Cooperative regulation and control system and method for permeability coefficient and thickness of water-rich layered surrounding rock stratum tunneling grouting ring

Abstract

The invention provides a water-rich layered surrounding rock stratum tunneling grouting ring permeability coefficient and thickness cooperative regulation and control system and method, belongs to the technical field of tunnel engineering safety monitoring, and aims to solve the problems of leakage channels and support failure caused by mismatching of the permeability coefficient and thickness of a layered water-rich stratum grouting ring. And a two-parameter dynamic perception-collaborative optimization-real-time regulation and control integrated solution is provided. The device comprises a permeability coefficient regulation and control module, a grouting ring thickness control module, a multi-source data fusion module, a collaborative decision module and a closed-loop feedback module. And grouting parameters are optimized in real time through the dynamic coupling model, and a bedding dip angle compensation factor is introduced to eliminate geological deviation. After application, the thickness uniformity of the grouting ring is improved to + / -8%, the leakage amount is reduced by 65%, and the pipe blocking rate is lt; 5%.

Description

Technical Field

[0001] This invention relates to the field of tunnel engineering safety monitoring technology, specifically to a system and method for coordinated control of the permeability coefficient and thickness of the grouting ring during tunnel excavation in water-rich layered surrounding rock strata, which is particularly suitable for dynamic stability assessment of tunnels with high water pressure and strong anisotropy in layered rock masses. Background Technology

[0002] As my country's infrastructure construction, including transportation and water conservancy projects, extends into deep and complex geological areas, the technical challenges of constructing tunnels in deeply buried layered water-rich strata are becoming increasingly severe. Layered water-rich strata are characterized by poor integrity of the surrounding rock mass, well-developed bedding, and complex groundwater occurrence conditions. Grouting reinforcement is a core technology to ensure the safety of tunnel construction. Its core objective is to form a grouting ring with low permeability and uniform thickness, thereby effectively sealing off groundwater and reliably reinforcing the surrounding rock.

[0003] Current traditional grouting techniques have many shortcomings in the application of deeply buried layered water-rich strata, and these shortcomings directly correspond to prominent engineering and technical problems: Isolated parameter control leads to parameter mismatch: In traditional grouting processes, parameters such as grouting pressure, water-cement ratio, and grouting rate are mostly set and controlled independently, without establishing a dynamic coupling relationship between permeability coefficient and grout ring thickness. In water-rich strata with well-developed bedding, grout tends to diffuse unidirectionally along the dominant bedding channels, causing a mismatch where the grout ring thickness is excessively thick in some areas with high permeability coefficient, and insufficient thickness in others, thus forming leakage channels. For example, in a deep-buried railway tunnel project, due to a sudden change in bedding dip angle, grout flowed along the bedding surface, resulting in a local surge in water inflow of 25 m³ / h, seriously threatening construction safety.

[0004] The sluggish response cannot adapt to dynamic changes in water pressure: The data acquisition and parameter adjustment of the existing grouting system have a response delay of 5-8 minutes. The groundwater pressure in the deeply buried water-rich strata is affected by the disturbance of tunnel excavation and exhibits dynamic fluctuation characteristics. The delayed control cannot match the changes in water pressure in time, which can easily lead to accidents such as grout ring rupture and groundwater surge.

[0005] Insufficient adaptability to layered strata: Although existing grouting-related patents have introduced some automated control equipment, they have not designed compensation mechanisms for the unique geological parameters of layered strata, such as bedding dip angle and interlayer bonding force. This leads to problems such as discontinuity of the grouting ring at the bedding plane and uneven support strength, which not only affects the reinforcement effect but also causes a grout material waste rate of more than 30%, significantly increasing the project cost.

[0006] Lack of efficient feedback correction mechanism: Traditional grouting process is mostly open-loop control. After grouting is completed, it is impossible to evaluate the effectiveness of the grouting ring in real time, and it is also difficult to dynamically correct the grouting parameters according to the actual reinforcement effect. When grouting defects occur, they cannot be remedied in time, which further reduces the reliability of grouting reinforcement.

[0007] In summary, developing a system and method that is suitable for water-rich layered surrounding rock formations and can achieve coordinated control of the permeability coefficient and thickness of the grouting ring is an urgent need to solve current tunnel construction problems. Summary of the Invention

[0008] To address the aforementioned shortcomings of existing technologies, the present invention aims to provide a system and method for collaboratively controlling the permeability coefficient and thickness of the grouting ring during tunnel excavation in water-rich layered surrounding rock strata. This system optimizes grouting parameters in real time through a dynamic coupling model and introduces a bedding dip angle compensation factor to eliminate geological deviations. After application, the uniformity of the grouting ring thickness is improved to ±8%, leakage is reduced by 65%, and the blockage rate is <5%.

[0009] To achieve the above-mentioned technical features, the objective of this invention is as follows: a system for coordinated control of the permeability coefficient and thickness of the grouting ring during tunnel excavation in water-rich layered surrounding rock strata, comprising: The permeability coefficient control module is used to control the permeability of the grout by adjusting the grouting pressure and water-cement ratio; The grouting ring thickness control module is used to control the grouting rate. Q ( t ) and time-varying gel time t g Adjusting the radial thickness of the grouting ring; The multi-source data fusion module is used to collect real-time data on seepage pressure, grouting ring thickness, and surrounding rock convergence and to construct a three-dimensional geological model. It collects pore pressure through an optical fiber network, scans the thickness distribution at a certain period using acoustic CT, and generates multi-dimensional feature vectors from the fused data. The collaborative decision-making module is used to run a dual-objective optimization algorithm for permeability coefficient and thickness, and outputs pressure. P Water-cement ratio W / C Grouting rate Q The optimal combination; The closed-loop feedback module is used to dynamically correct the model parameters based on the grouting ring efficiency coefficient calculation formula.

[0010] Preferably, the permeability coefficient control module includes an automatic water-cement ratio mixing machine and an electro-hydraulic proportional pressure valve; The water-cement ratio can be adjusted from 0.6 to 1.2, and the pressure fluctuation tolerance is ≤0.5MPa. The grouting pressure adjustment range is 0-40MPa, with a tolerance of ±0.3MPa; The water-cement ratio is 0.6-1.2, with an accuracy of ±0.03.

[0011] Preferably, the grouting ring thickness control module includes a gel time controller and a multi-channel variable frequency grouting pump; The gelation time controller has a control accuracy of ±5s, and the multi-channel variable frequency grouting pump has a flow range of 20-200L / min. The target value of the radial thickness of the grouting ring in the grouting ring thickness control module is T≥1.5m; initial rate Q The exponential curve for 0 is shown in the following formula: ; In the formula, for t Grouting rate at all times t For grouting time; for time-varying gelation time t g The regulation range is 30-90 minutes.

[0012] Preferably, the multi-source data fusion module includes a distributed fiber optic sensor, an acoustic CT probe array, a surrounding rock deformation sensor, and a laser tiltmeter; The range of the distributed fiber optic sensor is 0-5MPa, and the spacing between installations is ≤1.5m. The resolution of the acoustic CT probe array is ±5mm; The acoustic CT probe array is installed on the TBM shield in a radially staggered arrangement; The range of the surrounding rock deformation sensor is 0-100mm; Laser inclinometer measures the dip angle of bedding planes with an accuracy of ±0.1°; The multidimensional feature vector is a 12-dimensional feature vector containing the permeation gradient ∇ P Thickness deviation Δ T , bedding dip angle i pore water pressure P w Grouting pressure P Water-cement ratio W / C Grouting rate Q gel time t g Surrounding rock convergence deformation ΔS Rate of change in water inflow ΔQ w Slurry viscosity m Rock mass integrity coefficient K v .

[0013] Preferably, the collaborative decision-making module includes a distributed fiber optic sensor, an acoustic CT probe array, a surrounding rock deformation sensor, and a laser tiltmeter; The specific optimization algorithm for the dual objective of permeability coefficient and thickness in the collaborative decision-making module is as follows: The input feature vector is passed to a dual-objective optimization model for optimization, and the optimal value is output. Q andt g The optimization constraints are controlled by the layer angle and pressure threshold, and their control formula is as follows: ; In the formula, For the actual measured tilt angle, For the corner of the layer, This is the pressure threshold. The base grouting pressure.

[0014] Preferably, the parameter expression of the dynamic correction model based on the grouting ring efficiency coefficient calculation formula in the closed-loop feedback module is as follows: ; In the formula, The energy dissipation coefficient of the grouting ring is... For fill rate, the threshold is ≥90%, determined by comparison. If the deviation between the measured value and the target value is greater than 10%, the Case Inference Base (CBR) is triggered. The model weights are updated and optimized by matching historical cases using weighted Euclidean distance. The weighted Euclidean distance is calculated as follows: ; In the formula, d For weighted Euclidean distance, for i dimensional feature weights, For the current working condition i 3D eigenvalues For historical cases i 3D eigenvalues i For the characteristic value index, n The number of feature dimensions.

[0015] Preferably, the bi-objective optimization algorithm adopts the NSGA-II genetic algorithm, and the output parameter tolerance is calculated according to the following formula; ; In the formula, This is the grouting pressure deviation value, which is the difference between the actual grouting pressure and the target grouting pressure. This is the water-cement ratio deviation value, which is the difference between the actual water-cement ratio and the target water-cement ratio. The target water-cement ratio typically ranges from 0.6 to 1.2.

[0016] Preferably, the gelation time controller is implemented through a pulse-type additive injection valve, with a response time ≤ 1s, and the formula for calculating the amount of gelling agent added is as follows: ; In the formula, This refers to the amount of gelling agent added.

[0017] Preferably, the Case Reasoning Base (CBR) stores at least 1000 sets of historical working condition data, with feature weights. w i Dynamically assigned based on SHAP values, with priority order: permeability gradient ∇ P Thickness deviation Δ T Incline i .

[0018] Preferably, another aspect of the present invention provides a method for coordinated control of the permeability coefficient and thickness of the grouting ring in tunnel excavation in water-rich layered surrounding rock strata. The method is based on the aforementioned system for coordinated control of the permeability coefficient and thickness of the grouting ring in tunnel excavation in water-rich layered surrounding rock strata, and includes the following steps: S1. Permeability coefficient control: Activate the permeability coefficient control module, adjust the grouting pressure through the electro-hydraulic proportional pressure valve, adjust the water-cement ratio through the automatic water-cement ratio mixing machine, control the water-cement ratio within the range of 0.6-1.2, and control the grouting pressure fluctuation tolerance within ≤0.5MPa; S2. Grouting ring thickness control: Activate the grouting ring thickness control module and set the initial grouting rate. Q 0, grouting pump according to exponential curve Automatic speed reduction, while adjusting the amount of gelling agent added via a gel time controller, extending the gel time... t g The time should be controlled within 30-90 minutes to ensure that the radial thickness of the grouting ring is T≥1.5m; S3. Multi-source data acquisition and fusion: Start the multi-source data fusion module, collect seepage pressure through distributed optical fiber sensors, scan the thickness distribution of the grouting ring through the acoustic CT probe array, and collect the surrounding rock convergence data through the surrounding rock deformation sensor. Generate a 12-dimensional feature vector every 5 minutes and simultaneously construct a three-dimensional geological model. S4. Collaborative Decision Optimization: Activate the collaborative decision module, input the 12-dimensional feature vector generated by the multi-source data fusion module into the dual-objective optimization model, and combine it with the measured bedding angle. i The pressure was obtained by solving the problem using the NSGA-II genetic algorithm. P Water-cement ratio W / C ,rate Q The optimal combination is output to each execution module; S5. Closed-loop feedback correction: Activate the closed-loop feedback module to calculate the grouting ring efficiency coefficient in real time. E c ,contrast E c If the deviation between the measured value and the target value is greater than 10%, the case inference library is triggered, historical case studies are matched according to the weighted Euclidean distance, the model weights are updated and optimized, and the grouting parameters are dynamically corrected.

[0019] The present invention has the following beneficial effects: 1. This invention achieves coordinated control of the permeability coefficient and thickness of the grouting ring, optimizes the uniformity of the grouting ring thickness from the traditional ±40% to ±8%, reduces the leakage from ≥30L / min to ≤10L / min, and reduces the blockage rate from 15-20% to <5%, significantly improving the quality of grouting reinforcement.

[0020] 2. This invention pioneers a bedding dip angle compensation mechanism, which improves the grouting ring qualification rate from the traditional ≤60% to 95% for water-rich layered surrounding rock with bedding dip angles of 10°~60°, and increases the material utilization rate from 60-70% to ≥90%, effectively reducing material waste.

[0021] 3. The system response delay of this invention is reduced from the traditional 5-8 minutes to ≤1 minute. The dynamic correction mechanism based on the SHAP value weighted case reasoning library improves the control accuracy by 40%, realizing precise and intelligent control of the grouting process.

[0022] 4. This invention can save more than 3 million yuan in grout costs per project and reduce the risk of support failure by 90%, providing reliable technical support for the safe and efficient excavation of deep-buried, water-rich, layered surrounding rock tunnels, and has extremely high engineering promotion value. Attached Figure Description

[0023] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0024] Figure 1 This is a system architecture diagram of the device of the present invention.

[0025] Figure 2 This is a flowchart of the coordinated control process of the present invention.

[0026] Figure 3 This is a schematic diagram of the instrument layout for the system of the present invention.

[0027] Figure 4 This is a cross-sectional view of the instrument layout of the system of the present invention.

[0028] In the picture: Figure 1 The module consists of: 1. Permeability coefficient control module; 2. Grouting ring thickness control module; 3. Multi-source data fusion module; 4. Collaborative decision-making module; and 5. Closed-loop feedback module.

[0029] Figure 3 In the middle: automatic water-cement ratio mixing machine 1-1, electro-hydraulic proportional pressure valve 1-2; 2-1 gelation time controller, 2-2 multi-channel variable frequency grouting pump; Distributed fiber optic sensor 3-1, acoustic CT probe array 3-2, surrounding rock deformation sensor 3-3, 3-4 laser tilt meter. Detailed Implementation

[0030] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0031] Example 1: Please see Figure 1-4 A system for coordinated control of the permeability coefficient and thickness of the grouting ring during tunnel excavation in water-rich layered surrounding rock strata includes: a permeability coefficient control module 1, used to control the permeability of the grout by adjusting the grouting pressure and water-cement ratio; and a grouting ring thickness control module 2, used to control the grouting rate. Q ( t ) and time-varying gel time t g The radial thickness of the grouting ring is controlled; the multi-source data fusion module 3 is used to collect real-time data on seepage pressure, grouting ring thickness, and surrounding rock convergence, and to construct a three-dimensional geological model. It collects pore pressure via a fiber optic network, scans thickness distribution at regular intervals using acoustic CT, and generates multi-dimensional feature vectors from the fused data; the collaborative decision-making module 4 is used to run a dual-objective optimization algorithm for permeability coefficient and thickness, and outputs pressure. P Water-cement ratio W / C Grouting rate Q The optimal combination; closed-loop feedback module 5, used to dynamically correct model parameters based on the grouting ring efficiency coefficient calculation formula. Through the above-mentioned coordinated control system... Furthermore, the permeability coefficient control module 1 includes an automatic water-cement ratio mixing machine 1-1 and an electro-hydraulic proportional pressure valve 1-2; wherein, the water-cement ratio adjustment range is 0.6-1.2, and the pressure fluctuation tolerance is ≤0.5MPa; the grouting pressure adjustment range is 0-40MPa, with a tolerance of ±0.3MPa; the water-cement ratio is 0.6-1.2, with an accuracy of ±0.03.

[0032] Furthermore, the grouting ring thickness control module 2 includes a gel time controller 2-1 and a multi-channel variable frequency grouting pump 2-2; the gel time controller 2-1 has a control accuracy of ±5s, and the multi-channel variable frequency grouting pump 2-2 has a flow rate range of 20-200L / min; the target value of the radial thickness of the grouting ring in the grouting ring thickness control module is T≥1.5m; initial rate Q The exponential curve for 0 is shown in the following formula: ; In the formula, Let t be the grouting rate at time t, and t be the grouting time; let t be the time-varying gel time. t g The regulation range is 30-90 minutes.

[0033] Furthermore, the multi-source data fusion module includes a distributed fiber optic sensor 3-1, an acoustic CT probe array 3-2, a surrounding rock deformation sensor 3-3, and a laser inclinometer 3-4; the distributed fiber optic sensor 3-1 has a range of 0-5MPa and a spacing of ≤1.5m; the acoustic CT probe array 3-2 has a resolution of ±5mm; the acoustic CT probe array 3-2 is installed on the TBM shield in a radially staggered arrangement; the surrounding rock deformation sensor 3-3 has a range of 0-100mm; the laser inclinometer 3-4 measures the bedding dip angle with an accuracy of ±0.1°; The multidimensional feature vector is a 12-dimensional feature vector containing the permeation gradient ∇ P Thickness deviation Δ T , bedding dip angle i pore water pressure P w Grouting pressure P Water-cement ratio W / C Grouting rate Q gel time t g Surrounding rock convergence deformation ΔS Rate of change in water inflow ΔQ w Slurry viscosity m Rock mass integrity coefficient K v .

[0034] Furthermore, the collaborative decision-making module includes a distributed fiber optic sensor 3-1, an acoustic CT probe array 3-2, a surrounding rock deformation sensor 3-3, and a laser tiltmeter 3-4; The specific optimization algorithm for the dual objective of permeability coefficient and thickness in the collaborative decision-making module is as follows: The input feature vector is passed to a dual-objective optimization model for optimization, and the optimal value is output. Q and t g The optimization constraints are controlled by the layer angle and pressure threshold, and their control formula is as follows: ; In the formula, For the actual measured tilt angle, For the corner of the layer, This is the pressure threshold. The base grouting pressure.

[0035] Furthermore, the parameter expression of the dynamic correction model based on the grouting ring efficiency coefficient calculation formula in the closed-loop feedback module is as follows: ; In the formula, The energy dissipation coefficient of the grouting ring is... For fill rate, the threshold is ≥90%, determined by comparison. If the deviation between the measured value and the target value is greater than 10%, the Case Inference Base (CBR) is triggered. The model weights are updated and optimized by matching historical cases using weighted Euclidean distance. The weighted Euclidean distance is calculated as follows: ; In the formula, d For weighted Euclidean distance, for i dimensional feature weights, For the current working condition i 3D eigenvalues For historical cases i dimensional eigenvalues, i For the eigenvalue index, n The number of feature dimensions.

[0036] Furthermore, the bi-objective optimization algorithm adopts the NSGA-II genetic algorithm, and the output parameter tolerance is calculated according to the following formula; ; In the formula, This is the grouting pressure deviation value, which is the difference between the actual grouting pressure and the target grouting pressure. This is the water-cement ratio deviation value, which is the difference between the actual water-cement ratio and the target water-cement ratio. The target water-cement ratio typically ranges from 0.6 to 1.2.

[0037] Furthermore, the gelation time controller 2-1 is implemented through a pulse-type additive injection valve, with a response time ≤1s. The formula for calculating the amount of gelling agent added is as follows: ; In the formula, This refers to the amount of gelling agent added.

[0038] Furthermore, the Case Reasoning Base (CBR) stores at least 1000 sets of historical working condition data, with feature weights. w i Dynamically assigned based on SHAP values, with priority order: permeability gradient ∇ P Thickness deviation Δ T Incline i .

[0039] Example 2: Another aspect of the present invention provides a method for coordinated control of the permeability coefficient and thickness of the grouting ring during tunnel excavation in water-rich layered surrounding rock strata. The method is based on the aforementioned system for coordinated control of the permeability coefficient and thickness of the grouting ring during tunnel excavation in water-rich layered surrounding rock strata, and includes the following steps: S1. Permeability coefficient control: Activate the permeability coefficient control module, adjust the grouting pressure through the electro-hydraulic proportional pressure valve, adjust the water-cement ratio through the automatic water-cement ratio mixing machine, control the water-cement ratio within the range of 0.6-1.2, and control the grouting pressure fluctuation tolerance within ≤0.5MPa; S2. Grouting ring thickness control: Activate the grouting ring thickness control module and set the initial grouting rate. Q 0, grouting pump according to exponential curve Automatic speed reduction, while adjusting the amount of gelling agent added via a gel time controller, extending the gel time... t g The time should be controlled within 30-90 minutes to ensure that the radial thickness of the grouting ring is T≥1.5m; S3. Multi-source data acquisition and fusion: Start the multi-source data fusion module, collect seepage pressure through distributed optical fiber sensors, scan the thickness distribution of the grouting ring through the acoustic CT probe array, and collect the surrounding rock convergence data through the surrounding rock deformation sensor. Generate a 12-dimensional feature vector every 5 minutes and simultaneously construct a three-dimensional geological model. S4. Collaborative Decision Optimization: Activate the collaborative decision module, input the 12-dimensional feature vector generated by the multi-source data fusion module into the dual-objective optimization model, and combine it with the measured bedding angle. i The pressure was obtained by solving the problem using the NSGA-II genetic algorithm. P Water-cement ratio W / C ,rate Q The optimal combination is output to each execution module; S5. Closed-loop feedback correction: Activate the closed-loop feedback module to calculate the grouting ring efficiency coefficient in real time. E c ,contrast E c If the deviation between the measured value and the target value is greater than 10%, the case inference library is triggered, historical case studies are matched according to the weighted Euclidean distance, the model weights are updated and optimized, and the grouting parameters are dynamically corrected.

[0040] Example 3: A railway tunnel (450m burial depth, alternating layers of mudstone and sandstone, θ=35°, water inflow rate 60m³ / h).

[0041] A device for collaboratively controlling the permeability coefficient and thickness of the grouting ring during tunnel excavation in water-rich layered surrounding rock strata belongs to the field of intelligent construction technology for tunnel engineering. Addressing the problems of leakage channels and support failure caused by the mismatch between the permeability coefficient and thickness of the grouting ring in layered water-rich strata, an integrated solution of "dual-parameter dynamic sensing - collaborative optimization - real-time control" is proposed. The device includes a permeability coefficient control module 1, a grouting ring thickness control module 2, a multi-source data fusion module 3, a collaborative decision-making module 4, and a closed-loop feedback module 5.

[0042] like Figure 1 As shown, a system for coordinated control of the permeability coefficient and thickness of the grouting ring in tunnel excavation in water-rich layered surrounding rock strata includes a permeability coefficient control module 1, a grouting ring thickness control module 2, a multi-source data fusion module 3, a collaborative decision-making module 4, and a closed-loop feedback module 5. Its main implementation steps are as follows: S1. Operate the permeability coefficient control module 1 to control the grout permeability by adjusting the grouting pressure and water-cement ratio. The water-cement ratio adjustment range is 0.6-1.2, and the pressure fluctuation tolerance is ≤0.5MPa. The main devices include electro-hydraulic proportional pressure valves 1-2 (model REXROTHVT-VSPA2-1-2X) ​​and automatic water-cement ratio mixing machine 1-1 (model SMCITV2050), which adjust the grouting pressure to 0-40MPa (tolerance ±0.3MPa) and the water-cement ratio to 0.6-1.2 (accuracy ±0.03).

[0043] S2. Operate the grouting ring thickness control module 2, and control the grouting rate. Q ( t ) and time-varying gel time t g Adjust the radial thickness of the grouting ring (target value T≥1.5m). This is achieved by setting the initial rate. Q The exponential curve for 0 is shown in the following formula.

[0044] ; Automatic speed reduction to synchronized adjustment of gelling agent dosage control t g (Range 30-90min). The main equipment includes a multi-channel variable frequency grouting pump 2-2 (model: GRACOXM-158, flow range 20-200L / min) and a gel time controller 2-1 (model: OMEGACNi16, control accuracy ±5s).

[0045] S3. Run the multi-source data fusion module 3 to collect real-time data on seepage pressure, grouting ring thickness, and surrounding rock convergence, and construct a three-dimensional geological model. Pore pressure is collected via a fiber optic network, and thickness distribution is scanned using acoustic CT (cycle time 5 minutes). The fused data generates a 12-dimensional feature vector (including seepage gradient ∇). P Thickness deviation Δ T The main components include a distributed fiber optic sensor 3-1 (model: FOS-N, range 0-5MPa, deployment spacing ≤1.5m), an acoustic CT probe array 3-2 (model: PUNDITPL-200, resolution ±5mm), and a surrounding rock deformation sensor 3-3 (model: GEOSIGGMS-40, range 0-100mm).

[0046] S4. Run the collaborative decision-making module 4, execute the permeability coefficient-thickness dual-objective optimization algorithm, and output pressure. P Water-cement ratio W / C ,rate Q The optimal combination is found by inputting feature vectors, which are then fed into a dual-objective optimization model for optimization, and the optimal combination is output. Q and t g 。 The optimization constraints are controlled by the layer angle and pressure threshold, and the control formula is as follows: ; In the formula, i The measured tilt angle is shown. The main components of the device include: a distributed fiber optic sensor 3-1 (model: FOS-N, range 0-5MPa, spacing ≤1.5m), an acoustic CT probe array 3-2 (model: PUNDITPL-200, resolution ±5mm), and a surrounding rock deformation sensor 3-3 (model: GEOSIGGMS-40, range 0-100mm).

[0047] S5. Run the closed-loop feedback module 5 and dynamically correct the model parameters based on the grouting ring efficiency coefficient calculation formula, as shown in the following formula.

[0048] ; In the formula, or For fill rate, the threshold is ≥90%. This is compared... E c If the deviation between the measured value and the target value is greater than 10%, the Case Inference Base (CBR) is triggered, and the model weights are updated and optimized by matching historical cases using weighted Euclidean distance. The weighted Euclidean distance is calculated as follows: ; In the collaborative decision-making module 4, the acoustic CT probe array 3-2 is installed on the TBM shield in a radially staggered arrangement (0.8m × 0.8m spacing), and the layer inclination angle is measured using a laser inclinometer 3-4 (model: LEICANIVEL210, accuracy ±0.1°).

[0049] The bi-objective optimization algorithm uses the NSGA-II genetic algorithm with the following parameters: population size: 200, number of iterations: 100, crossover probability: 0.85. The output parameter tolerance is calculated according to the following formula.

[0050] ; In the grouting ring thickness control module 2, the gelation time controller is implemented through a pulse additive injection valve (model: BURKERT2832), with a response time ≤1s. The formula for calculating the amount of gelling agent added is as follows.

[0051] ; In closed-loop feedback module 5, the Case Reasoning Base (CBR) stores 1000 sets of historical working condition data, with feature weights. w i Dynamically assigned based on SHAP values, with priority order: permeability gradient ∇P (Weight 0.35) > Thickness Deviation Δ T (Weight 0.3) > Inclination Angle i (Weight 0.2).

[0052] Based on the above implementation steps, the data collected in Example 3 includes: ultrasound CT scan tomography tilt angle θ = 35°, correction factor... α =cos²35°=0.67; Osmotic pressure difference measured by distributed optical fiber network ΔP =1.8MPa, initial thickness value T meas =1.6m. NSGA-II output for collaborative decision-making and execution: W / C=0.8, P=3.8MPa. Q 0 = 120 L / min t g =60min; gel controller calculation V g =0.1×120×(60−30)=360mL / min and inject additive; the grouting pump is operated in flow control mode (the flow rate drops to 80L / min after 10 minutes). Actual measurement after the first grouting. T corr =1.85m (below the 2.0m target). E c =87%; CBR library matching cases (similarity 92%), parameter adjustment: W / C=0.78, t g =50min; after secondary grouting T corr =1.98m, K =4.8×10−8m / s, E c =94%.

[0053] In summary, by adopting the above technical solution, the beneficial effects of this invention are as follows: Through the coordinated control of the permeability coefficient and the thickness of the grouting ring, the problem of parameter mismatch in traditional grouting is solved; in terms of technical performance, the thickness uniformity is optimized from ±40% to ±8%, the leakage rate is reduced from ≥30L / min to ≤10L / min, and the blockage rate is reduced from 15-20% to <5%; in terms of geological adaptability, a pioneering bedding angle compensation mechanism is used, enabling the grouting ring qualification rate to reach 95% (traditionally ≤60%), and the material utilization rate is increased from 60-70% to ≥90%; in terms of intelligent control, the response delay is shortened from 5-8min to ≤1min, and the dynamic correction based on the CBR library weighted by SHAP value improves the control accuracy by 40%; the economic benefits are significant, saving over 3 million yuan in grout costs per project, reducing the risk of support failure by 90%, providing reliable technical support for safe and efficient tunnel excavation under complex geological conditions, and possessing outstanding engineering application value.

[0054] The above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A water-rich layered surrounding rock stratum tunneling grouting ring permeability coefficient and thickness synergistic regulation system, characterized in that, include: The permeability coefficient control module is used to control the permeability of the grout by adjusting the grouting pressure and water-cement ratio; A grout ring thickness control module for controlling grout rate Q t ) with time varying gel time t g Modulating grout ring radial thickness​ The multi-source data fusion module is used to collect real-time data on seepage pressure, grouting ring thickness, and surrounding rock convergence and to construct a three-dimensional geological model. It collects pore pressure through an optical fiber network, scans the thickness distribution at a certain period using acoustic CT, and generates multi-dimensional feature vectors from the fused data. The collaborative decision-making module is used to run a dual-objective optimization algorithm for permeability coefficient and thickness, and outputs pressure. P Water-cement ratio W / C Grouting rate Q The optimal combination; The closed-loop feedback module is used to dynamically correct the model parameters based on the grouting ring efficiency coefficient calculation formula.

2. The system for coordinated control of permeability coefficient and thickness of grouting ring in tunnel excavation in water-rich layered surrounding rock strata according to claim 1, characterized in that, The permeability coefficient control module (1) includes an automatic water-cement ratio mixing machine (1-1) and an electro-hydraulic proportional pressure valve (1-2). The water-cement ratio can be adjusted from 0.6 to 1.2, and the pressure fluctuation tolerance is ≤0.5MPa. The grouting pressure adjustment range is 0-40MPa, with a tolerance of ±0.3MPa; The water-cement ratio is 0.6-1.2, with an accuracy of ±0.

03.

3. The system for coordinated control of permeability coefficient and thickness of grouting ring in tunnel excavation in water-rich layered surrounding rock strata according to claim 1, characterized in that, The grouting ring thickness control module (2) includes a gel time controller (2-1) and a multi-channel variable frequency grouting pump (2-2). The gelation time controller (2-1) has a control accuracy of ±5s, and the multi-channel variable frequency grouting pump (2-2) has a flow range of 20-200L / min; The target value of the radial thickness of the grouting ring in the grouting ring thickness control module is T≥1.5m; initial rate Q The exponential curve for 0 is shown in the following formula: ； In the formula, for t Grouting rate at all times t Grouting time; time-varying gelation time t g The regulation range is 30-90 minutes.

4. The system for coordinated control of permeability coefficient and thickness of grouting ring in tunnel excavation in water-rich layered surrounding rock strata according to claim 1, characterized in that, The multi-source data fusion module includes a distributed fiber optic sensor (3-1), an acoustic CT probe array (3-2), a surrounding rock deformation sensor (3-3), and a laser tiltmeter (3-4). The range of the distributed fiber optic sensor (3-1) is 0-5MPa, and the spacing between installations is ≤1.5m. The resolution of the acoustic CT probe array (3-2) is ±5mm; The acoustic CT probe array (3-2) is installed on the TBM shield in a radially staggered arrangement; The range of the surrounding rock deformation sensor (3-3) is 0-100mm; Laser inclinometer (3-4) measures the dip angle of bedding planes with an accuracy of ±0.1°; The multidimensional feature vector is a 12-dimensional feature vector containing the permeation gradient ∇ P Thickness deviation Δ T , bedding dip angle θ pore water pressure P w Grouting pressure P Water-cement ratio W / C Grouting rate Q gel time t g Surrounding rock convergence deformation ΔS Rate of change in water inflow Δ Q w Slurry viscosity μ Rock mass integrity coefficient K v .

5. The system for coordinated control of permeability coefficient and thickness of grouting ring in tunnel excavation in water-rich layered surrounding rock strata according to claim 1, characterized in that, The collaborative decision-making module includes a distributed fiber optic sensor (3-1), an acoustic CT probe array (3-2), a surrounding rock deformation sensor (3-3), and a laser tiltmeter (3-4). The specific optimization algorithm for the dual objective of permeability coefficient and thickness in the collaborative decision-making module is as follows: The input feature vector is passed to a bi-objective optimization model for optimization, and the optimal value is output. Q and t g The optimization constraints are controlled by the layer angle and pressure threshold, and their control formula is as follows: ； In the formula, For the actual measured tilt angle, For the corner of the layer, This is the pressure threshold. The base grouting pressure.

6. The system for coordinated control of permeability coefficient and thickness of grouting ring in tunnel excavation in water-rich layered surrounding rock strata according to claim 1, characterized in that, The parameter expression for the dynamic correction model based on the grouting ring efficiency coefficient calculation formula in the closed-loop feedback module is as follows: ； In the formula, The energy dissipation coefficient of the grouting ring is... For fill rate, the threshold is ≥90%, and it is compared... If the deviation between the measured value and the target value is greater than 10%, the Case Inference Base (CBR) is triggered. The model weights are updated and optimized by matching historical cases using weighted Euclidean distance. The weighted Euclidean distance is calculated as follows: ； In the formula, d For weighted Euclidean distance, for i dimensional feature weights, For the current working condition i 3D eigenvalues For historical cases i 3D eigenvalues i For the characteristic value index, n The number of feature dimensions.

7. The system for coordinated control of permeability coefficient and thickness of grouting ring in tunnel excavation in water-rich layered surrounding rock strata according to claim 5, characterized in that, The bi-objective optimization algorithm uses the NSGA-II genetic algorithm, and the output parameter tolerance is calculated according to the following formula; ； In the formula, This is the grouting pressure deviation value, which is the difference between the actual grouting pressure and the target grouting pressure. This is the water-cement ratio deviation value, which is the difference between the actual water-cement ratio and the target water-cement ratio. The target water-cement ratio typically ranges from 0.6 to 1.

2.

8. The system for coordinated control of permeability coefficient and thickness of grouting ring in tunnel excavation in water-rich layered surrounding rock strata according to claim 5, characterized in that, The gelation time controller (2-1) is implemented through a pulse-type additive injection valve, with a response time ≤1s. The formula for calculating the amount of gelling agent added is as follows: ； In the formula, This refers to the amount of gelling agent added.

9. The system for coordinated control of permeability coefficient and thickness of grouting ring in tunnel excavation in water-rich layered surrounding rock strata according to claim 6, characterized in that, The Case Reasoning Base (CBR) stores at least 1000 sets of historical working condition data, with feature weights. w i Dynamically assigned based on SHAP values, with priority order: permeability gradient ∇ P Thickness deviation Δ T Incline θ .

10. A method for synergistically controlling the permeability coefficient and thickness of the grouting ring during tunnel excavation in water-rich layered surrounding rock strata, characterized in that... The method is based on the system for coordinated control of permeability coefficient and thickness of the grouting ring in tunnel excavation in water-rich layered surrounding rock formations as described in any one of claims 1-9, and includes the following steps: S1. Permeability coefficient control: Activate the permeability coefficient control module, adjust the grouting pressure through the electro-hydraulic proportional pressure valve, adjust the water-cement ratio through the automatic water-cement ratio mixing machine, control the water-cement ratio within the range of 0.6-1.2, and control the grouting pressure fluctuation tolerance within ≤0.5MPa; S2. Grouting ring thickness control: Activate the grouting ring thickness control module and set the initial grouting rate. Q 0, grouting pump according to exponential curve Automatic speed reduction, while adjusting the amount of gelling agent added via a gel time controller, extending the gel time... t g The time should be controlled within 30-90 minutes to ensure that the radial thickness of the grouting ring is T≥1.5m; S3. Multi-source data acquisition and fusion: Start the multi-source data fusion module, collect seepage pressure through distributed optical fiber sensors, scan the thickness distribution of the grouting ring through the acoustic CT probe array, and collect the surrounding rock convergence data through the surrounding rock deformation sensor. Generate a 12-dimensional feature vector every 5 minutes and simultaneously construct a three-dimensional geological model. S4. Collaborative Decision Optimization: Activate the collaborative decision module, input the 12-dimensional feature vector generated by the multi-source data fusion module into the dual-objective optimization model, and combine it with the measured bedding angle. θ The pressure was obtained by solving the problem using the NSGA-II genetic algorithm. P Water-cement ratio W / C ,rate Q The optimal combination is output to each execution module; S5. Closed-loop feedback correction: Activate the closed-loop feedback module to calculate the grouting ring efficiency coefficient in real time. E c ,contrast E c If the deviation between the measured value and the target value is greater than 10%, the case inference library is triggered, historical case studies are matched according to the weighted Euclidean distance, the model weights are updated and optimized, and the grouting parameters are dynamically corrected.

Images