Intelligent monitoring method for large-diameter shield tunnel in karst water-rich stratum

Abstract

The invention relates to the technical field of tunnel engineering monitoring, and particularly discloses a karst water-rich stratum large-diameter shield tunnel intelligent monitoring method which comprises the steps of S1, real-time geological detection, S2, shield attitude and mechanics monitoring, S3, hydrology and seepage monitoring, S4, surrounding rock deformation and stress monitoring and S5, comprehensive early warning and feedback. According to the intelligent monitoring method for the large-diameter shield tunnel in the karst water-rich stratum, accurate early warning and intelligent response of construction safety are achieved through multi-source geological detection, real-time mechanical and attitude monitoring, hydrological seepage monitoring and surrounding rock deformation stress analysis in combination with an AI algorithm, edge calculation and an optical fiber sensor; the tunnel construction efficiency and the long-term operation stability are effectively improved, and the intelligent monitoring method effectively reduces the construction safety problems of water burst, ground surface settlement, shield deviation and the like in the karst water-rich stratum by integrating various real-time monitoring technologies and algorithms.

Description

Technical Field

[0001] The invention belongs to the technical field of tunnel engineering monitoring, and in particular relates to an intelligent monitoring method for a large-diameter shield tunnel in a karst water-rich stratum. Background Art

[0002] With the acceleration of urbanization, tunnel engineering plays an increasingly important role in transportation construction. Especially in karst water-rich strata, large-diameter shield tunnel construction faces many challenges. In order to ensure the safety and efficiency of construction, advanced monitoring methods are needed to grasp the various parameters and states of the tunnel construction process in real time.

[0003] Traditional geological exploration methods, such as geological radar and advance drilling, can reveal the stratigraphic structure to a certain extent. However, in karst water-rich strata, due to the complexity and uncertainty of geological conditions, these methods are often difficult to accurately predict and identify the volume of rock caves, fault zones and water-rich areas. A single geological exploration method may have errors and limitations, and requires a combination of multiple methods for verification and supplementation.

[0004] In karst water-rich strata, the velocity, temperature and pressure changes of groundwater have an important impact on tunnel construction and long-term stability. However, existing hydrological monitoring methods often lack systematicity and it is difficult to fully and accurately grasp the dynamic changes of groundwater. The accuracy and reliability of hydrological numerical simulations need to be improved to more accurately predict groundwater seepage paths and water inrush risks.

[0005] In view of this, the inventors proposed an intelligent monitoring method for large-diameter shield tunnels in karst water-rich strata to solve the above problems. Summary of the invention

[0006] The purpose of the present invention is to provide an intelligent monitoring method for a large-diameter shield tunnel in a karst water-rich stratum to solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions: The intelligent monitoring method for a large-diameter shield tunnel in a karst water-rich stratum comprises the following steps: S1. Real-time geological detection: Multi-source geological radar and advance drilling analysis are used in combination with artificial intelligence algorithms to identify and predict the geological structure in front of the shield in real time. The geological structure includes the volume of rock caves, fault zones and water-rich areas in the formation. S2. Shield posture and mechanical monitoring: The shield machine posture, propulsion force and grouting pressure are monitored in real time through a sensor network, and real-time feedback and abnormality identification are achieved based on edge computing and Internet of Things technology. The sensor network includes high-precision gyroscopes, acceleration sensors and pressure sensors. S3. Hydrology and seepage monitoring: Use distributed fiber optic sensing systems to monitor groundwater velocity, temperature and pressure changes, and combine hydrological numerical simulation to predict groundwater seepage paths and water inrush risks; S4. Surrounding rock deformation and stress monitoring: deploy multi-dimensional monitoring equipment, including laser scanners, acoustic emission sensors and strain gauges, to monitor surrounding rock deformation and stress field changes in real time; S5. Comprehensive early warning and feedback: Based on the big data analysis platform, abnormalities are detected in the monitoring data and early warning information is generated, and automatic response is achieved through a multi-level linkage mechanism; fiber grating sensors are used to record and analyze the long-term deformation of the tunnel structure and changes in the water environment, and predict stability during operation.

[0008] Preferably, the rock formation cave volume calculation expression is: ; V: volume of the cave, m 3 ; f(x,y,z): probability density function of cave generated by the reflected signal intensity data of multi-source geological radar and advance drilling; x1,x2,y1,y2,z1,z2: The boundary coordinates of the cave, determined by radar scanning and artificial intelligence model prediction.

[0009] Preferably, the real-time geological detection step further includes fiber Raman distributed sensing technology for monitoring the temperature distribution of the rock formation in front of the shield and evaluating the groundwater flow and the intensity of dissolution activity and the water-rich areas of the formation.

[0010] Preferably, the prediction expression of the formation water-richness of the water-rich area is: ; Pw: formation water richness index; T: Formation temperature gradient detected by Raman distributed optical fiber sensing; C: Groundwater conductivity data obtained by drilling; S: intensity attenuation value of geological radar reflection signal; α, β, γ: weight parameters obtained through machine learning algorithms, linear regression or support vector machine training.

[0011] Preferably, the optimized expression of the propulsion force is: ; Ft: thrust force of shield machine, kN; Pi: support pressure of each partition of the shield face, kPa; Ai: the area of ​​the corresponding partition, m 2 ; ΔF: Dynamic adjustment value, calculated by the AI ​​algorithm based on surrounding rock deformation and tunneling speed optimization.

[0012] Preferably, the control formula of the shield machine posture is: ; θ, : Shield machine attitude deviation angle, °; Δy, Δx: displacement deviation of the shield machine in the vertical and horizontal directions, m; L: Current excavation length of the shield machine, m.

[0013] Preferably, the calculation expression of the groundwater flow rate is: ; v: groundwater velocity, m / s; K: Permeability coefficient, obtained from field tests; : Hydraulic gradient, calculated from pressure changes monitored by a fiber optic sensing network.

[0014] Preferably, the simulation formula of the groundwater seepage path is: ; h(x,y,t): change in seepage head, m; h0: initial water head height, m; Q: Groundwater flow per unit time, m 3 / s; T: Permeability coefficient of the formation, m 2 / s; r, r0: current radius and initial radius of the water flow path, m.

[0015] Preferably, the expression of the anomaly detection is: ; A(t): outlier indicator; Xi(t): the monitoring value of the i-th sensor; μi: the normal operating mean of the i-th sensor; wi: weight of the i-th sensor, obtained by training the machine learning model; δ: Threshold value, exceeding this value triggers an alarm.

[0016] Compared with the prior art, the present invention has the following beneficial effects: (1) The intelligent monitoring method for large-diameter shield tunnels in karst water-rich strata in the present invention realizes accurate early warning and intelligent response for construction safety through multi-source geological detection, real-time mechanical and posture monitoring, hydrological seepage monitoring, and surrounding rock deformation and stress analysis, combined with AI algorithms, edge computing, and fiber optic sensors, effectively improving tunnel construction efficiency and long-term operational stability.

[0017] (2) The intelligent monitoring method of the present invention effectively reduces construction safety issues such as water gushing, surface subsidence, and shield deviation in karst water-rich strata by integrating a variety of real-time monitoring technologies and algorithms. It combines distributed optical fiber sensor technology, seismic wave imaging technology, and water pressure monitoring technology to achieve all-round dynamic monitoring of caves, water-rich areas, and shield forces. Real-time monitoring data is analyzed through an adaptive algorithm to accurately predict the location of water gushing points, settlement distribution, and soil stability, thereby avoiding potential risks in advance and ensuring the safety of the construction environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 The present invention is a flow chart of the intelligent monitoring method for large-diameter shield tunnels in karst water-rich strata. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] Example 1 See also Figure 1 As shown, the intelligent monitoring method for a large-diameter shield tunnel in a karst water-rich stratum comprises the following steps: S1. Real-time geological detection: Multi-source geological radar and advanced drilling analysis are used in combination with artificial intelligence algorithms to identify and predict the geological structure in front of the shield in real time. The geological structure includes the volume of rock karst caves, fault zones and water-rich areas in the strata; S2. Shield machine posture and mechanical monitoring: The shield machine posture, propulsion force and grouting pressure are monitored in real time through a sensor network, and real-time feedback and abnormality identification are achieved based on edge computing and Internet of Things technologies. The sensor network includes high-precision gyroscopes, acceleration sensors and pressure sensors. S3. Hydrology and seepage monitoring: Use distributed fiber optic sensing systems to monitor groundwater velocity, temperature and pressure changes, and combine hydrological numerical simulation to predict groundwater seepage paths and water inrush risks; S4. Surrounding rock deformation and stress monitoring: deploy multi-dimensional monitoring equipment, including laser scanners, acoustic emission sensors and strain gauges, to monitor surrounding rock deformation and stress field changes in real time; S5. Comprehensive early warning and feedback: Based on the big data analysis platform, abnormalities are detected in the monitoring data and early warning information is generated, and automatic response is achieved through a multi-level linkage mechanism; fiber grating sensors are used to record and analyze the long-term deformation of the tunnel structure and changes in the water environment, and predict stability during operation.

[0021] From the above, it can be seen that the intelligent monitoring method of large-diameter shield tunnels in karst water-rich strata achieves accurate early warning and intelligent response for construction safety through multi-source geological detection, real-time mechanical and posture monitoring, hydrological seepage monitoring, and surrounding rock deformation and stress analysis, combined with AI algorithms, edge computing, and fiber optic sensors, effectively improving tunnel construction efficiency and long-term operational stability.

[0022] Example 2 The calculation expression of rock cave volume is: ; V: volume of the cave, m 3 ; f(x,y,z): probability density function of cave generated by the reflected signal intensity data of multi-source geological radar and advance drilling; x1,x2,y1,y2,z1,z2: the boundary coordinates of the cave, determined by radar scanning and artificial intelligence model prediction; This formula integrates the three-dimensional distribution of radar signals to quickly predict the volume and location of caves in the rock formation, providing a basis for shield tunneling path planning and reducing the risk of cave collapse.

[0023] Specifically, the real-time geological detection step further includes fiber Raman distributed sensing technology, which is used to monitor the temperature distribution of the rock formation in front of the shield and evaluate the water-rich areas of the formation with the intensity of groundwater flow and dissolution activity.

[0024] Specifically, the prediction expression of the formation water-richness of the water-rich area is: ; Pw: formation water richness index; T: Formation temperature gradient detected by Raman distributed optical fiber sensing; C: Groundwater conductivity data obtained by drilling; S: intensity attenuation value of geological radar reflection signal; α, β, γ: weight parameters obtained through machine learning algorithms, linear regression or support vector machine training; By comprehensively analyzing temperature changes, electrical conductivity and radar signal characteristics, the distribution of water-rich areas in the rock formation can be accurately assessed, providing guidance for adjusting the construction parameters of the shield machine.

[0025] Specifically, the optimization expression of the propulsion force is: ; Ft: thrust force of shield machine, kN; Pi: support pressure of each partition of the shield face, kPa; Ai: the area of ​​the corresponding partition, m 2 ; ΔF: dynamic adjustment value, calculated by the AI ​​algorithm based on surrounding rock deformation and tunneling speed optimization; This formula combines the distribution of support pressure with the shield advancement speed and reduces the risk of surface settlement and rock disturbance caused by tunneling by dynamically adjusting the advancement force.

[0026] Specifically, the control formula of the shield machine posture is: ; θ, : Shield machine attitude deviation angle, °; Δy, Δx: displacement deviation of the shield machine in the vertical and horizontal directions, m; L: current excavation length of the shield machine, m; The displacement deviation is used to calculate the offset angle, which provides a reference for the posture adjustment of the shield machine and ensures the accuracy of the excavation route.

[0027] Specifically, the calculation expression of the groundwater flow rate is: ; v: groundwater velocity, m / s; K: Permeability coefficient, obtained from field tests; : hydraulic gradient, calculated from pressure changes monitored by a fiber optic sensing network; This formula calculates groundwater flow velocity and direction by monitoring hydraulic gradient in real time, providing key data for predicting water gushing risks and surrounding rock damage caused by water flow.

[0028] Specifically, the simulation formula of the groundwater seepage path is: ; (x,y,t): change in seepage head, m; h0: initial water head height, m; Q: Groundwater flow per unit time, m 3 / s; T: Permeability coefficient of the formation, m2 / s; r, r0: current radius and initial radius of the water flow path, m; By dynamically simulating the seepage path and water head changes, possible groundwater flow channels near the shield machine can be identified to prevent water inrush accidents.

[0029] Specifically, the expression of the anomaly detection is: ; A(t): outlier indicator; Xi(t): the monitoring value of the i-th sensor; μi: the normal operating mean of the i-th sensor; wi: weight of the i-th sensor, obtained by training the machine learning model; δ: threshold, exceeding this value triggers an alarm; Through weighted anomaly detection of multi-sensor data, potential risks in shield construction can be quickly identified, providing real-time decision-making basis for construction management.

[0030] From the above, it can be seen that this intelligent monitoring method effectively reduces construction safety issues such as water gushing, surface subsidence, and shield deviation in karst water-rich strata by integrating a variety of real-time monitoring technologies and algorithms. Combined with distributed fiber optic sensor technology, seismic wave imaging technology, and water pressure monitoring technology, it realizes all-round dynamic monitoring of caves, water-rich areas, and shield forces. Real-time monitoring data is analyzed through adaptive algorithms to accurately predict the location of water gushing points, settlement distribution, and soil stability, avoid potential risks in advance, and ensure the safety of the construction environment.

[0031] Based on algorithms such as thrust calculation and dynamic adjustment of earth pressure balance pressure, the operating stability of the shield machine in complex strata is ensured, thereby reducing unnecessary downtime and mechanical wear and tear. Through seismic wave reflection and laser scanning technology, the volume and shape of the cave can be accurately detected to avoid landslides or mud and water surges caused by blind construction. Based on the water pressure monitoring and risk assessment model, the risk of water gushing can be effectively quantified to ensure that targeted measures, such as grouting or drainage, are taken in a timely manner.

[0032] Example 3 This design is specifically applied to the construction of shield tunnels in karst strata. Karst strata are widely distributed, especially in southern China and Southeast Asia. Their geological conditions are complex and the risk of water inrush is high, which often brings great challenges to underground engineering. Furthermore, a large-diameter shield tunnel with a diameter of 12.8 meters and a total length of 4 kilometers was built in a karst water-rich stratum. During the construction, the geological conditions were complex, including caves, fault zones, and water-rich areas, and there was a high risk of water gushing and stratum collapse. The project adopted an intelligent monitoring method based on multi-source sensing and artificial intelligence to ensure construction safety and efficiency.

[0033] Implementation steps and parameters 1. Real-time geological detection Equipment used: Multi-source geological radar (frequency: 200MHz, detection depth: 10 meters); Advanced drilling equipment (drilling depth: 15 meters).

[0034] Algorithm application: Combined with the three-dimensional distribution of geological radar signals, the rock cave volume prediction formula is adopted: ; Input parameters: spatial distribution data of radar reflection signals; Test results: There is a volume of about 4.8m 10 meters in front of the shield. 3 The cave has a center coordinate of (5, 3,-2) meters.

[0035] Effect: A reinforcement plan was formulated in advance, and the grouting method was used to fill the cave to avoid collapse accidents during the advancement of the shield machine.

[0036] 2. Shield posture and mechanical monitoring Equipment used: High-precision gyroscope (accuracy: 0.01°); Propulsion force monitoring sensor (range: 0-5000kN).

[0037] Algorithm application: Propulsion optimization formula: ; Among them, the shield surface partition pressure is: P1=200kPa, P2=250kPa, P3=210kPa, the corresponding partition areas are: A1=6m 2 ,A2=8m 2 ,A3=5m 2 The dynamic adjustment value ΔF is predicted by the artificial intelligence model to be 30 kN.

[0038] Calculation results: Propulsion force Ft = (200 × 6 + 250 × 8 + 210 × 5) + 30 = 4280 kN Effect: By optimizing the propulsion force, the shield machine advanced smoothly, avoiding the problem of excessive surface settlement, and the settlement was reduced from the original predicted value of 5mm to 1.8mm.

[0039] 3. Hydrology and seepage monitoring Equipment used: Distributed fiber optic sensor (temperature resolution: 0.01°C, pressure resolution: 1kPa); Miniature water quality sensor (monitoring parameters: pH, conductivity, dissolved oxygen).

[0040] Algorithm application: Groundwater flow rate formula: ; Among them, the permeability coefficient K=5×10 -6 m / s; Hydraulic gradient =2; Calculation results: Groundwater velocity is v=5×10 -6 ×2=1×10 -5 m / s Water infiltration path simulation formula: ; Input parameters: Initial water head height h0=15m, groundwater flow per unit time Q=0.01m 3 / s, water permeability coefficient T = 1.2 × 10 - 3 m 2 / s, path radius r=10m, r0=2m; Calculation results: The change in water head height is h(x,y,t)≈12.8m; Through hydrological monitoring, the risk of water inrush in water-rich strata can be assessed in real time and the drainage design can be optimized to reduce the probability of water inrush accidents during construction.

[0041] 4. Comprehensive early warning and feedback Equipment used: Abnormal early warning system (based on edge computing); Blockchain storage module (storage speed: 1000TPS).

[0042] Anomaly detection formula: ; Parameter input: The sensor data includes propulsion force (X1=4280kN), support pressure (X2=240kPa), normal mean μ1=4350kN, μ2=230kPa, weight w1=0.7, w2=0.3, threshold δ=50 Calculation result: |A(t)|=0.7×|4280-4350|+0.3×|240-230|=52>50; If the threshold is exceeded, an alarm is triggered.

[0043] Effect: Timely discover abnormal shield thrust, adjust support pressure, avoid construction interruptions, and improve construction continuity.

[0044] From the above, it can be seen that the collapse accidents caused by caves during shield machine excavation can be reduced and the stability of the tunnel construction area can be improved by 50%.

[0045] Through hydrological monitoring and optimized drainage design, the probability of water sudden accidents is reduced to 2%.

[0046] The tunneling speed of the shield machine increased from an average of 20m / day to 25m / day.

[0047] The excavation route deviation is controlled within 2cm.

[0048] Record geological and mechanical data during the construction period to provide comprehensive digital support for subsequent tunnel operation and maintenance.

[0049] Example 4 Application of mountain highway tunnel engineering Background and Project Description: A highway in a mountainous area needs to pass through karst water-rich strata, and its tunnel construction faces problems such as dense caves, high groundwater pressure and unstable strata.

[0050] Tunnel diameter: 11.6 meters Construction length: 3.2 km Geological characteristics: The density of karst caves is about 8 per square kilometer, and the groundwater pressure is about 1.2 MPa.

[0051] Project duration: 20 months The project fully applies the intelligent monitoring method of large-diameter shield tunnels in karst water-rich strata, including the following specific implementation steps: Geological exploration and data modeling Data collection: Using seismic wave imaging and laser scanning technology, a three-dimensional geological model was constructed for the construction area, and 32 caves were discovered with a total volume of approximately 12,500 cubic meters.

[0052] Risk prediction: Through deep learning algorithms, the distribution of karst caves and groundwater flow characteristics were analyzed, 10 high-risk construction points were predicted, and a grouting reinforcement plan was designed.

[0053] Real-time monitoring and dynamic construction adjustment Multi-point real-time monitoring: Distributed fiber optic sensors are installed, with a monitoring point set up every 5 meters to collect soil stress, surface settlement and water pressure data in real time.

[0054] Parameter optimization: Dynamically adjust the shield machine cutter head speed, thrust and earth pressure balance pressure based on monitoring data to ensure stable advancement.

[0055] Intelligent early warning and emergency response Water inrush risk control: When the monitoring system detects that the water pressure fluctuation in a certain area is greater than 0.7 MPa, the drainage system will be activated in advance to avoid sudden inrush accidents.

[0056] Settlement control: When the surface settlement rate exceeds 3mm / hour, the system will sound an alarm and automatically adjust the propulsion parameters to ensure that the settlement is lower than the design range.

[0057] The key monitoring and construction parameters are shown in Table 1 below; Table 1

[0058] .Effect and effectiveness analysis Improved security Cave risk control: The cave area was reinforced in advance to avoid four possible water inrush accidents.

[0059] Surface settlement control: The maximum settlement value was 22.3 mm, which did not exceed the regulatory requirements and ensured the safety of the surrounding environment of the construction area.

[0060] Improved construction efficiency Through dynamic parameter optimization, the propulsion efficiency of the shield machine is improved by 16% compared with traditional methods.

[0061] The number of shutdowns required for adjustments was reduced by 60%, and the overall construction period was shortened by 1.5 months.

[0062] Economic Benefit Analysis Direct cost savings: The optimization of cave treatment saved about 4 million yuan in grouting material costs.

[0063] Reduce emergency shutdowns caused by water inrush and reduce shutdown losses by approximately RMB 6 million.

[0064] Indirect benefits: The shortened construction period saved approximately RMB 4.5 million in equipment rental and management costs.

[0065] Total savings: $14.5 million.

[0066] Social Benefits It has reduced public complaints caused by geological disasters and enhanced social recognition of engineering projects.

[0067] Intelligent monitoring data provides support for subsequent tunnel operations and improves operational management efficiency.

[0068] The economic benefit indicators are summarized in Table 2 below; Table 2

[0069] Application scope and effectiveness Scope of application: This method is suitable for geological conditions with dense caves and high groundwater pressure, such as mountain highways, railway tunnels, and water supply engineering tunnels.

[0070] It is particularly suitable for projects involving complex karst formations and long construction lengths.

[0071] Effectiveness and economic significance: Safety guarantee: significantly reduce construction safety hazards caused by geological disasters.

[0072] Cost control: Reduce direct economic losses caused by cave treatment and shutdown, saving an average of more than 4.5 million yuan per kilometer of tunnel.

[0073] Efficiency improvement: The promotion efficiency is increased by 10%-20%, and the construction period is significantly shortened.

[0074] This method not only has direct benefits for a single project, but can also form a standardized intelligent monitoring solution that is applicable to engineering projects with similar geological conditions across the country and has the potential for large-scale promotion.

[0075] From the above, it can be seen that this embodiment takes mountain highway tunnels as the application scenario, and demonstrates in detail the remarkable results of the intelligent monitoring method under complex geological conditions, reflecting its comprehensive advantages in improving safety, reducing construction costs, and optimizing efficiency. It has clear economic value and broad promotion prospects.

[0076] Example 5 Application of subway shield tunnel engineering in a coastal city: Background and Project Description Metro Line 11 is under construction in a coastal city, where a section of the tunnel passes through karst water-rich strata. The area has a high groundwater level, well-developed caves, and uneven strata, posing great risks of water gushing, surface subsidence, and shield machine deviation.

[0077] Tunnel diameter: 12.4 meters Construction length: 1.8 km Construction period: 12 months

[0078] The project applied the intelligent monitoring method proposed in this paper. The system integrated distributed fiber optic sensors, seismic wave detection, real-time water pressure monitoring equipment, and risk prediction and optimization algorithms based on deep learning. The specific steps include: Geological prediction and cave identification: In the early stages of construction, seismic wave imaging technology was used to identify the location and size of the caves, and about 15 caves were confirmed with a total volume of about 8,200 cubic meters.

[0079] The karst cave area was treated with grouting in advance, costing RMB 5 million in materials.

[0080] Intelligent monitoring of shield construction: Distributed fiber optic sensors are installed to monitor surface subsidence. When abnormal subsidence rate is detected, the system automatically adjusts the propulsion force and cutterhead speed.

[0081] Analyze groundwater level changes in real time and dynamically adjust earth pressure balance parameters according to water pressure.

[0082] Risk early warning system: The deep learning algorithm predicts water gushing points based on real-time monitoring data, arranges drainage measures in advance, and avoids shield machine shutdown.

[0083] Key monitoring and construction parameters Real-time monitoring data: Allowable range of surface settlement: <20mm (average settlement is 13.2mm, in line with the standard).

[0084] Water pressure fluctuation range: <0.5 MPa (water inrush was predicted twice and both were handled in advance).

[0085] System response time: <3 seconds Advance speed: After adjustment, the average speed is 6.2 meters / day, which is about 12% higher than traditional construction.

[0086] Effect and effectiveness analysis Security: Three major construction accidents that could have caused water gushing were avoided, ensuring the normal advancement of the shield machine.

[0087] The maximum value of surface settlement is controlled at 18.7mm, with no risk of exceeding the standard.

[0088] Economic benefits: Direct cost savings: By identifying caves in advance and injecting grout, emergency shutdowns caused by water gushing were reduced, saving approximately RMB 3.2 million.

[0089] The optimization of construction parameters reduced the tool wear rate and saved equipment maintenance costs by approximately RMB 2 million.

[0090] Indirect economic benefits: The construction period was shortened by 15 days, saving about 200,000 yuan in management and rental costs per day, for a total savings of 3 million yuan.

[0091] Social benefits: Through the precise control of the intelligent monitoring system, residents’ complaints and secondary disaster risks caused by surface subsidence have been reduced, and the social recognition and brand image of the project have been improved.

[0092] The economic benefit indicators are summarized in Table 3 below; Table 3

[0093] Application scope and prospects The implementation of this intelligent monitoring method not only provides an accurate and efficient solution for shield tunnel construction in karst water-rich strata, but also demonstrates its application potential in the following fields: Coastal high groundwater tunnel: The ability to adapt to high water pressure and complex formations has been significantly improved, making it suitable for cross-sea tunnels and port area projects.

[0094] Urban subway and underground space development: Reduce ground subsidence and damage to surrounding buildings caused by construction, and reduce insurance and compensation costs.

[0095] Economical improvements: Through large-scale promotion, the cost savings for a single project can exceed 10 million yuan in the future, forming economies of scale.

[0096] As can be seen from the above, this embodiment clearly demonstrates the specific effectiveness and economic benefits of the intelligent monitoring method in actual engineering, especially in improving construction safety and reducing costs. This model provides a replicable and popularizable technical route for the intelligent development of complex geological engineering.

[0097] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0098] In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other.

[0099] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent monitoring method for a large-diameter shield tunnel in a karst water-rich stratum, characterized in that: The following steps are involved: S1. Real-time geological detection: Multi-source geological radar and advanced drilling analysis are used in combination with artificial intelligence algorithms to identify and predict the geological structure in front of the shield in real time. The geological structure includes the volume of rock karst caves, fault zones and water-rich areas in the strata; S2. Shield machine posture and mechanical monitoring: The shield machine posture, propulsion force and grouting pressure are monitored in real time through a sensor network, and real-time feedback and abnormality identification are achieved based on edge computing and Internet of Things technologies. The sensor network includes high-precision gyroscopes, acceleration sensors and pressure sensors. S3. Hydrology and seepage monitoring: Use distributed fiber optic sensing systems to monitor groundwater velocity, temperature and pressure changes, and combine hydrological numerical simulation to predict groundwater seepage paths and water inrush risks; S4. Surrounding rock deformation and stress monitoring: deploy multi-dimensional monitoring equipment, including laser scanners, acoustic emission sensors and strain gauges, to monitor surrounding rock deformation and stress field changes in real time; S5. Comprehensive early warning and feedback: Based on the big data analysis platform, abnormalities are detected in the monitoring data and early warning information is generated, and automatic response is achieved through a multi-level linkage mechanism; fiber grating sensors are used to record and analyze the long-term deformation of the tunnel structure and changes in the water environment, and predict stability during operation.

2. The intelligent monitoring method for large-diameter shield tunnels in karst water-rich strata according to claim 1 is characterized in that: The calculation expression of the rock cave volume in step S1 is: ； V: volume of the cave, m 3 ; f(x,y,z): probability density function of cave generated by the reflected signal intensity data of multi-source geological radar and advance drilling; x1,x2,y1,y2,z1,z2: The boundary coordinates of the cave, determined by radar scanning and artificial intelligence model prediction.

3. The intelligent monitoring method for large-diameter shield tunnels in karst water-rich strata according to claim 1 is characterized in that: The real-time geological detection step further includes fiber Raman distributed sensing technology for monitoring the temperature distribution of the rock formation in front of the shield and evaluating the groundwater flow and dissolution activity intensity of the water-rich area of ​​the formation.

4. The intelligent monitoring method for large-diameter shield tunnels in karst water-rich strata according to claim 3 is characterized in that: The prediction expression of the formation water-richness of the formation water-rich area in step S1 is: ； Pw: formation water richness index; T: Formation temperature gradient detected by Raman distributed optical fiber sensing; C: Groundwater conductivity data obtained by drilling; S: intensity attenuation value of geological radar reflection signal; α, β, γ: weight parameters obtained through machine learning algorithms, linear regression or support vector machine training.

5. The intelligent monitoring method for large-diameter shield tunnels in karst water-rich strata according to claim 1 is characterized in that: The optimization expression of the propulsion force in step S2 is: ； Ft: thrust force of shield machine, kN; Pi: support pressure of each partition of the shield face, kPa; Ai: the area of ​​the corresponding partition, m 2 ; ΔF: Dynamic adjustment value, calculated by the AI ​​algorithm based on surrounding rock deformation and tunneling speed optimization.

6. The intelligent monitoring method for large-diameter shield tunnels in karst water-rich strata according to claim 1 is characterized in that: The control formula of the shield machine posture in step S2 is: ； θ, : Shield machine attitude deviation angle, °; Δy, Δx: displacement deviation of the shield machine in the vertical and horizontal directions, m; L: Current excavation length of the shield machine, m.

7. The intelligent monitoring method for large-diameter shield tunnels in karst water-rich strata according to claim 1 is characterized in that: The calculation expression of groundwater flow velocity in step S3 is: ； v: groundwater velocity, m / s; K: Permeability coefficient, obtained from field tests; : hydraulic gradient, calculated from pressure changes monitored by a fiber optic sensing network; This formula calculates groundwater flow velocity and direction by real-time monitoring of hydraulic gradient, providing data for predicting water gushing risks and surrounding rock damage caused by water flow.

8. The intelligent monitoring method for large-diameter shield tunnels in karst water-rich strata according to claim 1 is characterized in that: The simulation formula of the groundwater seepage path is: ； h(x,y,t): change in seepage head, m; h0: initial water head height, m; Q: Groundwater flow per unit time, m 3 / s; T: Permeability coefficient of the formation, m 2 / s; r, r0: current radius and initial radius of the water flow path, m.

9. The intelligent monitoring method for large-diameter shield tunnels in karst water-rich strata according to claim 1 is characterized in that: The expression for anomaly detection in step S5 is: ； A(t): outlier indicator; Xi(t): the monitoring value of the i-th sensor; μi: the normal operating mean of the i-th sensor; wi: weight of the i-th sensor, obtained by training the machine learning model; δ: Threshold value, exceeding this value triggers an alarm.

Images