A method and system for automatically monitoring road surface settlement based on shield tunneling under an airport runway

Abstract

The present application provides a method and system for automatically monitoring the pavement settlement based on a shield machine passing under an airport runway. Specifically, a dynamic database is constructed by real-time collection of operating parameters such as the thrust pressure, cutter head torque, and synchronous grouting pressure of the shield machine, combined with three-dimensional deformation data obtained by laser scanning. Strain sensing units are arranged in the soil layer to form a layered monitoring network, and the strain changes of soil layers at different depths are collected, and spatial correlation is established with the excavation position. The spatial attenuation law is analyzed by a dynamic correlation processing unit to generate a multidimensional feature data set. A settlement prediction model is established, and the dynamic load sequence of the shield machine and the layered strain conduction characteristics are integrated to output settlement distribution information. The system automatically compares the settlement difference values ​​of adjacent areas with the preset safety threshold, and generates a graded warning signal after spatial verification of the three-dimensional deformation data. The technical solution provided by the present application realizes real-time three-dimensional prediction and spatially verified graded warning of airport runway settlement.

Description

Technical Field

[0001] The present application relates to the technical field of underground engineering and tunnel construction, and in particular to a method and system for automatically monitoring road surface settlement based on a shield tunnel passing under an airport runway. Background Art

[0002] In the engineering scenario of an urban subway shield tunnel passing under an airport runway, the pavement settlement monitoring system needs to have a three-dimensional continuous monitoring capability with sub-millimeter accuracy, while also realizing dynamic correlation analysis of shallow fill settlement, deep foundation disturbance, and shield tunneling parameters. The system needs to analyze in real time the impact of propulsion pressure fluctuations on the elastic modulus of the soil layer, the matching relationship between the grouting pressure diffusion path and the soil consolidation rate, and establish a spatial mapping model of the tunneling trajectory and the three-dimensional deformation field of the pavement. However, this field faces the settlement conduction hysteresis effect under the coupling of multiple physical fields. The anisotropy of the soil makes it difficult to quantify the strain attenuation law, and traditional monitoring methods cannot synchronously integrate shield mechanical parameters and stratum dynamic response data, resulting in the settlement prediction model having blind spots for advanced warning and the risk of multi-source error accumulation.

[0003] Currently, distributed fiber optic sensing-based monitoring technology is being used in engineering practice. An array of sensing cables is laid longitudinally along the runway. This technology uses the principle of Brillouin optical time-domain reflectometry to obtain real-time, continuous strain distribution from the surface to the deep soil. The system uses a multi-channel demodulator to synchronously process the strain signals from the kilometer-long sensing cables, generating a two-dimensional strain contour map of the soil beneath the runway. This map then generates a pavement deformation trend analysis report based on a pre-defined strain-to-settlement conversion algorithm. Summary of the Invention

[0004] The present application provides a method and system for automatically monitoring pavement settlement based on a shield tunnel passing under an airport runway, in order to solve the problems of early warning hysteresis and multi-source error transmission in the prior art.

[0005] In a first aspect, the present application provides a method for automatically monitoring road surface settlement based on a shield tunnel passing under an airport runway, comprising:

[0006] Collecting thrust pressure data, cutterhead torque data, and synchronous grouting pressure data to form an operating parameter set. Simultaneously, a laser scanning device is used to acquire three-dimensional deformation data. The operating parameter set and the three-dimensional deformation data are combined to form a database based on timestamps and spatial coordinates of the shield machine's excavation trajectory.

[0007] Deploy multiple groups of strain sensing units to form a layered monitoring network, continuously collect strain change data of soil layers at different depths through the strain sensing units, and establish spatial position correlation between the strain change data and the real-time excavation position of the shield machine;

[0008] Inputting the operating parameter group in the database and the strain change data associated with spatial positions into a dynamic association processing unit, the dynamic association processing unit synchronously analyzes the dynamic change characteristics of the operating parameter group and the spatial attenuation characteristics of the strain change data at the corresponding positions, and generates a feature data set;

[0009] A road surface settlement prediction model is established based on the characteristic data set, and the road surface settlement prediction model is used to integrate the dynamic load sequence during the shield tunneling process and the strain transmission characteristics collected by the hierarchical monitoring network to output settlement distribution information in different areas of the road surface and the shield axis;

[0010] According to the preset safety assessment rules, the difference values ​​of adjacent areas in the settlement distribution information are compared to generate a graded warning instruction, and the graded warning instruction is spatially verified with the three-dimensional deformation data updated in real time to output a road settlement warning signal.

[0011] Optionally, the operation parameter group in the database, the layered strain data with spatial position tags, and the spatial coordinate correspondence based on the timestamp and the shield machine tunneling trajectory are input into a dynamic association processing unit;

[0012] By means of the dynamic correlation processing unit, time series data of the propulsion pressure, cutterhead torque and synchronous grouting pressure in the operation parameter group are extracted section by section according to the propulsion direction of the shield machine, and a characteristic curve reflecting the intensity of the dynamic load change of the shield machine is generated based on the time series data;

[0013] For the strain change data associated with spatial positions, extract the strain attenuation rate as the shield machine excavation distance increases according to the soil layer depth, and combine the strain attenuation rate with the vertical distance to generate a distribution curve reflecting the spatial attenuation gradient of the soil layer strain;

[0014] The characteristic curve and the distribution curve are superimposed in time and space, and a multidimensional feature data set including the dynamic characteristics of shield operation and the attenuation characteristics of soil layer response is generated by allocating the weight of the influence of dynamic load on soil layer depth layer by layer.

[0015] Optionally, based on the dynamic load variation intensity characteristic curve and the soil strain spatial attenuation gradient distribution curve in the characteristic data set, a pavement settlement prediction model is constructed with the dynamic load action time sequence as the driving source and the soil strain conduction path as the constraint condition;

[0016] The dynamic load sequence is divided into segmented load units according to the shield machine's excavation direction, and the attenuation gradient distribution parameters in the layered strain conduction characteristics are converted into strain transfer coefficients at each soil layer depth.

[0017] By using the pavement settlement prediction model, the segmented load unit and the strain transfer coefficient are integrated to simulate the layered transmission process of the dynamic load along the depth direction of the soil layer;

[0018] Based on the strain accumulation of soil layers at different depths during the layered conduction process, the settlement distribution information of the surface area on both sides of the shield axis within the horizontal projection range is output.

[0019] Optionally, extracting settlement difference values ​​of adjacent areas in the settlement distribution information, comparing the settlement difference values ​​with multi-level thresholds in preset safety assessment rules step by step, and generating a graded warning instruction;

[0020] The coordinates of the region corresponding to the graded warning instruction are spatially matched with the three-dimensional deformation data updated in real time, and the deviation between the actual deformation amount of the three-dimensional deformation data in the corresponding region and the predicted settlement amount in the warning instruction is calculated;

[0021] If the deviation value is greater than a preset tolerance threshold, the spatial mapping relationship between the layered strain data set and the real-time position of the shield machine in the dynamic association processing unit is adjusted based on the actual deformation amount of the three-dimensional deformation data, and the warning instruction generation process is re-executed after updating;

[0022] If the deviation value is less than a preset tolerance threshold, a road subsidence warning signal is generated according to the warning level and regional coordinates in the graded warning instruction.

[0023] Optionally, during the shield machine's advancement process, the advancement pressure data, the cutterhead torque data, and the synchronous grouting pressure data are collected in real time, and the three are combined into an operation parameter group at preset time intervals;

[0024] At each preset distance interval on the shield machine's excavation trajectory, a laser scanning device is used to perform a three-dimensional deformation scan of the ground surface to obtain three-dimensional deformation data;

[0025] Binding the timestamp of the operation parameter group to the spatial coordinates of the shield machine's excavation trajectory, and binding the timestamp of the three-dimensional deformation data to the spatial coordinates of the position of the laser scanning device, thereby forming a corresponding relationship between the timestamp and the spatial coordinates;

[0026] According to the corresponding relationship, the operating parameter group of the shield machine excavation trajectory in the same time period is integrated with the three-dimensional deformation data of the corresponding spatial coordinates to form a time-space associated database.

[0027] Optionally, in symmetrical areas on both sides of the shield tunnel axis below the runway pavement, vertical holes are drilled at preset intervals to form a monitoring hole group, and multiple strain sensing units are installed in each monitoring hole at intervals along the depth direction;

[0028] When the shield machine is excavating, the strain sensor unit in each monitoring hole synchronously collects the strain change data of the soil layer at the corresponding depth, and adds the monitoring hole number, installation depth mark and collection time stamp to each data;

[0029] According to the dynamic three-dimensional coordinates of the real-time excavation position of the shield machine, the horizontal projection distance between the shield machine and each monitoring hole is calculated, and based on the horizontal projection distance, a hierarchical spatial mapping relationship is established with the cutterhead center as the reference;

[0030] Based on the hierarchical spatial mapping relationship, the strain change data collected from each monitoring hole is divided into regions according to the advancement direction of the shield machine cutterhead, and the data of each region is dynamically bound to the three-dimensional coordinates of the real-time position of the shield machine cutterhead to establish a spatial position association.

[0031] Optionally, the time series data in the characteristic curve is mapped to a corresponding spatial coordinate region according to the time window order of the shield machine excavation direction, and the attenuation rate data in the distribution curve is mapped to a corresponding spatial coordinate region according to the vertical distance between the soil layer depth and the shield machine cutterhead;

[0032] Based on the dual matching relationship between time and space coordinates, the values ​​of the two types of curves in the same spatial coordinate area are superimposed to form a spatiotemporal correlation superposition data set;

[0033] For each spatial coordinate point in the superimposed data set, a weight distribution coefficient of the dynamic load on the soil layer is calculated layer by layer according to the vertical distance between the shield machine cutterhead position and the soil layer depth;

[0034] Based on the weight distribution coefficient, weighted correction is performed on the superimposed values ​​of the dynamic load intensity and the soil layer strain attenuation rate in the superimposed data set;

[0035] The corrected superposition values ​​are bound to the corresponding spatial coordinates, soil depth, time window and weight distribution coefficient to generate a multidimensional feature dataset containing the dynamic characteristics of shield operation and the attenuation characteristics of soil response.

[0036] In a second aspect, the present application provides an automatic monitoring system for road surface settlement based on a shield tunnel passing under an airport runway, comprising:

[0037] An acquisition module collects thrust pressure data, cutterhead torque data, and synchronous grouting pressure data to form an operating parameter set. It also acquires three-dimensional deformation data through a laser scanning device and constructs a database based on the timestamp and spatial coordinates of the shield machine's tunneling trajectory.

[0038] The correlation module deploys multiple sets of strain sensing units to form a layered monitoring network, continuously collects strain change data of soil layers at different depths through the strain sensing units, and establishes spatial correlation between the strain change data and the real-time excavation position of the shield machine;

[0039] an analysis module, inputting the operation parameter group in the database and the strain change data associated with spatial positions into a dynamic association processing unit, and synchronously analyzing the dynamic change characteristics of the operation parameter group and the spatial attenuation characteristics of the strain change data at the corresponding positions through the dynamic association processing unit, and generating a feature data set;

[0040] A fusion module establishes a pavement settlement prediction model based on the feature data set, and through the pavement settlement prediction model, integrates the dynamic load sequence during the shield advancement process with the strain transmission characteristics collected by the hierarchical monitoring network to output settlement distribution information in different areas of the pavement and the shield axis;

[0041] A generation module generates a graded warning instruction based on a preset safety assessment rule according to the difference value comparison between adjacent areas in the settlement distribution information, and performs spatial position verification on the graded warning instruction and the three-dimensional deformation data updated in real time to output a pavement settlement warning signal.

[0042] In a third aspect, an embodiment of the present application provides a computing device comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a method for automatic monitoring of pavement settlement based on a shield tunnel passing under an airport runway as described in the first aspect above.

[0043] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program. When the computer program is executed by a computer, it implements a method for automatically monitoring pavement settlement based on a shield tunnel passing under an airport runway as described in the first aspect.

[0044] In the embodiment of the present application, propulsion pressure data, cutter head torque data and synchronous grouting pressure data are collected to form an operation parameter group, and three-dimensional deformation data are obtained by a laser scanning device at the same time, and the operation parameter group and the three-dimensional deformation data are constructed into a database according to the time stamp and the spatial coordinates of the shield machine's excavation trajectory; multiple groups of strain sensing units are arranged to form a layered monitoring network, and the strain change data of soil layers at different depths are continuously collected by the strain sensing units, and the strain change data are spatially associated with the real-time excavation position of the shield machine; the operation parameter group in the database and the strain change data with spatial position association are input into a dynamic association processing unit, and the dynamic closing A processing unit is connected to synchronously analyze the dynamic change characteristics of the operation parameter group and the spatial attenuation characteristics of the strain change data at the corresponding position, and generate a feature data set; a pavement settlement prediction model is established based on the feature data set, and through the pavement settlement prediction model, the dynamic load sequence during the shield advancement process and the strain conduction characteristics collected by the hierarchical monitoring network are integrated to output the settlement distribution information of different areas of the pavement and the shield axis; according to the difference values ​​of adjacent areas in the settlement distribution information, a preset safety assessment rule is compared to generate a graded warning instruction, and the graded warning instruction is spatially verified with the real-time updated three-dimensional deformation data to output a pavement settlement warning signal.

[0045] This application has the following beneficial effects:

[0046] Through the synergistic effect of multi-source data fusion and a hierarchical monitoring network, full-dimensional dynamic perception and accurate prediction of pavement settlement during the shield tunneling process under the airport runway were achieved. By adopting spatiotemporal correlation modeling of operating parameter groups and three-dimensional deformation data, combined with spatial attenuation characteristic analysis of strain change data of soil layers at different depths, a prediction model coupling dynamic load sequences with soil response transmission mechanisms was constructed, effectively improving the ability to quantitatively assess the disturbance effects of shield tunneling on pavement structures under complex geological conditions. Through a hierarchical early warning mechanism and spatial position verification of three-dimensional deformation data, a closed-loop control system was formed from dynamic analysis of construction parameters to real-time feedback on settlement risks. While reducing the lag of manual monitoring, it enhanced the spatial directionality and time sensitivity of settlement warning signals, providing multi-dimensional automated protection for airport runway structural safety.

[0047] Furthermore, a coupled analysis mechanism combining spatiotemporal superposition with dynamic weight distribution enabled refined correlation modeling of shield tunneling parameters and soil response characteristics. A multidimensional fusion method of time series characteristic curves and spatial attenuation distribution curves overcomes the limitations of traditional monitoring methods that separate construction parameters from geological responses, enabling precise quantification of the energy transfer characteristics of shield dynamic loads at different soil depths. Through segmented analysis of the thrust direction and collaborative mapping of vertical layered strain attenuation gradients, a time-varying correlation model between tunneling mechanical forces and soil deformation transmission paths was established, significantly enhancing the ability to assess the layered dynamic response of shield disturbances on pavement settlement. Combined with a weighting mechanism for dynamic load distribution based on soil depth, the differential impact of transient operational characteristics such as shield cutterhead torque mutations and grouting pressure fluctuations on soil layers at different depths was effectively identified. This provides spatially specific characteristic data support for pavement settlement gradient prediction under complex construction conditions, enhances the real-time matching between settlement warning signals and dynamic adjustment of shield tunneling parameters, and significantly improves the active control capability for airport runway structural safety protection.

[0048] These and other aspects of the present application will become more readily apparent from the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0050] Figure 1 A flow chart of an automatic monitoring method for road surface settlement based on a shield tunnel passing under an airport runway provided by the present application is shown;

[0051] Figure 2 A scene diagram showing a method for automatically monitoring road surface settlement based on a shield tunnel passing under an airport runway provided by the present application is shown;

[0052] Figure 3 The present invention provides a schematic structural diagram of an automatic monitoring system for road surface settlement based on a shield tunnel passing under an airport runway;

[0053] Figure 4 A schematic structural diagram of a computing device provided by the present application is shown. DETAILED DESCRIPTION

[0054] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0055] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this document or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any order of execution. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to being different types.

[0056] Researchers have discovered that traditional settlement monitoring methods for shield tunneling under airport runways suffer from problems such as fragmented data from multiple sources and disconnected responses from layered soil masses. This makes it difficult to correlate dynamic tunneling parameters with the three-dimensional deformation characteristics of the road surface in real time. In particular, the method lacks the ability to couple dynamic load transmission with strain attenuation in soil layers at different depths. This results in delayed settlement predictions and an inability to accurately locate risk areas. Therefore, an intelligent monitoring method that integrates dynamic construction parameters with layered soil responses is urgently needed.

[0057] To address the above-mentioned issues, the present invention proposes a settlement monitoring method based on dynamic correlation of multi-source data. The core of this method is to establish a full-element spatiotemporal mapping mechanism for shield operation parameters, layered soil strain, and three-dimensional deformation. Specifically, a "surface-deep" three-dimensional monitoring system is constructed through laser scanning and a strain sensing network. A dynamic correlation processing unit is used to synchronously analyze the propulsion pressure sequence, grouting pressure fluctuations, and the spatial attenuation law of strain in soil layers at different depths, thereby constructing a settlement prediction model that integrates dynamic load transmission characteristics. This method achieves real-time coupled analysis of shield tunneling parameters and stratum response, and can accurately output the settlement gradient distribution of different zones within a 30-meter radius around the shield axis, increasing the early warning response speed by more than 60%, effectively solving the problem of traditional methods failing to monitor hidden settlement and deep soil disturbance.

[0058] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0059] Figure 1 The present invention provides a flowchart of a method for automatically monitoring road surface settlement based on a shield tunnel passing through an airport runway. Figure 1 As shown, the method includes:

[0060] 101. Collect propulsion pressure data, cutterhead torque data, and synchronous grouting pressure data to form an operating parameter set. Simultaneously, obtain three-dimensional deformation data using a laser scanning device. Construct a database by combining the operating parameter set and the three-dimensional deformation data according to timestamps and spatial coordinates of the shield machine's tunneling trajectory.

[0061] Optionally, step 101 may specifically include the following steps:

[0062] 1011. During the shield machine's advancement process, real-time data on advancement pressure, cutterhead torque, and synchronous grouting pressure are collected, and the three are combined into an operation parameter group at preset time intervals;

[0063] 1012. At each preset distance interval along the tunneling trajectory of the shield machine, a laser scanning device is used to perform a three-dimensional deformation scan of the ground surface to obtain three-dimensional deformation data;

[0064] 1013. Bind the timestamp of the operation parameter group to the spatial coordinates of the shield machine's tunneling trajectory, and bind the timestamp of the three-dimensional deformation data to the spatial coordinates of the laser scanning device's location, thereby forming corresponding relationships between the timestamps and the spatial coordinates.

[0065] 1014. According to the corresponding relationship, the operating parameter group of the shield machine excavation trajectory in the same time period is integrated with the three-dimensional deformation data of the corresponding spatial coordinates to form a time-space associated database.

[0066] In the above steps, thrust pressure data refers to the longitudinal pressure applied by the cylinders in the shield machine's hydraulic thrust system, reflecting the magnitude of thrust resistance. Cutterhead torque data refers to the torque output by the motor when the shield machine's cutterhead rotates to cut soil, representing the intensity of the cutting load. Synchronous grouting pressure data refers to the real-time pressure data from the grouting pipeline at the rear of the shield machine when slurry is injected into the gap between the segments and the soil, used to evaluate the grouting filling effect. Three-dimensional deformation data refers to the displacement change of the ground surface in the horizontal X-axis, vertical Y-axis, and vertical Z-axis directions, collected by a laser scanning device. Timestamps refer to the system clock ticks accurate to the millisecond during data collection. Spatial coordinates refer to the three-dimensional geographic coordinates of the shield machine's excavation position, determined based on the engineering survey coordinate system. A database refers to a structured storage system that associates operating parameters with ground deformation data in a time-series and spatially distributed manner.

[0067] In the embodiment of the present application, first, real-time collection and merging of shield machine operating parameters are achieved through step 1011. The shield machine hydraulic system's built-in pressure sensor collects propulsion pressure data at a frequency of 10 times per second, the cutterhead drive motor collects torque data at a frequency of 5 times per second through a torque sensor, and the synchronous grouting pipeline pressure sensor collects grouting pressure data at a frequency of 2 times per second. Secondly, the data acquisition module uses a time sliding window algorithm to align the three types of raw data at time intervals of one minute, eliminate outliers, and merge them into an operating parameter group containing a unified timestamp. Then, the operating parameter group is transmitted to the central data processing unit cache via the Industrial Internet of Things protocol.

[0068] Next, the periodic collection of three-dimensional surface deformation data is completed through step 1012. When the shield machine's tunneling reaches a preset interval of 5 meters, the PLC control system automatically triggers the laser scanning device to start. Next, the laser scanner uses line scanning mode to collect three-dimensional point clouds in a 50-meter by 30-meter area above the tunneling section. A RANSAC-based point cloud denoising technique is used to eliminate environmental interference points. The ICP point cloud registration algorithm is then used to compare the current scan data with the benchmark model to calculate three-dimensional deformation data of surface subsidence and uplift. Finally, the deformation data is stored in a local storage device along with the timestamp of the scan time and the millimeter-level spatial coordinates obtained by the laser scanner's built-in GNSS module.

[0069] Next, step 1013 achieves a precise association between data and spatiotemporal information. First, the shield machine guidance system uses total station positioning technology to output the three-dimensional spatial coordinates of the tunneling trajectory in real time. The data acquisition system binds the operating parameter group generated in step 1011 to the timestamp of its acquisition moment. Second, a spatiotemporal interpolation algorithm is used to map the timestamp of the operating parameter group to the spatial coordinates of the tunneling trajectory corresponding to the shield machine at that point in time, forming a spatiotemporal sequence of operating parameters. Simultaneously, the timestamp of the three-dimensional deformation data acquired in step 1012 is bound to the spatial coordinates of the laser scanner using a geographic coordinate system conversion algorithm to generate a spatiotemporal sequence of deformation data.

[0070] Finally, a spatiotemporal correlation database is constructed through step 1014. First, the data fusion module uses a 15-minute time window to sort the spatiotemporal sequence of operating parameters generated in step 1013 by the spatial coordinates of the tunneling trajectory, forming a parameter dataset distributed along the shield machine axis. Second, the Kriging spatial interpolation algorithm is used to map the three-dimensional deformation data within the same time period to the spatial coordinate grid corresponding to the tunneling trajectory. Then, the spatiotemporal matching model is used to associate the operating parameter dataset with the deformation data grid one by one according to the coordinate points, establishing a quantitative correspondence between the parameters and deformation. Finally, the spatiotemporal extension module of the PostgreSQL database is used to store the associated data in a structured form with the timestamp as the primary key and the spatial coordinates as the auxiliary index, forming an engineering database that supports spatiotemporal joint queries.

[0071] In practical applications, for example, in a subway tunnel construction project, the construction team used a shield machine to simultaneously collect multi-dimensional engineering data during tunneling. The shield machine automatically records the thrust cylinder pressure every five seconds, maintaining a pressure range of 12 to 28 MPa. It also collects cutterhead drive torque data, with typical values ​​ranging from 1800 to 3200 kN·m. Grouting pressure is continuously monitored and stably controlled within a range of 0.3 to 0.5 MPa, generating a real-time operational data set containing three sets of parameters. Laser scanning stations are located every 1.5 meters along the tunneling trajectory, using a 3D laser scanner with an accuracy of 0.5 mm to capture deformation indicators such as surface settlement and segment displacement. The data synchronization system improves the timestamp accuracy of the operating parameters recorded by the shield machine's PLC to the millisecond level and dynamically links them with the 3D coordinates provided by the GNSS positioning system. The shield machine's real-time position is located at 121.48 degrees east longitude, 31.23 degrees north latitude, and an elevation of -28.5 meters. The time tags of the laser scanning data were spatially registered with the scanner base station coordinates (121.48 degrees east longitude, 31.23 degrees north latitude, and an elevation of 2.3 meters). A temporal alignment algorithm was used to establish a spatiotemporal mapping relationship between the shield machine's excavation parameters and the surface deformation data of the corresponding sections. Ultimately, a spatiotemporal database containing over 12,000 sets of parameter records and 3D point cloud data was constructed. This provided data support for the dynamic optimization of shield construction parameters and coupled 3D deformation analysis, effectively enhancing the safety management and control of tunnel construction in complex strata.

[0072] In the overall solution of the above step 101, an operation parameter group is formed by real-time collection of shield machine thrust pressure, cutterhead torque and synchronous grouting pressure data, and a laser scanning device is used to obtain surface three-dimensional deformation data at preset distance intervals. Based on the dual binding mechanism of timestamp and spatial coordinates, the dynamic operation parameters are temporally and spatially correlated with the surface deformation data of the corresponding area, and a multidimensional database with temporal and spatial consistency is constructed. This breaks through the limitations of isolated analysis of construction parameters and surface deformation data in traditional monitoring, and realizes automatic matching of shield tunneling process parameters and geological response data, providing an accurate data basis for the subsequent establishment of a construction parameter optimization model and prediction of surface deformation trends, effectively improving the dynamic perception capability and control accuracy of shield construction risks under complex geological conditions, and reducing the error risk of manual data processing through automated data integration, providing reliable technical support for the safe construction of urban underground projects and environmental protection.

[0073] 102. Deploy multiple groups of strain sensing units to form a layered monitoring network, continuously collect strain change data of soil layers at different depths through the strain sensing units, and establish a spatial correlation between the strain change data and the real-time excavation position of the shield machine;

[0074] Optionally, step 102 may specifically include the following steps:

[0075] 1021. In the symmetrical areas on both sides of the shield tunnel axis below the runway pavement, vertical holes are drilled at preset intervals to form a monitoring hole group, and multiple strain sensing units are installed in each monitoring hole at intervals along the depth direction;

[0076] 1022. When the shield machine is excavating, the strain sensor units in each monitoring hole synchronously collect strain change data of the soil layer at the corresponding depth, and attach the monitoring hole number, installation depth identifier and collection time stamp to each data;

[0077] 1023. Calculate the horizontal projection distance between the shield machine's real-time excavation position and each monitoring hole based on the dynamic three-dimensional coordinates of the shield machine's real-time excavation position, and establish a hierarchical spatial mapping relationship based on the cutterhead center based on the horizontal projection distance;

[0078] 1024. Based on the hierarchical spatial mapping relationship, the strain change data collected from each monitoring hole is divided into regions according to the advancement direction of the shield machine cutter head, and the data of each region is dynamically bound to the three-dimensional coordinates of the real-time position of the shield machine cutter head to establish a spatial position association.

[0079] In the above steps, strain sensing units refer to microsensor devices embedded in the soil layer to measure soil compression or tension deformation. A layered monitoring network refers to a three-dimensional monitoring system formed by multiple sensor groups spaced apart in the vertical depth direction. A monitoring hole group refers to a set of vertical boreholes drilled at preset intervals in symmetrical areas along the shield tunnel axis. Strain change data refers to the quantitative value of soil shape changes over time collected by the sensors. A monitoring hole number refers to an alphanumeric code that uniquely identifies the location of each borehole. The installation depth identifier records the vertical depth coordinate of the sensor's embedded position within the borehole. The horizontal projection distance refers to the straight-line distance on the ground plane between the center of the shield machine's cutterhead and the center of the monitoring hole. The layered spatial mapping relationship refers to a spatial correspondence model of soil strain data established based on the real-time position of the shield machine and the distance between the monitoring holes. The cutterhead center refers to the three-dimensional coordinate center point of the shield machine's cutterhead rotation axis. Spatial position association refers to a data relationship that dynamically binds the strain data collected by each monitoring hole to the shield machine's excavation position.

[0080] In the embodiment of the present application, the monitoring hole layout and sensor installation are first completed through step 1021. In the area offset 10 meters outward on both sides of the shield tunnel axis, the monitoring hole positioning coordinates are determined at intervals of every 15 meters. Secondly, a rotary drilling rig is used to drill monitoring holes with a depth of 30 meters vertically downward at the positioning point to form two rows of symmetrically distributed monitoring hole groups. Then, a strain sensing unit is installed every 3 meters from the surface downward in each monitoring hole, and a hydraulic expansion device is used to tightly fit the sensor to the hole wall. Finally, a unique number is assigned to each monitoring hole and the installation depth mark corresponding to each sensor is recorded.

[0081] Next, strain data is collected and labeled in step 1022. When the shield machine begins advancing, the strain sensing units in each monitoring hole synchronously collect soil strain data at a sampling frequency of twice per second. The data acquisition module then converts the analog signal into a digital signal and uses a Kalman filter algorithm to eliminate environmental noise interference. Each strain data entry is then annotated with the monitoring hole number, sensor installation depth, and a millisecond-accurate acquisition timestamp. Finally, the data is transmitted via optical fiber to a data processing center for temporary storage.

[0082] Next, a hierarchical spatial mapping relationship is established through step 1023. First, the shield machine's guidance system acquires the three-dimensional coordinate data of the cutterhead center in real time. Next, the horizontal projection distance between the cutterhead center and the center of each monitoring hole is calculated based on the plane coordinate system. Specifically, the square root function is used to calculate the two-dimensional plane linear distance. Next, concentric circular areas are divided at 10-meter intervals, with the cutterhead center as the origin. Finally, the strain data collected from each monitoring hole is dynamically classified into the corresponding annular spatial layer based on the real-time distance.

[0083] Finally, step 1024 completes the dynamic binding of data and location. First, the front of the shield machine's excavation direction is divided into three influence zones: 0-20 meters, 20-40 meters, and 40-60 meters. Secondly, based on the layered spatial mapping relationship, the monitoring hole data within each annular area is matched to the corresponding influence range. Then, the inverse distance weighted interpolation algorithm is used to spatially fuse the data of multiple monitoring holes in the same area to generate the comprehensive strain change curve of each layer. Finally, the fused data is dynamically associated with the three-dimensional coordinates of the real-time position of the cutterhead through spatiotemporal coding technology to form a soil layer strain database with a spatial position index.

[0084] In practical applications, for example, during a shield tunnel underpass project for an airport runway, the construction team deployed a monitoring network within 20 meters of the tunnel's centerline on both sides. Monitoring holes were drilled vertically at 15-meter intervals to a depth of 35 meters, for a total of 12 monitoring holes on each side. Within each monitoring hole, a fiber Bragg grating strain sensor was installed every 5 meters along the depth. Seven layers of sensors were deployed per hole, for a total of 168 monitoring nodes across the entire cross-section. As the shield machine advanced, the sensors collected soil strain at various depths 10 times per second. The data was annotated in real time with the monitoring hole number, depth identifiers such as the sensor's buried depth of 18 or 23 meters, and millisecond-level timestamps. The shield machine's guidance system acquired the three-dimensional coordinates of the cutterhead center: 116.40 degrees east longitude, 40.05 degrees north latitude, and an elevation of -19.6 meters. The projected distance from the cutterhead center to monitoring hole C7 was calculated to be 13.2 meters. A spatial coordinate system was established based on the cutterhead's direction of excavation, with the area 0-10 meters from the cutterhead designated as the direct impact zone, 10-20 meters as the transition impact zone, and 20 meters beyond the cutterhead designated as the indirect impact zone. The data synchronization management platform dynamically correlated the 325μ peak strain data collected at a depth of 18 meters in hole C7 to a position 8.5 meters in front of the cutterhead. Combined with a 3D geological model, this platform displayed in real time the disturbance of the silty clay layer beneath the runway subgrade caused by shield tunneling. This provided a basis for dynamic grouting pressure control, effectively ensuring the safe operation of the airport runway.

[0085] In the overall solution of step 102 above, a layered monitoring network is symmetrically arranged on both sides of the shield tunnel axis. Multi-depth strain sensing units in vertical boreholes are used to synchronously collect the dynamic strain responses of different soil layers. Combined with the spatial mapping relationship between the three-dimensional coordinates of the real-time excavation position of the shield machine and the horizontal projection distance of the monitoring holes, a dynamic binding mechanism for layered strain data in the cutterhead advancement direction is established. This overcomes the technical bottleneck of traditional single-point or shallow monitoring, which does not fully capture the internal disturbance response of the soil. It achieves three-dimensional real-time perception of the strain evolution of soil layers at different depths during shield tunneling. The dynamic coupling between shield advancement parameters and the mechanical behavior of deep soil is effectively revealed through spatial position correlation. This provides high-resolution data support for accurately assessing the impact range of construction on the stratum structure and identifying potential settlement risk areas. At the same time, dynamic coordinate binding makes the strain data traceable in spatial dimensions, significantly improving the monitoring and early warning capabilities of shield construction for hidden soil disturbances under complex geological conditions, and providing a scientific basis for dynamic optimization of construction parameters and control of stratum stability.

[0086] 103. Inputting the operation parameter group in the database and the strain change data associated with spatial positions into a dynamic association processing unit, the dynamic association processing unit synchronously analyzes the dynamic change characteristics of the operation parameter group and the spatial attenuation characteristics of the strain change data at the corresponding positions, and generates a feature data set;

[0087] Optionally, step 103 may specifically include the following steps:

[0088] 1031. Input the operation parameter group, the layered strain data with spatial location tags, and the spatial coordinate correspondence between the timestamp and the shield machine excavation trajectory in the database into a dynamic association processing unit;

[0089] 1032. Extracting time series data of the thrust pressure, cutterhead torque, and synchronous grouting pressure in the operation parameter group in each section according to the thrust direction of the shield machine through the dynamic correlation processing unit, and generating a characteristic curve reflecting the intensity of the dynamic load change of the shield machine based on the time series data;

[0090] 1033. For the strain change data associated with spatial positions, extract the strain attenuation rate as the shield machine excavation distance increases according to the soil layer depth, and combine the strain attenuation rate with the vertical distance to generate a distribution curve reflecting the spatial attenuation gradient of the soil layer strain;

[0091] 1034. Superimpose the characteristic curve and the distribution curve in time and space, and generate a multidimensional feature data set including the dynamic characteristics of shield operation and the attenuation characteristics of soil layer response by allocating the weight of the impact of dynamic load on soil layer depth layer by layer.

[0092] Among them, step 1034 may specifically include the following processes: mapping the time series data in the characteristic curve to the corresponding spatial coordinate area according to the time window order of the shield machine excavation direction, and at the same time mapping the attenuation rate data in the distribution curve to the corresponding spatial coordinate area according to the vertical distance between the soil layer depth and the shield machine cutter head; based on the dual matching relationship between time and space coordinates, superimposing the values ​​of the two types of curves in the same spatial coordinate area to form a time-space associated superimposed data set; for each spatial coordinate point in the superimposed data set, according to the vertical distance between the shield machine cutter head position and the soil layer depth, calculating the weight distribution coefficient of the dynamic load on the soil layer layer layer by layer; based on the weight distribution coefficient, performing weighted correction on the superimposed values ​​of the dynamic load intensity and the soil layer strain attenuation rate in the superimposed data set; binding the corrected superimposed values ​​with the corresponding spatial coordinates, soil layer depth, time window and weight distribution coefficient to generate a multidimensional feature data set containing the dynamic characteristics of the shield operation and the soil layer response attenuation characteristics.

[0093] In the above steps, the dynamic correlation processing unit refers to the calculation module used to synchronously analyze the relationship between shield machine operating parameters and soil strain response. The characteristic curve refers to a trend graph that reflects the intensity of changes in the shield machine's thrust pressure, cutterhead torque, and synchronous grouting pressure over time. Time series data refers to continuous sampling data of shield machine operating parameters arranged in chronological order. The strain decay rate refers to the rate at which soil strain decreases as the shield machine's excavation distance increases. The distribution curve refers to a gradient change graph that reflects the relationship between the strain decay rate of soil layers at different depths and vertical distance. Spatiotemporal superposition refers to the process of fusing characteristic data in the time dimension with distribution data in the spatial dimension in a unified coordinate system. The weight distribution coefficient refers to the dynamic load influence proportional coefficient calculated based on the vertical distance between the shield machine's cutterhead position and the soil depth. The multidimensional feature dataset refers to a structured data set that contains the relationship between time, space, soil depth, and dynamic load and strain response.

[0094] In the embodiment of the present application, data input and initialization are first completed through step 1031. The dynamic association processing unit reads the operation parameter group and the layered strain data with spatial location tags through the database interface, and simultaneously loads the spatial coordinate mapping table of the timestamp and the shield machine excavation trajectory. Secondly, the data format is standardized, and the units of thrust pressure, cutterhead torque, and synchronous grouting pressure are uniformly converted to MPa, kN·m, and kPa. Then, a correspondence matrix between the time axis and the spatial coordinate axis is established to complete the initialization of the data processing environment.

[0095] Secondly, the shield machine dynamic load characteristic curve is generated through step 1032. First, the data segment is divided into 5-meter intervals along the shield machine propulsion direction, and the time series of the propulsion pressure, cutterhead torque and synchronous grouting pressure data in each segment are extracted. Secondly, the sliding window Fourier transform algorithm is used to analyze the fluctuation characteristics of the time series, and the root mean square value of each parameter is calculated as the dynamic load strength index. Then, the strength indexes of the three parameters are connected in chronological order to generate a composite characteristic curve containing propulsion pressure fluctuations, torque changes and grouting pressure pulsations. Finally, the characteristic curve is bound to the spatial coordinates of the corresponding segment and stored.

[0096] Then, a spatial attenuation distribution curve of soil layer strain is generated through step 1033. First, the strain data is divided into three soil layer depth layers of 0-10 meters, 10-20 meters, and 20-30 meters according to the installation depth of the sensor in the monitoring hole. Secondly, the strain change data of each layer of data when the shield machine cutter head advances to the horizontal projection distance of 0-50 meters of the monitoring hole is extracted, and the linear regression algorithm is used to calculate the attenuation slope of the strain as the excavation distance increases as the attenuation rate. Then, the attenuation rate of each soil layer and its corresponding vertical depth data are fitted through the cubic spline interpolation algorithm to generate a distribution curve reflecting the strain attenuation gradient change of soil layers at different depths. Finally, the distribution curve is associated with the spatial coordinates of the monitoring hole and the soil layer depth information and stored.

[0097] Finally, a multidimensional feature dataset is constructed in step 1034. First, the characteristic curves generated in step 1032 are mapped sequentially in time windows to the spatial coordinate grid corresponding to the shield machine's excavation trajectory. Second, the distribution curves generated in step 1033 are mapped to the vertical dimension of the same spatial coordinate grid based on the monitoring hole coordinates and soil depth. Spatiotemporal coding techniques are then used to align the two types of curves at the nodes of the three-dimensional spatial grid. The characteristic curve intensity value and the distribution curve attenuation rate value at each node are arithmetic superimposed. A weight distribution coefficient is then calculated based on the vertical distance between the cutterhead center and the soil depth using the formula 1 / (1 + 0.1d) (where d is the vertical distance in meters). The superimposed result is then weighted and corrected. Finally, the corrected values ​​are bound to the spatial coordinates, soil depth, time window, and weight coefficient to form a five-dimensional feature dataset containing dynamic load intensity, soil response attenuation gradient, and spatiotemporal position information.

[0098] In practical applications, for example, in a cross-river tunnel construction project, the engineering team constructed a dynamic correlation model between shield machine operations and ground response. The dynamic correlation processing unit accessed a database of shield machine propulsion parameters, including a 2-second sampled data set of 24.6 MPa propulsion cylinder pressure, 2850 kN·m cutterhead torque, and 0.48 MPa synchronous grouting pressure. It also correlated 182 microstrain data points of soil compressive strain collected from monitoring hole D12 at a depth of 16 meters. The system divided the analysis cells into 10-meter intervals along the shield tunneling direction, extracting time series data from 30 minutes before to 60 minutes after the cutterhead's passage. This generated a dynamic load intensity curve for propulsion pressure fluctuations up to 8.2 MPa. For the riverbed silt-fine sand layer, strain decay was analyzed vertically at 2-meter intervals. The strain rate at a depth of 25 meters, 9 meters from the cutterhead, decreased to 32% of the peak value. The spatiotemporal overlay module matched the shield machine's excavation parameters at milepost K15+763 with the three-dimensional strain data from six monitoring holes within the corresponding projection area, using a 0.5-meter-by-0.5-meter-by-0.2-meter spatial grid for data fusion. Based on the vertical distance between the cutterhead center elevation of -45.2 meters and the 25-meter-deep monitoring point, the system calculated the dynamic load weight coefficient using an exponential decay model. This weighted calculation combined the 0.68 MPa grouting pressure in the clay layer at a depth of 18.7 meters with the strain decay rate of 4.3 με / minute. The resulting data generated 24,800 sets of characteristic data, including spatial coordinates, a 15-minute time window, and seven layers of soil response parameters. This enabled a multidimensional coupled analysis of shield machine excavation parameters and stratum mechanical behavior, providing precise decision-making support for shield construction in complex riverbed strata.

[0099] In the overall solution of step 103 above, the shield operation parameters and layered strain data are subjected to spatiotemporal fusion analysis through the dynamic correlation processing unit, and the dynamic load characteristic curves of the thrust pressure, cutterhead torque and grouting pressure are superimposed and mapped with the spatial attenuation gradient distribution curve of the soil layer strain. The vertical distance between the cutterhead position and the soil layer depth is used to calculate the weight coefficient of the dynamic load on the soil layer, thus realizing the spatiotemporal coupling correlation between the dynamic load intensity of shield construction and the attenuation rate of deep soil response. A multidimensional feature data set including time series, spatial coordinates, soil layer depth and weight distribution is constructed, which breaks through the traditional method. In order to overcome the limitations of isolated analysis of construction parameters and geological response data, the inherent correlation mechanism between the shield load propagation path and the soil disturbance attenuation law is revealed through spatiotemporal superposition correction and layered weight distribution, providing a dynamic feedback basis for quantifiable soil response for construction parameter optimization. At the same time, the multi-dimensional data fusion in the spatiotemporal coordinate domain significantly improves the prediction accuracy of the disturbance effect of shield tunneling on complex strata, providing decision support data with both time evolution characteristics and spatial distribution laws for dynamic adjustment of tunneling parameters, control of stratum deformation and prevention of construction risks, forming a full-chain closed-loop analysis capability from construction dynamics to geological response.

[0100] 104. Establish a road surface settlement prediction model based on the characteristic data set, and output settlement distribution information of different areas of the road surface and the shield axis by integrating the dynamic load sequence during the shield tunneling process and the strain transmission characteristics collected by the layered monitoring network through the road surface settlement prediction model;

[0101] Optionally, step 104 may specifically include the following steps:

[0102] 1041. Based on the dynamic load variation intensity characteristic curve and the soil strain spatial attenuation gradient distribution curve in the characteristic data set, a road surface settlement prediction model is constructed with the dynamic load action time sequence as the driving source and the soil strain conduction path as the constraint condition;

[0103] 1042. Divide the dynamic load sequence into load units according to the shield machine's excavation direction, and convert the attenuation gradient distribution parameters in the layered strain transmission characteristics into strain transfer coefficients at each soil layer depth;

[0104] 1043. By using the pavement settlement prediction model, the segmented load unit and the strain transfer coefficient are integrated to simulate the layered transmission process of the dynamic load along the depth direction of the soil layer;

[0105] 1044. Based on the strain accumulation of soil layers at different depths during the layered conduction process, the settlement distribution information of the surface area on both sides of the shield axis within the horizontal projection range is output.

[0106] In the above steps, the road surface settlement prediction model refers to a mathematical model for calculating surface settlement based on the relationship between dynamic loads and soil strain transmission. The dynamic load sequence refers to the load action sequence formed by the combination of propulsion pressure, cutterhead torque, and grouting pressure that changes over time during the shield machine's propulsion process. The layered monitoring network refers to a three-dimensional data acquisition system formed by multiple groups of strain sensors arranged along the vertical depth direction. The strain transmission characteristic refers to the attenuation pattern of soil strain with depth during the process of transmission from the shield operation area to the surface. The layered transmission process refers to the physical process in which dynamic loads are transmitted layer by layer through soil layers at different depths, resulting in strain accumulation. The strain accumulation refers to the sum of the irrecoverable deformations produced in a specific soil layer under the repeated action of dynamic loads. The settlement distribution information refers to the spatial distribution data of settlement in the surface area on both sides of the shield tunnel axis within the horizontal projection range.

[0107] In the embodiment of the present application, a pavement settlement prediction model is first constructed through step 1041. Based on the dynamic load change intensity characteristic curve in the characteristic data set, the time series analysis method is used to extract the fluctuation period and amplitude characteristics of the propulsion pressure, cutterhead torque and grouting pressure. Secondly, the spatial attenuation gradient distribution curve of the soil layer strain is processed by finite element discretization to establish the strain transfer path constraint matrix of soil layers at different depths. Then, the dynamic load time series is used as the input driving source, the soil layer strain transfer path matrix is ​​used as the boundary condition, and the viscoelastic constitutive equation is used to construct the core algorithm framework of the pavement settlement prediction model.

[0108] Next, load and strain parameter conversion is achieved through step 1042. First, a load unit is divided into two-meter advances for the shield machine. A sliding window segmentation algorithm is used to segment the dynamic load sequence into continuous time-space load units. Next, the attenuation gradient distribution parameters in the layered strain conduction characteristics are converted into strain transfer coefficients for each soil layer depth using an exponential function fitting algorithm. The coefficients for the 0-10 meter soil layer are 0.8, 0.6 for 10-20 meters, and 0.4 for 20-30 meters. Each load unit is then assigned a corresponding spatial coordinate identifier and soil layer depth parameter.

[0109] Next, the fusion calculation of load and strain is completed through step 1043. First, the load unit is mapped to the three-dimensional grid nodes of the shield tunneling trajectory according to the spatial coordinates. Secondly, a layered convolution algorithm is used to perform matrix multiplication on the load unit value and the strain transfer coefficient corresponding to the soil layer depth to calculate the layered transmission amount of dynamic load in the 0-30 meter soil layer. Then, through the time domain superposition method, the instantaneous transmission amount generated by each load unit in the soil layer is accumulated to simulate the strain transmission accumulation process of each soil layer during continuous tunneling.

[0110] Finally, the settlement distribution information is output through step 1044. First, the strain accumulation of the 0-10 m, 10-20 m, and 20-30 m soil layers during the layered conduction process is integrated and calculated to obtain the total deformation of each depth layer. Secondly, the Boussinesq stress distribution theory is used to superimpose the total deformation of each soil layer on the corresponding surface area according to the vertical projection relationship. Then, the Kriging spatial interpolation algorithm is used to generate the contour distribution map of the surface settlement within 50 meters on both sides of the shield axis, and the output includes quantitative distribution data with a maximum settlement of 12 mm in the east area and a maximum settlement of 9 mm in the west area.

[0111] In practical applications, for example, in a shield tunneling project for a certain city's underground integrated pipeline corridor, the construction team developed an intelligent road surface settlement prediction system. Based on shield machine cutterhead torque fluctuation data stored in a spatiotemporal database, with typical torque values ​​ranging from 2200 to 3400 kN·m, the system dynamically adjusted the grouting pressure within a range of 0.35 to 0.52 MPa. Combined with the maximum compressive strain of 265 microstrains in the silty clay layer collected at monitoring hole E5 at a depth of 18 meters, a road surface settlement prediction model was developed. The model divides the shield tunneling axis into dynamic load analysis units of 6 meters in length, extracting time-series features within each unit, such as a peak thrust pressure of 28.6 MPa and a valley grouting pressure of 0.32 MPa. Based on data from 84 strain sensors installed in 12 monitoring holes, the system calculated a strain transfer coefficient of 0.45 for the shallow fill 8 meters from the shield axis, decreasing to 0.18 for the deeper sand layers. A three-dimensional finite element model coupled the dynamic load cell within 15 meters in front of the cutterhead with the transfer coefficients of various soil layers. Simulating a grouting pressure of 0.4 MPa, the silt layer at a depth of 18 meters generated a cumulative strain of 172 microstrains. After attenuation through a 4.5-meter-thick layer of sand and gravel, the surface strain was reduced to 39 microstrains. The prediction model output a maximum surface settlement prediction of 9.8 mm within 12 meters to the left of the shield axis. Settlement in the area 10 meters to the right was limited to 5.2 mm due to the thick clay layer. This created a settlement distribution cloud map centered on the axis, asymmetrical east and west. This provided a quantitative basis for the grouting compensation plan, ensuring that road surface deformation remained within the design threshold during passage through the city's main arterial road.

[0112] In the overall solution of step 104 above, a road surface settlement prediction model is constructed by integrating the dynamic load sequence and the layered strain transmission characteristics. The dynamic load units divided into sections during the shield advancement process and the soil strain transmission coefficient are simulated in layers. The dual mechanism of dynamic load action time sequence driving and soil strain attenuation gradient constraint is used to achieve a quantitative analysis of the dynamic transmission process of the shield tunneling load in the soil with depth. Through the dynamic load layered transmission simulation and soil strain accumulation calculation, the settlement spatial distribution information of the surface area around the shield axis is accurately output, breaking through the traditional settlement prediction model that relies on The limitations of static load assumptions or single soil layer response data, combined with the spatiotemporal correlation between dynamic construction parameters and multi-depth soil disturbance responses, significantly improve the spatial resolution and time series matching accuracy of pavement settlement prediction under complex stratum conditions. At the same time, through the constrained optimization of layered strain transmission paths, the differential settlement laws of the impact of shield tunneling on shallow and deep soil layers are effectively identified, providing a real-time and multi-dimensional decision-making basis for dynamically adjusting excavation parameters, optimizing grouting compensation strategies, and preventing runway pavement settlement risks, forming a full-link prediction capability from construction dynamic loading to stratum response transmission to surface settlement output.

[0113] 105. Generate a graded warning instruction based on the preset safety assessment rules according to the difference values ​​of adjacent areas in the settlement distribution information, perform spatial position verification on the graded warning instruction and the three-dimensional deformation data updated in real time, and output a road settlement warning signal.

[0114] Optionally, step 105 may specifically include the following steps:

[0115] 1051. Extract settlement difference values ​​of adjacent areas in the settlement distribution information, compare the settlement difference values ​​with the multi-level thresholds in the preset safety assessment rules step by step, and generate a graded warning instruction;

[0116] 1052. Perform spatial position matching on the coordinates of the region corresponding to the graded warning instruction and the three-dimensional deformation data updated in real time, and calculate the deviation between the actual deformation amount of the three-dimensional deformation data in the corresponding region and the predicted settlement amount in the warning instruction;

[0117] 1053. If the deviation value is greater than a preset tolerance threshold, adjusting the spatial mapping relationship between the layered strain data set and the real-time position of the shield machine in the dynamic association processing unit based on the actual deformation amount of the three-dimensional deformation data, and re-executing the warning instruction generation process after updating;

[0118] 1054. If the deviation value is less than a preset tolerance threshold, a road surface subsidence warning signal is generated according to the warning level and regional coordinates in the graded warning instruction.

[0119] In the above steps, the settlement difference value refers to the absolute difference in surface settlement between adjacent monitoring areas. The preset safety assessment rule refers to the pre-set judgment standard containing three thresholds of yellow warning, orange warning, and red warning. The graded warning instruction refers to the instruction data containing the warning level and regional coordinates generated based on the difference value comparison results. The three-dimensional deformation data refers to the three-dimensional displacement change data of the surface obtained in real time by the laser scanning device. The tolerance threshold refers to the maximum deviation value allowed between the predicted settlement and the actual deformation. The spatial mapping relationship refers to the dynamic coordinate association model between the layered strain data and the real-time position of the shield machine. The road surface settlement warning signal refers to the final output warning information containing the warning level, position coordinates and recommended measures.

[0120] In the embodiment of the present application, the preliminary generation of the early warning instruction is first completed through step 1051. The settlement amount of adjacent 1 meter × 1 meter grid areas in the settlement distribution information is extracted, and the absolute value difference of the settlement amount between adjacent grids is calculated. Secondly, the difference value is compared with the preset three-level threshold value. A difference value less than 5 mm is marked as normal, 5-10 mm triggers a yellow warning, 10-15 mm triggers an orange warning, and greater than 15 mm triggers a red warning. Then, a hierarchical early warning instruction containing a warning level code is generated according to the spatial coordinates of the exceeding area and stored in the early warning instruction buffer.

[0121] Next, step 1052 implements real-time verification of the warning instructions. The regional coordinates in the graded warning instructions are converted to a 50-meter x 50-meter geofence. Next, the real-time 3D deformation database is accessed to extract the latest laser scanning deformation data within the corresponding geofence, and the average actual settlement within the area is calculated. The deviation calculation formula (predicted settlement - actual deformation) / predicted settlement × 100% is then used to calculate the percentage deviation, with two decimal places of accuracy.

[0122] Then, dynamic model correction is performed through step 1053. When the deviation value exceeds the preset 20% tolerance threshold, the model correction process is triggered. First, the layered strain data set in the dynamic association processing unit is reloaded, and the soil strain conduction path is inverted based on the three-dimensional deformation data. Secondly, the Kalman filter algorithm is used to adjust the spatial mapping relationship parameters between the layered strain data and the real-time position of the shield machine. Then, the corrected spatial mapping relationship is written into the model parameter library, and the prediction calculation process of steps 1041 to 1044 is re-executed to generate updated settlement distribution information.

[0123] Finally, step 1054 outputs the final warning signal. When the deviation value is less than or equal to the 20% tolerance threshold, the warning level code in the graded warning instruction is extracted. Next, the warning level is mapped to a visual identifier: a yellow warning corresponds to the RGB color value 2552550, an orange warning corresponds to 2551650, and a red warning corresponds to 25500. The warning area coordinates are then converted into polygon vertex data in the engineering coordinate system and overlaid onto the 3D real-world model. Finally, a road subsidence warning signal is generated, including the warning level color block, the coordinate bounding box, and the text prompt "Recommended inspection frequency increased to 2 times / hour."

[0124] In practical applications, for example, a safety monitoring system implemented an intelligent early warning mechanism during a shield tunneling project under a highway. The system extracted the difference between the maximum settlement of 8.7 mm in the 15-meter area to the left of the axis and 5.3 mm in the 12-meter area to the right, as output by the road surface settlement prediction model. The system then compared this difference with three preset safety thresholds: 3 mm for the first warning, 5 mm for the second, and 8 mm for the third. When the settlement difference reached 4.8 mm across adjacent 10-meter grids between mileposts K23+415 and K23+430, a second-level warning was triggered, locking the affected area to the coordinates of 118.25 degrees east longitude and 32.07 to 32.08 degrees north latitude. Real-time 3D laser scanning data revealed the actual settlement in this area was 5.1 mm, deviating 0.3 mm from the warning value and falling below the system's 0.5 mm tolerance. The safety management and control platform spatially superimposed the secondary warning instructions with the crack data of six road panel joints obtained by the scanner (crack width 0.8-1.2 mm). After confirming that the spatial matching degree of the warning area coordinates and the three-dimensional deformation data reached 95%, it generated a road surface settlement warning signal containing the geographic fence coordinates, warning level, and deformation characteristics, and simultaneously pushed it to the construction site control center and road administration platform, launching the directional grouting compensation and traffic diversion plan, ensuring the normal passage of the six-lane bidirectional highway.

[0125] In the overall solution of the above step 105, by comparing the difference values ​​of adjacent areas in the road surface settlement distribution information with the multi-level thresholds of the preset safety assessment rules, a hierarchical warning instruction combining the warning level and the regional coordinates is generated, and at the same time, the real-time updated three-dimensional deformation data is introduced to perform spatial position matching verification to calculate the deviation between the predicted value and the actual deformation variable, and a dynamic closed-loop verification mechanism for the warning result is established. When the deviation exceeds the limit, the self-optimization adjustment of the spatial mapping relationship between the layered strain data set and the real-time position of the shield machine is triggered. The dynamic correction of the warning logic is achieved through iterative updating of the model parameters. If the deviation is within the tolerance range, the warning after spatial verification is issued. The signal is combined with three-dimensional deformation data for dual confirmation output, breaking through the static mode limitations of traditional settlement warning that relies on single prediction or offline data verification. Through the real-time feedback and model self-correction capabilities of multi-source data fusion, the spatial positioning accuracy and temporal effectiveness of the warning signal are significantly improved, and the risk of false alarms or missed alarms caused by soil heterogeneity or sudden changes in construction dynamics is effectively reduced. At the same time, the regional correlation of warning levels and deviation-driven closed-loop optimization enhance the adaptability of the warning system to complex working conditions, providing a highly reliable judgment basis for real-time dynamic prevention and control of pavement settlement risks and emergency decision-making during shield construction.

[0126] The following is a complete embodiment of steps 101 to 105:

[0127] like Figure 2 As shown in the figure, during shield tunneling construction on an international airport runway, a system integrated shield operating parameters with ground response monitoring to achieve intelligent settlement control. The shield machine collected thrust pressure (18-26 MPa), cutterhead torque (2400-3100 kN·m), and simultaneous grouting pressure (0.38-0.47 MPa) at a 3-second interval to form a dynamic data set. Combined with 0.2mm precision laser scanners (spaced 10 meters apart) on both sides of the runway, these data were used to acquire three-dimensional deformation data and construct a spatiotemporal database. Eight monitoring holes, each 30 meters deep and spaced 12 meters apart, were located along the tunnel axis. Five layers of fiber optic strain sensors were installed in each hole. These sensors collected real-time strain data from different soil layers and dynamically correlated them with the real-time coordinates of the shield machine. When the cutterhead reached a specified distance, the system automatically matched peak strain data within 9.8 meters of the monitoring point to support ground response analysis.

[0128] The dynamic correlation processing module analyzes the cutterhead torque fluctuation characteristics and soil strain attenuation patterns, constructing a correlation dataset containing 4,200 sets of 3D coordinates, load intensities, and soil parameters through spatiotemporal superposition. The settlement prediction model, combining 6-meter segmented dynamic loads with the soil strain transfer coefficient (0.58 for clay layers and 0.32 for sand layers), simulates and predicts a maximum settlement of 7.8mm in the area 15 meters to the left of the shield axis and 3.9mm to the right, forming an asymmetric settlement map. After real-time 3D scanning data verified the accuracy of the prediction, areas of abnormal settlement triggered graded warnings. When the measured settlement of 4.5mm in a certain section deviated from the predicted value by less than the 0.5mm threshold, the system automatically adjusted the grouting pressure to 0.49MPa, reducing the settlement rate by over 60% within 30 minutes, effectively ensuring runway operational safety. This solution establishes a complete technical system from dynamic monitoring, intelligent analysis to closed-loop control through the fusion of multi-source data of shield parameters, formation response and three-dimensional deformation. It achieves millimeter-level precise control of settlement during the construction of the airport runway underpass, and provides a full-process automated management and control example for similar projects.

[0129] Figure 3 The present application provides a schematic diagram of a structure of an automatic monitoring system for road surface settlement based on a shield tunnel passing through an airport runway. Figure 3 As shown, the system includes:

[0130] The acquisition module 31 collects thrust pressure data, cutterhead torque data, and synchronous grouting pressure data to form an operation parameter set. Simultaneously, it acquires three-dimensional deformation data through a laser scanning device. The operation parameter set and the three-dimensional deformation data are combined to form a database based on timestamps and spatial coordinates of the shield machine's tunneling trajectory.

[0131] Correlation module 32 deploys multiple sets of strain sensing units to form a layered monitoring network, continuously collects strain change data of soil layers at different depths through the strain sensing units, and establishes spatial correlation between the strain change data and the real-time excavation position of the shield machine;

[0132] The analysis module 33 inputs the operation parameter group in the database and the strain change data associated with the spatial position into a dynamic association processing unit. The dynamic association processing unit synchronously analyzes the dynamic change characteristics of the operation parameter group and the spatial attenuation characteristics of the strain change data at the corresponding position, and generates a feature data set.

[0133] A fusion module 34 establishes a road surface settlement prediction model based on the feature data set, and integrates the dynamic load sequence during the shield tunneling process with the strain transmission characteristics collected by the hierarchical monitoring network through the road surface settlement prediction model to output settlement distribution information in different areas of the road surface and the shield axis;

[0134] The generation module 35 generates a graded warning instruction based on the preset safety assessment rules according to the difference values ​​of adjacent areas in the settlement distribution information, and verifies the spatial position of the graded warning instruction with the three-dimensional deformation data updated in real time, and outputs a road surface settlement warning signal.

[0135] Figure 3 The automatic monitoring system for road surface settlement based on shield tunneling under the airport runway can be performed Figure 1 The implementation principle and technical effects of the automatic monitoring method for road surface settlement based on a shield tunnel under an airport runway described in the illustrated embodiment will not be elaborated on here. The specific manner in which each module and unit performs operations in the automatic monitoring system for road surface settlement based on a shield tunnel under an airport runway in the above embodiment has been described in detail in the embodiments of the method and will not be elaborated on here.

[0136] In one possible design, Figure 3 The automatic monitoring system for road surface settlement based on shield tunneling under an airport runway in the embodiment shown can be implemented as a computing device, such as Figure 4 As shown, the computing device may include a storage component 41 and a processing component 42;

[0137] The storage component 41 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 42 .

[0138] The processing component 42 is used for the above Figure 1 The embodiment provides an automatic monitoring method for road surface settlement when a shield tunnel passes under an airport runway.

[0139] The processing component 42 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above method.

[0140] The storage component 41 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile memory device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0141] Of course, a computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0142] The input / output interface provides an interface between the processing component and the peripheral interface module, which can be an output device, an input device, etc.

[0143] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0144] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0145] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The illustrated embodiment is a method for automatically monitoring road surface settlement based on a shield tunnel passing under an airport runway.

[0146] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0147] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0148] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0149] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for automatically monitoring road surface settlement based on a shield tunnel passing through an airport runway, characterized in that: include: Collecting thrust pressure data, cutterhead torque data, and synchronous grouting pressure data to form an operating parameter set. Simultaneously, a laser scanning device is used to acquire three-dimensional deformation data. The operating parameter set and the three-dimensional deformation data are combined to form a database based on timestamps and spatial coordinates of the shield machine's excavation trajectory. Deploy multiple groups of strain sensing units to form a layered monitoring network, continuously collect strain change data of soil layers at different depths through the strain sensing units, and establish spatial position correlation between the strain change data and the real-time excavation position of the shield machine; Inputting the operating parameter group in the database and the strain change data associated with spatial positions into a dynamic association processing unit, the dynamic association processing unit synchronously analyzes the dynamic change characteristics of the operating parameter group and the spatial attenuation characteristics of the strain change data at the corresponding positions, and generates a feature data set; A road surface settlement prediction model is established based on the characteristic data set, and the road surface settlement prediction model is used to integrate the dynamic load sequence during the shield tunneling process and the strain transmission characteristics collected by the hierarchical monitoring network to output settlement distribution information in different areas of the road surface and the shield axis; Generate a graded warning instruction based on the difference values ​​of adjacent areas in the settlement distribution information compared with preset safety assessment rules, and perform spatial position verification on the graded warning instruction and the three-dimensional deformation data updated in real time to output a road settlement warning signal; Inputting the operating parameter group in the database and the strain change data associated with a spatial position into a dynamic association processing unit, the dynamic association processing unit synchronously analyzes the dynamic change characteristics of the operating parameter group and the spatial attenuation characteristics of the strain change data at the corresponding position, and generates a feature data set, including: Inputting the operation parameter group, the layered strain data with spatial position tags, and the spatial coordinate correspondence between the timestamp and the shield machine excavation trajectory in the database into a dynamic association processing unit; By means of the dynamic correlation processing unit, time series data of the propulsion pressure, cutterhead torque and synchronous grouting pressure in the operation parameter group are extracted section by section according to the propulsion direction of the shield machine, and a characteristic curve reflecting the intensity of the dynamic load change of the shield machine is generated based on the time series data; For the strain change data associated with spatial positions, extract the strain attenuation rate as the shield machine excavation distance increases according to the soil layer depth, and combine the strain attenuation rate with the vertical distance to generate a distribution curve reflecting the spatial attenuation gradient of the soil layer strain; The characteristic curve and the distribution curve are superimposed in time and space, and a multidimensional feature data set including the dynamic characteristics of shield operation and the attenuation characteristics of soil layer response is generated by allocating the weight of the influence of dynamic load on soil layer depth layer by layer.

2. The method according to claim 1, characterized in that A road surface settlement prediction model is established based on the characteristic data set. The road surface settlement prediction model integrates the dynamic load sequence during the shield tunneling process and the strain transmission characteristics collected by the hierarchical monitoring network to output settlement distribution information in different areas of the road surface and the shield axis, including: Based on the dynamic load variation intensity characteristic curve and the soil strain spatial attenuation gradient distribution curve in the characteristic data set, a pavement settlement prediction model is constructed with the dynamic load action time sequence as the driving source and the soil strain conduction path as the constraint condition; The dynamic load sequence is divided into segmented load units according to the shield machine's excavation direction, and the attenuation gradient distribution parameters in the layered strain conduction characteristics are converted into strain transfer coefficients at each soil layer depth. By using the pavement settlement prediction model, the segmented load unit and the strain transfer coefficient are integrated to simulate the layered transmission process of the dynamic load along the depth direction of the soil layer; Based on the strain accumulation of soil layers at different depths during the layered conduction process, the settlement distribution information of the surface area on both sides of the shield axis within the horizontal projection range is output.

3. The method according to claim 1, characterized in that The method comprises: generating a graded warning instruction based on a comparison of difference values ​​between adjacent areas in the settlement distribution information with a preset safety assessment rule; performing spatial position verification on the graded warning instruction and the three-dimensional deformation data updated in real time, and outputting a road settlement warning signal, including: Extracting settlement difference values ​​of adjacent areas in the settlement distribution information, comparing the settlement difference values ​​with the multi-level thresholds in the preset safety assessment rules step by step, and generating a graded warning instruction; The coordinates of the region corresponding to the graded warning instruction are spatially matched with the three-dimensional deformation data updated in real time, and the deviation between the actual deformation amount of the three-dimensional deformation data in the corresponding region and the predicted settlement amount in the warning instruction is calculated; If the deviation value is greater than a preset tolerance threshold, the spatial mapping relationship between the layered strain data set and the real-time position of the shield machine in the dynamic association processing unit is adjusted based on the actual deformation amount of the three-dimensional deformation data, and the warning instruction generation process is re-executed after updating; If the deviation value is less than a preset tolerance threshold, a road subsidence warning signal is generated according to the warning level and regional coordinates in the graded warning instruction.

4. The method according to claim 1, wherein The propulsion pressure data, cutterhead torque data, and synchronous grouting pressure data are collected to form an operating parameter set. At the same time, three-dimensional deformation data is acquired through a laser scanning device. The operating parameter set and the three-dimensional deformation data are combined according to the timestamp and the spatial coordinates of the shield machine's excavation trajectory to construct a database, including: During the shield machine's advancement process, the thrust pressure data, cutterhead torque data, and synchronous grouting pressure data are collected in real time, and the three are combined into an operation parameter group at preset time intervals; At each preset distance interval on the shield machine's excavation trajectory, a laser scanning device is used to perform a three-dimensional deformation scan of the ground surface to obtain three-dimensional deformation data; Binding the timestamp of the operation parameter group to the spatial coordinates of the shield machine's excavation trajectory, and binding the timestamp of the three-dimensional deformation data to the spatial coordinates of the position of the laser scanning device, thereby forming a corresponding relationship between the timestamp and the spatial coordinates; According to the corresponding relationship, the operating parameter group of the shield machine excavation trajectory in the same time period is integrated with the three-dimensional deformation data of the corresponding spatial coordinates to form a time-space associated database.

5. The method according to claim 1, characterized in that Multiple groups of strain sensing units are deployed to form a layered monitoring network. The strain sensing units continuously collect strain change data of soil layers at different depths, and spatially associate the strain change data with the real-time excavation position of the shield machine, including: In the symmetrical areas on both sides of the shield tunnel axis below the runway pavement, vertical holes are drilled at preset intervals to form a monitoring hole group, and multiple strain sensing units are installed in each monitoring hole at intervals along the depth direction; When the shield machine is excavating, the strain sensor unit in each monitoring hole synchronously collects the strain change data of the soil layer at the corresponding depth, and adds the monitoring hole number, installation depth mark and collection time stamp to each data; According to the dynamic three-dimensional coordinates of the real-time excavation position of the shield machine, the horizontal projection distance between the shield machine and each monitoring hole is calculated, and based on the horizontal projection distance, a hierarchical spatial mapping relationship is established with the cutterhead center as the reference; Based on the hierarchical spatial mapping relationship, the strain change data collected from each monitoring hole is divided into regions according to the advancement direction of the shield machine cutterhead, and the data of each region is dynamically bound to the three-dimensional coordinates of the real-time position of the shield machine cutterhead to establish a spatial position association.

6. The method according to claim 1, characterized in that The characteristic curve and the distribution curve are superimposed in time and space, and the influence weight of the dynamic load on the soil depth is distributed layer by layer to generate a multidimensional feature data set containing the dynamic characteristics of shield operation and the attenuation characteristics of soil layer response, including: Mapping the time series data in the characteristic curve to the corresponding spatial coordinate area according to the time window order of the shield machine excavation direction, and mapping the attenuation rate data in the distribution curve to the corresponding spatial coordinate area according to the vertical distance between the soil layer depth and the shield machine cutterhead; Based on the dual matching relationship between time and space coordinates, the values ​​of the two types of curves in the same spatial coordinate area are superimposed to form a spatiotemporal correlation superposition data set; For each spatial coordinate point in the superimposed data set, a weight distribution coefficient of the dynamic load on the soil layer is calculated layer by layer according to the vertical distance between the shield machine cutterhead position and the soil layer depth; Based on the weight distribution coefficient, weighted correction is performed on the superimposed values ​​of the dynamic load intensity and the soil layer strain attenuation rate in the superimposed data set; The corrected superposition values ​​are bound to the corresponding spatial coordinates, soil depth, time window and weight distribution coefficient to generate a multidimensional feature dataset containing the dynamic characteristics of shield operation and the attenuation characteristics of soil response.

7. An automatic monitoring system for road surface settlement based on a shield tunnel under an airport runway, used to execute the automatic monitoring method for road surface settlement based on a shield tunnel under an airport runway according to any one of claims 1 to 6, characterized in that: include: An acquisition module collects thrust pressure data, cutterhead torque data, and synchronous grouting pressure data to form an operating parameter set. It also acquires three-dimensional deformation data through a laser scanning device and constructs a database based on the timestamp and spatial coordinates of the shield machine's tunneling trajectory. The correlation module deploys multiple sets of strain sensing units to form a layered monitoring network, continuously collects strain change data of soil layers at different depths through the strain sensing units, and establishes spatial correlation between the strain change data and the real-time excavation position of the shield machine; an analysis module, inputting the operation parameter group in the database and the strain change data associated with spatial positions into a dynamic association processing unit, and synchronously analyzing the dynamic change characteristics of the operation parameter group and the spatial attenuation characteristics of the strain change data at the corresponding positions through the dynamic association processing unit, and generating a feature data set; A fusion module establishes a pavement settlement prediction model based on the feature data set, and through the pavement settlement prediction model, integrates the dynamic load sequence during the shield advancement process with the strain transmission characteristics collected by the hierarchical monitoring network to output settlement distribution information in different areas of the pavement and the shield axis; A generation module generates a graded warning instruction based on a preset safety assessment rule according to the difference value comparison between adjacent areas in the settlement distribution information, and performs spatial position verification on the graded warning instruction and the three-dimensional deformation data updated in real time to output a pavement settlement warning signal.

8. A computing device, characterized in that It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement an automatic monitoring method for pavement settlement based on a shield tunnel passing under an airport runway as described in any one of claims 1 to 6.

9. A computer storage medium, characterized in that A computer program is stored, and when the computer program is executed by a computer, an automatic monitoring method for pavement settlement based on a shield tunnel passing under an airport runway as described in any one of claims 1 to 6 is implemented.

Images