Cold region tunnel grouting reinforcement intelligent construction system and method based on crack detection

Abstract

The invention discloses a cold region tunnel grouting reinforcement intelligent construction system and method based on crack detection, and the system comprises six modules: a control center unit, an information sensing unit, a data transmission unit, an intelligent decision-making unit, an automatic execution unit, and an evaluation feedback unit. The information sensing unit senses crack and temperature information, the crack and temperature information is transmitted to the intelligent decision-making unit through the data transmission unit, and then a grouting material formula and process parameter decision-making result is generated, so that the automatic execution unit executes grout preparation and grouting operation. And finally, the evaluation feedback unit evaluates the grouting effect in real time and feeds back the grouting effect to the intelligent decision-making unit to verify a scheme and guide optimization, so that a'detection-decision-execution-evaluation-optimization 'closed-loop system is formed, and the problems of excessive dependence on manpower, improper material preparation, low construction efficiency and the like in a traditional method are solved. And efficient, accurate and stable reinforcement of the tunnel surrounding rock in the alpine region is achieved.

Description

Technical Field

[0001] This invention relates to the field of tunnel engineering maintenance technology, and more specifically, to an intelligent construction system and method for grouting reinforcement of tunnels in cold regions based on crack detection. Background Technology

[0002] The construction of tunnels in cold regions is a crucial engineering measure to overcome the harsh natural conditions of frigid areas and ensure smooth transportation. However, the unique geological and climatic environment of cold regions, especially freeze-thaw erosion, causes micro-cracks within the rock mass to gradually enlarge, expand, and interconnect, while simultaneously generating new cracks. This significantly reduces the mechanical properties of the rock mass, thus posing a serious threat to the tunnel structure. Grouting technology, as a core method for ground reinforcement and leakage control, effectively restores structural integrity, enhances load-bearing capacity, and improves water-stopping effects by injecting specific grout materials into the cracks. Therefore, it has become an indispensable key technology for the maintenance of tunnels in cold regions.

[0003] However, grouting reinforcement of tunnels in cold regions faces a series of severe technical challenges. For example, traditional crack inspection mainly relies on manual visual inspection, which makes it easy to miss minute cracks under conditions of poor lighting and limited space inside the tunnel. Furthermore, the error in manually identifying crack characteristics is relatively large, affecting the accuracy of subsequent grouting design and defect assessment. At the same time, the selection of core parameters for grouting materials and grouting processes is too simplistic, failing to effectively consider the crack characteristics and temperature conditions of specific tunnel sections, and lacking refined and dynamic design, which can easily lead to insufficient or excessive grouting. In addition, grouting operations in frigid environments present harsh working conditions for workers, and problems such as borehole positioning deviations and unstable pressure control are common, directly affecting the final effect of grouting reinforcement. Summary of the Invention

[0004] To address the aforementioned bottlenecks, the field of grouting reinforcement for tunnels in cold regions urgently needs a highly integrated, intelligent, and automated systematic solution that combines precise perception and quantitative analysis of diverse information, intelligent decision-making and dynamic adjustment of grouting parameters, and integrated and automated drilling and grouting operations. By integrating perception, decision-making, execution, and feedback functions, this solution overcomes the limitations of traditional methods and significantly improves the construction quality, efficiency, safety, and environmental adaptability of grouting reinforcement for tunnels in cold regions.

[0005] Based on this, the present invention provides an intelligent construction system and method for grouting reinforcement of tunnels in cold regions based on crack detection. Its purpose is to solve the problems of excessive reliance on manpower, single parameter design and low construction efficiency in traditional methods, and to achieve efficient, accurate and stable reinforcement of the surrounding rock of tunnels in cold regions.

[0006] The specific technical solutions include: The first aspect provides an intelligent construction system for grouting reinforcement of tunnels in cold regions based on crack detection, including: The control center unit is used for monitoring and coordinating the grouting and reinforcement construction of tunnels in cold regions. The information sensing unit is used to sense crack information, temperature information, and detect raw information. The data transmission unit is used to transmit the information perceived by the information sensing unit to the intelligent decision-making unit; The intelligent decision-making unit includes an intelligent decision-making engine, which is used to train a big data model based on a historical case database. The trained big data model is used to predict the grouting effect of the initial combination. Then, based on the prediction results, the decision results of the grouting material formula and process parameters are obtained through multi-objective optimization. The initial combination is the grouting material formula and grouting process parameters that match the deep fractures and shallow fractures. The initial combination is obtained based on the fracture geological model and temperature distribution model. The fracture geological model and temperature distribution model are constructed by processing the information perceived by the information sensing unit. And an automatic execution unit, used to perform grout preparation and grouting operations based on the decision results of grouting material formulation and process parameters.

[0007] In one embodiment, the system further includes an evaluation feedback unit for analyzing crack information, temperature information, and original detection information to obtain grouting effect evaluation results, and feeding them back to the intelligent decision-making unit for the intelligent decision-making unit to verify the decision results, improve the case library, and optimize the scheme.

[0008] In one implementation, the control center unit, intelligent decision-making unit, and feedback evaluation unit are mounted on a fixed working platform, while the information sensing unit and automatic execution unit are mounted on a mobile working platform, and the signal exchange between the fixed working platform and the mobile working platform is realized by the data transmission unit.

[0009] In one embodiment, the information sensing unit includes a crack detection subsystem, a temperature detection subsystem, and an effect detection subsystem. The crack detection subsystem includes a high-definition endoscope for shallow crack detection and a ground-penetrating radar for deep crack detection. The temperature detection subsystem includes a low-temperature temperature sensor for detecting ambient temperature. The effect detection subsystem includes an infrared thermal imager for detecting slurry temperature, an ultrasonic viscometer for detecting slurry viscosity, a laser rangefinder for detecting clearance convergence, and a comprehensive detection instrument for detecting leakage.

[0010] In one embodiment, the intelligent decision-making unit further includes a model generator, a historical case library, and an output interface. The model generator is used to perform noise reduction filtering, feature extraction, and fusion processing on the original detection information to construct a fracture geological model and a temperature distribution model. The historical case library includes a grouting material formula library, a grouting process parameter library, and a field detection database associated with fracture characteristics and temperature conditions. The output interface is used to form an instruction set from the decision results of the grouting material formula and process parameters given by the intelligent decision engine and send it to the control center unit.

[0011] In one embodiment, the automatic execution unit includes an intelligent grout mixing subsystem and an intelligent grouting subsystem, wherein the intelligent grout mixing subsystem is used to perform grout mixing operations according to a set of instructions regarding the grouting material formulation; and the intelligent grouting subsystem is used to perform grouting operations according to a set of instructions regarding grouting process parameters.

[0012] In one embodiment, the grouting material formula library stores the mix proportions and performance parameters of grouting materials under different crack characteristics and temperature conditions; the grouting process parameter library stores the grouting process parameters under different crack characteristics and temperature conditions; and the field testing database stores the grouting effect evaluation results of successful grouting reinforcement cases of cold-region tunnels under different working conditions.

[0013] In one embodiment, the intelligent grout preparation subsystem is specifically used to receive the instruction set from the intelligent decision-making unit regarding the grouting material formula, automatically weigh, mix, and stir according to the proportion to prepare a grout that meets the preset requirements, and obtain the grout temperature and grout viscosity in real time through an infrared thermal imager and an ultrasonic viscometer, respectively; the intelligent grouting subsystem is specifically used to receive the instruction set from the intelligent decision-making unit regarding the grouting process parameters, first control the multi-functional grouting gun on the mechanical clamping arm to drill grouting holes at designated positions and complete the hole cleaning work, then precisely insert the multi-functional grouting gun into the grouting hole, and control the grouting pump to perform grouting according to the specified grouting pressure and grouting flow rate.

[0014] Based on the same inventive concept, a second aspect of this invention provides an intelligent construction method for grouting reinforcement of tunnels in cold regions based on crack detection, comprising: The control center unit was used to monitor and coordinate the grouting reinforcement construction of tunnels in cold regions. The information sensing unit is used to sense crack information, temperature information, and detect raw information. The information sensed by the information sensing unit is transmitted to the intelligent decision-making unit using the data transmission unit. The intelligent decision-making engine of the intelligent decision-making unit is used to train a big data model based on a historical case database. The trained big data model is used to predict the grouting effect of the initial combination. Then, based on the prediction results, the decision results of grouting material formula and process parameters are obtained through multi-objective optimization. The initial combination is the grouting material formula and grouting process parameters that match deep fractures and shallow fractures. The initial combination is obtained based on the fracture geological model and temperature distribution model. The fracture geological model and temperature distribution model are constructed by processing the information perceived by the information sensing unit. The automatic execution unit performs grout preparation and grouting operations based on the decision results of the grouting material formula and process parameters.

[0015] In one embodiment, the method further includes: The evaluation feedback unit analyzes crack information, temperature information, and original detection information to obtain grouting effect evaluation results, which are then fed back to the intelligent decision-making unit for verification of decision results, improvement of case library, and optimization of scheme.

[0016] Compared with the prior art, the advantages and beneficial technical effects of the present invention are as follows: This invention provides an intelligent construction system for grouting reinforcement of cold-region tunnels based on crack detection. The system comprises a control center unit, an information sensing unit, a data transmission unit, an intelligent decision-making unit, and an automatic execution unit. The control center unit monitors and coordinates the construction process. The information sensing unit detects crack and temperature information, which is transmitted to the intelligent decision-making unit via the data transmission unit. The intelligent decision-making engine in the intelligent decision-making unit trains a big data model based on a historical case database. The trained big data model predicts the grouting effect of a preliminary combination of grouting elements. Based on the prediction results, multi-objective optimization is used to obtain decision results for the grouting material formula and process parameters, thereby generating the grouting material formula and process parameter decision results, which then enable the automatic execution unit to perform grout preparation and grouting operations. This system comprehensively perceives multi-dimensional information such as cracks and temperature using advanced sensing technology, generating refined crack geological models and temperature distribution models. This solves the problems of inaccurate and incomplete information acquisition in existing methods. Based on the crack and temperature models, it intelligently matches the grouting material formula and grouting process parameters most suitable for the low-temperature environment and crack characteristics, significantly improving the adaptability and effectiveness of grouting in cold-region tunnels under different working conditions.

[0017] Furthermore, the system also includes an evaluation feedback unit, which analyzes crack information, temperature information, and original detection information to obtain grouting effect evaluation results and feeds them back to the intelligent decision-making unit for the intelligent decision-making unit to verify the decision results, improve the case library, and optimize the scheme.

[0018] Furthermore, the intelligent grouting subsystem and intelligent grouting subsystem in the system achieve a high degree of automation from material preparation to grouting execution. The entire process minimizes manual operation in frigid environments, significantly improving construction efficiency, accuracy, and safety.

[0019] Furthermore, the system has constructed a complete closed-loop feedback mechanism of "detection-decision-execution-evaluation-optimization" and can automatically archive all data for updating the case library and optimizing the decision model, while also helping to continuously improve the performance of other modules of the system. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is an overall structural diagram of the intelligent construction system for grouting reinforcement of cold-region tunnels based on crack detection, as described in this embodiment of the invention.

[0022] Figure 2 This is a detailed structural diagram of the intelligent construction system for grouting reinforcement of cold-region tunnels based on crack detection, as described in this embodiment of the invention.

[0023] Figure 3 This is a flowchart illustrating the steps of the intelligent construction method for grouting reinforcement of cold-region tunnels based on crack detection in an embodiment of the present invention. Figure 4 This is a schematic diagram illustrating the change in fluidity of low-temperature epoxy modified slurry at different temperatures in an embodiment of the present invention; Figure 5 This is a schematic diagram illustrating the variation of initial setting time of low-temperature epoxy modified slurry at different temperatures in an embodiment of the present invention; Figure 6 This is a schematic diagram illustrating the variation of final setting time of low-temperature epoxy modified slurry at different temperatures in an embodiment of the present invention; Figure 7 A schematic diagram illustrating the viscosity changes of low-temperature epoxy modified slurry at different temperatures in this embodiment of the invention. Detailed Implementation

[0024] This embodiment provides an intelligent construction system for grouting reinforcement of tunnels in cold regions based on crack detection. Please refer to [link to relevant documentation]. Figure 1 ,include: Control center unit 101 is used for monitoring and coordinating the grouting reinforcement construction of tunnels in cold regions. The information sensing unit 102 is used to sense crack information, temperature information, and detect raw information; Data transmission unit 103 is used to transmit information perceived by information perception unit to intelligent decision-making unit; The intelligent decision-making unit 104 includes an intelligent decision-making engine, which is used to train a big data model based on a historical case library. The trained big data model is used to predict the grouting effect of the initial combination. Then, based on the prediction results, the decision results of the grouting material formula and process parameters are obtained through multi-objective optimization. The initial combination is the grouting material formula and grouting process parameters that match the deep fracture and the shallow fracture. The initial combination is obtained based on the fracture geological model and the temperature distribution model. The fracture geological model and the temperature distribution model are constructed by processing the information perceived by the information sensing unit. And an automatic execution unit 105, used to perform grout preparation and grouting operations based on the decision results of the grouting material formula and process parameters.

[0025] The system includes an evaluation feedback unit 106, which analyzes crack information, temperature information and original detection information to obtain grouting effect evaluation results and feeds them back to the intelligent decision-making unit for the intelligent decision-making unit to verify the decision results, improve the case library and optimize the scheme.

[0026] Specifically, the grouting effect evaluation results are obtained through quantitative analysis based on multi-sensor data fusion. Specifically, the physical state of the rock mass after grouting (filling degree, deformation, leakage) can be detected by scientific instruments, and these detection data are compared with the expected target values, so as to objectively and accurately evaluate the actual effect of grouting reinforcement and provide data support for the system's self-learning and continuous optimization.

[0027] The control center unit, intelligent decision-making unit, and feedback evaluation unit are mounted on a fixed working platform, while the information sensing unit and automatic execution unit are mounted on a mobile working platform. The signal exchange between the fixed working platform and the mobile working platform is realized by the data transmission unit.

[0028] Please see Figure 2 This is a detailed structural diagram of the intelligent construction system for grouting reinforcement of cold-region tunnels based on crack detection, as described in this embodiment of the invention.

[0029] In one implementation, the control center unit consists of a human-machine interface and a main controller; the human-machine interface is used for equipment status control, real-time data browsing, 3D model display, decision result preview, flexible parameter adjustment, and fault diagnosis alarm; the main controller is used to coordinate the work of various modules (intelligent decision unit, feedback evaluation unit, information perception unit, and automatic execution unit) and process feedback signals (feedback signals generated by the feedback evaluation unit, which are generated after evaluating grouting parameters or results).

[0030] In one embodiment, the information sensing unit includes a crack detection subsystem, a temperature detection subsystem, and an effect detection subsystem. The crack detection subsystem includes a high-definition endoscope for shallow crack detection and a ground-penetrating radar for deep crack detection. The temperature detection subsystem includes a low-temperature temperature sensor for detecting ambient temperature. The effect detection subsystem includes an infrared thermal imager for detecting slurry temperature, an ultrasonic viscometer for detecting slurry viscosity, a laser rangefinder for detecting clearance convergence, and a comprehensive detection instrument for detecting leakage.

[0031] Specifically, crack detection refers to acquiring information related to the location, length, width, orientation, distribution density, and connectivity of cracks in the surrounding rock of tunnels in cold regions. Cracks are then classified into three categories based on their length and width: Class I cracks have a width of no more than 0.3 mm and a length of no more than 5 mm; Class II cracks have a width of 0.3 to 1 mm and a length of 5 to 10 mm; and Class III cracks have a width greater than 1 mm and a length of no less than 10 mm.

[0032] It should be noted that the acquired location, orientation, and distribution density help the system construct a three-dimensional geometric model of the crack. Connectivity makes this geometric model a dynamic system model that reflects the material transport patterns within the rock mass. Ultimately, by analyzing this comprehensive model, the system finds an optimal grouting hole location (based on location and connectivity), determines an optimal drilling angle (based on orientation), calculates a reasonable grouting pressure and material usage (based on distribution density and connectivity), and can accurately analyze the reasons when the effect evaluation fails to meet the standards (e.g., whether it is due to unidentified connecting channels causing grout loss).

[0033] The low-temperature sensor has a measurement range of -20℃ to 5℃ and an accuracy of 0.01℃, enabling real-time and continuous monitoring of air temperature, rock wall temperature, and borehole temperature in cold-region tunnels.

[0034] The data transmission unit transmits the raw on-site detection data (raw detection information) such as images, waveforms, temperature, and deformation acquired by the information sensing unit to the intelligent decision-making unit via 5G wireless means.

[0035] In one implementation, the intelligent decision-making unit further includes a model generator, a historical case library, and an output interface. The model generator is used to perform noise reduction filtering, feature extraction, and fusion processing on the raw detection information to construct a fracture geological model and a temperature distribution model. The historical case library includes a grouting material formula library, a grouting process parameter library, and a field detection database associated with fracture characteristics and temperature conditions. The output interface is used to form an instruction set from the decision results of the grouting material formula and process parameters given by the intelligent decision engine and send it to the control center unit.

[0036] Specifically, for image data from high-definition endoscopes, infrared thermal imagers, etc., waveform data from ground-penetrating radar, ultrasonic viscometers, etc., and temperature data from waveform data, adaptive filtering algorithms are used to reduce noise and ensure data quality; feature extraction combines computer vision and signal processing techniques to extract quantitative features related to cracks and temperature; fusion processing generates a high-precision model through multi-sensor data fusion algorithms.

[0037] The intelligent decision engine obtains the decision results for grouting material formulations and process parameters through rapid indexing and algorithm optimization. Rapid indexing refers to selecting the grouting material formulations and grouting process parameters that best match deep and shallow fractures, respectively, based on the constructed fracture geological model and temperature distribution model. Algorithm optimization involves first training a big data model using a historical case database, then predicting the grouting effect of the initial selection combination, and finally obtaining the decision result through multi-objective optimization.

[0038] In practice, the rapid index extracts features from the fracture geological model and temperature distribution model, performs preprocessing and index construction in the case library, and can use a weighted similarity calculation to generate a preliminary selection combination.

[0039] In multi-objective systems, the objectives refer to balancing multiple conflicting goals such as effectiveness, cost, efficiency, and environmental adaptability. The decision-making outcome is determined by a single final decision based on preset weight preferences or manual selection, thereby achieving efficient, precise, stable, and economical reinforcement of the surrounding rock of tunnels in high-altitude and cold regions.

[0040] In one embodiment, the automatic execution unit includes an intelligent grout preparation subsystem and an intelligent grouting subsystem, wherein the intelligent grout preparation subsystem is used to perform grout preparation operations according to a set of instructions regarding the grouting material formulation; and the intelligent grouting subsystem is used to perform grouting operations according to a set of instructions regarding grouting process parameters.

[0041] Specifically, the intelligent grouting subsystem includes a raw material storage tank, a high-precision weighing sensor, a feed pipeline, a constant temperature mixing tank, and a mixer; the intelligent grouting subsystem includes a grouting pump, a grouting pipeline, a mechanical clamping arm, and a multi-functional grouting gun that integrates drilling, hole cleaning, and grouting functions.

[0042] In one embodiment, the grouting material formula library stores the mix proportions and performance parameters of grouting materials under different crack characteristics and temperature conditions; the grouting process parameter library stores the grouting process parameters under different crack characteristics and temperature conditions; and the field testing database stores the grouting effect evaluation results of successful grouting reinforcement cases of cold-region tunnels under different working conditions.

[0043] Specifically, the grouting material mix design includes raw materials, water-cement ratio, and admixture dosage. Performance parameters include setting time, fluidity, strength development curve, viscosity, frost resistance, permeability, adhesion to surrounding rock, and environmental friendliness. The grouting process parameter library stores grouting process parameters under different crack characteristics and temperature conditions, including borehole diameter, borehole depth, borehole angle, grouting pressure, and grouting flow rate.

[0044] In one embodiment, the intelligent grout preparation subsystem is specifically used to receive the instruction set from the intelligent decision-making unit regarding the grouting material formula, automatically weigh, mix, and stir according to the proportion to prepare a grout that meets the preset requirements, and obtain the grout temperature and grout viscosity in real time through an infrared thermal imager and an ultrasonic viscometer, respectively; the intelligent grouting subsystem is specifically used to receive the instruction set from the intelligent decision-making unit regarding the grouting process parameters, first control the multi-functional grouting gun on the mechanical clamping arm to drill grouting holes at designated positions and complete the hole cleaning work, then precisely insert the multi-functional grouting gun into the grouting hole, and control the grouting pump to perform grouting according to the specified grouting pressure and grouting flow rate.

[0045] The system of the present invention will be described below through specific embodiments. Background of the embodiments: In a certain high-altitude and cold region, the average annual temperature is -5℃, and the extreme winter temperature is -19℃. There is a highway tunnel under construction, located in a stratum of moderately weathered granite. Several sections of the tunnel have numerous cracks caused by freeze-thaw cycles. Preliminary investigation shows that the maximum width of the cracks is 3.2mm, with a longitudinal penetration of 5.8m, and the internal temperature of the temporary testing borehole is -18 to -12℃.

[0046] To ensure the safe construction of the aforementioned cold-region tunnels, it is proposed to adopt an intelligent construction system for grouting repair of cold-region tunnels based on crack detection, as disclosed in this invention. The system includes six modules: a control center unit, an information sensing unit, a data transmission unit, an intelligent decision-making unit, an automatic execution unit, and a feedback evaluation unit. The control center unit, intelligent decision-making unit, and feedback evaluation unit are mounted on a fixed working platform, while the information sensing unit and automatic execution unit are mounted on a mobile working platform. Furthermore, the signal exchange between the fixed working platform and the mobile working platform is achieved by the data transmission unit.

[0047] The temperature detection subsystem contains no fewer than three low-temperature temperature sensors to monitor the air temperature, rock wall temperature, and borehole temperature in cold regions in real time and continuously.

[0048] Based on the same inventive concept, this embodiment also provides an intelligent construction method for grouting reinforcement of tunnels in cold regions based on crack detection, including: The control center unit was used to monitor and coordinate the grouting reinforcement construction of tunnels in cold regions. The information sensing unit is used to sense crack information, temperature information, and detect raw information. The information sensed by the information sensing unit is transmitted to the intelligent decision-making unit using the data transmission unit. The intelligent decision-making engine of the intelligent decision-making unit is used to train a big data model based on a historical case database. The trained big data model is used to predict the grouting effect of the initial combination. Then, based on the prediction results, the decision results of grouting material formula and process parameters are obtained through multi-objective optimization. The initial combination is the grouting material formula and grouting process parameters that match deep fractures and shallow fractures. The initial combination is obtained based on the fracture geological model and temperature distribution model. The fracture geological model and temperature distribution model are constructed by processing the information perceived by the information sensing unit. The automatic execution unit performs grout preparation and grouting operations based on the decision results of the grouting material formula and process parameters.

[0049] The above methods also include: The evaluation feedback unit analyzes crack information, temperature information, and original detection information to obtain grouting effect evaluation results, which are then fed back to the intelligent decision-making unit for verification of decision results, improvement of case library, and optimization of scheme.

[0050] For specific instructions on the operation of the intelligent construction system for grouting repair of tunnels in cold regions based on crack detection, please refer to [link to relevant documentation]. Figure 3 It includes the following steps: S1.1: After on-site investigation, the section of the tunnel in the cold region that needs grouting reinforcement was determined. The fixed working platform was deployed to a safe area, and the mobile working platform was mounted on a modified engineering vehicle and moved into the working area. Typical sections in the working area were selected for testing and grouting.

[0051] S1.2: Conduct system self-checks to ensure the normal operation of all modules and equipment. For example, the probe frequency of the ground-penetrating radar is set to 1GHz to adapt to the dielectric constant of moderately weathered granite; the low-temperature sensor is calibrated to a measurement range of -20℃ to 5℃; the big data model of the intelligent decision-making unit has been trained based on the historical case database. Figures 4-7 This is the performance data of low-temperature epoxy modified slurry under different crack characteristics and temperature conditions from the historical case library.

[0052] S1.3: Using the control center unit, the mechanical clamping arm is used to drive the multi-functional grouting gun to the designated position of the typical section, and seven temporary inspection holes are drilled, including one on the arch and three on each side of the sidewall. The drilling angle is 30°, the drilling diameter is 20mm, and the drilling depth is 1.5m. After drilling is completed, the hole cleaning work is carried out.

[0053] S2: Crack identification and temperature detection; S2.1: Control the mechanical clamping arm to drive the high-definition camera and ground-penetrating radar to the designated positions, start the crack detection subsystem, first use the high-definition camera to observe the surface of the surrounding rock of the current section and the inside of the temporary detection hole, then use the ground-penetrating radar to detect the inside of the surrounding rock, and finally identify the cracks as mainly Class III cracks.

[0054] S2.2: Control the mechanical clamping arm to move the low-temperature temperature sensor to the designated position, start the temperature detection subsystem, and place the low-temperature temperature sensor inside the tunnel, on the surface, and inside the temporary detection hole in the cold region. According to the feedback, the air temperature is -13℃, the rock wall temperature is -15℃, and the temperature inside the hole is -10.5℃, confirming that the current section has reached the low-temperature environment state.

[0055] S3: Data transmission and fusion modeling; S3.1: The data transmission unit transmits the raw on-site detection data related to cracks and temperature, such as images, waveforms, and temperatures captured by the information sensing unit, to the intelligent decision-making unit via 5G wireless means.

[0056] S3.2: The intelligent decision-making unit first performs noise reduction filtering on the above-mentioned raw on-site detection data. Then, through feature extraction and fusion processing, it generates a crack geological model that includes the three-dimensional spatial distribution, geometric features, and type classification of cracks, as well as a temperature distribution model that reflects the temperature gradient of the section to be grouted and reinforced.

[0057] S4: Intelligent decision-making and parameter generation; S4.1: The intelligent decision-making unit calls the historical case library and, based on the fused fracture geological model and temperature distribution model, selects the grouting material formula and grouting process parameters that are most closely matched to the deep fracture and shallow fracture as the initial combination. Here, MS-5 type low-temperature epoxy modified grout is selected, material library number C-07, which is suitable for Class III surrounding rock fractures and tunnel temperatures of -25℃ to 0℃.

[0058] The integration of fracture geological models and temperature distribution models is a process of creating a digitally coupled "geology-temperature" relationship. Physical correlations can be established through spatial registration; coupled descriptive indices can be created through feature correlations; and coupled analysis ultimately achieves: precise grouting by zone and category, and dynamic and synergistic optimization of grout materials and process parameters.

[0059] S4.2: The trained big data model is used to predict the grouting effect of the initially selected combination, and the optimal grouting material formula and grouting process parameters are determined through multi-objective optimization as follows: water-cement ratio 0.42, antifreeze dosage 8%, grout temperature 35℃, grout viscosity 45MPa·s, grouting flow rate 5.2L / min, grouting pressure 1.0MPa, and for deep cracks, the pressure is increased to 1.5MPa. The above decision results are used to generate the corresponding instruction set, which is sent from the control center unit to the automatic execution unit.

[0060] S5: Automatic slurry preparation and mixing; S5.1: The intelligent grouting subsystem receives the instruction set from the intelligent decision-making unit regarding the grouting material formula, and, in conjunction with a high-precision weighing sensor, controls the raw material storage tank to accurately output 120kg of epoxy resin, 35kg of nano-silica powder, and 12.4L of antifreeze into the constant temperature mixing tank.

[0061] S5.2: Start the agitator and simultaneously activate the temperature control function of the constant temperature mixing chamber during the mixing process. Combined with the infrared thermal imager and ultrasonic viscometer, ensure that the mixture is maintained at a slurry temperature of 35℃ and a slurry viscosity of 45MPa·s until it is fully mixed.

[0062] S6: Drilling and Precision Grouting; S6.1: The intelligent grouting subsystem receives the instruction set of the intelligent decision-making unit regarding the grouting process parameters, enlarges the seven temporary detection holes to convert them into grouting holes, keeps the drilling angle unchanged, increases the drilling diameter to 40mm, increases the drilling depth to 4m, and performs hole cleaning work after the grouting hole construction is completed.

[0063] S6.2: The mechanical clamping arm precisely inserts the multi-functional grouting gun into the grouting hole, starts the grouting pump, and sequentially grouts the deep cracks and shallow cracks. The system monitors and records the actual grouting flow rate (5.2 L / min) and grouting pressure (1 MPa) in real time. When the grouting pressure stabilizes for 6 minutes, the grouting of the hole is automatically stopped, and the system moves to the next grouting hole according to the decision result to repeat the above operation.

[0064] S7: Process monitoring and closed-loop feedback; S7.1: Throughout the construction process, the control center unit intuitively displays the equipment status, 3D model, and real-time data. By comparing with the set values, it can make small adaptive adjustments. After the typical section is grouted and reinforced, the effect detection subsystem is activated. The original on-site detection data such as section filling, clearance convergence, and leakage are sent to the evaluation feedback unit through the data transmission unit to generate the grouting effect evaluation results for the current section. The crack filling rate of the typical section is 72%.

[0065] It should be noted that the devices in S7.1 include: The first part consists of the equipment on the mobile work platform: mechanical clamping arm, multi-functional grouting gun, crack detection sensor, and temperature sensor; the second part consists of the fixed work platform and supporting equipment: raw material storage tank, high-precision weighing sensor, and constant temperature mixing box in the intelligent grouting subsystem, and grouting pump, data transmission unit, and control center itself in the intelligent grouting subsystem.

[0066] Status information can be summarized into three categories: Operating status: Power on, Power off, Standby, Running, Fault, Alarm.

[0067] Performance parameters: speed, pressure, temperature, position, power, signal strength.

[0068] Health and safety status: fault codes, alarm information, maintenance reminders.

[0069] The 3D model is a virtual tunnel that integrates "geological conditions (cracks) + environmental conditions (temperature) + construction progress (equipment, drilling) + reinforcement effect (grout diffusion)", allowing operators to have a clear overview of the entire construction site and its details.

[0070] Real-time data refers to the continuously updated and dynamically changing data stream on the monitoring interface, serving as the basis for the system's "minor adaptive adjustments" and for personnel decision-making. It mainly includes: Construction parameter data: Grouting process: real-time grouting pressure, grouting flow rate, and cumulative grouting volume.

[0071] Slurry preparation process: real-time slurry temperature, slurry viscosity, and actual proportions of various raw materials.

[0072] Drilling process: drilling depth and drilling speed.

[0073] Environmental and state perception data: Temperature data: Real-time temperatures of air, rock walls, borehole, and slurry.

[0074] Crack monitoring data: Real-time feedback of the change in net clearance convergence value from the laser rangefinder.

[0075] Effect detection data: Temperature field changes during the solidification process of slurry as seen by an infrared thermal imager.

[0076] Decision and setpoint data: The intelligent decision-making unit issues the following settings: grouting pressure setting range and grout viscosity target value.

[0077] Deviation value: The difference between real-time data and set value, which is the direct basis for making "small adaptive adjustments".

[0078] S7.2: The evaluation feedback unit feeds back the above grouting effect evaluation results to the intelligent decision unit, and concludes that the typical section has not achieved the grouting reinforcement target. The reason is determined to be that some deep cracks have been missed in identification. At the same time, four new grouting holes are generated as a secondary grouting scheme, and the automatic execution unit is driven to grout the new grouting holes. Finally, the evaluation feedback unit analyzes the re-inspection results and finds that the filling rate reaches 98%, which can achieve the grouting reinforcement target.

[0079] S8: Construction completion and data archiving; Repeat steps S1 to S7 until the grouting reinforcement of the cold region tunnel is completed. Then the system automatically generates a construction report containing test data, decision results, construction records, evaluation results, etc. The report clearly states that this embodiment saves 15% of materials and improves overall efficiency by 40%. All data is stored in the intelligent decision unit for database updates and model upgrades.

[0080] This invention provides an intelligent construction system and method for grouting repair of tunnels in cold regions based on crack detection, which has the following significant advantages: (1) The system uses advanced sensing technology to comprehensively perceive multi-dimensional information such as cracks and temperature, and then generates a refined crack geological model and temperature distribution model, which completely solves the problem of inaccurate and incomplete information acquisition by traditional methods.

[0081] (2) Based on the crack model and temperature model, the system intelligently matches the grouting material formula and grouting process parameters that are most suitable for low temperature environment and crack characteristics, which significantly improves the adaptability and effectiveness of grouting in cold tunnels under different working conditions.

[0082] (3) The intelligent grouting subsystem and intelligent grouting subsystem in the system realize highly automated operation of the entire process from material preparation to grouting execution. The entire process minimizes the manual operation links in the cold environment and greatly improves construction efficiency, accuracy and safety.

[0083] (4) The system has built a complete closed-loop feedback mechanism of “detection-decision-execution-evaluation-optimization” and can automatically archive all data for updating the case library and optimizing the decision model. It also helps to continuously improve the performance of other modules of the system.

[0084] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0085] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0086] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention. Clearly, those skilled in the art can make various modifications and variations to the embodiments of the invention without departing from the spirit and scope of the invention. Thus, if these modifications and variations of the embodiments of the invention fall within the scope of the claims of the invention and their equivalents, the invention also intends to include these modifications and variations.

Claims

1. A smart construction system for grouting reinforcement of tunnels in cold regions based on crack detection, characterized in that, include: The control center unit is used for monitoring and coordinating the grouting and reinforcement construction of tunnels in cold regions. The information sensing unit is used to sense crack information, temperature information, and detect raw information. The data transmission unit is used to transmit the information perceived by the information sensing unit to the intelligent decision-making unit; The intelligent decision-making unit includes an intelligent decision-making engine, which is used to train a big data model based on a historical case database. The trained big data model is used to predict the grouting effect of the initial combination. Then, based on the prediction results, the decision results of the grouting material formula and process parameters are obtained through multi-objective optimization. The initial combination is the grouting material formula and grouting process parameters that match the deep fractures and shallow fractures. The initial combination is obtained based on the fracture geological model and temperature distribution model. The fracture geological model and temperature distribution model are constructed by processing the information perceived by the information sensing unit. And an automatic execution unit, used to perform grout preparation and grouting operations based on the decision results of grouting material formulation and process parameters.

2. The intelligent construction system for grouting reinforcement of cold-region tunnels based on crack detection as described in claim 1, characterized in that, The system also includes an evaluation feedback unit, which analyzes crack information, temperature information, and original detection information to obtain grouting effect evaluation results and feeds them back to the intelligent decision-making unit for the intelligent decision-making unit to verify the decision results, improve the case library, and optimize the scheme.

3. The intelligent construction system for grouting reinforcement of cold-region tunnels based on crack detection as described in claim 1, characterized in that, The control center unit, intelligent decision-making unit, and feedback evaluation unit are mounted on a fixed working platform, while the information sensing unit and automatic execution unit are mounted on a mobile working platform. The signal exchange between the fixed working platform and the mobile working platform is realized by the data transmission unit.

4. The intelligent construction system for grouting reinforcement of cold-region tunnels based on crack detection as described in claim 1, characterized in that, The information sensing unit includes a crack detection subsystem, a temperature detection subsystem, and an effect detection subsystem. The crack detection subsystem includes a high-definition endoscope for shallow crack detection and a ground-penetrating radar for deep crack detection. The temperature detection subsystem includes a low-temperature temperature sensor for detecting ambient temperature. The effect detection subsystem includes an infrared thermal imager for detecting slurry temperature, an ultrasonic viscometer for detecting slurry viscosity, a laser rangefinder for detecting clearance convergence, and a comprehensive detection instrument for detecting leakage.

5. The intelligent construction system for grouting reinforcement of cold-region tunnels based on crack detection as described in claim 1, characterized in that, The intelligent decision-making unit also includes a model generator, a historical case library, and an output interface. The model generator is used to perform noise reduction filtering, feature extraction, and fusion processing on the raw detection information to construct a fracture geological model and a temperature distribution model. The historical case library includes a grouting material formula library, a grouting process parameter library, and a field detection database associated with fracture characteristics and temperature conditions. The output interface is used to form an instruction set from the decision results of the grouting material formula and process parameters given by the intelligent decision engine and send it to the control center unit.

6. The intelligent construction system for grouting reinforcement of cold-region tunnels based on crack detection as described in claim 5, characterized in that, The automatic execution unit includes an intelligent grout preparation subsystem and an intelligent grouting subsystem. The intelligent grout preparation subsystem is used to perform grout preparation operations according to a set of instructions regarding the grouting material formula; the intelligent grouting subsystem is used to perform grouting operations according to a set of instructions regarding grouting process parameters.

7. The intelligent construction system for grouting reinforcement of cold-region tunnels based on crack detection as described in claim 5, characterized in that, The grouting material formula library stores the mix proportions and performance parameters of grouting materials under different crack characteristics and temperature conditions; the grouting process parameter library stores the grouting process parameters under different crack characteristics and temperature conditions; and the field testing database stores the grouting effect evaluation results of successful grouting reinforcement cases of cold-region tunnels under different working conditions.

8. The intelligent construction system for grouting reinforcement of cold-region tunnels based on crack detection as described in claim 6, characterized in that, The intelligent grout preparation subsystem is specifically used to receive the instruction set from the intelligent decision-making unit regarding the grouting material formula, automatically weigh, mix, and stir according to the ratio to prepare a grout that meets the preset requirements, and obtain the grout temperature and viscosity in real time through an infrared thermal imager and an ultrasonic viscometer, respectively. The intelligent grouting subsystem is specifically used to receive the instruction set from the intelligent decision-making unit regarding the grouting process parameters, first controlling the multi-functional grouting gun on the mechanical clamping arm to drill grouting holes at designated positions and complete the hole cleaning work, then precisely inserting the multi-functional grouting gun into the grouting hole, and controlling the grouting pump to perform grouting at the specified grouting pressure and grouting flow rate.

9. A smart construction method for grouting reinforcement of tunnels in cold regions based on crack detection, characterized in that, include: The control center unit was used to monitor and coordinate the grouting reinforcement construction of tunnels in cold regions. The information sensing unit is used to sense crack information, temperature information, and detect raw information. The information sensed by the information sensing unit is transmitted to the intelligent decision-making unit using the data transmission unit. The intelligent decision-making engine of the intelligent decision-making unit is used to train a big data model based on a historical case database. The trained big data model is used to predict the grouting effect of the initial combination. Then, based on the prediction results, the decision results of grouting material formula and process parameters are obtained through multi-objective optimization. The initial combination is the grouting material formula and grouting process parameters that match deep fractures and shallow fractures. The initial combination is obtained based on the fracture geological model and temperature distribution model. The fracture geological model and temperature distribution model are constructed by processing the information perceived by the information sensing unit. The automatic execution unit performs grout preparation and grouting operations based on the decision results of the grouting material formula and process parameters.

10. The intelligence compilation method based on multi-stage thinking chain and retrieval enhancement as described in claim 9, characterized in that, The method further includes: The evaluation feedback unit analyzes crack information, temperature information, and original detection information to obtain grouting effect evaluation results, which are then fed back to the intelligent decision-making unit for verification of decision results, improvement of case library, and optimization of scheme.

Images