Intelligent Prediction and Control Method and System for Tunnel Multi-Source Fusion Dynamic Twin Surrounding Rock

Abstract

The present invention discloses a method and system for intelligent prediction and control of tunnel surrounding rock using multi-source fusion dynamic twinning. The method comprises: real-time acquisition of multi-source heterogeneous data through intelligent drilling equipment, distributed fiber-optic sensor networks, and mobile scanning devices deployed at the tunnel construction surface; inputting the multi-source heterogeneous data into a spatiotemporal graph convolutional network to construct a spatiotemporal correlation model between geological characteristics and construction disturbance parameters, and outputting a coupled feature matrix; based on the coupled feature matrix, simulating the dynamic response of the surrounding rock and support system through a streaming voxelization engine and a multi-physics field coupling engine to generate a three-dimensional heat map of risk evolution; and inputting the three-dimensional heat map of risk evolution into a deep reinforcement learning model to dynamically optimize and generate construction parameter control instructions that meet safety constraints. The present invention's closed-loop technology opens up a full-link channel from "data perception, mechanical analysis, and decision execution," thereby avoiding the dual risks of "data distortion and misjudgment" and "response lag and loss of control" associated with traditional methods.

Description

Technical Field

[0001] This application relates to the technical field of tunnel engineering, and particularly to a method and system for intelligent prediction and control of tunnel multi-source fusion dynamic twin surrounding rock. Background Art

[0002] In the process of tunnel engineering intelligentization, the dynamic perception of surrounding rock state and precise construction control have always been core problems. As tunnels extend into deep and complex geological environments, traditional methods have gradually revealed systematic limitations: on the one hand, due to the strong coupling characteristics of multi-source monitoring data (such as acoustic waves, deformation, and vibration signals) with geological structures and construction disturbances, it is difficult to achieve effective fusion in dynamic scenarios, resulting in the accumulation of deviation in the interpretation of the mechanical state of the surrounding rock; on the other hand, existing numerical models are limited by static calculation frameworks and cannot synchronously map the non-linear response of the surrounding rock caused by the operation of tunneling machines, resulting in significant lags in support decision-making and risk prevention and control. Summary of the Invention

[0003] To solve the above problems, an embodiment of the present invention provides a method for intelligent prediction and control of tunnel multi-source fusion dynamic twin surrounding rock, the method comprising:

[0004] Real-time collecting multi-source heterogeneous data through intelligent drilling equipment, distributed optical fiber sensing networks, and mobile scanning devices deployed on the tunnel construction surface;

[0005] Inputting the multi-source heterogeneous data into a spatio-temporal graph convolutional network to construct a spatio-temporal correlation model of geological features and construction disturbance parameters, and outputting a coupling feature matrix;

[0006] Based on the coupling feature matrix, simulating the dynamic response of the surrounding rock-support system through a streaming voxelization engine and a multi-physics field coupling engine to generate a three-dimensional heat map of risk evolution;

[0007] Inputting the three-dimensional heat map of risk evolution into a deep reinforcement learning model to dynamically optimize and generate construction parameter regulation instructions that meet safety constraint conditions.

[0008] Further, the intelligent drilling equipment includes an axial thrust detection module and a rock acoustic wave feature acquisition module; the distributed optical fiber sensing network is arranged along the tunnel excavation direction and includes a temperature-compensated strain sensing unit; the mobile scanning device uses a multi-line lidar to realize the three-dimensional point cloud reconstruction of the construction surface.

[0009] Further, the construction method of the spatio-temporal graph convolutional network includes:

[0010] Mapping the distribution of structural planes in geological exploration data into the spatial topological relationship of the graph structure;

[0011] Using a time convolutional layer to extract the temporal propagation characteristics of construction machinery vibration parameters;

[0012] Fusing the correlation weight distribution of geological parameters and construction parameters through a multi-head attention mechanism.

[0013] Furthermore, the streaming voxelization engine dynamically adjusts the computational grid resolution according to the surrounding rock stress gradient; the multi-physics coupling engine includes an interaction interface between the discrete element module and the fluid dynamics module; the risk evolution three-dimensional thermal map includes a plastic strain distribution layer and a support stress warning layer.

[0014] Furthermore, the real-time calibration operation includes:

[0015] Dynamically comparing the surrounding rock strain data monitored by the distributed optical fiber sensing network with the simulated strain values in the risk evolution three-dimensional thermal map;

[0016] When the deviation between the monitored data and the simulated data exceeds the preset threshold, triggering the weight retraining mechanism of the spatio-temporal graph convolutional network;

[0017] Based on the updated coupled feature matrix, correcting the constitutive model parameters of the multi-physics coupling engine.

[0018] Furthermore, the action space of the deep reinforcement learning model is defined as a set of continuous construction control parameters, mapping the construction control parameters into a high-dimensional continuous action vector; compressing the construction parameter regulation instructions into the standardized space of [-1, 1], and adopting the double-delayed deep deterministic policy gradient algorithm;

[0019] The safety constraint conditions include the surrounding rock convergence threshold and the bearing safety factor of the support structure;

[0020] The construction parameter regulation instructions include a tunneling rate adjustment instruction and a support timing optimization instruction;

[0021] The generation method of the construction parameter regulation instructions includes:

[0022] Based on the coupled feature matrix, the output layer of the policy network adopts a branch structure to generate construction parameter regulation instructions. The generation method of the construction parameter regulation instructions includes:

[0023] The tunneling rate instruction is processed by a time series smoothing algorithm to limit the speed adjustment amplitude within adjacent decision cycles;

[0024] The support timing instruction is realized through an event trigger mechanism. When the rock mass damage factor exceeds the critical value, a multi-level support collaborative deployment plan is started; the multi-level support collaborative deployment plan includes primary support, secondary support and tertiary support.

[0025] Furthermore, it also includes:

[0026] Filtering and noise reduction processing of the collected multi-source heterogeneous data through edge computing nodes;

[0027] Synchronously update the dynamic mapping relationship between the physical tunnel and the virtual model based on the digital twin platform;

[0028] Deviation analysis of real-time monitoring data and simulation prediction results is superimposed and displayed in the visual interface.

[0029] Tunnel multi-source fusion dynamic twin surrounding rock intelligent prediction and control system, the system includes:

[0030] Synchronous perception module, which collects multi-source heterogeneous data in real time through intelligent drilling equipment, distributed fiber optic sensor networks, and mobile scanning devices deployed on the tunnel construction surface;

[0031] Feature extraction module: The feature extraction module inputs multi-source heterogeneous data into the spatiotemporal graph convolutional network, constructs a spatiotemporal correlation model between geological characteristics and construction disturbance parameters, and outputs a coupling feature matrix;

[0032] Dynamic simulation module: Based on the coupling characteristic matrix, the dynamic simulation module simulates the dynamic response of the surrounding rock-support system through the fluid voxelization engine and the multi-physics field coupling engine, and generates a three-dimensional thermal map of risk evolution;

[0033] Intelligent decision-making module: The intelligent decision-making module inputs the three-dimensional heat map of risk evolution into the deep reinforcement learning model, and dynamically optimizes and generates construction parameter control instructions that meet safety constraints.

[0034] The technical effects and advantages of the tunnel multi-source fusion dynamic twin surrounding rock intelligent prediction and control method and system provided by the present invention are as follows:

[0035] The technical closed loop of the present invention opens up a full-link real-time channel of "data perception-mechanical analysis-decision execution", providing an intelligent control paradigm with both robustness and sensitivity for complex geological tunnel construction, and fundamentally avoiding the dual risks of "data distortion and misjudgment" and "response lag and loss of control" in traditional methods; the present invention addresses the feature interference problem under the coupling of geology and construction, and uses a dynamic feature decoupling algorithm to separate construction disturbances and geological intrinsic responses in multimodal data such as sound wave attenuation, deformation rate, and vibration spectrum, breaking the feature confusion caused by time sequence dislocation and spatial superposition in traditional methods, and improving the accuracy of surrounding rock crack development judgment; based on the dynamic numerical modeling technology driven by streaming data, a millisecond-level bidirectional mapping channel of surrounding rock stress-seepage field and excavation parameters is established, and real-time working condition parameters such as tool penetration and support reaction force are synchronously integrated, compressing the minute-level delay of traditional offline modeling to the construction beat synchronization level, realizing seamless connection between advanced warning and dynamic parameter adjustment. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 This is a flow chart of the tunnel multi-source fusion dynamic twin surrounding rock intelligent prediction and control method in Example 1;

[0037] Figure 2 It is the flow chart of the intelligent prediction and control method for the tunnel multi-source fusion dynamic twin surrounding rock in Embodiment 2;

[0038] Figure 3 It is the schematic connection diagram of the tunnel multi-source fusion dynamic twin surrounding rock intelligent prediction and control system in Embodiment 3. Detailed implementation manners

[0039] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0040] Embodiment 1: Please refer to Figure 1 As shown, the embodiment of the present invention provides an intelligent prediction and control method for tunnel multi-source fusion dynamic twin surrounding rock, and the method includes:

[0041] Real-time collection of multi-source heterogeneous data through intelligent drilling equipment, distributed optical fiber sensing network and mobile scanning device deployed on the tunnel construction surface;

[0042] Input the multi-source heterogeneous data into the spatio-temporal graph convolutional network, construct a spatio-temporal correlation model of geological features and construction disturbance parameters, and output a coupled feature matrix;

[0043] Based on the coupled feature matrix, simulate the dynamic response of the surrounding rock-support system through a streaming voxelization engine and a multi-physics field coupling engine to generate a three-dimensional thermal map of risk evolution;

[0044] Input the three-dimensional thermal map of risk evolution into the deep reinforcement learning model, and dynamically optimize and generate construction parameter adjustment instructions that meet the safety constraint conditions.

[0045] The multi-source heterogeneous data includes geological structure parameters, surrounding rock deformation data and three-dimensional spatial form data;

[0046] The intelligent drilling equipment includes an axial thrust detection module and a rock acoustic wave feature acquisition module; the distributed optical fiber sensing network is arranged along the tunnel excavation direction and includes a temperature-compensated strain sensing unit; the mobile scanning device uses a multi-line lidar to realize the three-dimensional point cloud reconstruction of the construction surface.

[0047] The data acquisition link realizes collaborative perception through three types of core equipment;

[0048] As the core device for geological structure detection, the intelligent drilling equipment is equipped with an axial thrust detection module that can monitor the dynamic resistance changes during the drill pipe propulsion in real time. At the same time, through the rock acoustic wave feature acquisition module, it conducts time-frequency domain analysis on the acoustic wave signals generated during the drilling operation. Based on the acoustic wave propagation speed, energy attenuation characteristics, and main frequency shift rules, it comprehensively judges the distribution of rock mass fissures and the structural stability.

[0049] The distributed optical fiber sensing network is continuously arranged along the tunneling direction of the tunnel construction surface. Its temperature-compensated strain sensing unit adopts a dual-core optical fiber architecture. Among them, the main core optical fiber is used to measure the strain distribution of the surrounding rock, and the auxiliary core optical fiber eliminates the influence of environmental temperature fluctuations on the measurement results through thermal isolation packaging technology, achieving a deformation monitoring accuracy at the micro-strain level.

[0050] The mobile scanning device is equipped with a multi-line lidar module. Based on the time-of-flight ranging principle, it conducts three-dimensional space scanning on the construction surface. Through an unevenly distributed laser beam array and a high-frequency scanning mechanism, it obtains high-density point cloud data. Combining with the SLAM (Simultaneous Localization and Mapping) algorithm, it realizes the dynamic reconstruction of the three-dimensional shape of the construction surface, providing a spatial reference with sub-centimeter-level accuracy for the convergence analysis of the surrounding rock.

[0051] The three types of devices achieve the alignment of data acquisition time sequences through a unified time-domain synchronization protocol, ensuring the spatio-temporal consistency of geological parameters, deformation data, and spatial form information.

[0052] The construction method of the spatio-temporal graph convolutional network includes:

[0053] Mapping the distribution of structural planes in geological exploration data into the spatial topological relationship of the graph structure;

[0054] Using a time convolutional layer to extract the time sequence propagation characteristics of construction machinery vibration parameters;

[0055] Fusing the correlation weight distribution of geological parameters and construction parameters through a multi-head attention mechanism.

[0056] In the construction of the spatio-temporal correlation model, first, based on the distribution characteristics of structural planes (including fissures, joints, and bedding planes) in geological exploration data, a spatial topological graph structure is established.

[0057] [[ID=2,7]]Specifically, taking the spatial proximity and attitude similarity between adjacent structural planes as edge weights, and taking the geometric center of the structural plane as the graph node, an initial graph model reflecting the spatial correlation of geological structures is constructed. On this basis, for dynamic disturbance parameters such as construction machinery vibration and support stress loading, a stacked time convolutional layer is used to extract features from time sequence data, and a dilated convolutional kernel cross-layer connection structure is used to capture the long-range time sequence dependence relationships of parameters such as vibration acceleration and energy spectral density.

[0058] Furthermore, the multi-head attention mechanism is introduced to map geological parameters (such as rock mass strength and joint density) and construction parameters (such as tunneling speed and grouting pressure) into multiple groups of independent feature subspaces. By calculating the mutual information correlation degree between different parameters in parallel, a geological-construction coupling feature weight matrix is generated.

[0059] Finally, through graph convolution operation, the spatio-temporal features and the weight matrix are fused to output a coupling feature matrix including the evolution law of geological conditions and the propagation characteristics of construction disturbances, providing a high-dimensional feature representation for subsequent mechanical response simulation.

[0060] During the generation process of the three-dimensional thermal map of risk evolution, the streaming voxelization engine dynamically adjusts the calculation grid resolution according to the surrounding rock stress gradient;

[0061] The multi-physics coupling engine includes the interaction interface between the discrete element module and the fluid dynamics module;

[0062] The three-dimensional thermal map of risk evolution includes a plastic strain distribution layer and a support stress warning layer.

[0063] Based on the real-time updated surrounding rock stress gradient field, the streaming voxelization engine dynamically reconstructs the calculation grid using an octree structure. Specifically, when the local stress gradient value exceeds a preset threshold (e.g., > 2 MPa / m), the grid encryption mechanism is triggered, and the basic grid is recursively subdivided to a resolution of 0.125 m³. In the area where the stress gradient change rate exceeds 5% / min, the anisotropic subdivision mode is enabled to ensure that the aspect ratio of the grid in the crack propagation direction is controlled within 3:1. At the same time, a virtual buffer layer is used to achieve a smooth transition between grids with different resolutions, avoiding numerical oscillations.

[0064] The multi-physics coupling engine realizes cross-scale interaction through a discrete element-fluid dynamics bidirectional coupling interface. The discrete element module uses the Hertz-Mindlin contact model to simulate the particle motion of jointed rock masses and outputs the change matrix of the porosity in the fracture zone in real time; the fluid dynamics module calculates the fracture seepage field based on the Brinkman equation and feeds back the permeability tensor to the discrete element system through a custom field mapping protocol. The two adopt an asynchronous time-step coupling strategy and achieve cross-time-scale data synchronization through the momentum interpolation algorithm.

[0065] The three-dimensional thermal map of risk evolution integrates the plastic strain field and the support monitoring data through a feature fusion algorithm: the plastic strain distribution layer calculates the equivalent plastic strain using the J2 flow criterion and maps the strain value in the HSV color space (red corresponds to the critical failure area > 5%); the support stress warning layer fuses multi-source data such as bolt axial force and lining concrete strain through a Bayesian probability model. When the local support stress exceeds 80% of the material yield strength, a radial warning halo is generated, and the halo radius R and the overrun degree Δσ satisfy:

[0066] R = 0.2Δσ 1.5 (Unit: m), to achieve the visual expression of the spatio-temporal cumulative effect of the risk situation.

[0067] During the generation process of the three-dimensional thermal map of risk evolution, real-time calibration operations are required, and the real-time calibration operations include:

[0068] Dynamically compare the surrounding rock strain data real-time monitored by the distributed optical fiber sensing network with the simulated strain values in the three-dimensional thermal map of risk evolution;

[0069] Through the streaming data processing pipeline, spatio-temporal registration is performed on the time series signal of the surrounding rock strain collected by the distributed optical fiber sensing network and the simulated strain field output by the three-dimensional thermal map of risk evolution; the feature space projection algorithm is used to calculate the vector similarity between the multi-dimensional strain tensors (including axial strain and shear strain components) at the monitoring points and the simulated values of the corresponding spatial coordinates, and a difference field distribution matrix with time scale alignment characteristics is generated.

[0070] When the deviation between the monitoring data and the simulated data exceeds the preset threshold, trigger the weight retraining mechanism of the spatio-temporal graph convolutional network;

[0071] When the statistical deviation (including root mean square error and peak-valley offset) between the monitoring value and the simulated value exceeds the preset dynamic threshold, activate the online learning module of the spatio-temporal graph convolutional network. By constructing a mixed training set including real-time monitoring data augmented samples, an incremental retraining is performed on the multi-head attention weights and graph convolutional kernel parameters in the network, and the associated dimensions of the geological-construction coupling feature matrix are updated synchronously;

[0072] Based on the updated coupling feature matrix, correct the constitutive model parameters of the multi-physical field coupling engine;

[0073] Input the updated coupling feature matrix into the parameter optimizer of the multi-physical field coupling engine. Based on the tensor decomposition method, extract the rock mass damage evolution characteristics and the fluid-solid coupling action mode. By constructing an implicit mapping relationship between the constitutive equation parameters and the high-dimensional features, adopt a non-intrusive correction strategy to dynamically adjust the key parameters such as the hardening modulus and permeability coupling coefficient in the elastoplastic constitutive model, and form a model self-evolution mechanism driven by monitoring data.

[0074] ]Achieve millisecond-level response through the microservice architecture to ensure the dynamic consistency between the numerical model and the physical reality.

[0075] The action space of the deep reinforcement learning model is defined as a set of continuous construction control parameters;

[0076] Map construction control parameters to a high-dimensional continuous action vector, including adjustable variables such as the propulsion speed of the tunneling system, the torque distribution ratio of the cutterhead, and the activation time window of temporary support; compress the construction parameter regulation instructions to the standardized space of [-1, 1], and use the Twin Delayed Deep Deterministic Policy Gradient algorithm (TD3) to achieve action noise suppression and strategy stability improvement.

[0077] Safety constraint conditions include the surrounding rock convergence threshold and the bearing safety factor of the support structure;

[0078] Fuse the real-time monitoring data of the surrounding rock convergence rate and the stress-strain relationship matrix of the support structure in the state observation space to construct a constraint violation degree evaluation function; when the monitoring data approaches the convergence threshold, dynamically adjust the exploration boundary of the policy network by the Lagrange multiplier method, and at the same time introduce a quadratic penalty term in the reward function to suppress the action strategy that may lead to the degradation of the support safety factor.

[0079] Construction parameter regulation instructions include tunneling rate adjustment instructions and support timing optimization instructions;

[0080] The generation method of construction parameter regulation instructions includes:

[0081] Based on the coupled feature matrix, the output layer of the policy network uses a branch structure to generate construction parameter regulation instructions. The generation method of construction parameter regulation instructions includes:

[0082] The tunneling rate instruction is processed by a time series smoothing algorithm to limit the speed adjustment amplitude within adjacent decision cycles;

[0083] The support timing instruction is realized through an event trigger mechanism. When the rock mass damage factor exceeds the critical value, a multi-level support collaborative deployment plan is started; the multi-level support collaborative deployment plan includes primary support, secondary support, and tertiary support;

[0084] Primary support: Adopt a flexible support of shotcrete + short bolts, and quickly construct it within 30 minutes after the tunneling face is exposed to control the initial deformation of the surrounding rock (such as automatically triggering the shotcrete operation of the robotic arm when the fiber optic monitors 0.15% strain);

[0085] Secondary support: Arrange a rigid support of steel arch + long cable bolts, start it after the face advances 5 times the tunnel diameter, and dynamically adjust the cable bolt tension through prestress monitoring (such as activating 2,000 kN-class prestressed cable bolts when the convergence rate > 2 mm / d)

[0086] Tertiary support: Set a permanent support of reinforced concrete lining + grouting reinforcement, and determine the best construction timing according to the long-term deformation trend pre-acted by the BIM model.

[0087] The multi-level support collaborative deployment includes spatial collaboration, temporal collaboration, and mechanical collaboration;

[0088] Spatial coordination: Achieve the stiffness matching of different support layers through the support parameter mapping matrix (for example, the thickness h of shotcrete and the bolt spacing s satisfy the stiffness coupling condition of h / s ≤ 0.3);

[0089] Temporal coordination: Establish a support activation time window function to ensure that the construction interval between adjacent support layers satisfies the surrounding rock creep equation (critical creep time);

[0090] Mechanical coordination: Use a distributed fiber optic sensing network to monitor the internal force redistribution of the support structure in real time, and adjust the load sharing ratio of each support layer through a PID controller.

[0091] After the control instruction is generated, the physical constraint verification module filters out abnormal outputs that violate the equipment operating conditions boundary to ensure the executability of the instruction.

[0092] Embodiment 2: As Figure 2 shown, this embodiment further improves the design on the basis of Embodiment 1. The difference is that in the actual operation of Embodiment 1, it is found that there are high-frequency noise interferences in the original monitoring data, resulting in feature extraction deviation, and there is a time-delay effect in the dynamic mapping between the virtual model and the physical entity, which will cause system prediction inaccuracy and decision-making lag, and ultimately lead to the failure of surrounding rock deformation control and a doubling of the tunnel construction safety risk. Based on this, the intelligent prediction and control method for the tunnel multi-source fusion dynamic twin surrounding rock also includes:

[0093] Perform filtering and noise reduction processing on the multi-source heterogeneous data (geological structure parameters, surrounding rock deformation data, and three-dimensional spatial form data) collected by the edge computing node;

[0094] Synchronously update the dynamic mapping relationship between the physical tunnel and the virtual model based on the digital twin platform;

[0095] Overlay and display the deviation analysis of the real-time monitoring data and the simulation prediction results in the visualization interface.

[0096] In the specific implementation process of the tunnel intelligent construction system, through the deep integration of edge computing and digital twin technology, a full-chain closed-loop control system from data collection to decision support is constructed. The core implementation process of this system is as follows:

[0097] During the data preprocessing phase, edge computing devices (miniaturized computing units deployed on-site) are deployed at key nodes along the tunnel to clean the multi-source, heterogeneous data collected by the shield machine's sensors in real time. Adaptive filtering algorithms are used to eliminate signal noise caused by mechanical vibration. For example, wavelet transforms are used to isolate the effective signal components from high-frequency interference in cutterhead torque monitoring data. A sliding time window statistical detection mechanism is also implemented. If statistically significant fluctuations in pressure sensor readings (exceeding three standard deviations) are detected, data recollection is automatically triggered to ensure the reliability of the input data.

[0098] During the model dynamic mapping phase, a virtual-reality synchronization mechanism for the tunnel project is established based on digital twin technology (a technique that mirrors the state of a physical entity through a virtual model). A high-fidelity three-dimensional model, including the surrounding rock structure, support system, and construction machinery, is constructed in virtual space. The stress-strain relationship of the rock and soil is described using an elastoplastic constitutive model, and the support structure simulates its coordinated deformation characteristics using beam-shell coupling elements. The system receives pre-processed data from the field at specific intervals and dynamically corrects the geomechanical parameters in the model using an inverse parameter identification algorithm. When there is a significant deviation between the monitoring data and the simulated predicted values, adaptive mesh encryption technology is used to reconstruct the local model of key areas. For example, when constructing in a soft rock area, the virtual model automatically adjusts the rock mass Poisson's ratio parameter to improve the settlement prediction accuracy to within the project's allowable error range.

[0099] During the visualization interaction stage, a three-dimensional visualization platform was developed to realize the spatial integration display of multi-source information. The platform aligns the real-time monitoring data stream (such as shield thrust pressure, segment displacement, etc.) with the digital twin simulation results in time and space, and uses color mapping technology to generate a thermal map superposition display of the surrounding rock stress field; the system has a built-in deviation analysis module, which calculates the relative error matrix between the measured values and the simulated values, and marks abnormal areas with pulsed halos on the surface of the tunnel model; engineers can use interactive cutting tools to compare the actual deformation curve of any section with the predicted trend line. When a systematic deviation in the stress distribution of the support structure is identified (for example, a monitoring found that the deviation in the arch area continued to exceed 25%), the system automatically pushes a grouting reinforcement proposal.

[0100] Example 3: Figure 3 As shown, based on the same inventive concept as the tunnel multi-source fusion dynamic twin surrounding rock intelligent prediction and control method in the aforementioned embodiment, this application provides a tunnel multi-source fusion dynamic twin surrounding rock intelligent prediction and control system. The system and method embodiments in the embodiments of this application are based on the same inventive concept. Among them, the system includes:

[0101] Synchronous perception module. The synchronous perception module collects multi-source heterogeneous data in real time through intelligent drilling equipment, distributed optical fiber sensing networks, and mobile scanning devices deployed on the tunnel construction surface;

[0102] Feature extraction module. The feature extraction module inputs the multi-source heterogeneous data into a spatio-temporal graph convolutional network, constructs a spatio-temporal correlation model of geological features and construction disturbance parameters, and outputs a coupled feature matrix;

[0103] Dynamic simulation module. The dynamic simulation module, based on the coupled feature matrix, simulates the dynamic response of the surrounding rock-support system through a streaming voxelization engine and a multi-physics field coupling engine, and generates a three-dimensional thermal map of risk evolution;

[0104] Intelligent decision-making module. The intelligent decision-making module inputs the three-dimensional thermal map of risk evolution into a deep reinforcement learning model, and dynamically optimizes and generates construction parameter regulation instructions that meet the safety constraint conditions.

[0105] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these changes and modifications.

[0106] The above are only the preferred specific embodiments of the embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed in the present application, according to the technical solution and its concept of the present application, makes equivalent substitutions or changes, and should be covered by the protection scope of the present application.

Claims

1. Tunnel multi-source fusion dynamic twin surrounding rock intelligent prediction and control method, characterized in that Including: Real-time collection of multi-source heterogeneous data through intelligent drilling equipment, distributed optical fiber sensing network and mobile scanning device deployed on the tunnel construction face; Input the multi-source heterogeneous data into the spatio-temporal graph convolutional network, construct the spatio-temporal correlation model of geological features and construction disturbance parameters, and output the coupled feature matrix; Based on the coupled feature matrix, simulate the dynamic response of the surrounding rock-support system through the streaming voxelization engine and the multi-physics field coupling engine, and generate a three-dimensional thermal map of risk evolution; The streaming voxelization engine dynamically adjusts the calculation grid resolution according to the surrounding rock stress gradient; The multi-physics field coupling engine includes an interaction interface between the discrete element module and the fluid dynamics module; the three-dimensional thermal map of risk evolution includes a plastic strain distribution layer and a support stress warning layer. During the generation process of the three-dimensional thermal map of risk evolution, real-time calibration operations are required, and the real-time calibration operations include: Dynamically compare the surrounding rock strain data monitored by the distributed optical fiber sensing network with the simulated strain values in the three-dimensional thermal map of risk evolution; When the deviation between the monitored data and the simulated data exceeds the preset threshold, trigger the weight retraining mechanism of the spatio-temporal graph convolutional network; Based on the updated coupled feature matrix, correct the constitutive model parameters of the multi-physics field coupling engine; Input the three-dimensional thermal map of risk evolution into the deep reinforcement learning model, and dynamically optimize to generate construction parameter regulation instructions that meet the safety constraint conditions.

2. The method according to claim 1, wherein The intelligent drilling equipment includes an axial thrust detection module and a rock acoustic wave feature acquisition module; the distributed optical fiber sensing network is arranged along the tunnel driving direction and includes a temperature compensation type strain sensing unit; the mobile scanning device uses a multi-line lidar to realize the three-dimensional point cloud reconstruction of the construction face.

3. The method according to claim 1, wherein The construction method of the spatio-temporal graph convolutional network includes: Map the structural plane distribution in the geological exploration data into the spatial topological relationship of the graph structure; Adopt a time convolutional layer to extract the time series propagation characteristics of the construction machinery vibration parameters; Fuse the correlation weight distribution of geological parameters and construction parameters through a multi-head attention mechanism.

4. The method according to claim 1, wherein The action space of the deep reinforcement learning model is defined as a set of continuous construction control parameters, map the construction control parameters into a high-dimensional continuous action vector; compress the construction parameter regulation instructions to the standardized space of [-1, 1], and adopt the double-delay deep deterministic policy gradient algorithm; The safety constraint conditions include the surrounding rock convergence threshold and the bearing safety factor of the support structure; The construction parameter regulation instructions include a tunneling rate adjustment instruction and a support timing optimization instruction; The generation method of the construction parameter regulation instructions includes: Based on the coupled feature matrix, the output layer of the policy network adopts a branch structure to generate construction parameter regulation instructions. The generation method of the construction parameter regulation instructions includes: The tunneling rate instruction is processed by a time series smoothing algorithm to limit the speed adjustment amplitude within adjacent decision cycles; The support timing instruction is realized through an event trigger mechanism. When the rock mass damage factor exceeds the critical value, start the multi-level support collaborative deployment plan; the multi-level support collaborative deployment plan includes primary support, secondary support and tertiary support.

5. The method according to claim 1, wherein Also including: Filter and denoise the collected multi-source heterogeneous data through an edge computing node; Synchronously update the dynamic mapping relationship between the physical tunnel and the virtual model based on the digital twin platform; Overlay and display the deviation analysis of real-time monitoring data and simulation prediction results in the visualization interface.

6. Tunnel multi-source fusion dynamic twin surrounding rock intelligent prediction and control system, characterized in that, The system includes: A synchronous perception module that collects multi-source heterogeneous data in real time through intelligent drilling equipment, distributed optical fiber sensing networks, and mobile scanning devices deployed on the tunnel construction surface; A feature extraction module that inputs the multi-source heterogeneous data into a spatio-temporal graph convolutional network, constructs a spatio-temporal correlation model of geological features and construction disturbance parameters, and outputs a coupled feature matrix; A dynamic simulation module that, based on the coupled feature matrix, simulates the dynamic response of the surrounding rock-support system through a streaming voxelization engine and a multi-physics field coupling engine to generate a three-dimensional thermal map of risk evolution; the streaming voxelization engine dynamically adjusts the calculation grid resolution according to the surrounding rock stress gradient; the multi-physics field coupling engine includes an interaction interface between a discrete element module and a fluid dynamics module; the three-dimensional thermal map of risk evolution includes a plastic strain distribution layer and a support stress warning layer, and real-time calibration operations are required during the generation of the three-dimensional thermal map of risk evolution. The real-time calibration operations include: Dynamically compare the surrounding rock strain data monitored in real time by the distributed optical fiber sensing network with the simulated strain values in the three-dimensional thermal map of risk evolution; When the deviation between the monitoring data and the simulation data exceeds a preset threshold, trigger the weight retraining mechanism of the spatio-temporal graph convolutional network; Based on the updated coupled feature matrix, correct the constitutive model parameters of the multi-physics field coupling engine; An intelligent decision-making module that inputs the three-dimensional thermal map of risk evolution into a deep reinforcement learning model and dynamically optimizes to generate construction parameter regulation instructions that meet safety constraint conditions.

Images