Intelligent self-adaptive dual-mode cooperative grouting control system, grouting method and application

Abstract

The invention relates to the technical field of tunnel engineering grouting, particularly provides an intelligent self-adaptive dual-mode cooperative grouting control system, a grouting method and application, and aims to solve the problems of non-uniform grout diffusion, blind area grout leakage and out-of-control grouting pressure of a traditional advanced curtain grouting technology under complex working conditions. The grouting method comprises the following steps that S1, a three-dimensional stratum model used for controlling the dual-mode collaborative grouting process is constructed, and initial grouting parameters are set; s2, on the basis of the initial grouting parameters in the step S1, advancing type segmented grouting is adopted, a three-dimensional stratum model monitors a real-time grouting result, and the grouting parameters are dynamically adjusted; s3, when the real-time grouting result in the step S2 is monitored to be abnormal, drill rod retreating compensation grouting is automatically conducted on a blind area in an abnormal section; and the step S2 is continued after the drill rod in the abnormal section retreats for compensation grouting repair until grouting is completed. In the whole grouting process, the grouting control system operates cooperatively. And the construction safety can be effectively guaranteed when grouting reinforcement projects under complex working conditions are applied.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of tunnel engineering grouting technology, in particular to an intelligent self-adaptive dual-mode collaborative grouting control system, a grouting method and application. BACKGROUND

[0002] With the rapid development of infrastructure construction in China, tunnel engineering gradually extends from traditional deep mountains and steep ridges to urban areas, and the construction environment is becoming increasingly complex. There are more and more cases of shallow-buried tunnels underpassing operating highways, railways and sensitive structures, which puts higher requirements on the safety and efficiency of tunnel construction. Especially in the case of uneven strata distribution, special non-homogeneous strata (such as water-rich sand layer, soft interlayer) and adjacent sensitive buildings, the traditional advanced grouting process exposes many technical defects and is difficult to meet the needs of modern tunnel engineering.

[0003] The current technology of traditional grouting process has the following difficulties: parameter control relies on manual experience, adaptability is insufficient, grouting mode switching lags behind, collaboration is poor, and slurry ratio solidification lacks dynamic optimization. In recent years, scholars have tried to improve the grouting effect by introducing pressure sensors and flow meters to monitor the grouting process, innovating materials and optimizing processes, but there are still significant shortcomings: for example, by introducing pressure sensors and flow meters to monitor the grouting process, but the data is only used for post-analysis and does not form a closed-loop control with the grouting equipment; new ultra-fine cement and nanocomposite materials have improved the permeability of the slurry, but the cost is high and the construction process is complex, making it difficult to be widely promoted; the length optimization model of segmented grouting (such as prediction algorithms based on ground penetrating radar) still remains in the theoretical stage and is not combined with real-time strata response, with limited practical application effect.

[0004] Therefore, an intelligent dual-mode collaborative grouting system is needed to deal with complex conditions such as uneven strata distribution, special non-homogeneous strata (such as water-rich sand layer, soft interlayer) and adjacent sensitive buildings. SUMMARY

[0005] The present application provides an intelligent self-adaptive dual-mode collaborative grouting system, a grouting method and application, which aims to realize dynamic adaptation to strata changes, precise elimination of blind areas and intelligent optimization of slurry ratio through real-time monitoring, AI algorithms and deep integration of automated equipment, thereby ensuring construction safety.

[0006] To achieve the above purpose, the technical solution adopted by the present application is as follows:

[0007] The application discloses an intelligent adaptive bimodal collaborative grouting method, which comprises forward sectional grouting and drill pipe retreat compensation grouting.

[0008] S1: a three-dimensional stratum model for controlling the bimodal collaborative grouting process is constructed, and initial grouting parameters are set;

[0009] S2: based on the initial grouting parameters in step S1, the forward sectional grouting is adopted, the three-dimensional stratum model monitors real-time grouting results, and the grouting parameters are dynamically adjusted;

[0010] S3: when the real-time grouting results in step S2 are monitored to be abnormal, drill pipe retreat compensation grouting is automatically performed on a blind area in an abnormal section; after the drill pipe retreat compensation grouting in the abnormal section is repaired, step S2 is continuously performed until the grouting is completed.

[0011] Further, the real-time grouting results in step S2 include a grouting pressure curve, a flow change curve, a temperature distribution field and a sound wave velocity.

[0012] Further, the three-dimensional stratum model in step S2 dynamically adjusts the grouting parameters through a random forest model.

[0013] Further, the process of dynamically adjusting the grouting parameters by the random forest model comprises the following steps: according to the monitored grouting pressure curve, flow change curve, temperature distribution field and sound wave velocity, the parameters of the three-dimensional stratum model are dynamically optimized, and the grouting parameters are updated once every 5 grouting holes as a grouting parameter adjustment period.

[0014] Further, the abnormal conditions of the real-time grouting results in step S3 include the following: a grouting pressure sudden drop is greater than 0.5 MPa / 10 s, a flow abnormality is greater than 70 L / min and a temperature mutation is greater than 5 DEG C / min.

[0015] Further, the identification conditions for identifying the blind area from the abnormal section in step S3 are as follows: based on a permeation cloud atlas analysis, a coverage rate threshold is less than 90% and a size determination is greater than 0.5.

[0016] Furthermore, the present invention also provides an intelligent adaptive dual-mode grouting control system, the control system comprising: a three-dimensional formation model module, an advancing segmented grouting control module, a drill pipe retraction compensation grouting control module, a real-time monitoring control module, and a grouting parameter adjustment module; the three-dimensional formation model module is used to simulate the formation conditions of the grouting section; the advancing segmented grouting control module is used to control the grouting parameters of the advancing segmented grouting according to the simulation results of the three-dimensional formation model module; the drill pipe retraction compensation grouting control module is used to control the grouting of the drill pipe retraction compensation grouting according to the simulation results of the three-dimensional formation model module. The system includes parameters for drilling positioning in blind zone repair; a real-time monitoring and control module for detecting the bottom layer temperature field, strain field, and acoustic velocity in real time during the operation of the forward segmented grouting control module and the drill pipe retraction compensation grouting control module; a grouting parameter adjustment module for dynamically optimizing the model parameters of the three-dimensional formation model module based on the results data provided by the real-time monitoring and control module; and intelligent adaptive dual-mode collaborative grouting method for the three-dimensional formation model module, the forward segmented grouting control module, the drill pipe retraction compensation grouting control module, the real-time monitoring and control module, and the grouting parameter adjustment module.

[0017] Furthermore, the present invention also provides the application of the intelligent adaptive dual-mode collaborative grouting control system as described above in grouting reinforcement projects.

[0018] Furthermore, grouting reinforcement works include grouting reinforcement of shallow-buried tunnels passing under operating highways, sensitive structures, and complex heterogeneous strata.

[0019] The present invention has the following beneficial effects:

[0020] 1. The intelligent adaptive dual-mode collaborative grouting method of the present invention effectively solves the problems of uneven grout diffusion, blind zone leakage and pressure runaway in traditional grouting technology under complex working conditions, and verifies the grouting effect during the grouting process.

[0021] 2. The intelligent adaptive dual-mode collaborative grouting control system of the present invention establishes a three-dimensional geological model and realizes the dual-mode coordinated grouting process through multi-module coordinated control, realizing automatic switching of grouting mode and grouting material during the grouting process.

[0022] 3. By establishing a real-time monitoring and feedback system, and applying it to actual engineering projects, higher grouting efficiency, lower material consumption, and optimized reinforcement effects can be ensured. Real-time monitoring and feedback also facilitate construction personnel's control over the construction progress. Attached Figure Description

[0023] The accompanying drawings, which form part of this application, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings:

[0024] Figure 1 This is a flowchart of an intelligent adaptive dual-mode collaborative grouting system according to the present invention;

[0025] Figure 2 This is a schematic diagram illustrating the input of dimensions for the three-dimensional geological model of this invention;

[0026] Figure 3 This is a schematic diagram of the input of stratigraphic parameters for the three-dimensional geological model of the present invention;

[0027] Figure 4 This is a schematic diagram illustrating the grouting parameters, mode switching conditions, and input of compensating grouting parameters according to the present invention.

[0028] Figure 5 This is a schematic diagram illustrating the input of monitoring parameters, acoustic detection parameters, and water pressure test parameters for this invention.

[0029] Figure 6 This is a three-dimensional geological model diagram of the present invention;

[0030] Figure 7 The following diagrams illustrate the monitoring and feedback effects of this invention: (a) is a pressure chart; (b) is a temperature chart; (c) is a flow rate chart; (d) is a segment length chart; (e) is a coverage chart; and (f) is a blind zone volume chart.

[0031] Figure 8 This is feedback on the optimized effect of the present invention after undergoing acoustic wave detection and water pressure test;

[0032] Figure 9 This is a graph showing the effect of grouting volume changing with date according to the present invention;

[0033] Figure 10 This is a schematic diagram of the intra-hole imaging results of the present invention;

[0034] Figure 11 This is a diagram showing the water pressure test results of the present invention;

[0035] Figure 12 This is a schematic diagram of the core sampling verification results of the present invention. Detailed Implementation

[0036] To enable those skilled in the art to better understand the technical solutions of the present invention, the technical solutions of the present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0037] Example 1

[0038] This embodiment provides an intelligent adaptive dual-mode collaborative grouting method, as shown in the attached figure. Figure 1 As shown, the specific steps include:

[0039] (1) Three-dimensional stratigraphic modeling and initial parameter setting: Based on the on-site geological survey report, ground-penetrating radar scanning data, and borehole core analysis, a three-dimensional stratigraphic model including permeability coefficient (k), porosity (n), and water content (w) is constructed. First, grouting parameters can be manually estimated based on past engineering experience. Then, the built-in AI algorithm (such as a random forest model) can predict and adjust the initial grouting parameters. The forward segment length is generally between 1.2 and 1.8 m. Depending on the stratigraphic permeability, the segment length is dynamically adjusted using the built-in AI algorithm. Similarly, the initial estimated grouting pressure threshold is between 1.5 and 3.5 MPa, and is also dynamically adjusted using the built-in AI algorithm. The initial estimated grouting volume per borehole ranges from 0.5 to 2.0 m. 3 Based on the different formation porosity n, the parameters were dynamically adjusted using an AI algorithm.

[0040] The final prediction results of random forests differ depending on whether the task is classification or regression. For classification problems, the final prediction result of a random forest is the majority vote result of all decision trees, using the following basic formula for prediction:

[0041]

[0042] in: The final predicted category is T, where M is the total number of decision trees in the random forest, and T is the total number of decision trees in the random forest. m (X) is the predicted class of sample X by the m-th decision tree, and I(·) is the indicator function. If T m If (X) = k, then take 1; otherwise, take 0.

[0043] For regression problems, the final prediction result of a random forest is the mean of the predictions from all decision trees, and the prediction is performed using the following basic formula:

[0044]

[0045] in: The final predicted category is T, where M is the number of decision trees in the random forest, and T is the number of decision trees in the random forest. m (X) is the predicted value of the m-th decision tree.

[0046] Through the built-in AI algorithm, the initial grouting parameters can be dynamically adjusted during the subsequent grouting process based on the predicted results.

[0047] (2) Dual-mode grouting and real-time monitoring: Dual-mode grouting employs two modes: forward segmented grouting and drill rod retraction compensation grouting. For forward segmented grouting, a 90mm diameter drill bit is used, equipped with a built-in micro pressure sensor (range 0-10MPa, accuracy 0.1MPa) and an integrated temperature sensor (range -20~80℃). The sensor enables dynamic monitoring of grouting parameters during the grouting process, controlling the segmented advance speed within the range of 0.5~1.0m / min, using a water-cement ratio of 0.8:1 for the single-liquid grout mix, and maintaining the grouting pump flow rate within the range of 10~50L / min. A real-time monitoring system is then constructed using a distributed optical fiber sensor network. The sensing optical fiber is arranged spirally along the borehole (pitch 0.5m), using temperature field, strain field, and acoustic velocity as monitoring parameters. The temperature field accuracy is controlled at 0.5℃, the strain field at 5℃, and the acoustic velocity at 50m / s, with a data acquisition frequency of 10Hz. Intelligent mode switching is triggered by pressure drop > 0.5 MPa / 10s, abnormal flow rate > 70 L / min, and temperature change > 5℃ / min. The forward segmented grouting is stopped, the drill rod is retracted to the abnormal section, and the retraction compensation grouting mode is started. The mode switching response time is controlled within < 30s.

[0048] (3) Retreat compensation grouting and blind zone repair: The drill rod is retreated to the abnormal section, and the grouting material is switched to two-liquid rapid setting grout (cement-water glass volume ratio 1:1, gel time 30s, compressive strength ≥5MPa / 8h). The grouting pressure is controlled at 1.0~2.0MPa, the grouting rate is 20~30L / min, and the single-point grouting time is 3~5min. Compensation grouting is implemented. During the intelligent blind zone repair process, based on the permeability cloud map analysis, the coverage threshold is set to <90% and the size judgment is >0.5 as the blind zone identification conditions. The borehole is automatically positioned with an accuracy control of 10cm. A borehole with a diameter of 50mm is used to ensure that the viscosity is >100 and the impermeability coefficient is <10. -8 cm / s. After the borehole is automatically positioned, backfill grouting is performed to compensate for the identified blind spots.

[0049] (4) Effect Verification and Parameter Iterative Optimization: In the established three-dimensional geological model, the results of acoustic wave detection and water pressure test were used as the basis for quality inspection. During acoustic wave detection, the spacing between measuring points was controlled at 1.0m, and the wave velocity standard was ≥2000m / s and the wave velocity increase rate was ≥20% as reference. During the water pressure test, the test pressure was controlled at 1.0MPa, the duration was 30min, and the permeability was ≤5Lu. During the simulated grouting process, acoustic wave detection and water pressure test were performed after grouting was completed in each grouting hole. Then, during the parameter optimization process, a data feedback system was established based on the grouting pressure curve, flow rate change curve, temperature distribution field, and wave velocity detection results. The data feedback system visualizes the grouting pressure curve, flow rate change curve, temperature distribution field, and wave velocity detection results. The model was then optimized based on the data feedback system. Incremental random forest was used as the online learning algorithm, and the parameter adjustment cycle was set at once every 5 grouting holes, in order to maximize grouting efficiency, minimize material consumption, and optimize the reinforcement effect.

[0050] Example 2

[0051] This embodiment provides an intelligent adaptive dual-mode grouting control system, including: a three-dimensional formation model module, a forward segmented grouting control module, a drill pipe retraction compensation grouting control module, a real-time monitoring control module, and a grouting parameter adjustment module. Wherein:

[0052] The 3D formation model module is used to simulate the formation conditions of the grouting section;

[0053] The forward segmented grouting control module is used to control the grouting parameters of the forward segmented grouting based on the simulation results of the three-dimensional formation model module;

[0054] The drill pipe retraction compensation grouting control module is used to control the grouting parameters of drill pipe retraction compensation grouting and the borehole positioning parameters for blind zone repair based on the simulation results of the three-dimensional formation model module.

[0055] The real-time monitoring and control module is used to detect the bottom layer temperature field, strain field and acoustic wave velocity in real time during the operation of the forward segmented grouting control module and the drill pipe retraction compensation grouting control module.

[0056] The grouting parameter adjustment module is used to dynamically optimize the model parameters of the three-dimensional formation model module based on the result data provided by the real-time monitoring and control module.

[0057] The three-dimensional formation model module, the forward segmented grouting control module, the drill pipe retraction compensation grouting control module, the real-time monitoring control module, and the grouting parameter adjustment module all adopt the intelligent adaptive dual-mode collaborative grouting method of Example 1.

[0058] This intelligent adaptive dual-mode collaborative grouting control system can be used in grouting reinforcement projects, especially for shallow tunnels passing under operating highways, sensitive structures, and complex heterogeneous strata.

[0059] Example 3

[0060] This embodiment, using an engineering case of a shallow-buried tunnel passing under an operational highway, further details Embodiment 1. It should be noted that during the implementation of the grouting method in Embodiment 1, the grouting control system of Embodiment 2 operates in coordination.

[0061] The following case study, using a shallow-buried tunnel passing under an operating highway, details the implementation process and key parameters of the intelligent adaptive dual-mode collaborative grouting method. This shallow-buried tunnel is 15m deep and passes under an existing highway. The geological strata consist of backfill soil from the 0-5m depth, with a porosity n = 0.35 and a permeability coefficient k = 1 × 10⁻⁶. -4 The flow rate is cm / s, and the 5-10m depth is a water-rich sand layer with a porosity n = 0.28 and a permeability coefficient k = 5 × 10⁻⁶. -3 The velocity is cm / s, and the 10-15m depth is a weak clay interlayer. The porosity of this stratum is n = 0.20, and the permeability coefficient is k = 1 × 10⁻⁶. -6 cm / s. The difficulty of this project lies in the fact that the water-rich sand layer is prone to water inrush, and the poor permeability of the clay interlayer makes grout diffusion difficult, requiring dynamic adjustment of the grouting mode. When performing three-dimensional stratum modeling and initial parameter setting, the stratum water content obtained from the ground-penetrating radar scanning data and the measured values ​​of the permeability coefficient of the borehole core were as follows: the water content of the backfill soil was 0.15%, the water content of the water-rich sand layer was 0.25%, and the water content of the weak clay interlayer was 0.15%. According to the three-centered circular construction form of the shallow buried tunnel cross section, the arch height is 6m, the arch span is 10m, and it penetrates along the direction of the operating highway with a penetration angle of 0°. The basic parameters of the above three-dimensional stratum modeling were completed and input, such as... Figure 2 and Figure 3 As shown.

[0062] Initially, manual estimates were used for inputting the initial grouting parameters. During subsequent grouting, the parameters are predicted and adjusted using a built-in AI algorithm (such as a random forest model). The forward segment length is dynamically adjusted based on formation permeability. Similarly, the grouting pressure threshold is dynamically adjusted using a built-in AI algorithm, and the grouting volume per borehole is dynamically adjusted based on the formation porosity (n). See [link to initial grouting parameter input] for details. Figure 4 .

[0063] The dual-mode grouting employs two techniques: forward segmented grouting and drill rod retraction compensation grouting. Forward segmented grouting uses a 90mm diameter drill bit, which utilizes a built-in micro pressure sensor and an integrated temperature sensor to dynamically monitor grouting parameters during the grouting process. The segmented advance speed is controlled within the range of 0.5–1.0 m / min, the single-liquid grout mix uses a water-cement ratio of 0.8:1, and the grouting pump flow rate is controlled within the range of 10–50 L / min. A real-time monitoring system is then constructed using a distributed fiber optic sensor network. The sensing fibers are arranged spirally along the borehole, with temperature field, strain field, and acoustic velocity as the main monitoring parameters. The required accuracy is ±0.5℃ for the temperature field, ±5με for the strain field, and ±50m / s for the acoustic velocity, with a data acquisition frequency of 10Hz. Intelligent mode switching is triggered by pressure drop ΔP > 0.5 MPa / 10s, abnormal flow rate > 70 L / min, and temperature change ΔT > 5℃ / min. Upon triggering, the forward segmented grouting process automatically stops, the drill pipe retracts to the abnormal section, and then the compensation grouting mode automatically starts. The intelligent mode switching response time is controlled within 30 seconds. Grouting parameters such as minimum advance speed, maximum advance speed, water-cement ratio, and minimum single-hole grouting volume are still input as per [reference needed]. Figure 4 Here, the pressure drop threshold, flow anomaly threshold, and temperature change threshold are used as the criteria for mode switching. Figure 4 Input the pressure drop threshold, flow anomaly threshold, temperature change threshold, and response time value.

[0064] When the drill pipe retracts to the fracture location, the grouting material will be switched to a dual-liquid rapid-setting grout. At this time, the grouting pressure is controlled between 1.0 and 2.0 MPa, the grouting rate is controlled between 20 and 30 L / min, and the single-point grouting time is controlled between 3 and 5 minutes for compensation grouting. The control parameter input is as follows: Figure 4 .

[0065] During the intelligent blind spot remediation process, analysis is performed based on permeability cloud maps. Coverage threshold <90% and size judgment >0.5 are used as blind spot identification conditions for automatic borehole positioning. This process requires precision control of 10cm, using 50mm diameter boreholes to ensure viscosity >100 and impermeability coefficient <10. -8 cm / s, see the input process for intelligent blind spot repair parameters. Figure 5 .

[0066] The results of acoustic wave testing and water pressure testing are used as the basis for quality inspection. In acoustic wave testing, a wave velocity standard of ≥2000 m / s and a wave velocity increase rate of ≥20% are used as reference standards. During water pressure testing, the test pressure is controlled at 1.0 MPa, and the test duration is 30 minutes, ensuring a maximum permeability ≤5 Lu. Then, in the parameter optimization process, a data feedback system is established using grouting pressure curves, flow rate change curves, temperature distribution fields, and wave velocity testing results. Model optimization is achieved based on this data feedback system, using incremental random forest as the online learning algorithm. The parameter adjustment cycle is set at once every 5 grouting holes to maximize grouting efficiency, minimize material consumption, and optimize reinforcement effect. The input process for acoustic wave testing and water pressure testing control parameters is described below. Figure 5 After inputting all the required parameters, the geological parametric modeling system is used to establish the geological model, simulate the dual-mode grouting process, and optimize grouting efficiency, minimize material consumption, and achieve the best reinforcement effect through algorithms. See the 3D geological model diagram. Figure 6 .

[0067] After the 3D geological model is generated, the system automatically starts the grouting process simulation and optimizes grouting parameters during the grouting process to complete the grouting process, while continuously monitoring and providing feedback in real time. The monitoring and feedback results are shown in [link to documentation]. Figure 7 .

[0068] The 3D geological model undergoes real-time feedback after grouting, including acoustic wave detection and water pressure testing. This feedback is used to optimize the model via a data feedback system. An incremental random forest algorithm is employed as the online learning algorithm, with a parameter adjustment cycle of every five grouting holes to maximize grouting efficiency, minimize material consumption, and optimize reinforcement effect. (See the feedback diagram.) Figure 8 .

[0069] After grouting is completed, the intelligent adaptive dual-mode collaborative grouting control system can monitor and dynamically adjust the entire grouting process, thereby improving grouting efficiency, reducing material consumption, and optimizing reinforcement effect.

[0070] Example 4

[0071] This embodiment verifies the effectiveness of the intelligent adaptive dual-mode collaborative grouting method in Embodiment 1.

[0072] Project Overview: The lithology revealed at the tunnel face is Quaternary alluvial and diluvial deposits. The tunnel arch section reveals a gravel-bearing sand layer, primarily composed of sandstone, siltstone, and dolomite, with a particle size of 1.0cm–4.0cm, comprising approximately 80%–85% of the material. The gravel is sub-rounded to rounded, containing approximately 10%–15% sand, exhibiting sorting characteristics, and is semi-cemented, with a thickness of approximately 2.0–3.0m. The middle and lower sections of the tunnel reveal mainly bluish-gray clay, primarily composed of clay and silty clay, exhibiting a soft plastic to plastic state, with a thickness greater than 5.0m. The project took 40 days, completing 103 grouting boreholes and 21 additional boreholes. A total of 1219.647t of cement grout, 145.110t of water glass, and 164.769t of HPC were injected.

[0073] The intelligent adaptive dual-mode collaborative grouting method described in Example 1 was applied during the construction process. After the grouting was completed, the grouting effect was analyzed and evaluated using grouting analysis, in-hole imaging, core sampling verification, and water pressure testing. Grouting analysis, in-hole imaging, core sampling verification, and water pressure testing are all standard procedures in this field, and the specific procedures will not be elaborated upon in this example. The grouting effect will be analyzed and evaluated based on the corresponding experimental results below.

[0074] (1) Grouting volume analysis

[0075] like Figure 9 As shown, the geological conditions obtained from the boreholes and the distribution of grouting volume are relatively regular. The effect diagram of grouting volume change over time in a single borehole also shows that the grouting volume decreased significantly in the later stages, the grouting pressure increased significantly and rapidly, the formation's grout absorption capacity was significantly weakened, and the formation was basically reinforced and compacted. The water and sand inrush phenomena that occurred in some grouting holes during drilling were less frequent in the later stages of drilling, the pipe length was basically guaranteed, and no holes were missed.

[0076] (2) In-aperture imaging

[0077] like Figure 10 As shown, an in-hole imaging inspection was conducted on the weak areas of the tunnel through the inspection borehole. The imaging showed no obvious pore collapse in the borehole wall, obvious grout veins, clear cementation of pebbles, and water outflow of less than 5m³. 3 / m*d.

[0078] (3) Pressure test

[0079] like Figure 11 As shown, the pressure of this water pressure test was 1 MPa, and the value was taken with reference to Appendix C of SL / T62-2020 "Technical Specification for Cement Grouting Construction of Hydraulic Structures". The water permeability of the inspection holes met the technical standards and requirements of not more than 5 Lu.

[0080] (4) Core extraction verification

[0081] like Figure 12As shown, the core sampling was carried out through the inspection hole at the working face. The drilling speed was uniform during the drilling process, and there was no jamming. The core sample showed a large amount of cement-aggregate, obvious cementation, and the core sample was relatively complete and evenly distributed longitudinally. There was no water in the hole or a small amount of seepage. The grouting has met the design requirements.

[0082] In summary, the intelligent adaptive dual-mode collaborative grouting method described in Example 1 not only ensures the stability of the foundation consolidation system and achieves the high efficiency requirement of one-time hole formation, but also guarantees the continuity and uniformity of the foundation reinforcement system by eliminating blind spots through re-grouting. It also effectively controls the grout diffusion path and prevents grout loss, thus ensuring the reliability of construction quality during the construction process. This demonstrates the technical effectiveness of the intelligent adaptive dual-mode collaborative grouting method of this invention.

[0083] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.

Claims

1. A smart adaptive dual-mode collaborative grouting method, characterized in that, Dual-mode collaborative grouting includes forward segmented grouting and drill pipe retraction compensation grouting; the grouting method includes the following steps: S1: Construct a three-dimensional formation model to control the dual-mode collaborative grouting process and set the initial grouting parameters; S2: Based on the initial grouting parameters in step S1, advance segmented grouting is adopted, and the real-time grouting results are monitored by a three-dimensional formation model to dynamically adjust the grouting parameters. S3: When an abnormality is detected in the real-time grouting results in step S2, automatic drill rod retraction compensation grouting is performed on the blind area in the abnormal section; after the drill rod retraction compensation grouting repairs the abnormal section, step S2 continues until grouting is completed.

2. The intelligent adaptive dual-mode collaborative grouting method according to claim 1, characterized in that, The real-time grouting results mentioned in step S2 include grouting pressure curve, flow rate change curve, temperature distribution field, and acoustic wave velocity.

3. The intelligent adaptive dual-mode collaborative grouting method according to claim 2, characterized in that, In step S2, the three-dimensional stratigraphic model dynamically adjusts the grouting parameters using a random forest model.

4. The intelligent adaptive dual-mode collaborative grouting method according to claim 3, characterized in that, The process of dynamically adjusting grouting parameters using a random forest model includes: Based on the grouting pressure curve, flow rate change curve, temperature distribution field, and acoustic wave velocity obtained from monitoring, the parameters of the three-dimensional formation model are dynamically optimized, with an adjustment cycle of grouting parameters every 5 grouting holes.

5. The intelligent adaptive dual-mode collaborative grouting method according to claim 3, characterized in that, In step S3, abnormal conditions for real-time grouting results include: a sudden drop in grouting pressure greater than 0.5 MPa / 10s, an abnormal flow rate greater than 70 L / min, and a sudden temperature change greater than 5℃ / min.

6. The intelligent adaptive dual-mode collaborative grouting method according to claim 1, characterized in that, In step S3, the identification conditions for identifying blind spots from abnormal sections are: based on penetration cloud map analysis, coverage threshold < 90% and size determination > 0.

5.

7. An intelligent adaptive dual-mode grouting control system, characterized in that: The control system includes: a three-dimensional formation model module, a forward segmented grouting control module, a drill pipe retraction compensation grouting control module, a real-time monitoring control module, and a grouting parameter adjustment module; The 3D formation model module is used to simulate the formation conditions of the grouting section; The forward segmented grouting control module is used to control the grouting parameters of the forward segmented grouting based on the simulation results of the three-dimensional formation model module; The drill pipe retraction compensation grouting control module is used to control the grouting parameters of drill pipe retraction compensation grouting and the borehole positioning parameters for blind zone repair based on the simulation results of the three-dimensional formation model module. The real-time monitoring and control module is used to detect the bottom layer temperature field, strain field and acoustic wave velocity in real time during the operation of the forward segmented grouting control module and the drill pipe retraction compensation grouting control module. The grouting parameter adjustment module is used to dynamically optimize the model parameters of the three-dimensional formation model module based on the result data provided by the real-time monitoring and control module. The three-dimensional formation model module, the forward segmented grouting control module, the drill pipe retraction compensation grouting control module, the real-time monitoring control module, and the grouting parameter adjustment module all adopt the intelligent adaptive dual-mode collaborative grouting method described in any one of claims 1-6.

8. The application of the intelligent adaptive dual-mode collaborative grouting control system as described in claim 7 in grouting reinforcement projects.

9. The application according to claim 8, characterized in that, The grouting reinforcement project includes grouting reinforcement of shallow-buried tunnels passing under operating highways, sensitive structures, and complex heterogeneous strata.

Images