Three-dimensional tunnel gushing water analysis method and system based on autonomous controllability

Abstract

The invention relates to the technical field of tunnel engineering safety monitoring, in particular to an autonomous controllable three-dimensional tunnel gushing analysis method and system. The method comprises the following steps: collecting multi-source heterogeneous geological, hydrological and construction data, fusing to obtain multi-source heterogeneous data, and constructing a dynamically updated three-dimensional geological-construction coupling digital twinborn model after alignment coding; carrying out multi-scale physical-AI hybrid modeling, correcting real-time data, carrying out water gushing evolution rolling prediction, and outputting prediction data; a three-dimensional visual platform is constructed, and multi-level linkage early warning is started based on a risk threshold value; the system comprises a data fusion module, a water gushing evolution rolling prediction module and a multi-stage linkage early warning module. By fusing geological data, hydrological monitoring data and construction parameters and combining three-dimensional visual rendering and deep learning fluid simulation technologies, the requirements for rapid early warning and timely decision making of water burst disasters in the tunnel construction process are met, and intelligent support is provided for engineering disaster prevention decision making.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of tunnel engineering safety monitoring, in particular to a three-dimensional tunnel water gushing analysis method and system based on autonomous control. BACKGROUND

[0002] In the field of tunnel engineering construction, water gushing disaster is a key problem that has long plagued construction safety and engineering progress. With the continuous advancement of transportation, energy and other infrastructure construction, tunnel engineering is developing in the direction of deeper, longer and more complex geological conditions, which significantly increases the frequency and severity of water gushing disasters. Once water gushing occurs, it may not only cause equipment in the tunnel to be flooded, construction to be interrupted, and cause significant economic losses, but also may cause serious consequences such as personnel casualties, and may also cause irreversible damage to the surrounding ecological environment. Therefore, accurately predicting and effectively preventing tunnel water gushing disasters is of great significance to ensure the safe construction and long-term stable operation of tunnel engineering.

[0003] Currently, in existing tunnel water gushing analysis, the time for a single simulation can be shortened to within half an hour, but under actual complex geological conditions, especially when large-scale geological models and detailed hydrological simulations are involved, the time for a single simulation is still relatively long. For example, for some large tunnel projects, the geological model contains a large number of geological units and complex geological structures, and the hydrological model needs to consider complex water flow motion equations and boundary conditions, and a complete water gushing simulation may take several hours or even several days. This seriously affects the real-time performance of tunnel water gushing analysis and cannot meet the needs of rapid warning and timely decision-making for water gushing disasters during tunnel construction. SUMMARY

[0004] The purpose of the present application is to provide a three-dimensional tunnel water gushing analysis method and system based on autonomous control, which aims to meet the needs of rapid warning and timely decision-making for water gushing disasters during tunnel construction.

[0005] To achieve the above-mentioned purpose, a three-dimensional tunnel water gushing analysis method based on autonomous control is adopted, which includes the following steps: Collecting multi-source heterogeneous geological, hydrological and construction data, fusing to obtain multi-source heterogeneous data, and constructing a dynamically updated three-dimensional geological-construction coupled digital twin model after alignment and coding; Through multi-scale physical-AI hybrid modeling and real-time data correction, water gushing evolution rolling prediction is carried out, and prediction data is output; Building a three-dimensional visualization platform, starting multi-level linkage early warning based on risk threshold.

[0006] In the step of collecting multi-source heterogeneous geological, hydrological and construction data, fusing multi-source heterogeneous data, and constructing a dynamically updated three-dimensional geological-construction coupled digital twin model after alignment and coding: Integrate geological exploration data, real-time hydrological monitoring data, and construction management system BIM parameters to obtain multi-source heterogeneous data. Process multi-source heterogeneous data through a spatio-temporal alignment algorithm to establish a unified coordinate reference system. Construct a three-dimensional geological-construction coupled digital twin model with permeability attribute labels.

[0007] In the step of integrating geological exploration data, real-time hydrological monitoring data, and construction management system BIM parameters to obtain multi-source heterogeneous data: Multi-source heterogeneous geological data includes millimeter-level precision point cloud data obtained by three-dimensional laser scanning, geological radar detection results, and rock mass mechanical parameters obtained by drilling exploration; real-time hydrological monitoring data includes water pressure, flow, and temperature parameters collected by a distributed optical fiber sensor network; and construction management system BIM parameters include excavation progress and support strength information.

[0008] After the step of processing multi-source heterogeneous data through a spatio-temporal alignment algorithm to establish a unified coordinate reference system: Convert the fracture network topology structure into graph structure data containing multi-dimensional features, where node features include porosity and permeability coefficients.

[0009] In the step of using multi-scale physical-AI and graph neural network hybrid modeling to capture the seepage correlation characteristics between fractures, and dynamically correcting model parameters based on real-time data: Use multi-scale physical-AI and graph neural network hybrid modeling to capture the seepage correlation characteristics between fractures. Real-time receive and process field monitoring data, extract spatio-temporal features, and dynamically correct model parameters.

[0010] After the step of real-time receiving and processing field monitoring data, extracting spatio-temporal features, and dynamically correcting model parameters: Rolling predict the evolution process of water inrush within the time window, and output the path data of water inrush at different times.

[0011] After the step of rolling predicting the evolution process of water inrush within the time window, and outputting the path data of water inrush at different times: Extract risk key indicators and perform quantitative processing for each key indicator to output a comprehensive risk value.

[0012] In the step of constructing a three-dimensional visualization platform and starting multi-level linkage warning based on risk threshold: A three-dimensional visualization platform is constructed based on an autonomous controllable graphics engine, and a progressive rendering is adopted to display path trend data and comprehensive risk values. A first threshold value and a second threshold value are set, the comprehensive risk value, the first threshold value and the second threshold value are compared, and multi-level linkage early warning is performed according to the comparison result.

[0013] In the step of setting the first threshold value and the second threshold value, comparing the comprehensive risk value, the first threshold value and the second threshold value, and performing multi-level linkage early warning according to the comparison result, the step includes: When the comprehensive risk value is less than the first threshold value, a third-level early warning is triggered; When the comprehensive risk value is greater than the first threshold value and less than the second threshold value, a second-level early warning is triggered; When the comprehensive risk value is greater than the second threshold value, a first-level early warning is triggered.

[0014] The application also provides a three-dimensional tunnel water inrush analysis system based on autonomous control, comprising a data fusion module, a water inrush evolution rolling prediction module and a multi-level linkage early warning module. The data fusion module is used to collect multi-source heterogeneous geological, hydrological and construction data, fuse the multi-source heterogeneous data, and construct a dynamically updated three-dimensional geological-construction coupled digital twin model after alignment coding. The water inrush evolution rolling prediction module is used to perform water inrush evolution rolling prediction and output prediction data by multi-scale physical-AI hybrid modeling and real-time data correction. The multi-level linkage early warning module is used to construct a three-dimensional visualization platform and start multi-level linkage early warning based on a risk threshold value.

[0015] The three-dimensional tunnel water inrush analysis method and system based on autonomous control, adopts the data fusion module, the water inrush evolution rolling prediction module and the multi-level linkage early warning module to perform the following steps: collecting multi-source heterogeneous geological, hydrological and construction data, fusing the multi-source heterogeneous data, and constructing a dynamically updated three-dimensional geological-construction coupled digital twin model after alignment coding; performing water inrush evolution rolling prediction and outputting prediction data by multi-scale physical-AI hybrid modeling and real-time data correction; constructing a three-dimensional visualization platform and starting multi-level linkage early warning based on a risk threshold value; and meeting the demand for rapid early warning and timely decision-making of water inrush disasters in the tunnel construction process by fusing geological data, hydrological monitoring data and construction parameters, combining three-dimensional visualization rendering and deep learning fluid simulation technology, and providing intelligent support for engineering disaster prevention decision-making. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only represent some of the embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0017] Figure 1 is a step flow chart of the three-dimensional tunnel water gushing analysis method based on autonomous controllability of the present application.

[0018] Figure 2 is a step flow chart of S100 of the present application.

[0019] Figure 3 is a step flow chart of S200 of the present application.

[0020] Figure 4 is a step flow chart of S300 of the present application.

[0021] Figure 5 is a structure principle diagram of the three-dimensional tunnel water gushing analysis system based on autonomous controllability of the present application.

[0022] Figure 6 is a structure principle diagram of the electronic device of the present application.

[0023] 401-data fusion module, 402-water gushing evolution rolling prediction module, 403-multistage linkage early warning module. DETAILED DESCRIPTION

[0024] The exemplary embodiments will be described in detail herein with reference to the attached drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application.

[0025] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0026] It should be understood that, although the terms first, second, third, etc. can be employed in this application to describe various information, the information is not to be limited to these terms. These terms are only used to distinguish one category of information from another. For example, without departing from the scope of the application, first information could also be referred to as second information, and, similarly, second information can also be referred to as first information. Depending on the context, the word "if' as used herein can be interpreted to mean "when" or "in response to determining".

[0027] Referring to Figures 1-4 The application provides a self-controllable three-dimensional tunnel water gushing analysis method, comprising the following steps: S100: Collecting multi-source heterogeneous geological, hydrological and construction data, fusing to obtain multi-source heterogeneous data, and constructing a dynamically updated three-dimensional geological-construction coupled digital twin model after alignment coding.

[0028] In this embodiment, multi-source heterogeneous geological, hydrological and construction data are collected, multi-source heterogeneous data are fused, and a dynamically updated three-dimensional geological-construction coupled digital twin model is constructed after alignment coding. The specific process is as follows: S101: Integrating geological exploration data, real-time hydrological monitoring data and construction management system BIM parameters to obtain multi-source heterogeneous data; the multi-source heterogeneous geology includes millimeter-level precision point cloud data obtained by three-dimensional laser scanning, geological radar detection results and rock mass mechanical parameters obtained by drilling exploration; the real-time hydrological monitoring data includes water pressure, flow and temperature parameters collected by a distributed optical fiber sensor network; the construction management system BIM parameters include excavation progress and support strength information; S102: Process the multi-source heterogeneous data through a space-time alignment algorithm to establish a unified coordinate reference system; S103: Convert the fracture network topology structure into graph structure data containing multi-dimensional features, wherein the node features include porosity and permeability coefficient; S104: Construct a three-dimensional geological-construction coupled digital twin model with permeability attribute labels.

[0029] In the above process, the geological exploration data integration: millimeter-level precision point cloud data are obtained by using three-dimensional laser scanning technology, which can accurately present the morphological characteristics of the tunnel surrounding surface; the information of underground geological structure at different depths is obtained by using geological radar detection technology, and the possible geological abnormal bodies such as faults and karst caves are identified; the rock mass mechanical parameters such as compressive strength and tensile strength of rock are obtained through drilling exploration, which provide basic data for analyzing the influence of geological structure on water gushing.

[0030] Real-time Hydrological Monitoring Data Integration: Deploy a distributed fiber-optic sensor network to collect hydrological parameters such as water pressure, flow rate, and temperature in real-time. These sensors can accurately perceive the dynamic changes of water bodies around the tunnel and reflect the impact of changes in hydrological conditions on water gushing risks in a timely manner.

[0031] Construction Management System BIM Parameter Integration: Obtain information such as excavation progress and support strength from the construction management system. Excavation progress reflects the speed and location of tunnel excavation, while support strength represents the support capacity of the surrounding rock of the tunnel. These information is crucial for assessing the impact of the construction process on water gushing.

[0032] After integrating the multi-source heterogeneous data, a spatio-temporal alignment algorithm is used to process the data. After completing the time and space alignment, all data is represented in the same coordinate system, establishing a unified coordinate reference system. Due to the differences in collection time and spatial location of different data sources, the spatio-temporal alignment algorithm adjusts all data to a unified time reference and spatial coordinate system through interpolation, timestamp matching, and coordinate transformation. For example, geological exploration data, hydrological monitoring data, and construction BIM data are transformed into the global coordinate system set by the project through coordinate transformation. At the same time, through timestamp matching, the consistency of all data in time is ensured to facilitate subsequent time series analysis.

[0033] Convert the fracture network topology structure into graph structure data containing multi-dimensional features. In this process, nodes and edges in the graph structure are determined. Node features include porosity, permeability coefficient, and other parameters that reflect the physical properties of the fracture network; edge features represent the connectivity of seepage channels and describe the flow path of water in the fracture network.

[0034] Based on the above processed data, a three-dimensional geological-construction coupled digital twin model with permeability attribute labels is constructed; wherein the permeability attribute labels include specific numerical values or descriptions related to the permeability of each geological element in the model, such as porosity, permeability coefficient, etc. The model organically combines data and information from multiple aspects such as geological structure, hydrological conditions and construction state, forming a unified whole model, which can truly reflect the geological structure, hydrological conditions and construction state around the tunnel, and support dynamic incremental updating during construction, ensuring that the model is real-time synchronized with the actual working conditions on site, providing an accurate model basis for subsequent water gushing analysis and prediction. Among them, geological-hydrological coupling: fuse geological exploration data and hydrological monitoring data, analyze the influence of geological structure on water flow. For example, through the detection results of geological radar, identify possible geological anomalies such as faults and karst caves, and analyze the influence of these geological anomalies on water flow path and water gushing volume in combination with hydrological monitoring data. Geological-construction coupling: fuse geological exploration data and BIM parameters of construction management system, analyze the influence of construction process on geological structure. For example, through excavation progress and support strength information, analyze the disturbance of construction activities to the geological structure around the tunnel, and the water gushing risk that may be caused by such disturbance. Hydrology-construction coupling: fuse hydrological monitoring data and BIM parameters of construction management system, analyze the influence of construction process on hydrological conditions. For example, through real-time monitoring of water pressure and flow data, combined with excavation progress and support strength information, analyze the influence of construction activities on the dynamic changes of water around the tunnel.

[0035] S200: Through multi-scale physical-AI hybrid modeling and real-time data correction, rolling prediction of water gushing evolution is carried out, and prediction data is output.

[0036] In this embodiment, through multi-scale physical-AI hybrid modeling and real-time data correction, rolling prediction of water gushing evolution is carried out, and prediction data is output. The specific process is: S201: Multi-scale physical-AI and graph neural network hybrid modeling is adopted to capture the seepage correlation characteristics between fractures; S202: Real-time receiving and processing of field monitoring data, extraction of spatio-temporal features, and dynamic correction of model parameters; S203: Rolling prediction of water gushing evolution process in the time window, output of water gushing path data at different times; S204: Extracting risk key indicators and quantifying each key indicator, outputting a comprehensive risk value.

[0037] In the above process, a multi-scale physical-AI hybrid modeling method is adopted, combined with a graph neural network (GNN) to capture the seepage correlation characteristics between fractures. At the macro scale, a fluid dynamics model is constructed based on the improved Navier-Stokes equation to describe the flow law of water flow in a larger range; at the micro scale, a graph neural network is used to model the complex seepage behavior in the fracture network, and through a specially designed message passing mechanism, the non-Darcy seepage characteristics in the geological fracture network are learned, so that the flow of water in the fracture can be simulated more accurately.

[0038] Real-time monitoring data is received and processed, and a spatio-temporal convolutional neural network (ST-CNN) is used to extract the spatio-temporal features of the data. The extracted features are fused with the model to dynamically correct the model parameters, so that the model can timely reflect the changes in the actual situation on site, improving the accuracy and adaptability of the model.

[0039] Based on the corrected model, the evolution process of the gushing water in a time window (such as the next 2 hours) is predicted. By continuously updating the model parameters and inputting real-time data, the path of the gushing water at different times is continuously predicted, and the corresponding path data is output, providing dynamic information of the gushing water development for engineers.

[0040] From the gushing water evolution prediction results, key risk indicators such as gushing water flow, water pressure, and influence range in different regions are extracted. Each key indicator is quantitatively processed, and the corresponding risk weight for each indicator is set according to the actual engineering situation and experience. Through weighted calculation, the comprehensive risk value of each region is obtained to evaluate the size of the gushing water risk. For example: The gushing water flow may account for 40% of the risk assessment weight, the water pressure accounts for 30% of the weight, and the influence range accounts for 30% of the weight. Through weighted calculation, the quantified risk indicators are combined to obtain the comprehensive risk value of each region. For example, the gushing water flow quantization value of a certain region is 80, the water pressure quantization value is 70, and the influence range quantization value is 60. According to the above weight calculation, the comprehensive risk value of this region = 80x0.4 + 70x0.3 + 60x0.3 = 71.

[0041] S300: Construct a three-dimensional visualization platform and start multi-level linkage warning based on risk threshold.

[0042] In this embodiment, a three-dimensional visualization platform is constructed, and multi-level linkage warning is started based on the risk threshold. The specific process is as follows: S301: Construct a three-dimensional visualization platform based on an autonomous controllable graphics engine, and use progressive rendering to display path data and comprehensive risk value; S302: Set a first threshold and a second threshold, compare the comprehensive risk value, the first threshold and the second threshold, and perform multi-level linkage warning according to the comparison result.

[0043] Further, in setting the first threshold and the second threshold, in the step of comparing the comprehensive risk value, the first threshold and the second threshold, and performing multi-level warning according to the comparison result: When the comprehensive risk value is less than the first threshold, a third-level warning is triggered; When the comprehensive risk value is greater than the first threshold and less than the second threshold, a second-level warning is triggered; When the comprehensive risk value is greater than the second threshold, a first-level warning is triggered.

[0044] In the above process, a three-dimensional visualization platform is built based on an autonomous controllable graphics engine, and a progressive rendering technology is used to display path trend data and comprehensive risk values. This platform can present the geological structure, water gushing path and risk distribution around the tunnel in an intuitive way, support multi-scale dynamic rendering of risk heat maps, and include both overall risk distribution overview and detailed display of local high-risk areas, providing clear and intuitive visualization effects for engineering personnel.

[0045] Establish risk thresholds: Establish a first threshold and a second threshold to divide different risk levels. The thresholds can be adjusted according to actual engineering conditions, historical data and relevant specification standards. For example: The first threshold is 50 and the second threshold is 80.

[0046] Compare the thresholds with the comprehensive risk value: Compare the calculated comprehensive risk value with the first threshold and the second threshold.

[0047] Perform warning according to the comparison result: When the comprehensive risk value is less than the first threshold, a third-level warning is triggered. At this time, the risk area is marked in the three-dimensional model, disposal suggestions are generated and pushed to relevant terminals, and engineering personnel are reminded to pay attention to potential risks, but no emergency measures are taken.

[0048] When the comprehensive risk value is greater than the first threshold and less than the second threshold, a second-level warning is triggered. On the basis of the third-level warning, the monitoring frequency is increased, the risk change is closely monitored, and emergency preparations are made.

[0049] When the comprehensive risk value is greater than the second threshold, a first-level warning is triggered. The pre-set emergency response measures are executed, such as stopping construction, starting drainage equipment, etc., and relevant personnel are notified to arrive at the scene immediately for processing to ensure engineering safety. For example: The risk thermodynamic diagram is used to represent different risk level areas with different colors. Red color is used to represent high risk areas (the comprehensive risk value is above 80), orange color is used to represent higher risk areas (the comprehensive risk value is between 50 and 80), and yellow color is used to represent medium risk areas (the comprehensive risk value is below 50), so as to intuitively present the risk distribution of the whole tunnel area. The quantitative value of the water inflow of a certain area is 80, the quantitative value of the water pressure is 70, and the quantitative value of the influence range is 60. After weight calculation, the comprehensive risk value of the area = 80*0.4 + 70*0.3 + 60*0.3 = 71. Based on the calculated comprehensive risk 71, the area is a higher risk area, which is displayed as orange, and triggers a secondary early warning.

[0050] Corresponding to the foregoing embodiments of the self-controllable three-dimensional tunnel water gushing analysis method, the application also provides embodiments of a self-controllable three-dimensional tunnel water gushing analysis system.

[0051] Figure 5 is a block diagram of a self-controllable three-dimensional tunnel water gushing analysis system according to an exemplary embodiment. Referring to Figure 5 , the system can include a data fusion module 401, a water gushing evolution rolling prediction module 402, and a multi-level linkage early warning module 403. Wherein: The data fusion module 401 is configured to collect multi-source heterogeneous geological, hydrological and construction data, fuse the multi-source heterogeneous data, and construct a dynamically updated three-dimensional geological-construction coupled digital twin model after alignment and coding. The water gushing evolution rolling prediction module 402 is configured to perform water gushing evolution rolling prediction by multi-scale physical-AI hybrid modeling and correcting real-time data, and output prediction data. The multi-level linkage early warning module 403 is configured to construct a three-dimensional visualization platform and start multi-level linkage early warning based on a risk threshold.

[0052] In this embodiment, the data fusion module 401 collects multi-source heterogeneous geological, hydrological and construction data, fuses the multi-source heterogeneous data, and constructs a dynamically updated three-dimensional geological-construction coupled digital twin model after alignment and coding. The water gushing evolution rolling prediction module 402 performs water gushing evolution rolling prediction by multi-scale physical-AI hybrid modeling and correcting real-time data, and outputs prediction data. The multi-level linkage early warning module 403 constructs a three-dimensional visualization platform and starts multi-level linkage early warning based on a risk threshold. By fusing geological data, hydrological monitoring data and construction parameters, combining three-dimensional visualization rendering and deep learning fluid simulation technology, the demand for rapid early warning and timely decision-making of water gushing disasters in the tunnel construction process is met, and intelligent support for engineering disaster prevention decision-making is provided.

[0053] As to the system in the above-mentioned embodiments, the specific manner in which the various modules perform operations has been described in detail in the embodiments related to the method, and will not be elaborated here.

[0054] As to the system embodiments, since they basically correspond to the method embodiments, the relevant parts are referred to the part of the method embodiments. The above-described device embodiments are only schematic, wherein the units shown as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., can be located in one place or distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the present application. Those skilled in the art can understand and implement without creative labor.

[0055] Correspondingly, the present application also provides an electronic device, comprising: one or more processors; a memory for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the autonomous controllable three-dimensional tunnel water analysis method as described above. As Figure 6 As shown in the figure, a hardware structure diagram of an autonomous controllable three-dimensional tunnel water analysis system provided by an embodiment of the present application is provided in any data processing capable device, in addition to Figure 6 In addition to the processor, memory and network interface shown in the figure, any data processing capable device in which the device in the embodiment is usually based on the actual function of the data processing capable device, and can also include other hardware, which will not be described here.

[0056] Correspondingly, the present application also provides a computer readable storage medium having computer instructions stored thereon, which are executed by a processor to implement the autonomous controllable three-dimensional tunnel water analysis method as described above. The computer readable storage medium can be an internal storage unit of any data processing capable device, such as a hard disk or a memory. The computer readable storage medium can also be an external storage device, such as a plug-in hard disk, a smart media card (SMC), an SD card, a flash card, etc. Further, the computer readable storage medium can include both the internal storage unit of any data processing capable device and the external storage device. The computer readable storage medium is used to store the computer program and other programs and data required by the data processing capable device, and can also be used to temporarily store data that has been output or will be output.

[0057] Those skilled in the art will readily conceive of other embodiments of the present application after considering the specification and practicing the contents disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of this application and include common knowledge or customary techniques in the art that are not disclosed in this application.

[0058] It will be understood that the present application is not limited to the exact construction that has been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof.

Claims

1. A three-dimensional tunnel water inrush analysis method based on autonomous control, characterized in that: The steps include: Collect multi-source heterogeneous geological, hydrological, and construction data, fuse and acquire these data, and construct a dynamically updated 3D geological-construction coupled digital twin model after alignment and coding. Through multi-scale physics-AI hybrid modeling and correction of real-time data, rolling prediction of water inflow evolution is carried out and the predicted data is output; Build a three-dimensional visualization platform and initiate multi-level linkage warning based on risk thresholds.

2. The autonomous and controllable three-dimensional tunnel water inrush analysis method according to claim 1, characterized in that: In the steps of collecting multi-source heterogeneous geological, hydrological and construction data, fusing and acquiring multi-source heterogeneous data, and constructing a dynamically updated 3D geological-construction coupled digital twin model after alignment coding: Integrate geological exploration data, real-time hydrological monitoring data, and construction management system BIM parameters to obtain multi-source heterogeneous data; Process multi-source heterogeneous data through spatiotemporal alignment algorithms to establish a unified coordinate reference system; Construct a three-dimensional geological-construction coupled digital twin model with permeability property labels.

3. The autonomous and controllable three-dimensional tunnel water inrush analysis method according to claim 2, characterized in that: In the step of integrating geological exploration data, real-time hydrological monitoring data, and construction management system BIM parameters to obtain multi-source heterogeneous data: Multi-source heterogeneous geology includes millimeter-level precision point cloud data obtained by 3D laser scanning, geological radar detection results, and rock mechanical parameters obtained by drilling exploration; real-time hydrological monitoring data includes water pressure, flow, and temperature parameters collected by a distributed fiber optic sensor network; and construction management system BIM parameters include excavation progress and support strength information.

4. The autonomous and controllable three-dimensional tunnel water inrush analysis method according to claim 3, characterized in that: After processing multi-source heterogeneous data through the spatiotemporal alignment algorithm and establishing a unified coordinate reference system: The fracture network topology is converted into graph structure data containing multi-dimensional features, where node features include porosity and permeability.

5. The autonomous and controllable three-dimensional tunnel water inrush analysis method according to claim 1, characterized in that: In the steps of performing rolling prediction of water inflow evolution through multi-scale physics-AI hybrid modeling and correcting real-time data, and outputting prediction data: Adopting multi-scale physics-AI and graph neural network hybrid modeling to capture the seepage correlation characteristics between fractures; Receive and process field monitoring data in real time, extract spatiotemporal features, and dynamically modify model parameters.

6. The autonomous and controllable three-dimensional tunnel water inrush analysis method according to claim 5, characterized in that: After receiving and processing field monitoring data in real time, extracting spatiotemporal features, and dynamically correcting model parameters: The evolution process of water inrush within the rolling prediction time window is output, and the path direction data of water inrush at different times are output.

7. The autonomous and controllable three-dimensional tunnel water inrush analysis method according to claim 6, characterized in that: After the step of outputting the path direction data of the water inrush at different times during the water inrush evolution process within the rolling prediction time window: Extract key risk indicators, quantify each key indicator, and output a comprehensive risk value.

8. The autonomous and controllable three-dimensional tunnel water inrush analysis method according to claim 1, characterized in that: In the steps of building a 3D visualization platform and initiating multi-level linkage warnings based on risk thresholds: A 3D visualization platform is built based on an independent and controllable graphics engine, using progressive rendering to display path direction data and comprehensive risk values; Establish the first threshold and the second threshold, compare the comprehensive risk value, the first threshold and the second threshold, and conduct multi-level linkage warning based on the comparison results.

9. The autonomous and controllable three-dimensional tunnel water inrush analysis method according to claim 8, characterized in that: In the steps of establishing the first threshold and the second threshold, comparing the comprehensive risk value, the first threshold and the second threshold, and performing a multi-level linkage warning based on the comparison results: When the comprehensive risk value is less than the first threshold, the third-level warning is triggered; When the comprehensive risk value is greater than the first threshold and less than the second threshold, a secondary warning is triggered; When the comprehensive risk value is greater than the second threshold, a first-level warning is triggered.

10. A three-dimensional tunnel water inrush analysis system based on autonomous control, applied to the three-dimensional tunnel water inrush analysis method based on autonomous control according to claim 1, characterized in that: It includes data fusion module, water inrush evolution rolling prediction module, and multi-level linkage early warning module; among which: The data fusion module is used to collect multi-source heterogeneous geological, hydrological and construction data, fuse the multi-source heterogeneous data, and construct a dynamically updated three-dimensional geological-construction coupled digital twin model after alignment coding; The water inflow evolution rolling prediction module is used to perform water inflow evolution rolling prediction through multi-scale physics-AI hybrid modeling and correct real-time data, and output prediction data; The multi-level linkage warning module is used to build a three-dimensional visualization platform and initiate a multi-level linkage warning based on a risk threshold.

Images