numerical simulation software was used, inputting the grouting parameters from the candidate solutions and the soil mechanics parameters from the digital twin model into the software to simulate the grout diffusion process in the soil. The focus was on verifying whether the grout diffusion range covered the target repair area and whether the minimum distance between the grout and the pipeline met safety requirements. Candidate solutions that failed the simulation verification were eliminated.

[0038] Based on the grout diffusion simulation verification results, the final scheme was selected from the Pareto optimal solution set using the analytic hierarchy process. The evaluation indicators included grouting effect, construction cost, and pipeline safety risk. Each qualified candidate scheme was scored, and the scheme with the highest score was the final scheme.

[0039] Once the final plan is determined, a construction planning diagram is drawn up, clearly marking the plane coordinates, elevation, hole depth, design grouting volume, grouting pressure, and other parameters of each grouting hole. At the same time, the location, direction, burial depth, and minimum safety distance of underground pipelines are marked, as well as the three-dimensional boundary of the target repair area. The diagram is output for on-site construction personnel to review and use, ensuring that the construction process is strictly carried out in accordance with the plan.

[0040] For step S120, on-site drilling is carried out according to the construction plan, using an engineering geological drilling rig. During drilling, a level is used to calibrate the verticality of the borehole, ensuring that the borehole inclination angle meets the design requirements and the drilling depth is consistent with the design depth. After drilling, debris inside the borehole is cleaned to avoid blocking the grouting channel. Simultaneously, a distributed fiber optic acoustic sensor network is deployed, using single-mode optical fibers, buried at a safe distance around the grouting hole, at the same depth as the grouting hole. The fiber optic connectors are connected using fusion splicing, with both ends connected to a fiber optic sensor demodulator. The demodulator's sampling frequency is set to ensure real-time acquisition of vibration signals.

[0041] In addition, based on the pipeline vulnerability index and spatial distance in the pipeline vector network, high-risk pipelines with vulnerability indices exceeding the threshold and distances from grouting holes within a set range are screened. Pore water pressure sensors and pH sensors are installed near the high-risk pipelines, using sensors with appropriate range and accuracy. At least two sensors are installed in each high-risk pipeline segment, with the sensors buried at the same depth as the pipeline center. After burial, bentonite is used for sealing to ensure full contact between the sensors and the soil. The sensors are connected to the data processing terminal based on LoRa or underground wireless transmission modules with relay functions, forming a multi-scale monitoring network that combines macroscopic (distributed optical fiber) and microscopic (pore water pressure, pH) monitoring to achieve comprehensive monitoring of the grouting process.

[0042] For step S130, during the grouting process, the distributed fiber optic acoustic sensor network collects vibration data in real time through the demodulator, and the micro-sensors collect pore water pressure and pH data at a set frequency. The collected data is uploaded to the data processing terminal in real time through the transmission module. The terminal preprocesses the data to ensure its accuracy.

[0043] Preprocessed monitoring data is input into a pre-trained data-driven inversion prediction model. This model employs a CNN-LSTM hybrid architecture, with vibration data, pore water pressure data, and pH data as inputs, and outputs a three-dimensional probability field of grout distribution and grout front pressure. The model first extracts temporal features from multi-source monitoring data using an LSTM network. Then, it combines the three-dimensional spatial coordinate information from distributed optical fibers and microscopic sensors, utilizing a 3D deconvolution layer for feature upscaling and spatial mapping to generate a gridded three-dimensional probability field. During model training, monitoring data from similar grouting projects and measured grout diffusion data from previous projects are used as training samples to ensure the accuracy of the model's inversion. The three-dimensional probability field is presented using a grid, where the probability value of each grid represents the probability that the location is filled with grout. A probability value greater than or equal to a set upper threshold indicates that the grout filling at that location is relatively dense, while a probability value less than a set lower threshold indicates that the location is not filled with grout. The grout front pressure is calculated through model inversion, reflecting the real-time pressure state at the grout diffusion front and providing data support for risk assessment.

[0044] For step S140, based on the three-dimensional probability field of slurry distribution generated by the inversion model, a spatial distance calculation algorithm is used to calculate the minimum spatial distance between the slurry and each pipeline in the target remediation area, and a macro risk index is generated in combination with the minimum safety distance. In order to maintain logical consistency with the risk model in the optimization planning stage, the calculation formula of the macro risk index adopts a boundary normalization function based on negative exponent: , wherein d is the minimum distance between the slurry and the pipeline, D is the minimum safety distance for this type of pipeline, is the attenuation coefficient consistent with that in the planning stage. When d≥D, M=0 (no macro risk); when d<D, M>0, and the larger the value of M, the higher the macro risk. For example, for a gas pipeline, the minimum safety distance D=1.5m, the attenuation coefficient β=0.8, and the minimum distance between the slurry and the pipeline d=1.2m, then the macro risk index .

[0045] Meanwhile, based on the data collected by micro sensors, the variation of pore water pressure and the variation of pH are calculated, where the variation of pore water pressure ΔP = current pore water pressure value - initial pore water pressure value, and the variation of pH ΔpH = |current pH value - initial pH value|, so as to generate micro risk indexes respectively. To avoid saturation and instability of the control algorithm caused by unlimited increase of the risk index, amplitude-limiting normalization is adopted for calculation: the micro risk index of pore water pressure P=min(1,ΔP / ΔPmax), wherein ΔPmax is the maximum allowable variation of pore water pressure; the micro risk index of pH H=min(1,ΔpH / ΔpHmax), wherein ΔpHmax is the maximum allowable variation of pH. For example, the initial pore water pressure is 0.1MPa, the current value is 0.15MPa, and ΔPmax=0.1MPa, then P=min(1,0.05 / 0.1)=0.5; the initial pH value is 7.2, the current value is 8.0, and ΔpHmax=1.0, then H=min(1,0.8 / 1.0)=0.8. The macro risk index and the micro risk index together constitute the risk evaluation system for the grouting process.

[0046] In S150, the step of dynamically making decisions and generating real-time pressure control instructions and slurry ratio adjustment instructions for each grouting hole specifically includes S151-S153 (not shown in the figure): S151: when any micro risk index exceeds the emergency risk threshold, generate an emergency stop or pressure reduction instruction, and trigger the emergency plugging grouting procedure; S152, when the macro risk index exceeds the macro threshold or any micro risk index exceeds the optimized risk threshold, the real-time optimization controller is activated. The optimized risk threshold is less than the emergency risk threshold. The real-time optimization controller aims to minimize the weighted sum of the macro risk index and the micro risk index while maximizing the filling efficiency. It uses the pressure of each grouting hole and the water-cement ratio of the grout as optimization variables. Based on a pre-trained lightweight proxy model, it quickly evaluates the fitness and solves the problem within the pressure range allowed by the equipment and the formation. It outputs the optimized pressure and proportion instruction set. S153, when both the macro risk index and any micro risk index are below the optimized risk threshold, continue grouting according to the design parameters in the construction plan.

[0047] Reference Figure 3 In S151, the emergency sealing grouting process specifically includes S310-S330: S310, after an emergency risk is triggered during the main grouting process, immediately injects a fast-setting inert isolation grout at a pressure lower than that of the main grouting into the high-risk pipeline adjacent area corresponding to the microscopic sensor that exceeds the standard. S320 monitors the readings of pore water pressure sensors deployed in the adjacent area of ​​high-risk pipelines in real time. When the readings continue to decrease and stabilize within the safe threshold range within a set time window, it is determined that an emergency sealing barrier has been formed. S330 incorporates the adjacent area of ​​high-risk pipelines into the main grouting adaptive control closed loop and enables a micro-risk early warning threshold for the adjacent area of ​​high-risk pipelines that is below the optimized risk threshold.

[0048] Specifically, for step S150, emergency thresholds for the pore water pressure micro-risk index P and the pH micro-risk index H are preset. When either micro-risk index exceeds the emergency risk threshold, the data processing terminal immediately generates an emergency stop or pressure reduction command, which is sent to the intelligent grouting equipment via a wireless transmission module. Upon receiving the command, the equipment stops grouting or reduces the grouting pressure (to below 50% of the design pressure) within 10 seconds, while simultaneously triggering the emergency sealing grouting process to ensure pipeline safety.

[0049] The emergency sealing grouting process is implemented as follows: Upon triggering an emergency risk during the main grouting process, for the high-risk pipeline adjacent area corresponding to the microscopic sensor exceeding the standard, a grouting pump is immediately used to inject a rapidly setting inert isolation grout (such as rapidly setting bentonite-cement mixture grout) at a pressure lower than that of the main grouting. The injection volume is determined based on the volume of the high-risk pipeline adjacent area. A pore water pressure sensor monitors the pore water pressure reading in the high-risk pipeline adjacent area in real time, setting a time window (e.g., 30 minutes). If the reading continuously decreases and stabilizes within the safe threshold range within this time window, an emergency sealing barrier is determined to have formed, effectively preventing further leakage of the main grouting slurry into the high-risk pipeline. Subsequently, the high-risk pipeline adjacent area is incorporated into the main grouting adaptive control closed loop, and a microscopic risk warning threshold is activated for the high-risk pipeline adjacent area that is below the optimized risk threshold. Simultaneously, the data acquisition frequency of the microscopic sensor is increased to strengthen the monitoring of the high-risk area and promptly identify potential risks.

[0050] A macro-risk threshold and an optimized risk threshold are pre-set, with the optimized risk threshold being lower than the emergency risk threshold. When the macro-risk index exceeds the macro-risk threshold, or any micro-risk index exceeds the optimized risk threshold, the real-time optimization controller is immediately activated. To meet the real-time control requirement within 10 seconds, the real-time optimization controller employs a particle swarm optimization algorithm and replaces the deep learning inversion model with a lightweight surrogate model pre-trained based on the inversion model for rapid fitness evaluation. The optimization objective is to minimize the weighted sum of the macro-risk index and the micro-risk index while maximizing filling efficiency, using the grouting pressure and water-cement ratio of each grouting hole as optimization variables. The optimization controller completes the solution within 10 seconds by calling monitoring data in real time, outputting the optimized grouting pressure and mix ratio instruction set.

[0051] When both the macro risk index and any micro risk index are below the optimized risk threshold, the real-time optimization controller stops working, and the intelligent grouting equipment continues to grout according to the design parameters (grouting pressure, water-cement ratio, grouting volume) in the construction plan, ensuring construction efficiency and grouting effect.

[0052] The intelligent grouting equipment employs a fully automatic grouting pump with automatic adjustment capabilities. Equipped with pressure sensors, flow sensors, and a grout mixing device, the equipment can automatically adjust grouting pressure, grout flow rate, and mix ratio. The equipment receives pressure control commands and grout mix ratio adjustment commands from the real-time optimization controller via a wireless transmission module, with a command response time ≤5s. When receiving a pressure adjustment command, the equipment adjusts the output pressure of the grouting pump through the hydraulic system, ensuring that the error between the actual grouting pressure and the commanded pressure is ≤±0.02MPa. When receiving a grout mix ratio adjustment command, the equipment controls the water-cement ratio of the grout by adjusting the cement and water delivery flow rates. For example, when the commanded water-cement ratio is 1.0, the equipment adjusts the cement delivery rate to 30L / min and the water delivery rate to 30L / min, ensuring a mix ratio error ≤±0.05. During the grouting process, the equipment collects real-time data on actual grouting pressure, flow rate, and mix ratio, and uploads it to the data processing terminal for real-time monitoring by staff. If equipment failure occurs (such as abnormal pressure or flow interruption), the equipment immediately issues an alarm signal and automatically stops grouting. After the fault is cleared, the grouting operation resumes according to the terminal instructions until the grouting task of all grouting holes is completed, ensuring the intelligent and precise nature of the grouting operation.

[0053] Reference Figure 4 In S160, the steps for assessing soil compaction based on the attenuation rate of the distributed optical fiber vibration signal spectrum before and after grouting specifically include S410-S440: S410, extract the root mean square amplitude of the background vibration signal in a specific frequency band of the target repair area before grouting as the reference value; S420, extract the root mean square amplitude of the vibration signal in the same area and frequency band after grouting is completed as the posterior value; S430, calculates the regional average attenuation rate based on the baseline and posterior values; S440 compares the regional average attenuation rate with the preset compaction level threshold and outputs the quantitative assessment results of soil compaction.

[0054] Specifically, for step S160, before the grouting construction begins, a distributed fiber optic acoustic sensor network is deployed to collect the vibration response signal of the target repair area under a specific constant vibration source excitation. The collection time is continuously set for a set duration, and the sampling frequency meets the signal restoration requirements.

[0055] The collected vibration response signals are preprocessed to remove noise, and then the root mean square amplitude of the vibration response signals is extracted as the reference value A0 by the root mean square amplitude calculation method. This reference value is stored in the data processing terminal as a reference standard for subsequent grouting effect evaluation.

[0056] After grouting is completed in all grouting holes, and the grout has fully solidified and the soil condition has stabilized, vibration response signals are collected using the same distributed fiber optic acoustic sensing network in the same target repair area under the same constant vibration source excitation. After collection, noise is removed using the same preprocessing method, and the root mean square amplitude of the vibration response signal is extracted as the posterior value A1 by the root mean square amplitude calculation method. This ensures that the collection conditions are consistent with those before grouting and avoids the accuracy of subsequent evaluation results being affected by differences in excitation sources.

[0057] Based on the extracted baseline value A0 and the extracted posterior value A1, the average attenuation rate of the target repair area is calculated using the attenuation rate calculation formula. The formula for calculating the attenuation rate is as follows: ,in Let A0 be the average attenuation rate of the region, A1 be the reference value, and A0 be the posterior value.

[0058] Multiple fiber optic monitoring segments were deployed within the target repair area. Each monitoring segment corresponds to an attenuation rate. The attenuation rates of all monitoring segments were arithmetically averaged to obtain the regional average attenuation rate. The regional average attenuation rate can directly reflect the compactness of the soil after grouting. The higher the attenuation rate, the better the compactness of the soil.

[0059] A pre-set threshold for soil compaction level is established, classifying compaction levels into four grades: excellent, good, acceptable, and unacceptable. The regional average attenuation rate is compared with the aforementioned threshold to output a quantitative assessment result of soil compaction. If the assessment result is "unacceptable," supplementary grouting measures must be taken until the compaction reaches the acceptable standard. The assessment results must be compiled into a written report to provide a basis for project acceptance.

[0060] After grouting is completed, the data from the microscopic sensors are continuously monitored, with a focus on data recovery to confirm the continuous seepage and chemical changes in the target repair area. If the pore water pressure sensor data gradually recovers to the allowable range of the initial value before grouting within the set time, it indicates that the soil structure is stable after grouting and there is no continuous seepage. If the pore water pressure data remains higher than the initial value and shows no downward trend, it indicates that there is continuous seepage, and the leakage point needs to be investigated and supplementary grouting carried out.

[0061] Meanwhile, if the pH sensor data recovers to the allowable range of the initial value before grouting within the set time, it indicates that the chemical reaction between the grout and the soil has become stable; if the pH data continues to deviate from the initial value and fluctuates greatly, it indicates that there are abnormal chemical changes, and the cause needs to be analyzed and corresponding treatment measures should be taken to ensure the stability and safety of the soil after grouting.

[0062] Furthermore, the road grouting control method also includes: The sensing data, inversion results, control command sequences, and final effect evaluation data of a single grouting project are packaged and stored in the case database. Historical data in the case database are periodically called to retrain and update the parameters of the inversion model and the risk index generation model. The updated model is then applied to the path planning and real-time control of subsequent projects.

[0063] Specifically, all data from a single grouting project throughout its entire lifecycle are organized, packaged, and stored uniformly in a case database. This database utilizes a relational database management system, categorizing and archiving data by project number and construction date for easy retrieval and access later. The packaged data includes: sensing data (ground radar data, pipeline detection data, geological survey data, and real-time monitoring data from a multi-scale monitoring network), inversion results (three-dimensional probability field data of grout distribution, grout front pressure data), control command sequences (emergency stop commands, pressure reduction commands, optimized pressure and mix proportion commands, etc.), and final effect evaluation data (regional average attenuation rate, quantitative evaluation results of soil compaction, and confirmation results of seepage and chemical changes). This ensures data integrity and traceability.

[0064] A regular update cycle is set, and historical data from the case database is retrieved. This data is then filtered to remove invalid data and retain only valid engineering case data. After filtering, the valid historical data is used as new training samples and input into the inversion prediction model and the risk index generation model for retraining and parameter updates. During training, model hyperparameters are adjusted, and cross-validation is used to verify model accuracy, ensuring that the model's prediction error is controlled within acceptable limits.

[0065] The updated inversion prediction model and risk index generation model were applied to the entire process of path planning and real-time control in subsequent road grouting projects. In the path planning stage, the updated model was used for grout diffusion simulation verification, improving the accuracy of the simulation results. In the real-time control stage, the updated risk index generation model was used to more accurately calculate macro and micro risk indices, providing early warnings of potential risks and shortening risk response time. Simultaneously, it optimized the solution accuracy of the real-time optimization controller, making the adjustment of grouting parameters more reasonable, balancing construction safety, cost, and grouting effect.

[0066] Based on the above method embodiments, the second embodiment of this application discloses a road grouting control system. The road grouting control system of this application embodiment can implement any of the above-described road grouting control methods, and the specific working process of each module in the road grouting control system can be referred to the corresponding process in the above method embodiments.

[0067] For ease of understanding, an example is as follows: A road grouting control system includes: The data acquisition and modeling module is used to collect ground-penetrating radar data, pipeline detection data and geological survey data of the target area, and generate a construction planning map that includes the coordinates of grouting hole locations and the range of design parameters. The on-site deployment and monitoring module is used to drill holes on-site according to the construction plan and deploy a distributed fiber optic acoustic sensor network, pore water pressure sensor and pH sensor to form a multi-scale monitoring network to acquire distributed fiber optic vibration data and micro-sensor data in real time. The grout dynamic inversion module is used to receive distributed optical fiber vibration data and microscopic sensor data during the grouting construction process, and input them into a pre-trained inversion model to dynamically generate a three-dimensional probability field of grout distribution and grout front pressure. The multi-scale risk assessment module is used to calculate the minimum distance between the slurry and the pipeline based on a three-dimensional probability field, and to calculate the changes in pore water pressure and pH based on microscopic sensor data, generating macroscopic risk index and microscopic risk index respectively. The intelligent decision-making and control command generation module is used to dynamically make decisions and generate real-time pressure control commands and grout ratio adjustment commands for each grouting hole based on the macro risk index and micro risk index. The intelligent grouting execution module is used to control the intelligent grouting equipment to execute real-time pressure control commands and grout ratio adjustment commands to complete the grouting operation; The effect evaluation module is used to assess the soil compaction based on the attenuation rate of the distributed optical fiber vibration signal spectrum before and after grouting, and to confirm the continuous seepage and chemical changes based on the recovery of microscopic sensor data.

[0068] The third embodiment of this application provides a computer device, which may include a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement a road grouting control method.

[0069] The memory can communicate with the processor via a communication bus, which can be an address bus, a data bus, a control bus, etc.

[0070] Additionally, the memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device.

[0071] Furthermore, the processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0072] The fourth embodiment of this application provides a computer-readable storage medium storing a computer program that can be loaded by a processor and executed as a road grouting control method.

[0073] The computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device; the program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0074] The above are all preferred embodiments of this application and are not intended to limit the scope of protection of this application. Any feature disclosed in this specification (including the abstract and drawings) may be replaced by other equivalent or similar features unless specifically stated otherwise. That is, unless specifically stated otherwise, each feature is only one example of a series of equivalent or similar features.

Claims

1. A method for controlling road grouting, characterized in that, include: Collect ground-penetrating radar data, pipeline detection data, and geological survey data of the target area to generate a construction planning map that includes the coordinates of grouting hole locations and the range of design parameters; Based on the construction plan, boreholes were drilled on site, and a distributed fiber optic acoustic sensor network, pore water pressure sensor, and pH sensor were deployed to form a multi-scale monitoring network. During the grouting process, distributed optical fiber vibration data and microscopic sensor data are acquired in real time and input into a pre-trained inversion model to dynamically generate a three-dimensional probability field of grout distribution and grout front pressure. The minimum distance between the slurry and the pipeline is calculated based on the three-dimensional probability field, and the changes in pore water pressure and pH are calculated based on the microscopic sensor data, generating macroscopic risk index and microscopic risk index respectively. Based on the macro risk index and the micro risk index, dynamic decisions are made and real-time pressure control commands and grout ratio adjustment commands are generated for each grouting hole. The intelligent grouting equipment executes the real-time pressure control command and the grout ratio adjustment command to complete the grouting operation; After grouting, the soil density is assessed based on the attenuation rate of the distributed optical fiber vibration signal spectrum before and after grouting, and the continuous seepage and chemical changes are confirmed based on the recovery of microscopic sensor data.

2. The road grouting control method according to claim 1, characterized in that, Generating a construction planning drawing that includes the coordinates of grouting hole locations and the range of design parameters specifically includes: Based on the aforementioned ground-penetrating radar data, pipeline detection data, and geological exploration data, a digital twin model is constructed that includes a soil mechanical parameter field, a pipeline vector network, and a three-dimensional boundary of the target repair area. Based on the digital twin model, with the optimization objectives of minimum drilling cost, minimum grouting material cost and minimum risk to adjacent pipelines, multi-objective path planning is carried out under the conditions of satisfying regional coverage constraints, pipeline avoidance constraints and construction constraints, and a construction planning map containing grouting hole coordinates and design parameter range is generated. The deployment of pore water pressure sensors and pH sensors specifically includes: Based on the pipeline vulnerability index and spatial distance in the pipeline vector network, pore water pressure sensors and pH sensors are deployed near high-risk pipelines.

3. The road grouting control method according to claim 2, characterized in that, The specific steps for generating a construction planning drawing that includes the coordinates of grouting hole locations and the range of design parameters include: Define the orientation of the grouting hole and the designed grouting volume as decision variables; An optimization function is constructed with the total drilling cost, total grouting material cost and pipeline proximity risk as the objective. The proximity risk of a single borehole to a single pipeline is characterized by the product of the pipeline vulnerability index in the pipeline vector network and the negative exponential function of the spatial distance between the two. The distance from any point within the target repair area to the nearest grouting hole is set to be no greater than the effective grouting radius, and the spatial distance between any grouting hole and any pipeline in the pipeline vector network is set to be no less than the minimum safe distance as a hard constraint. A multi-objective optimization algorithm was used to solve the problem, resulting in a set of Pareto optimal solutions. Slurry diffusion simulations were then performed to verify each candidate solution. Based on the verification results, the final solution is selected from the Pareto optimal solution set, and the construction planning diagram is output.

4. The road grouting control method according to claim 2, characterized in that, The specific steps for dynamically making decisions and generating real-time pressure control commands and grout ratio adjustment commands for each grouting hole include: When any of the aforementioned micro-risk indices exceeds the emergency risk threshold, an emergency stop or depressurization command is generated, and the emergency sealing grouting process is triggered. When the macro risk index exceeds the macro threshold or any of the micro risk indices exceeds the optimized risk threshold, the real-time optimization controller is activated. The optimized risk threshold is less than the emergency risk threshold. The real-time optimization controller aims to minimize the weighted sum of the macro risk index and the micro risk index while maximizing the filling efficiency. It uses the pressure of each grouting hole and the water-cement ratio of the grout as optimization variables, solves the problem within the pressure range allowed by the equipment and the formation, and outputs the optimized pressure and proportion instruction set. When both the macro risk index and any of the micro risk indices are below the optimized risk threshold, grouting shall continue according to the design parameters in the construction plan.

5. The road grouting control method according to claim 4, characterized in that, The emergency sealing and grouting process specifically includes: If an emergency risk is triggered during the main grouting process, a fast-setting inert isolation grout is immediately injected into the high-risk pipeline adjacent area corresponding to the microscopic sensor that exceeds the standard at a pressure lower than that of the main grouting. The readings of the pore water pressure sensors deployed in the adjacent area of ​​the high-risk pipeline are monitored in real time. When the readings continue to decrease and stabilize within a safe threshold range within a set time window, it is determined that an emergency sealing barrier has been formed. The high-risk pipeline adjacent area is included in the main grouting adaptive control closed loop, and a micro-risk early warning threshold is enabled for the high-risk pipeline adjacent area that is below the optimized risk threshold.

6. The road grouting control method according to claim 2, characterized in that, The specific steps for assessing soil compaction based on the attenuation rate of distributed optical fiber vibration signal spectra before and after grouting include: The root mean square amplitude of the background vibration signal in a specific frequency band of the target repair area before grouting is extracted as the reference value. The root mean square amplitude of the vibration signal in the same area and frequency band after grouting was completed was extracted as the posterior value. Calculate the regional average attenuation rate based on the baseline value and the posterior value; The average attenuation rate of the region is compared with the preset density level threshold to output the quantitative evaluation result of soil density.

7. The road grouting control method according to claim 1, characterized in that, The road grouting control method also includes: The sensing data, inversion results, control command sequence, and final effect evaluation data of a single grouting project are packaged and stored in the case database throughout the entire cycle. Historical data from the case database is periodically retrieved to retrain and update the parameters of the inversion model and the risk index generation related model. The updated model will be applied to path planning and real-time control in subsequent projects.

8. A road grouting control system, characterized in that, Performing the road grouting control method as described in any one of claims 1 to 7 includes: The data acquisition and modeling module is used to collect ground-penetrating radar data, pipeline detection data and geological survey data of the target area, and generate a construction planning map that includes the coordinates of grouting hole locations and the range of design parameters. The on-site deployment and monitoring module is used to drill holes on-site according to the construction plan and deploy a distributed fiber optic acoustic sensor network, a pore water pressure sensor, and a pH sensor to form a multi-scale monitoring network to acquire distributed fiber optic vibration data and micro-sensor data in real time. The grout dynamic inversion module is used to receive the distributed optical fiber vibration data and microscopic sensor data during the grouting construction process, and input them into the pre-trained inversion model to dynamically generate the three-dimensional probability field of grout distribution and grout front pressure. The multi-scale risk assessment module is used to calculate the minimum distance between the slurry and the pipeline based on the three-dimensional probability field, and to calculate the pore water pressure change and pH change based on the microscopic sensor data, thereby generating macroscopic risk index and microscopic risk index respectively. The intelligent decision-making and control instruction generation module is used to dynamically make decisions and generate real-time pressure control instructions and grout ratio adjustment instructions for each grouting hole based on the macro risk index and the micro risk index. The intelligent grouting execution module is used to control the intelligent grouting equipment to execute the real-time pressure control command and the grout ratio adjustment command to complete the grouting operation; The effect evaluation module is used to assess the soil compaction based on the attenuation rate of the distributed optical fiber vibration signal spectrum before and after grouting, and to confirm the continuous seepage and chemical changes based on the recovery of microscopic sensor data.

9. A computer device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the road grouting control method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The system contains a computer program that can be loaded by a processor and executed as described in any one of claims 1 to 7.

Images