A method and system for analyzing stratum disturbance under coupling effect of shield construction

Abstract

The present application provides a method and system for analyzing stratum disturbance under the coupling effect of shield construction. In particular, the cutting vibration spectrum data is collected in real time by the cutterhead vibration sensor, and a feature fingerprint library containing the vibration energy distribution pattern and the critical grouting interval is constructed in combination with the soil parameters. The vibration spectrum is aligned with the soil bin pressure in time and space to generate a disturbance field distribution map showing the energy gradient distribution curve and the stress diffusion path topology. Through the feature matching network optimized by transfer learning, the energy distribution curve is matched and the stratum interface propagation parameters are corrected, and the stratum type identification results and the disturbance dynamic parameters are output. Based on the mapping relationship between the parameters and the critical grouting interval, the surface displacement data is linked to dynamically control the grouting pressure, generate graded warnings and parameter adjustment instructions, and form a stratum disturbance monitoring and control closed loop. The technical solution provided by the present application realizes the dynamic optimization of grouting pressure and significantly reduces the risk of stratum deformation caused by shield construction.

Description

Technical Field

[0001] The present application relates to the field of intelligent sensing and Internet of Things technology, and in particular to a method and system for analyzing stratum disturbance under the coupling effect of shield construction. Background Art

[0002] In urban underground space development, when shield tunneling through interbedded clay and gravel strata, the dynamic contact between the cutterhead and the soil can cause ground disturbances to spread. Construction sites need to capture the coupling characteristics of cutterhead vibration and soil response in real time, establish a correlation model between stratum type identification and disturbance propagation, and dynamically adjust the synchronous grouting pressure and propulsion speed parameters during construction. However, sudden changes in stratum parameters cause sensor data to lag behind the actual disturbance state. The vibration waves generated by the cutterhead cutting and the soil stress waves form a nonlinear superposition effect. Existing monitoring methods have difficulty quantifying the spatial topological characteristics of the disturbance propagation path, and the energy dissipation mechanism at the interface between sand and clay lacks dynamic modeling capabilities, resulting in a time lag between early warning signals and actual ground damage.

[0003] Currently, the current technical solution uses a prediction method that combines cutterhead vibration spectrum analysis with a BP neural network. An array of accelerometers is placed on the cutterhead surface to collect vibration spectrum data at different rotational speeds. Wavelet packet transform is used to extract time-frequency energy distribution characteristics, and a training dataset containing stratum type labels is constructed. A mapping relationship between vibration energy peak frequency bands and soil parameters is established using the BP neural network. After outputting the stratum identification results, grouting pressure adjustment instructions are triggered based on a preset vibration intensity threshold. Summary of the Invention

[0004] The present application provides a method and system for analyzing stratum disturbance under the coupling effect of shield construction, so as to solve the problem of insufficient adaptive capability in the prior art.

[0005] In a first aspect, the present application provides a method for analyzing stratum disturbance under the coupled effect of shield construction, comprising:

[0006] Vibration sensors placed on the cutterhead of the shield machine collect vibration spectrum data generated when the cutterhead cuts the soil.

[0007] Based on the obtained soil plasticity index of the clay layer and the particle grading parameters of the gravel layer, a stratum characteristic atlas library was constructed. Combined with the soil shear modulus, groundwater permeability coefficient, and synchronous grouting pressure threshold, a vibration characteristic fingerprint was generated. The vibration characteristic fingerprint includes the vibration energy distribution pattern and the corresponding critical grouting pressure range under different stratum combinations;

[0008] The vibration spectrum data of different areas of the cutterhead are aligned in time and space with the monitored values ​​of the soil bin pressure to generate a disturbance field distribution map, which includes the energy gradient distribution curve of the vibration field and the stress diffusion path topology of the soil;

[0009] Inputting the disturbance field distribution map and the vibration characteristic fingerprint into a feature matching network optimized by transfer learning, so as to perform spectral matching between the energy gradient distribution curve and the vibration energy distribution pattern through the feature matching network, and simultaneously correcting the propagation path parameters of the stratum interface transition zone according to the stress diffusion path topology, so as to output the identification result of the current stratum type and extract the disturbance propagation dynamic parameters;

[0010] According to the mapping relationship between the disturbance propagation dynamic parameters and the critical grouting pressure range in the vibration characteristic fingerprint, the synchronous grouting pressure threshold is dynamically adjusted in combination with the surface displacement monitoring data, and a graded early warning signal and grouting parameter adjustment instruction are generated to complete the closed-loop control of the formation disturbance.

[0011] Optionally, based on the cutterhead rotation angle encoding signal and the spatial position information of the vibration monitoring point, a spatiotemporal alignment operation is performed on the vibration spectrum data of each area on the cutterhead surface and the soil bin pressure monitoring value to generate a spatiotemporally synchronized vibration and pressure joint data set;

[0012] Extract the vibration spectrum segment synchronized with the cutterhead rotation phase and the soil bin pressure mutation interval from the vibration-pressure joint data set, and establish a spatiotemporal correlation mapping relationship between vibration energy and pressure change;

[0013] Based on the time-space correlation mapping relationship, the cumulative increment of vibration energy in each area within the cutterhead excavation section during continuous rotation cycles is calculated to generate a vibration energy gradient distribution curve representing the stratum disturbance intensity;

[0014] Based on the spatial superposition relationship between the soil bin pressure fluctuation amplitude and the vibration energy gradient distribution curve, the stress concentration area of ​​the soil layer is identified and the stress diffusion direction is calibrated, and a stress diffusion topological network throughout the soil layer is generated.

[0015] The vibration energy gradient distribution curve is fused with the stress diffusion topological network to form a disturbance field distribution map containing spatiotemporal correlation disturbance characteristics.

[0016] Optionally, based on the mapping relationship between the disturbance propagation dynamic parameter and the critical grouting pressure interval in the vibration characteristic fingerprint, a critical grouting pressure threshold range of the stratum interface transition zone is determined;

[0017] Extracting the synchronous grouting benchmark pressure value corresponding to the current stratum combination from the stratum characteristic atlas library, and combining it with the instantaneous change of the surface settlement rate in the surface displacement monitoring data to generate a grouting pressure dynamic adjustment gradient table including a pressure fluctuation tolerance;

[0018] The dynamic difference between the grouting pipe outlet pressure and the tunnel face support pressure is collected in real time, and the displacement transmission rate of the formation interface in the stress diffusion topology network is simultaneously monitored. When the dynamic difference exceeds the tolerance range of the grouting pressure dynamic adjustment gradient table or the displacement transmission rate exceeds the preset diffusion rate threshold, a multi-level warning signal is triggered according to the degree of excess.

[0019] Based on the multi-level warning signal, the linked pressurization operation of the target grouting hole and its adjacent holes is activated, the surface displacement rebound and stress diffusion direction offset parameters after pressurization are simultaneously collected, and the grouting pressure compensation coefficient is calculated;

[0020] According to the grouting pressure compensation coefficient, the critical grouting pressure threshold range is adjusted, and a grouting parameter adjustment instruction is generated and bound to the corresponding formation combination in the formation characteristic atlas library to form a closed-loop control link based on stress diffusion topology and surface displacement feedback.

[0021] Optionally, based on the obtained plasticity index threshold of the clay layer and the particle grading parameter of the gravel layer, the stratum unit is divided in combination with the spatial coupling relationship between the plasticity index and the particle size distribution, and each stratum unit includes a shear modulus variation interval and a permeability coefficient stratification interval;

[0022] By dynamically matching the real-time torque fluctuation data of the screw conveyor with the shear modulus variation range of the stratum unit, a real-time association rule between the mechanical load response and the soil shear modulus is established, and a compensation correction coefficient for the grouting pressure is generated based on the dynamic difference between the grouting pipe outlet pressure and the tunnel face support pressure;

[0023] Integrate the compensation correction coefficient, permeability coefficient stratification interval and real-time association rules according to stratum units to construct a stratum characteristic atlas library including shear modulus association factors, grouting pressure compensation rules and permeability influencing parameters;

[0024] Based on the plasticity index weight, particle gradation weight and grouting pressure gradient distribution of each unit in the formation characteristic atlas library, a vibration characteristic fingerprint including the vibration energy distribution pattern under different formation combinations and the corresponding critical grouting pressure range is generated.

[0025] Optionally, the vibration energy gradient distribution curve in the disturbance field distribution map and the vibration energy distribution patterns of different stratum combinations in the vibration feature fingerprint are input into a feature matching network optimized by transfer learning, and the frequency band energy proportion and waveform similarity of the energy distribution curve are spectrally matched by the feature matching network to generate a stratum type matching index;

[0026] Extracting propagation path node parameters of the formation interface transition zone in the stress diffusion path topology, and correcting the propagation path node parameters of the transition zone based on the stress conduction direction offset angle and connection strength between the nodes;

[0027] Correlating the modified propagation path node parameters with the formation type matching index, extracting the critical grouting pressure interval corresponding to the current formation combination from the vibration characteristic fingerprint, and generating a dynamic parameter set for disturbance propagation in the formation interface transition zone;

[0028] According to the path offset and energy attenuation rate in the dynamic parameter set, the identification result of the current stratum type is output and the disturbance propagation dynamic parameters are extracted.

[0029] Optionally, based on the spatial distribution consistency of the soil bin pressure fluctuation amplitude and the vibration energy gradient distribution curve within the cutterhead excavation section, the pressure energy superposition coefficient representing the combined effect strength of the pressure amplitude and energy gradient in each region is calculated;

[0030] Screening the areas where the pressure-energy superposition coefficient exceeds a preset threshold, marking them as initial stress concentration areas, and extracting the energy gradient change slopes between adjacent initial stress concentration areas;

[0031] Based on the directionality of the energy gradient change slope, the stress diffusion direction between the initial stress concentration areas is calibrated, and adjacent areas with the same direction are merged into stress conduction links;

[0032] A stress diffusion topological network penetrating the soil layer is generated according to the attenuation rate of the pressure energy superposition coefficient in the stress conduction link and the link extension length.

[0033] Optionally, according to the level of the multi-level warning signal, the linkage boosting device of the target grouting hole and its adjacent holes is activated according to the preset priority, so that the grouting pressure of the target hole and the adjacent holes is synchronously increased to the preset boosting value;

[0034] Simultaneously collect data on the surface displacement rebound and stress diffusion direction offset angle in the supercharging area. The surface displacement rebound is the difference between the surface uplift height after supercharging and the settlement before supercharging. The stress diffusion direction offset angle is the angle deviation between the actual conduction direction and the preset diffusion path.

[0035] Calculating a displacement rebound compensation weight based on the ratio of the absolute value of the surface displacement rebound amount to a preset rebound expected value, and calculating a direction offset correction factor based on the difference ratio between the stress diffusion direction offset angle and the allowable offset angle threshold;

[0036] The displacement rebound compensation weight and the direction offset correction factor are weighted and superimposed to generate a grouting pressure compensation coefficient for quantifying the correction of the formation disturbance suppression effect caused by the linked boosting operation.

[0037] In a second aspect, the present application provides a system for analyzing stratum disturbance under the coupled action of shield construction, comprising:

[0038] The acquisition module collects vibration spectrum data generated when the cutterhead cuts soil through vibration sensors arranged on the surface of the shield machine cutterhead;

[0039] A construction module builds a stratum characteristic atlas based on the obtained soil plasticity index of the clay layer and the particle grading parameters of the gravel layer. Combined with the soil shear modulus, groundwater permeability coefficient, and synchronous grouting pressure threshold, it generates a vibration characteristic fingerprint. The vibration characteristic fingerprint includes the vibration energy distribution pattern and the corresponding critical grouting pressure range under different stratum combinations;

[0040] a generation module that aligns the vibration spectrum data of different areas of the cutterhead with the monitored values ​​of the soil bin pressure in time and space to generate a disturbance field distribution map, wherein the disturbance field distribution map includes an energy gradient distribution curve of the vibration field and a stress diffusion path topology of the soil;

[0041] a correction module, inputting the disturbance field distribution map and the vibration characteristic fingerprint into a feature matching network optimized by transfer learning, so as to perform spectral matching between the energy gradient distribution curve and the vibration energy distribution pattern through the feature matching network, and simultaneously correcting the propagation path parameters of the stratum interface transition zone according to the stress diffusion path topology, so as to output an identification result of the current stratum type and extract the disturbance propagation dynamic parameters;

[0042] The adjustment module dynamically adjusts the synchronous grouting pressure threshold according to the mapping relationship between the disturbance propagation dynamic parameters and the critical grouting pressure range in the vibration characteristic fingerprint, combined with the surface displacement monitoring data, generates a graded early warning signal and grouting parameter adjustment instructions, and completes the closed-loop control of the formation disturbance.

[0043] 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 analyzing stratum disturbance under the coupling action of shield construction as described in the first aspect above.

[0044] 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 analyzing stratum disturbance under the coupling effect of shield construction as described in the first aspect.

[0045] In the embodiment of the present application, vibration sensors arranged on the surface of the cutterhead of a shield machine are used to collect vibration spectrum data generated when the cutterhead cuts the soil; based on the obtained soil plasticity index of the clay layer and the particle grading parameters of the gravel layer, a stratum characteristic atlas library is constructed, and combined with the soil shear modulus, groundwater permeability coefficient and synchronous grouting pressure threshold, a vibration characteristic fingerprint is generated, and the vibration characteristic fingerprint includes the vibration energy distribution pattern under different stratum combinations and the corresponding critical grouting pressure range; the vibration spectrum data of different areas of the cutterhead are aligned with the monitored values ​​of the soil bin pressure in time and space to generate a disturbance field distribution map, and the disturbance field distribution map includes the energy gradient distribution curve of the vibration field and the stress gradient of the soil force diffusion path topology; input the disturbance field distribution map and the vibration characteristic fingerprint into the feature matching network optimized by transfer learning, so as to perform spectral matching between the energy gradient distribution curve and the vibration energy distribution mode through the feature matching network, and at the same time correct the propagation path parameters of the stratum interface transition zone according to the stress diffusion path topology to output the identification result of the current stratum type and extract the disturbance propagation dynamic parameters; according to the mapping relationship between the disturbance propagation dynamic parameters and the critical grouting pressure range in the vibration characteristic fingerprint, the synchronous grouting pressure threshold is dynamically adjusted in combination with the surface displacement monitoring data, and a graded early warning signal and grouting parameter adjustment instruction are generated to complete the closed-loop control of the stratum disturbance.

[0046] This application has the following beneficial effects:

[0047] By collecting cutterhead vibration spectrum data in real time, the accuracy of cutting state perception is improved. By combining multi-source geological parameters to generate vibration feature fingerprints, accurate mapping of stratum combinations and construction parameters is achieved. By using time-space alignment to generate disturbance field distribution maps, the correlation characteristics of energy gradients and stress diffusion paths are quantified. With the help of feature matching networks optimized by transfer learning, the dynamic analysis capability of energy dissipation mechanisms at complex stratum interfaces is enhanced. Finally, the grouting threshold is dynamically adjusted based on surface displacement data to establish a graded early warning and closed-loop control mechanism, effectively solving the problems of insufficient modeling of disturbance propagation in composite strata and delayed early warning in traditional methods.

[0048] Furthermore, by integrating the time-space alignment data of the cutterhead vibration spectrum and the soil bin pressure, the vibration energy gradient distribution and stress diffusion path of the stratum disturbance during excavation can be accurately quantified, and the dynamic calibration of the soil stress concentration area and the real-time tracking of the disturbance propagation direction can be achieved; based on the time-space related disturbance field distribution map, the risk of local stratum mutation within the cutterhead rotation cycle can be dynamically identified, and the disturbance propagation trend can be predicted in combination with the stress diffusion topological network, thereby optimizing the construction parameters such as the cutterhead speed and grouting pressure, actively suppressing the problems of stratum collapse and settlement caused by vibration energy accumulation or stress concentration, and significantly improving the safety of shield construction and the active prevention and control capabilities of stratum disturbance.

[0049] 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

[0050] 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.

[0051] Figure 1 A flow chart of a method for analyzing stratum disturbance under the coupling effect of shield construction provided by the present application is shown;

[0052] Figure 2 A scenario diagram showing a method for analyzing stratum disturbance under the coupling effect of shield construction provided by this application is shown;

[0053] Figure 3 The present invention shows a schematic structural diagram of a system for analyzing ground disturbance under the coupling effect of shield construction provided by the present application;

[0054] Figure 4 A schematic structural diagram of a computing device provided by the present application is shown. DETAILED DESCRIPTION

[0055] 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.

[0056] 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.

[0057] Researchers have found that sudden changes in ground parameters during shield tunneling cause sensor data to lag behind the actual disturbance state. The vibration waves generated by the cutterhead and the stress waves in the soil form a nonlinear superposition effect. Existing monitoring methods have difficulty quantifying the spatial topological characteristics of the disturbance propagation path. The energy dissipation mechanism at the interface between sand and clay lacks dynamic modeling capabilities, resulting in a time lag between early warning signals and actual ground damage. Therefore, a method that integrates multi-source data to dynamically analyze ground disturbances is urgently needed.

[0058] In response to the above problems, the present invention proposes a method for analyzing stratum disturbance under the coupling effect of shield construction, the core of which is to construct a dynamic matching mechanism between the stratum characteristic map library and the vibration characteristic fingerprint. Specifically, the vibration spectrum data of the cutterhead cutting is collected by a vibration sensor, and the vibration characteristic fingerprint containing the energy distribution pattern and the critical pressure range is generated by combining the soil plasticity index, particle grading parameters and grouting pressure threshold; the vibration spectrum and the soil bin pressure are fused through the time-space alignment technology to generate a disturbance field distribution map, revealing the energy gradient and stress diffusion path; and the energy distribution pattern is spectrally matched with the stratum characteristic map by using the feature matching network optimized by transfer learning, and the stratum interface propagation path parameters are dynamically corrected. This method solves the problem of sensor data hysteresis, improves the stratum identification accuracy by quantifying the topological characteristics of the disturbance propagation, and dynamically models the interface energy dissipation mechanism, so as to shorten the time difference between the warning signal and the actual stratum damage.

[0059] 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.

[0060] Figure 1 A flowchart of a method for analyzing stratum disturbance under the coupling effect of shield construction is provided for the embodiment of the present application. Figure 1 As shown, the method includes:

[0061] 101. Vibration sensors arranged on the surface of the shield machine cutterhead are used to collect vibration spectrum data generated when the cutterhead cuts the soil;

[0062] In the above steps, the shield machine cutterhead refers to the rotating metal disk structure at the front of the shield machine used to cut soil. Its surface is covered with cutting tools and a discharge port. A vibration sensor is a piezoelectric or accelerometer measurement device installed at a specific location on the cutterhead surface to detect mechanical vibration signals, converting them into electrical signals. Vibration spectrum data refers to the frequency-amplitude distribution data obtained by converting time-domain vibration signals into frequency-domain signals through Fourier transform. It contains the vibration energy characteristics of different frequency components.

[0063] In an embodiment of the present application, a three-axis vibration sensor array is first evenly arranged on the working face of the shield machine cutterhead, and connected to the data acquisition module at the center of the cutterhead through a shielded cable to form a monitoring network; when the cutterhead rotates to cut the soil, each sensor collects three-dimensional vibration acceleration signals in real time, and the data acquisition module synchronously collects vibration waveform data of each channel at a sampling frequency of 10kHz, and records the cutterhead rotation speed and thrust pressure parameters in a correlated manner; then, a 20-2000Hz bandpass filter is performed on the original signal through a digital signal processor, and the time domain signal is converted into a frequency domain spectrogram using a fast Fourier transform algorithm, and the 1 / 3 octave spectrum features are extracted to form a vibration spectrum matrix; finally, the processed spectrum data is aligned in time and space with the geological exploration parameters, and transmitted to the ground database server through industrial Ethernet, and the geological unit number and mileage label are added according to the tunneling ring to form a standardized vibration feature data set.

[0064] In practical applications, for example, triaxial accelerometer arrays are deployed at the center of the shield machine's cutterhead and at the cutterhead mounting base, sampling at a 4000Hz frequency to collect real-time vibration signals from the cutterhead during its rotational cutting process. During on-site construction, when the shield machine advances at 15 rpm through interbedded silty clay and gravel, the monitoring system acquires cutterhead axial, radial, and tangential vibration data using a six-channel synchronous acquisition module. After filtering through a 150-2500Hz digital bandpass filter to eliminate low-frequency mechanical noise and high-frequency electromagnetic interference, the time-domain waveform data is compressed and stored in 60-second segments. Fast Fourier transform (FFT) of 320 vibration signals collected during the eighth ring advance reveals key frequency components at 380±20Hz and 1350±50Hz in the spectrum. Combined with geological radar data, these characteristic spectral lines correspond to composite vibration modes generated by the interaction between the cutterhead and the gravel layer. This system successfully extracts effective features of the cutterhead-rock-soil coupled vibration at the complex stratum interface, providing a high-precision raw data foundation for subsequent disturbance level classification.

[0065] In the overall solution of the above step 101, by real-time collection of shield cutterhead vibration spectrum data and combining multi-dimensional feature fusion analysis methods, the dynamic response characteristics under the interaction between the cutterhead and the soil are accurately extracted, the spatial distribution law and energy transfer mode of the cutting resistance in complex strata are effectively identified, and a nonlinear mapping relationship based on the spectrum feature vector and the stratum disturbance intensity is established to form a multi-level early warning threshold system to achieve real-time monitoring of the stratum disturbance state and risk classification and prediction. At the same time, the shield tunneling parameter configuration is optimized through a dynamic feedback mechanism, which significantly improves the accuracy and adaptability of shield construction disturbance control under complex geological conditions, provides intelligent decision-making support for the safe advancement of the project, and reduces the risk of excessive stratum deformation while ensuring construction efficiency.

[0066] 102. Based on the obtained soil plasticity index of the clay layer and the particle grading parameters of the gravel layer, a stratum characteristic atlas library is constructed. Combined with the soil shear modulus, groundwater permeability coefficient, and synchronous grouting pressure threshold, a vibration characteristic fingerprint is generated. The vibration characteristic fingerprint includes the vibration energy distribution pattern and the corresponding critical grouting pressure range under different stratum combinations;

[0067] Optionally, step 102 may specifically include the following steps:

[0068] 1021. Based on the obtained plasticity index threshold of the clay layer and the particle gradation parameter of the gravel layer, the stratum unit is divided in combination with the spatial coupling relationship between the plasticity index and the particle size distribution, where each stratum unit includes a shear modulus variation interval and a permeability coefficient stratification interval;

[0069] 1022. Dynamically matching the real-time torque fluctuation data of the screw conveyor with the shear modulus variation interval of the stratum unit to establish a real-time association rule between the mechanical load response and the soil shear modulus, and generating a compensation correction coefficient for the grouting pressure based on the dynamic difference between the grouting pipe outlet pressure and the tunnel face support pressure;

[0070] 1023. Integrate the compensation correction coefficient, permeability coefficient stratification interval, and real-time association rules according to stratum units to construct a stratum characteristic atlas library including shear modulus association factors, grouting pressure compensation rules, and permeability influencing parameters;

[0071] 1024. Based on the plasticity index weight, particle gradation weight and grouting pressure gradient distribution of each unit in the formation characteristic atlas library, a vibration characteristic fingerprint including the vibration energy distribution pattern under different formation combinations and the corresponding critical grouting pressure range is generated.

[0072] In the above steps, the plasticity index threshold of the clay layer refers to the judgment standard that the difference between the liquid limit and the plastic limit water content reaches the characteristic value of clay; the particle grading parameters of the gravel layer include the unevenness coefficient and curvature coefficient of the particle size distribution curve; the stratigraphic unit refers to the three-dimensional geological body unit divided based on the spatial variation of geological parameters; the shear modulus variation range reflects the range of soil shear strength variation with water content; the permeability coefficient stratification range represents the difference in hydraulic conductivity characteristics of different geological layers; the grouting pressure compensation coefficient refers to the grouting pressure correction value dynamically adjusted according to the support pressure of the tunnel face; the vibration characteristic fingerprint is a set of vibration modes with stratigraphic identification characteristics generated by the fusion of multi-source geological parameters.

[0073] In this embodiment of the present application, first, in step 1021, a three-dimensional geological parameter field model is constructed using the geostatistical kriging interpolation algorithm based on the clay plasticity index and gravel particle size distribution data obtained from the engineering survey. The construction area is then divided into 2m×2m×2m cubic stratigraphic units according to the plasticity index mutation threshold and the particle size distribution critical value. For each stratigraphic unit, a direct shear test is performed to determine the variation range of the shear modulus with water content. Combined with the pumping test data, a vertical stratification interval table of the permeability coefficient is established, forming a basic geological unit containing mechanical parameters and hydraulic properties.

[0074] Next, in step 1022, real-time torque fluctuation data is collected using the current sensor of the screw conveyor drive motor. A dynamic time warping algorithm is used to pattern-match the torque fluctuation characteristics with the shear modulus variation range of the stratum unit, establishing an exponential correlation equation between torque amplitude and soil shear strength. Real-time data is simultaneously collected from the grouting pipe outlet pressure sensor and the earth pressure balance shield machine face pressure sensor. The dynamic pressure differential between the two is calculated using a fuzzy PID control algorithm, generating a grouting pressure compensation correction coefficient that varies with stratum characteristics, enabling dynamic adjustment of grouting parameters.

[0075] Next, in step 1023, the permeability coefficient intervals of each stratigraphic unit are quantified into five levels of permeability influencing parameters. The shear modulus correlation equation is converted into a correlation factor in the form of a weight coefficient, and the parameters are encoded in conjunction with the grouting pressure compensation rule. A three-dimensional geological model is constructed using knowledge graph technology. Each graph node stores the spatial coordinates, mechanical parameter set, and grouting strategy code of the corresponding stratigraphic unit. Adjacent units are connected through relationship edges to form a complete stratigraphic characteristic map library.

[0076] Finally, in step 1024, principal component analysis is used to extract the main influencing factors of the plasticity index and particle size distribution. Combined with the grouting pressure gradient distribution, a three-dimensional parameter space is constructed. The Mahalanobis distance algorithm is used to calculate the spatial distribution density of each parameter combination. Vibration main frequency band distribution patterns with a probability of occurrence exceeding 85% are screened to determine the critical grouting pressure range threshold required to maintain formation stability. Multi-source parameter fusion generates a vibration signature fingerprint library containing the vibration energy characteristics of typical formation combinations and grouting control parameters, providing a discriminant benchmark for subsequent formation disturbance analysis.

[0077] In practical applications, for example, in the shield construction of a certain composite stratum, based on the measured data that the plasticity index of the silty clay layer is 18-26 and the particle size of the gravel layer is 0.5 to 20 mm, accounting for 65%, the three-dimensional spatial grid modeling technology is used to divide the excavation section into 1.2 m × 1.2 m × 0.5 m stratum units, and the dynamic range of the clay shear modulus is set to 25-65 MPa and the gravel shear modulus is set to 80-150 MPa, and the measured parameters of the permeability coefficient of the clay layer is 1×10^-6 cm / s and that of the gravel layer is 5×10^-3 cm / s. By collecting real-time torque fluctuation data of 0-850 kN·m from the screw conveyor, the dynamic time warping algorithm is used to match it with the shear modulus of the formation unit. When the torque standard deviation exceeds 45 kN·m, the association rule update is triggered. The real-time difference between the grouting pipe outlet pressure of 2.5-3.2 MPa and the tunnel face support pressure of 1.7-2.4 MPa is simultaneously combined. When the pressure difference exceeds the 0.8 MPa threshold, a grouting compensation coefficient of 0.85-1.15 is generated, and closed-loop adjustment of the grouting pump speed is achieved through a PID controller. The final constructed characteristic atlas library of 325 stratigraphic units integrates 5-dimensional shear modulus correlation vectors, 3-level grouting pressure gradient rules and double-layer permeability correction parameters. A fusion algorithm with a plasticity index weight of 0.6 and a particle grading weight of 0.4 is used to generate a vibration fingerprint that includes the critical grouting pressure of 1.8-2.3 MPa for clay-gravel interlayers and the main frequency band characteristics of 200-800 Hz for gravel-dominated strata, enabling real-time identification of sudden changes in stratigraphic interface characteristics and dynamic optimization of grouting parameters.

[0078] In the overall solution of step 102 above, a multi-parameter coupling analysis framework is constructed by integrating the plasticity index of the clay stratum and the particle grading parameters of the gravel stratum. The stratum units are divided based on the spatial correlation between the plastic state and the particle size distribution. The dynamic range of the shear modulus, the stratification threshold of the permeability coefficient, and the grouting pressure difference compensation mechanism are combined to form a stratum characteristic atlas library with mechanical load response characteristics. A dynamic feedback mechanism between the shear properties of the soil and the mechanical behavior of the shield is established through the real-time mapping relationship between the torque fluctuation data of the screw conveyor and the shear modulus variation range. Based on the synergistic effect of the grouting pressure compensation rule and the permeability influencing parameter, a vibration characteristic fingerprint including the vibration energy distribution pattern and the critical grouting pressure range is generated. This achieves accurate matching of the stratum combination type and the dynamic response of the shield, effectively predicts the disturbance propagation trend at the interface of different strata, provides a quantitative basis for the dynamic optimization of grouting parameters and the prevention of stratum instability, and significantly improves the foresight and adaptability of disturbance control of shield construction under complex stratum conditions.

[0079] 103. Temporally and spatially align the vibration spectrum data of different areas of the cutterhead with the monitored values ​​of the soil bin pressure to generate a disturbance field distribution map, wherein the disturbance field distribution map includes an energy gradient distribution curve of the vibration field and a stress diffusion path topology of the soil;

[0080] Optionally, step 103 may specifically include the following steps:

[0081] 1031. Based on the cutterhead rotation angle encoding signal and the spatial position information of the vibration monitoring points, perform a spatiotemporal alignment operation on the vibration spectrum data of each area on the cutterhead surface and the soil bin pressure monitoring value to generate a spatiotemporally synchronized vibration and pressure joint dataset.

[0082] 1032. Extracting the vibration spectrum segment synchronized with the cutterhead rotation phase and the soil bin pressure mutation interval from the vibration-pressure joint data set, and establishing a spatiotemporal correlation mapping relationship between vibration energy and pressure change;

[0083] 1033. Calculate the cumulative increment of vibration energy in each region within the cutterhead excavation section within a continuous rotation cycle based on the time-space correlation mapping relationship, and generate a vibration energy gradient distribution curve representing the stratum disturbance intensity;

[0084] 1034. Based on the spatial superposition relationship between the soil bin pressure fluctuation amplitude and the vibration energy gradient distribution curve, the stress concentration area of ​​the soil layer is identified and the stress diffusion direction is calibrated to generate a stress diffusion topological network throughout the soil layer;

[0085] Among them, step 1034 may specifically include the following processes: according to the spatial distribution consistency of the soil bin pressure fluctuation amplitude and the vibration energy gradient distribution curve in the cutterhead excavation section, calculate the pressure energy superposition coefficient of each region that represents the combined effect strength of the pressure amplitude and the energy gradient; screen the regions where the pressure energy superposition coefficient exceeds the preset threshold, mark them as initial stress concentration regions, and extract the energy gradient change slope between adjacent initial stress concentration regions; based on the directionality of the energy gradient change slope, calibrate the stress diffusion direction between the initial stress concentration regions, and merge adjacent regions with the same direction into a stress conduction link; according to the attenuation rate of the pressure energy superposition coefficient in the stress conduction link and the link extension length, generate a stress diffusion topological network that penetrates the soil layer.

[0086] 1035. Fusing the vibration energy gradient distribution curve with the stress diffusion topological network to form a disturbance field distribution diagram containing spatiotemporal correlation disturbance characteristics.

[0087] In the above steps, the cutterhead rotation angle encoding signal refers to the angle pulse signal output by the photoelectric encoder installed on the cutterhead drive shaft, which is used to accurately calibrate the cutterhead rotation position; the spatial position information of the vibration monitoring point refers to the three-dimensional coordinate parameters of the vibration sensor arranged on the cutterhead surface in the cutterhead coordinate system; the spatiotemporal synchronized vibration pressure joint data set refers to a multidimensional data set of vibration spectrum data and soil bin pressure values ​​with time stamp alignment; the vibration energy gradient distribution curve refers to a spatial distribution curve generated based on the cumulative increment of vibration energy; the stress diffusion topological network refers to a directed graph network structure reflecting the stress transfer path of the soil layer; the pressure energy superposition coefficient is an action intensity index calculated by combining the pressure fluctuation amplitude and the vibration energy gradient; the stress conduction link refers to a connection path between adjacent areas with continuous stress transfer characteristics.

[0088] In this embodiment, step 1031 first completes the spatiotemporal data alignment. Based on the rotation angle signal output by the cutterhead drive shaft photoelectric encoder and the three-dimensional spatial coordinate parameters of the cutterhead surface vibration sensor, a coordinate transformation algorithm is used to convert the vibration spectrum data of each monitoring point into a fixed geographic coordinate system. Monitoring values ​​for the four pressure zones within the soil bin are then collected simultaneously. A timestamp alignment algorithm is then used to unify the vibration and pressure data to a millisecond-level time base, forming a joint vibration-pressure dataset that includes spatial location markers and time synchronization.

[0089] Next, in step 1032, a spatiotemporal correlation mapping is established. The vibration spectrum segments for each 15-degree phase interval of the cutterhead rotation are extracted from the joint dataset, and the soil bin pressure change data within the corresponding time window are intercepted. A dynamic time warping algorithm is used to analyze the correlation between the energy fluctuations in the main vibration frequency band and the pressure change curve. An exponential correlation equation is established between the peak vibration energy and the pressure change rate within each phase interval, generating a vibration-pressure mapping matrix with a spatiotemporal correspondence.

[0090] Next, step 1033 is executed to generate a vibration energy gradient distribution curve. The vibration energy in each phase interval is integrated over three consecutive cutterhead rotation cycles, and the cumulative energy increment is calculated for each 1°×1° grid cell within the tunneling section. Kriging spatial interpolation is used to convert the discrete point energy values ​​into a continuous distribution surface, generating a gradient distribution curve reflecting the ground disturbance intensity. The peak area of ​​the curve corresponds to the location of strong soil disturbance.

[0091] Then, in step 1034, a stress diffusion topology network is constructed. The product of the soil bin pressure fluctuation amplitude and the vibration energy gradient within each grid cell is calculated as the pressure energy superposition coefficient. Cells with coefficients exceeding a threshold of 2.5 are screened and marked as initial stress concentration areas. The energy gradient change rate vectors between adjacent concentrated areas are extracted, and the stress diffusion direction is determined based on the consistency of the vector direction angles. Adjacent areas with a directional deviation of less than 10 degrees are connected to form stress conduction links. By analyzing the coefficient attenuation gradient and extension length of the links, a tree-like topology network consisting of trunk paths and branch paths is constructed.

[0092] Finally, step 1035 fuses the generated disturbance field distribution map, overlaying the contour data of the vibration energy gradient curve with the directed edge data of the stress topology network in three-dimensional space. Color rendering technology is used to display the disturbance intensity in a graded manner using red, yellow, and blue colors, and arrows are used to indicate the direction of stress transmission. Ultimately, a disturbance field visualization model with spatiotemporal correlation features is generated. Red highlighted areas in the model represent strong disturbance zones, and arrow links indicate the main stress diffusion paths.

[0093] In practical applications, for example, during shield tunneling in a complex stratum, a spatiotemporal interpolation algorithm was used to align the cutterhead surface vibration spectrum data with the 0.18-0.35 MPa monitoring values ​​from the soil bin pressure sensor, based on the real-time signal from the cutterhead rotation angle encoder with a 0.5° resolution. This generated a spatiotemporally synchronized dataset containing 240 data points per minute. By extracting the vibration spectrum segments corresponding to each 15° rotation phase of the cutterhead and the intervals where the soil bin pressure exceeded 0.08 MPa, a correlation matrix was established between the vibration energy and the pressure change rate for the cutterhead's six cutting zones. The cumulative increase in vibration energy in each zone over three consecutive rotation cycles was calculated to generate disturbance intensity distribution curves with axial gradients of 0.8-3.2 kJ / m² and radial gradients of 0.5-2.4 kJ / m². Combined with the spatial distribution of the soil bin pressure fluctuation amplitude (0.12-0.28 MPa), the pressure energy superposition coefficient in the 3 o'clock direction of the cutterhead was calculated to be 0.76, marking it as the initial stress concentration zone. Directivity analysis of the energy gradient slope of 0.35-0.68 / m in adjacent areas was used to construct a stress conduction link extending 1.8 meters. Finally, the six stress conduction links were integrated with the vibration gradient curve to generate a three-dimensional disturbance field distribution map containing 12 disturbance hotspots and five main diffusion paths, enabling dynamic visualization of the formation disturbance characteristics within 2.4 meters in front of the cutterhead.

[0094] In the overall solution of step 103 above, by dual calibration of the cutterhead rotation angle encoding and the spatial position of the vibration monitoring point, the spatiotemporal synchronization of the vibration spectrum data and the soil bin pressure monitoring value is achieved, and a joint data set with phase correlation characteristics is constructed; based on the spatiotemporal mapping relationship between vibration energy and pressure mutation, the cumulative increment of vibration energy in each area of ​​the cutterhead during the continuous rotation cycle is extracted to generate a gradient distribution curve representing the stratum disturbance intensity, and combined with the spatial superposition effect of the soil bin pressure fluctuation amplitude, the pressure energy superposition coefficient is calculated and the energy gradient slope is analyzed to accurately identify the stress concentration area and calibrate the diffusion direction, forming a multi-level stress conduction link network throughout the soil layer; finally, through the dynamic fusion of the disturbance field distribution map, the three-dimensional disturbance field evolution law of the vibration energy gradient distribution, stress diffusion path and spatiotemporal correlation characteristics inside the stratum is fully presented, providing a visual analysis basis for the prediction and dynamic control of the stratum disturbance propagation range during shield tunneling, and effectively supporting the real-time optimization of construction parameters and the precise prevention and control of disturbance risks.

[0095] 104. Input the disturbance field distribution map and the vibration characteristic fingerprint into a feature matching network optimized by transfer learning, so as to perform spectral matching between the energy gradient distribution curve and the vibration energy distribution pattern through the feature matching network. Simultaneously, the propagation path parameters of the stratum interface transition zone are corrected according to the stress diffusion path topology, so as to output an identification result of the current stratum type and extract the disturbance propagation dynamic parameters.

[0096] Optionally, step 104 may specifically include the following steps:

[0097] 1041. Input the vibration energy gradient distribution curve in the disturbance field distribution map and the vibration energy distribution patterns of different stratum combinations in the vibration feature fingerprint into a feature matching network optimized by transfer learning. The feature matching network performs spectral matching on the frequency band energy proportion and waveform similarity of the energy distribution curve to generate a stratum type matching index.

[0098] 1042. Extracting propagation path node parameters of the stratum interface transition zone in the stress diffusion path topology, and correcting the propagation path node parameters of the transition zone based on the stress conduction direction offset angle and connection strength between the nodes;

[0099] 1043. Correlate the corrected propagation path node parameters with the formation type matching index, extract the critical grouting pressure interval corresponding to the current formation combination from the vibration characteristic fingerprint, and generate a dynamic parameter set for disturbance propagation in the formation interface transition zone;

[0100] 1044. According to the path offset and energy attenuation rate in the dynamic parameter set, output the identification result of the current formation type and extract the disturbance propagation dynamic parameters.

[0101] In the above steps, the feature matching network optimized by transfer learning refers to a deep learning model with cross-domain matching capabilities that is formed by fine-tuning the stratigraphic feature dataset using a pre-trained convolutional neural network architecture; spectral shape matching refers to a pattern recognition process performed by comparing the frequency band energy ratio and waveform similarity of the vibration energy distribution curve; the stratigraphic interface transition zone refers to a geological transition zone with gradual characteristics at the junction of different stratigraphic combinations; the propagation path node parameters include the stress conduction direction angle, the connection strength coefficient and the energy attenuation rate; the dynamic parameter set refers to a time-varying parameter group that reflects the path offset and energy attenuation characteristics during the disturbance propagation process; the path offset refers to the angle difference between the stress conduction direction and the stratigraphic interface direction; the energy attenuation rate refers to the attenuation gradient of the vibration energy per unit distance along the propagation path.

[0102] In the embodiment of the present application, a spectral shape matching analysis is first performed in step 1041, and the vibration energy gradient distribution curve in the disturbance field distribution diagram and the typical stratum combination energy pattern pre-stored in the vibration feature fingerprint library are input into the feature matching network. This network adopts a transfer learning strategy, loaded with the ResNet-50 model pre-trained on ImageNet, and achieves cross-domain adaptation by freezing the bottom convolutional layer and fine-tuning the top fully connected layer. A dynamic time warping algorithm is used to calculate the difference in energy proportion between the input curve and the feature fingerprint in the 1 / 3 octave frequency band, and combined with the waveform correlation coefficient to generate a stratum type matching index in the range of 0-1.

[0103] Next, in step 1042, propagation path parameters are corrected, and propagation path node data for the stratum interface transition zone is extracted from the stress diffusion topology network. A graph attention network is used to analyze the directional offset angles and connection strength coefficients between nodes. Direction cosines are used to calculate the deviation of the corrected stress conduction directional angles. Weakly conductive links with connection strengths below 0.7 are pruned, retaining valid path nodes with deviations from the main conduction direction of less than 15 degrees. The propagation directional angle parameters and connection strength coefficients for the transition zone are then updated.

[0104] Next, step 1043 is executed to generate a dynamic parameter set. The corrected path node azimuth parameters are then multimodally correlated with the formation type matching index. Based on the matching index ranking results, the critical grouting pressure intervals corresponding to the top three candidate formation combinations are retrieved from the vibration signature fingerprint library. Based on the node distribution density of the current stress diffusion path, the energy attenuation gradient along the main conduction direction is calculated, generating a dynamic parameter matrix containing the path offset, attenuation rate, and critical pressure value.

[0105] Finally, the identification results are output in step 1044. A weighted voting algorithm is used to combine the stratum type matching index and the path parameter consistency index, selecting stratum combinations with a comprehensive score exceeding 0.85 as the final identification results. The median offset and average attenuation rate of the main conduction path are extracted from the dynamic parameter matrix. A dynamic parameter report is generated, including the disturbance propagation velocity, energy dissipation coefficient, and recommended grouting pressure range, providing a decision-making basis for optimizing shield construction parameters.

[0106] In practical applications, for example, during the construction of a subway shield tunnel, a vibration energy distribution curve with an axial gradient of 0.8-3.2 kilojoules per square meter and a vibration fingerprint of the main frequency band of 200-800 Hz were input into a feature matching network optimized based on the ResNet-18 architecture. Through a three-layer temporal feature extraction layer with a 5×1 convolution kernel, the cosine similarity between the energy proportion of each sub-band of the energy distribution curve within the frequency range of 50-2000 Hz and the standard vibration mode was calculated, generating a stratigraphic type matching index of 0.72-0.89. Simultaneously, the propagation path parameters of the 12 transition zone nodes in the stress diffusion topological network were extracted. For weak sections where the stress conduction direction offset angle between nodes exceeded 15 degrees and the connection strength was less than 0.6, the path curvature radius was corrected to a range of 0.8-1.5 meters using a cubic spline interpolation algorithm. The corrected node coordinate parameters were mapped to the formation matching index in a multidimensional space. Combined with the critical grouting pressure standard of 1.8-2.3 MPa for clay-pebble interbeds in the vibration signature fingerprint, a dynamic parameter set was generated, including a path offset of 0.3-1.2 meters and an energy decay rate of 0.15-0.35 seconds. Finally, by integrating and analyzing the characteristics of strongly correlated regions with a matching index of 0.85 or higher and the extension direction of the stress transmission link, the transition interface from silty clay to pebble formations was successfully identified. Dynamic control parameters were then extracted, including a grouting pressure compensation coefficient of 1.05-1.12 and a main disturbance propagation path inclination of 28-35 degrees.

[0107] In the overall solution of step 104 above, a deep coupling analysis of the disturbance field distribution map and the vibration characteristic fingerprint is realized through a feature matching network optimized by transfer learning, and the spectral shape matching mechanism of the frequency band energy distribution and the waveform morphology is used to accurately calculate the stratum type matching degree. Combined with the dynamic correction of the node conduction direction offset angle and the connection strength in the stress diffusion path topology, a spatial correlation model of the disturbance propagation parameters in the stratum interface transition zone is established; through the multi-dimensional dynamic parameter fusion of the energy attenuation rate and the path offset, the stratum combination type identification result and the disturbance propagation characteristics of the interface transition zone are synchronously output, and at the same time, the shield grouting control strategy is adaptively optimized based on the matching critical grouting pressure interval, which significantly improves the prediction accuracy of the disturbance propagation path and the parameter adaptability at the complex stratum interface, provides real-time data support for the dynamic adjustment of the grouting pressure and the disturbance suppression when the shield passes through the overlapping area of ​​multiple strata, and effectively ensures the active prevention and control capability of the stratum interface mutation risk during the construction process.

[0108] 105. Based on the mapping relationship between the disturbance propagation dynamic parameters and the critical grouting pressure range in the vibration characteristic fingerprint, the synchronous grouting pressure threshold is dynamically adjusted in combination with the surface displacement monitoring data, and a graded early warning signal and grouting parameter adjustment instruction are generated to complete the closed-loop control of the formation disturbance.

[0109] Optionally, step 105 may specifically include the following steps:

[0110] 1051. Determine a critical grouting pressure threshold range of a stratum interface transition zone based on a mapping relationship between the disturbance propagation dynamic parameter and the critical grouting pressure interval in the vibration characteristic fingerprint;

[0111] 1052. Extracting the synchronous grouting reference pressure value corresponding to the current stratum combination from the stratum characteristic atlas library, and combining it with the instantaneous change of the surface settlement rate in the surface displacement monitoring data to generate a grouting pressure dynamic adjustment gradient table including a pressure fluctuation tolerance;

[0112] 1053. Real-time acquisition of the dynamic difference between the grouting pipe outlet pressure and the tunnel face support pressure, and simultaneous monitoring of the displacement transmission rate of the formation interface in the stress diffusion topological network. When the dynamic difference exceeds the tolerance range of the grouting pressure dynamic adjustment gradient table or the displacement transmission rate exceeds a preset diffusion rate threshold, a multi-level warning signal is triggered based on the degree of excess.

[0113] 1054. Based on the multi-level warning signal, activate the linked pressurization operation of the target grouting hole and its adjacent holes, synchronously collect the surface displacement rebound and stress diffusion direction offset parameters after pressurization, and calculate the grouting pressure compensation coefficient;

[0114] Among them, step 1054 may specifically include the following processes: according to the level of the multi-level warning signal, the linkage boosting device of the target grouting hole and its adjacent holes is activated according to the preset priority, so that the grouting pressure of the target hole and the adjacent holes is synchronously increased to the preset boosting value; the surface displacement rebound and stress diffusion direction offset angle data of the boosting area are synchronously collected, the surface displacement rebound is the difference between the surface uplift height after boosting and the settlement before boosting, and the stress diffusion direction offset angle is the angle deviation between the actual conduction direction and the preset diffusion path; based on the ratio of the absolute value of the surface displacement rebound to the preset rebound expected value, the displacement rebound compensation weight is calculated, and at the same time, based on the difference ratio between the stress diffusion direction offset angle and the allowable offset angle threshold, the direction offset correction factor is calculated; the displacement rebound compensation weight and the direction offset correction factor are weighted and superimposed to generate a grouting pressure compensation coefficient for quantifying the correction effect of the linkage boosting operation on the formation disturbance suppression effect.

[0115] 1055. According to the grouting pressure compensation coefficient, the critical grouting pressure threshold range is adjusted, a grouting parameter adjustment instruction is generated and bound to the corresponding formation combination in the formation characteristic atlas library, forming a closed-loop control link based on stress diffusion topology and surface displacement feedback.

[0116] In the above steps, the dynamic parameters of disturbance propagation refer to a real-time data set including path offset and energy decay rate. The vibration signature fingerprint library refers to a database storing the correlation between vibration energy patterns and critical pressures for different stratum combinations. The stratum interface transition zone refers to the gradually changing geological region at the interface between different stratum combinations. The pressure buffer zone refers to a safety redundancy interval outside the critical pressure threshold. The stratum characteristic atlas library refers to a structured database storing the mechanical parameters, grouting rules, and permeability coefficients of stratum units. The synchronous grouting baseline pressure value refers to the initial set pressure value required for stratum stability. The instantaneous change in surface settlement rate refers to the change in surface settlement height per minute. The pressure fluctuation tolerance refers to the maximum deviation of the grouting pressure from the baseline value. The grouting pipe outlet pressure refers to the real-time pressure value at the end of the grouting system. The tunnel face support pressure refers to the pressure in the soil chamber in front of the shield machine that maintains soil stability. The dynamic difference refers to the real-time deviation between the grouting and support pressures. The displacement transmission rate refers to the transmission speed of stratum displacement in the stress diffusion topological network (unit: mm / s). Multi-level early warning signals refer to three levels of alarms divided according to the degree to which parameters exceed the standard. Linked pressurization operation refers to the coordinated adjustment of the pressure of the target grouting hole and the adjacent holes. The surface displacement rebound refers to the change in surface height after pressurization. The stress diffusion direction offset angle refers to the angular deviation between the actual conduction direction and the preset path. The grouting pressure compensation coefficient refers to the pressure correction factor calculated by combining the rebound amount and the direction deviation. The closed-loop control link refers to a periodic control process consisting of monitoring, adjustment, and feedback. The grouting parameter adjustment instruction refers to an operation command that includes the target pressure value, response time, and control logic.

[0117] In the embodiment of the present application, the critical grouting pressure range is first determined by step 1051. Based on the path offset of 20 mm and the energy decay rate of 1.5 decibels / meter in the dynamic parameters of disturbance propagation, combined with the reference pressure value of 0.8 MPa matching the stratum combination in the vibration characteristic fingerprint library, the cubic spline interpolation algorithm is used to calculate the upper and lower limits of the critical pressure of the stratum interface transition zone. For example, for every 1 mm increase in the path offset, the corresponding lower pressure limit is reduced by 0.005 MPa, and for every 0.1 decibel / meter increase in the energy decay rate, the corresponding upper pressure limit is increased by 0.003 MPa. Secondly, the reference pressure value of 0.8 MPa is expanded by a positive and negative tolerance of 0.1 MPa to generate a safe operating range of 0.6 MPa to 0.945 MPa. By increasing the pressure buffer zone, redundant control of stratum stability is ensured. For example, the actual control range of a certain sand layer is set to 0.62-0.93 MPa.

[0118] Next, a dynamic adjustment gradient table is generated in step 1052. The synchronous grouting baseline pressure value of 0.8 MPa for the current formation combination is extracted from the formation characteristic atlas library. Combined with the surface settlement rate monitoring data of 4 mm / h, the adjustment range is calculated based on the proportional relationship between the settlement rate increment and the pressure adjustment of 0.1 MPa / mm / h. For example, a settlement rate of 4 mm / h corresponds to a pressure adjustment of 0.4 MPa. A tiered strategy is generated based on the safety tolerance range: when the settlement rate is 2-5 mm / h, a pressure fluctuation of ±0.15 MPa is allowed, with a response time of ≤10 seconds; when the settlement rate is 5-10 mm / h, the tolerance is increased to ±0.25 MPa, with a response time of ≤5 seconds. Finally, the gradient table is written to the formation characteristic atlas library. For example, in a silt formation, a settlement rate of 6 mm / h triggers a pressure adjustment of 0.8±0.25 MPa.

[0119] Next, step 1053 implements real-time monitoring and multi-level early warning. Pressure sensors collect the grouting pipe outlet pressure of 0.95 MPa and the tunnel face support pressure of 0.7 MPa in real time, calculating a dynamic difference of 0.25 MPa. Simultaneously, the displacement transmission rate of 6 mm / s at key nodes in the stress diffusion topology network is monitored. When the dynamic difference exceeds the ±0.15 MPa tolerance allowed by the gradient table or the displacement rate exceeds the 5 mm / s safety threshold, a graded early warning mechanism is triggered. For example, a dynamic difference of 0.25 MPa triggers an orange alert, automatically activating the backup grouting pump and recording the operation log. If the difference further rises to 0.36 MPa, a red alert is triggered, and the shield machine advance is abruptly halted.

[0120] Subsequently, step 1054 executes linked boost control. When the orange warning is triggered, the pressure at target grouting hole number 5 is increased to 1.2 times the baseline value, or 0.96 MPa. A distance weighting factor of 1.033 is calculated for three adjacent holes, based on a spacing of 1.5 meters, adjusting the pressure to 0.826 MPa. After boosting, the surface displacement rebound is measured at 3 mm (preset expected value of 5 mm) and a directional offset angle of 12 degrees (with a 30-degree threshold). The rebound compensation weight of 3 / 5 = 0.6 and the directional correction factor of 1 - 2 / 30 ≈ 0.93 are calculated. The weights of 0.6 and 0.4 are superimposed to generate a compensation factor of 0.75. For example, in a clay layer, a compensation factor of 0.8 extends the trigger pressure threshold to 0.55-1.0 MPa.

[0121] Finally, a closed-loop control link is established through step 1055. The critical pressure threshold is adjusted to a range of 0.6-0.945 MPa based on a compensation factor of 0.75, and the updated parameters are bound to the formation characteristic atlas library. Grouting parameter adjustment instructions are issued via the industrial bus, with a target pressure of 0.96 MPa and a response time of 5 seconds. The actuator is controlled to complete the pressure adjustment within 5 seconds. A 30-second monitoring cycle is initiated. For example, in a composite formation, rebound data is collected every 30 seconds. If the rebound is less than 2 mm, pressurization is triggered again, forming a continuously optimized closed-loop control process.

[0122] In practical applications, for example, in a cross-river shield tunnel project, a gradient descent algorithm was used to generate a three-level dynamically adjusted gradient table with a pressure fluctuation tolerance of ±0.15 MPa, based on the critical grouting pressure threshold of 1.8-2.3 MPa for the clay-gravel interbed, combined with 0.5-1.2 mm / hour settlement rate data collected by the surface displacement monitoring system. Pressure transmitters installed at the grouting pipe outlet and the tunnel face acquired real-time pressure differential data. When the shield machine advanced to the stratum interface, the pressure differential was monitored to increase suddenly from 0.6 MPa to 1.05 MPa. Simultaneously, the stress diffusion topological network indicated that the displacement transmission rate at the interface reached 3.8 mm / minute, exceeding the preset threshold of 2.5 mm / minute and triggering a Level 2 orange alert. The system immediately activated the interlocking booster devices at main grouting hole No. 3 and its adjacent holes No. 2 and No. 4, increasing the grouting pressure in a stepped manner from 1.9 MPa to 2.25 MPa within 12 seconds. The tilt sensor monitored the stress diffusion direction offset angle, which was corrected from 28 degrees to 15 degrees, and the surface rebound reached 0.7 mm. A displacement compensation weight of 0.7 was calculated based on the ratio of the displacement rebound of 0.7 mm to the preset expected value of 1.0 mm. Combined with the directional offset angle difference ratio of 0.43, a directional correction factor of 0.85 was calculated. A weighted superposition of these factors yielded a grouting pressure compensation coefficient of 0.79. Ultimately, the corrected critical pressure threshold was adjusted to 2.05-2.18 MPa and updated to the clay-pebbled interbedded unit in the stratigraphic characteristic atlas. This formed a multi-parameter closed-loop control link between grouting pressure, surface displacement, and stress diffusion with a 0.5-second period, achieving the engineering effect of increasing the reduction rate of the stratigraphic disturbance range and reducing grouting material loss.

[0123] In the overall scheme of the above step 105, by establishing a real-time mapping mechanism between the dynamic parameters of disturbance propagation and the critical grouting pressure range, combined with multi-source feedback of surface displacement monitoring data and the dynamic difference of grouting pressure, an adaptive closed-loop control system including linkage boost compensation and stress diffusion correction is constructed; based on the critical grouting pressure threshold range of the stratum interface transition zone, a dynamic adjustment gradient table is generated by synchronizing the grouting benchmark pressure value and the instantaneous change of the surface settlement rate, and a multi-level early warning signal is triggered by the dual criteria of the grouting pressure difference exceeding the limit and the displacement conduction rate breaking through the threshold; relying on the linkage of the target grouting hole and its adjacent holes, the system can automatically generate a dynamic adjustment gradient table based on the critical grouting pressure threshold range of the stratum interface transition zone, and generate a dynamic adjustment gradient table based on the instantaneous change of the grouting benchmark pressure value and the surface settlement rate. During the pressurization operation, the surface displacement rebound and stress diffusion direction offset parameters are collected in real time. The grouting pressure compensation coefficient is generated by weighted superposition of the rebound compensation weight and the direction offset correction factor, and the critical pressure threshold range is dynamically corrected and the adjustment instructions are optimized. By binding the compensation coefficient with the stratum characteristic map library in real time, a closed-loop control link of the stress diffusion path topology and surface displacement feedback is formed, and dynamic adaptation of the grouting pressure and stratum response is achieved, which significantly improves the disturbance warning accuracy of the multi-stratum interface and the efficiency of grouting parameter control, while reducing the risk of stratum mutation caused by shield tunneling and ensuring the adaptive control capability of the construction process.

[0124] The following is a complete embodiment of steps 101 to 105:

[0125] like Figure 2 As shown in the figure, in a shield tunneling project in a certain city subway section, 12 triaxial accelerometer arrays arranged on the cutterhead surface collected real-time vibration spectrum data at a sampling frequency of 4000 Hz during the cutterhead cutting process. When the shield machine advanced at a speed of 18 r / min, the monitoring system simultaneously acquired the energy distribution of the main vibration frequency bands at the 3 o'clock, 6 o'clock, and 9 o'clock zones of the cutterhead. In the clay layer, the 180-450 Hz frequency band accounted for 62% of the energy, while the gravel layer showed a sudden increase in high-frequency energy between 850 and 1300 Hz, with a maximum vibration acceleration peak of 12.3 m / s². This provided high-precision raw data for subsequent stratigraphic analysis.

[0126] In the shield tunneling section of composite strata, a characteristic atlas library consisting of 325 stratigraphic units was constructed based on measured data showing a clay layer plasticity index of 22.3 and a gravel layer with a particle size of 0.5 to 20 mm comprising 65%. Using 3D geological modeling, the dynamic ranges for the clay shear modulus were set to 30-60 MPa and the gravel layer shear modulus to 90-140 MPa, and these were correlated with layered permeability data (8 × 10-7 cm / s for the clay layer and 3 × 10-3 cm / s for the gravel layer). Combined with historical data from the synchronous grouting system, a vibration signature fingerprint for typical stratigraphic combinations was generated. The critical grouting pressure for clay-gravel interlayers ranged from 1.7 to 2.2 MPa, and the dominant frequency band of vibration energy was concentrated between 200 and 700 Hz, establishing a standardized benchmark for stratigraphic identification.

[0127] During shield tunnel construction across the river, the 0.2° resolution signal from the cutterhead's rotary angle encoder was used to spatially and temporally align the vibration spectrum data from six sections of the cutterhead surface with the monitored soil bin pressure of 0.2-0.4 MPa. By constructing a spatiotemporal correlation matrix, a disturbance field distribution map was generated, containing an axial vibration energy gradient of 0.6-2.8 kJ / m² and a radial gradient of 0.4-1.9 kJ / m². Combined with stress diffusion topological network analysis, a primary stress conduction path extending 2.1 meters from the 2 o'clock position of the cutterhead was identified. Its energy decay rate of 0.18 / s showed a significant spatial correlation with the pressure fluctuation amplitude of 0.15-0.28 MPa.

[0128] At the shield tunneling section at the geological interface, a disturbance field distribution map containing sudden high-frequency energy fluctuations between 650 and 1300 Hz was fed into a ResNet-34 feature matching network optimized through transfer learning. A three-layer convolution kernel was used to extract the waveform characteristics of the vibration energy gradient curve. The spectral shape was then matched with standard patterns in the stratigraphic feature map library, resulting in a stratigraphic matching index of 0.83. Simultaneously, the parameters of the three transition zone path nodes in the stress diffusion topological network were modified, optimizing the path curvature radius from 1.2 meters to 0.9 meters. The resulting output identified gravel-dominated stratigraphic formations and extracted dynamic parameters: a 32-degree inclination angle and an energy decay rate of 0.25 / s for the main disturbance propagation path.

[0129] During construction in sensitive building areas, a three-level pressure adjustment gradient table was dynamically generated based on the critical grouting pressure standard of 2.0-2.4 MPa for gravel formations, combined with 0.3-0.9 mm / h settlement data collected by the surface displacement monitoring system. When the difference between the grouting pipe outlet pressure and the face support pressure exceeded the 0.7 MPa threshold, a yellow warning was triggered and the joint pressurization of the No. 5 grouting hole group was activated, increasing the grouting pressure from 1.9 MPa to 2.3 MPa within 8 seconds. A grouting compensation coefficient of 0.87 was calculated based on the real-time feedback of the surface rebound of 0.5 mm and the 12-degree offset angle correction in the stress diffusion direction, forming a closed-loop control link between grouting pressure and formation deformation with a period of 10 seconds, effectively controlling surface settlement within the warning threshold.

[0130] Figure 3 The present invention provides a schematic diagram of a structure of a ground disturbance analysis system under the coupling effect of shield construction, as shown in FIG. Figure 2 As shown, the system includes:

[0131] The collection module 31 collects vibration spectrum data generated when the cutterhead cuts the soil through the vibration sensor arranged on the surface of the shield machine cutterhead;

[0132] Construction module 32, based on the obtained soil plasticity index of the clay layer and the particle grading parameters of the gravel layer, constructs a stratum characteristic atlas library, and combines the soil shear modulus, groundwater permeability coefficient and synchronous grouting pressure threshold to generate a vibration characteristic fingerprint, the vibration characteristic fingerprint including the vibration energy distribution pattern and the corresponding critical grouting pressure range under different stratum combinations;

[0133] A generation module 33 aligns the vibration spectrum data of different areas of the cutterhead with the monitored values ​​of the soil bin pressure in time and space to generate a disturbance field distribution map, which includes an energy gradient distribution curve of the vibration field and a stress diffusion path topology of the soil;

[0134] A correction module 34 inputs the disturbance field distribution map and the vibration characteristic fingerprint into a feature matching network optimized by transfer learning, so as to perform spectral matching between the energy gradient distribution curve and the vibration energy distribution pattern through the feature matching network, and simultaneously corrects the propagation path parameters of the stratum interface transition zone based on the stress diffusion path topology, so as to output an identification result of the current stratum type and extract the disturbance propagation dynamic parameters;

[0135] The adjustment module 35 dynamically adjusts the synchronous grouting pressure threshold according to the mapping relationship between the disturbance propagation dynamic parameters and the critical grouting pressure range in the vibration characteristic fingerprint, combined with the surface displacement monitoring data, generates a graded early warning signal and a grouting parameter adjustment instruction, and completes the closed-loop control of the formation disturbance.

[0136] Figure 3 The ground disturbance analysis system under the coupling effect of shield construction can perform Figure 1 The implementation principles and technical effects of the method for analyzing ground disturbances coupled with shield construction described in the illustrated embodiment are not further elaborated. The specific manner in which each module and unit performs operations in the system for analyzing ground disturbances coupled with shield construction in the aforementioned embodiment has been described in detail in the related embodiments and will not be further elaborated here.

[0137] In one possible design, Figure 3 The ground disturbance analysis system under the coupling effect of shield construction in the embodiment shown can be realized as a computing device, such as Figure 4 As shown, the computing device may include a storage component 41 and a processing component 42;

[0138] 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 .

[0139] The processing component 42 is used for the above Figure 1 The embodiment provides a method for analyzing stratum disturbance under the coupling effect of shield construction.

[0140] 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.

[0141] 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.

[0142] Of course, a computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0143] 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.

[0144] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0145] 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.

[0146] 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 embodiment shown is a method for analyzing stratum disturbance under the coupling effect of shield construction.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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 analyzing stratum disturbance under the coupling effect of shield construction, characterized in that: include: Vibration sensors placed on the cutterhead of the shield machine collect vibration spectrum data generated when the cutterhead cuts the soil. Based on the obtained soil plasticity index of the clay layer and the particle grading parameters of the gravel layer, a stratum characteristic atlas library was constructed. Combined with the soil shear modulus, groundwater permeability coefficient, and synchronous grouting pressure threshold, a vibration characteristic fingerprint was generated. The vibration characteristic fingerprint includes the vibration energy distribution pattern and the corresponding critical grouting pressure range under different stratum combinations; The vibration spectrum data of different areas of the cutterhead are aligned in time and space with the monitored values ​​of the soil bin pressure to generate a disturbance field distribution map, which includes the energy gradient distribution curve of the vibration field and the stress diffusion path topology of the soil; Inputting the disturbance field distribution map and the vibration characteristic fingerprint into a feature matching network optimized by transfer learning, so as to perform spectral matching between the energy gradient distribution curve and the vibration energy distribution pattern through the feature matching network, and simultaneously correcting the propagation path parameters of the stratum interface transition zone according to the stress diffusion path topology, so as to output the identification result of the current stratum type and extract the disturbance propagation dynamic parameters; According to the mapping relationship between the disturbance propagation dynamic parameters and the critical grouting pressure range in the vibration characteristic fingerprint, the synchronous grouting pressure threshold is dynamically adjusted in combination with the surface displacement monitoring data, and a graded early warning signal and grouting parameter adjustment instruction are generated to complete the closed-loop control of the formation disturbance.

2. The method according to claim 1, characterized in that The vibration spectrum data of different areas of the cutterhead are aligned with the monitored values ​​of the soil bin pressure in time and space to generate a disturbance field distribution map. The disturbance field distribution map includes the energy gradient distribution curve of the vibration field and the stress diffusion path topology of the soil, including: Based on the cutterhead rotation angle encoding signal and the spatial position information of the vibration monitoring points, a spatiotemporal alignment operation is performed on the vibration spectrum data of each area on the cutterhead surface and the soil bin pressure monitoring value to generate a spatiotemporally synchronized vibration and pressure joint dataset; Extract the vibration spectrum segment synchronized with the cutterhead rotation phase and the soil bin pressure mutation interval from the vibration-pressure joint data set, and establish a spatiotemporal correlation mapping relationship between vibration energy and pressure change; Based on the time-space correlation mapping relationship, the cumulative increment of vibration energy in each area within the cutterhead excavation section during continuous rotation cycles is calculated to generate a vibration energy gradient distribution curve representing the stratum disturbance intensity; Based on the spatial superposition relationship between the soil bin pressure fluctuation amplitude and the vibration energy gradient distribution curve, the stress concentration area of ​​the soil layer is identified and the stress diffusion direction is calibrated, and a stress diffusion topological network throughout the soil layer is generated. The vibration energy gradient distribution curve is fused with the stress diffusion topological network to form a disturbance field distribution map containing spatiotemporal correlation disturbance characteristics.

3. The method according to claim 1, characterized in that Based on the mapping relationship between the disturbance propagation dynamic parameters and the critical grouting pressure range in the vibration characteristic fingerprint, the synchronous grouting pressure threshold is dynamically adjusted in combination with the surface displacement monitoring data, and a graded early warning signal and grouting parameter adjustment instruction are generated to complete the closed-loop control of the formation disturbance, including: Determining a critical grouting pressure threshold range of a stratum interface transition zone based on a mapping relationship between the disturbance propagation dynamic parameter and the critical grouting pressure interval in the vibration characteristic fingerprint; Extracting the synchronous grouting benchmark pressure value corresponding to the current stratum combination from the stratum characteristic atlas library, and combining it with the instantaneous change of the surface settlement rate in the surface displacement monitoring data to generate a grouting pressure dynamic adjustment gradient table including a pressure fluctuation tolerance; The dynamic difference between the grouting pipe outlet pressure and the tunnel face support pressure is collected in real time, and the displacement transmission rate of the formation interface in the stress diffusion topology network is simultaneously monitored. When the dynamic difference exceeds the tolerance range of the grouting pressure dynamic adjustment gradient table or the displacement transmission rate exceeds the preset diffusion rate threshold, a multi-level warning signal is triggered according to the degree of excess. Based on the multi-level warning signal, the linked pressurization operation of the target grouting hole and its adjacent holes is activated, the surface displacement rebound and stress diffusion direction offset parameters after pressurization are simultaneously collected, and the grouting pressure compensation coefficient is calculated; According to the grouting pressure compensation coefficient, the critical grouting pressure threshold range is adjusted, and a grouting parameter adjustment instruction is generated and bound to the corresponding formation combination in the formation characteristic atlas library to form a closed-loop control link based on stress diffusion topology and surface displacement feedback.

4. The method according to claim 1, wherein Based on the obtained soil plasticity index of the clay layer and the particle grading parameters of the gravel layer, a stratum characteristic atlas library was constructed. Combined with the soil shear modulus, groundwater permeability coefficient, and synchronous grouting pressure threshold, a vibration characteristic fingerprint was generated. The vibration characteristic fingerprint contains the vibration energy distribution pattern and the corresponding critical grouting pressure range under different stratum combinations, including: Based on the obtained plasticity index threshold of the clay layer and the particle grading parameters of the gravel layer, the stratum unit is divided into the following categories: each stratum unit includes a shear modulus variation interval and a permeability coefficient stratification interval; By dynamically matching the real-time torque fluctuation data of the screw conveyor with the shear modulus variation range of the stratum unit, a real-time association rule between the mechanical load response and the soil shear modulus is established, and a compensation correction coefficient for the grouting pressure is generated based on the dynamic difference between the grouting pipe outlet pressure and the tunnel face support pressure; Integrate the compensation correction coefficient, permeability coefficient stratification interval and real-time association rules according to stratum units to construct a stratum characteristic atlas library including shear modulus association factors, grouting pressure compensation rules and permeability influencing parameters; Based on the plasticity index weight, particle gradation weight and grouting pressure gradient distribution of each unit in the formation characteristic atlas library, a vibration characteristic fingerprint including the vibration energy distribution pattern under different formation combinations and the corresponding critical grouting pressure range is generated.

5. The method according to claim 1, wherein The disturbance field distribution map and the vibration characteristic fingerprint are input into a feature matching network optimized by transfer learning, so as to perform spectral matching between the energy gradient distribution curve and the vibration energy distribution pattern through the feature matching network, and at the same time, the propagation path parameters of the stratum interface transition zone are corrected according to the stress diffusion path topology, so as to output the identification result of the current stratum type and extract the disturbance propagation dynamic parameters, including: The vibration energy gradient distribution curve in the disturbance field distribution map and the vibration energy distribution patterns of different stratum combinations in the vibration feature fingerprint are input into a feature matching network optimized by transfer learning. The frequency band energy proportion and waveform similarity of the energy distribution curve are spectrally matched by the feature matching network to generate a stratum type matching index. Extracting propagation path node parameters of the formation interface transition zone in the stress diffusion path topology, and correcting the propagation path node parameters of the transition zone based on the stress conduction direction offset angle and connection strength between the nodes; Correlating the modified propagation path node parameters with the formation type matching index, extracting the critical grouting pressure interval corresponding to the current formation combination from the vibration characteristic fingerprint, and generating a dynamic parameter set for disturbance propagation in the formation interface transition zone; According to the path offset and energy attenuation rate in the dynamic parameter set, the identification result of the current formation type is output and the disturbance propagation dynamic parameters are extracted.

6. The method according to claim 2, characterized in that Based on the spatial superposition relationship between the soil bin pressure fluctuation amplitude and the vibration energy gradient distribution curve, the stress concentration area of ​​the soil layer is identified and the stress diffusion direction is calibrated. The stress diffusion topological network throughout the soil layer is generated, including: Based on the spatial distribution consistency of the soil bin pressure fluctuation amplitude and the vibration energy gradient distribution curve within the cutterhead excavation section, the pressure energy superposition coefficient representing the combined effect strength of the pressure amplitude and energy gradient in each area is calculated. Screening the areas where the pressure-energy superposition coefficient exceeds a preset threshold, marking them as initial stress concentration areas, and extracting the energy gradient change slopes between adjacent initial stress concentration areas; Based on the directionality of the energy gradient change slope, the stress diffusion direction between the initial stress concentration areas is calibrated, and adjacent areas with the same direction are merged into stress conduction links; A stress diffusion topological network penetrating the soil layer is generated according to the attenuation rate of the pressure energy superposition coefficient in the stress conduction link and the link extension length.

7. The method according to claim 3, characterized in that Based on the multi-level warning signal, the linked pressurization operation of the target grouting hole and its adjacent holes is activated, the surface displacement rebound and stress diffusion direction offset parameters after pressurization are simultaneously collected, and the grouting pressure compensation coefficient is calculated, including: According to the level of the multi-level warning signal, the linkage boosting device of the target grouting hole and its adjacent holes is activated according to the preset priority, so that the grouting pressure of the target hole and the adjacent holes is synchronously increased to the preset boosting value; Simultaneously collect data on the surface displacement rebound and stress diffusion direction offset angle in the supercharging area. The surface displacement rebound is the difference between the surface uplift height after supercharging and the settlement before supercharging. The stress diffusion direction offset angle is the angle deviation between the actual conduction direction and the preset diffusion path. Calculating a displacement rebound compensation weight based on the ratio of the absolute value of the surface displacement rebound amount to a preset rebound expected value, and calculating a direction offset correction factor based on the difference ratio between the stress diffusion direction offset angle and the allowable offset angle threshold; The displacement rebound compensation weight and the direction offset correction factor are weighted and superimposed to generate a grouting pressure compensation coefficient for quantifying the correction of the formation disturbance suppression effect caused by the linked boosting operation.

8. A system for analyzing ground disturbance under the coupling effect of shield construction, characterized in that: include: The acquisition module collects vibration spectrum data generated when the cutterhead cuts soil through vibration sensors arranged on the surface of the shield machine cutterhead; A construction module builds a stratum characteristic atlas based on the obtained soil plasticity index of the clay layer and the particle grading parameters of the gravel layer. Combined with the soil shear modulus, groundwater permeability coefficient, and synchronous grouting pressure threshold, it generates a vibration characteristic fingerprint. The vibration characteristic fingerprint includes the vibration energy distribution pattern and the corresponding critical grouting pressure range under different stratum combinations; a generation module that aligns the vibration spectrum data of different areas of the cutterhead with the monitored values ​​of the soil bin pressure in time and space to generate a disturbance field distribution map, wherein the disturbance field distribution map includes an energy gradient distribution curve of the vibration field and a stress diffusion path topology of the soil; a correction module, inputting the disturbance field distribution map and the vibration characteristic fingerprint into a feature matching network optimized by transfer learning, so as to perform spectral matching between the energy gradient distribution curve and the vibration energy distribution pattern through the feature matching network, and simultaneously correcting the propagation path parameters of the stratum interface transition zone according to the stress diffusion path topology, so as to output an identification result of the current stratum type and extract the disturbance propagation dynamic parameters; The adjustment module dynamically adjusts the synchronous grouting pressure threshold according to the mapping relationship between the disturbance propagation dynamic parameters and the critical grouting pressure range in the vibration characteristic fingerprint, combined with the surface displacement monitoring data, generates a graded early warning signal and grouting parameter adjustment instructions, and completes the closed-loop control of the formation disturbance.

9. A computing device, characterized in that It comprises 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 analyzing stratum disturbance under the coupling action of shield construction as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that A computer program is stored, and when the computer program is executed by a computer, a method for analyzing stratum disturbance under the coupling effect of shield construction as described in any one of claims 1 to 7 is implemented.

Images