Intelligent Decision-Making Method for Opening Slurry Shield Tunneling Based on Geological-Equipment-Environment Collaboration

Abstract

This invention discloses an intelligent decision-making method for slurry shield tunneling based on geology-equipment-environment synergy, comprising: acquiring geological data and constructing a finite element model; acquiring simulated tunneling parameters; acquiring geological data and simulated tunneling parameters when the tunnel boring machine reaches the tunneling operation standard; calculating the tunneling risk data for each section; selecting a pool of tunneling sections; selecting at least one optimal tunneling section; acquiring the actual tunneling parameters for the optimal tunneling section when tunneling is completed, and performing secondary training on the risk prediction model using the actual tunneling parameters and corresponding geological data. This invention, through the above technical solution, overcomes the limitations of decision-making based on a geology-equipment-environment ternary data fusion architecture; simultaneously reduces human experience judgment in the tunneling site selection process, effectively improving the intelligence level of shield tunneling construction, significantly reducing tunneling risk, and exhibiting better real-time performance and applicability.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology, specifically to an intelligent decision-making method for opening a slurry shield tunnel based on geology-equipment-environment synergy. Background Technology

[0002] During tunnel boring machine (TBM) excavation, the cutting tools gradually wear down due to friction and impact with the ground. When the wear reaches a certain level, the cutter head needs to be opened to replace the tools to ensure tunneling efficiency and construction quality. However, existing technologies have the following problems in selecting the opening location: 1. Traditional methods rely on manual experience and lack quantitative data support, making them susceptible to subjective factors; 2. Insufficient geological forecasting accuracy makes it difficult to accurately predict risk sources such as soft-hard interfaces and fissure water distribution; 3. The timing and location of the opening are static and cannot be dynamically adjusted based on tunneling parameters. Summary of the Invention

[0003] In order to at least overcome the above-mentioned shortcomings in the prior art, the purpose of this application is to provide an intelligent decision-making method for slurry shield tunneling based on geology-equipment-environment synergy.

[0004] In a first aspect, embodiments of this application provide an intelligent decision-making method for slurry shield tunneling based on geology-equipment-environment synergy, including:

[0005] Geological data from multiple sections of the target tunneling area are acquired, and a finite element model is constructed based on the geological data. The geological data includes surrounding rock parameters, water level data, fracture water pressure, fracture development index, and hard rock ratio.

[0006] The finite element model was used to simulate the stress release and seepage field of the stratum when the tunnel boring machine opened at multiple locations, and the simulated opening parameters were obtained. The simulated opening parameters include water inflow, shield diameter, face pressure data, face displacement data and surface settlement.

[0007] When the tunnel boring machine reaches the standard for opening the tunnel, the geological data and simulated opening parameters of multiple sections within a preset range in front of the tunnel are acquired.

[0008] Input the geological data and the simulated opening parameters into the risk prediction model and obtain the opening risk data for each section output by the risk prediction model;

[0009] Multiple cross-sections that meet preset requirements for the opening risk data are selected to form an opening cross-section pool;

[0010] Select at least one optimal opening section from the opening section pool based on the objective conditions and constraints;

[0011] When the opening of the position is completed at the optimal opening section, the actual opening parameters of the opening at the optimal opening section are obtained, and the risk prediction model is trained a second time using the actual opening parameters and the corresponding geological data.

[0012] In the implementation of this application, geological data of different cross-sections can be obtained through methods such as borehole exploration, ground-penetrating radar, and TSP advanced prediction, and a finite element model can be constructed based on this geological data. The finite element model can simulate the opening state at different locations. Specifically, with the seepage field module loaded, the load change of the tunnel face (i.e., the surrounding area) is used to calculate the opening simulation process; after the calculation is completed, the corresponding simulated opening parameters can be obtained. During the tunneling process of the slurry shield machine, the wear degree of the cutterhead can be detected by the cutterhead wear sensor to determine whether the opening operation standard has been met. If the cutter wear reaches 80% of the cutter wear threshold, the opening site selection begins. At this time, geological data and simulated opening parameters of multiple cross-sections within a preset range need to be selected. Specifically, the preset range is the area from the current shield machine position to the position where the cutter wear reaches the cutter wear threshold. Since the cutter wear condition can be calculated through the cutter wear rate, the final position reaching the cutter wear threshold can also be calculated. When obtaining geological data and simulated opening parameters of multiple cross-sections, geological data and simulated opening parameters of all cross-sections within the preset range can be obtained for subsequent risk assessment.

[0013] In this embodiment, the risk data for opening the trench can be calculated for each cross-section using a pre-trained risk prediction model. Multiple cross-sections whose risk data meets the relevant requirements are then selected as candidate cross-sections for safe trench opening. At this point, it is necessary to evaluate which cross-section(s) to provide to the construction party. First, the target conditions and constraints need to be determined. Constraints are generally the hard indicators that must be met during trench opening, while target conditions are the desired conditions. For example, constraints may include hard requirements on the proportion of hard rock and surface subsidence, while target conditions include minimizing the risk prediction index, minimizing the trench opening prediction time, and minimizing the remaining tool life. Cross-sections that do not meet the constraints are then removed from the trench opening cross-section pool, and the target conditions are used to further screen the cross-sections. For example, the screening process is as follows: All sections selected through the constraints are treated as a candidate section set, and the risk prediction index, opening prediction duration, and remaining tool life of all sections in the candidate section set are obtained as target parameters for the sections. A section is randomly selected from the candidate section set as the selected section, and its target parameters are compared with those of other sections. If the target parameters of any other section are greater than those of the selected section, that other section is removed from the candidate section set. If the target parameters of any other section are less than those of the selected section, that selected section is removed from the candidate section set. This selection and comparison process is repeated until all remaining sections in the candidate section set have been selected and compared. The current candidate section set is then provided to the construction party as the optimal opening section. In this embodiment, after one tunnel opening is completed, the corresponding actual opening parameters can be obtained. Based on this, the risk prediction model can be retrained, allowing it to better adapt to the current geological conditions and further improve its prediction accuracy. This embodiment, through the above technical solution, overcomes the limitations of decision-making based on a geology-equipment-environment ternary data fusion architecture. Simultaneously, it reduces the reliance on human experience in the tunnel opening site selection process, effectively improving the intelligence level of tunnel boring machine construction, significantly reducing tunnel opening risks, and exhibiting better real-time performance and applicability.

[0014] In one possible implementation, constructing a finite element model based on the geological data includes:

[0015] Non-uniform B-spline interpolation is performed on the geological data of multiple cross sections based on the cross section mileage to obtain continuous stratigraphic data;

[0016] Finite element modeling was performed based on the continuous stratigraphic data.

[0017] In one possible implementation, the generation of the risk prediction model includes:

[0018] Acquire historical opening data, which includes corresponding risk indicator data, opening duration data, and risk assessment index; the characteristic indicators of the risk indicator data include surface subsidence data, water inflow, shield diameter, tunnel face displacement data, tunnel face pressure data, fissure water pressure, fissure development index, water level data, and hard rock ratio at the time of opening.

[0019] A random forest model is constructed based on the aforementioned feature indicators, and the random forest model is trained using the aforementioned risk indicator data as input data and the aforementioned risk assessment index as output data to generate a risk assessment model.

[0020] Using the risk indicator data as input data and the opening duration data as output data, a neural network model is trained to form an opening duration prediction model;

[0021] The risk prediction model is formed by combining the risk assessment model and the opening duration prediction model.

[0022] In one possible implementation, inputting the geological data and the simulated opening parameters into the risk prediction model and obtaining the opening risk data for each cross-section output by the risk prediction model includes:

[0023] The fracture water pressure, fracture development index, water level data, and hard rock ratio in the stratigraphic data of the cross section, as well as the surface subsidence data, water inflow, shield diameter, tunnel face displacement data, and tunnel face pressure data in the simulated tunnel opening parameters, are used as prediction input data.

[0024] Input the predicted input data into the risk assessment model and receive the risk prediction index output by the risk assessment model; input the predicted input data into the opening position duration prediction model and receive the opening position prediction duration output by the opening position duration prediction model.

[0025] The risk prediction index and the opening position prediction duration are used as the opening position risk data for this section.

[0026] In one possible implementation, selecting multiple cross-sections of the opening risk data that meet preset requirements to form an opening cross-section pool includes:

[0027] The opening position cross-section pool is formed by selecting multiple cross-sections with medium or low risk prediction indices.

[0028] In one possible implementation, secondary training of the risk prediction model using the actual opening parameters and corresponding geological data includes:

[0029] A risk assessment was conducted on this opening process to generate an actual risk index, and the duration of the opening process was recorded as the actual opening duration.

[0030] The risk assessment model is trained a second time using the actual opening parameters as new input data and the actual risk index as new output data.

[0031] The actual opening parameters are used as new input data, and the actual opening duration is used as new output data to perform secondary training on the opening duration prediction model. The actual opening parameters include surface subsidence data, water inflow, shield diameter, tunnel face displacement data, tunnel face pressure data, fissure water pressure, fissure development index, water level data, and hard rock ratio.

[0032] In one possible implementation, the constraints include a hard rock ratio of 40% or more and a surface subsidence of less than 3 mm; the target conditions include minimizing the risk prediction index, minimizing the opening prediction time, and minimizing the remaining tool life.

[0033] In one possible implementation, the calculation of the remaining tool life includes:

[0034] Obtain the cutter wear rate of the tunnel boring machine and calculate the number of rings from the tunnel boring machine to the corresponding section;

[0035] The tool wear amount is calculated based on the tool wear rate and the number of rings;

[0036] Obtain the current remaining lifespan of the tunnel boring machine's cutters, and calculate the difference between the current remaining lifespan of the cutters and the amount of cutter wear as the remaining lifespan of the cutters corresponding to that section.

[0037] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0038] This invention, through the above-mentioned technical solution, breaks through the decision-making limitations of a single data source based on the geological-equipment-environment three-dimensional data fusion architecture; at the same time, it reduces the judgment of human experience in the tunnel opening site selection process, effectively improves the intelligence level of tunnel boring machine construction, can greatly reduce the risk of tunnel opening, and has better real-time performance and applicability. Attached Figure Description

[0039] The accompanying drawings, which are included to provide a further understanding of embodiments of the invention and form part of this application, do not constitute a limitation thereof. In the drawings:

[0040] Figure 1 This is a schematic diagram of the method steps in an embodiment of this application. Detailed Implementation

[0041] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the accompanying drawings in this application are for illustrative and descriptive purposes only and are not intended to limit the scope of protection of this application. Furthermore, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of this application. It should be understood that the operations in the flowcharts may not be implemented in sequence, and steps without logical contextual relationships may be reversed or implemented simultaneously. In addition, those skilled in the art, guided by the content of this application, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts.

[0042] Furthermore, the described embodiments are merely some, not all, of the embodiments of this application. The components of the embodiments of this application described and illustrated herein can typically be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0043] Please refer to the following: Figure 1 This is a flowchart illustrating the intelligent decision-making method for opening a slurry shield tunnel based on geology-equipment-environment synergy provided in an embodiment of the present invention. Further, the intelligent decision-making method for opening a slurry shield tunnel based on geology-equipment-environment synergy may specifically include the contents described in steps S1-S7.

[0044] S1: Obtain geological data from multiple sections of the target tunneling area and construct a finite element model based on the geological data; the geological data includes surrounding rock parameters, water level data, fracture water pressure, fracture development index, and hard rock ratio;

[0045] S2: Perform ground stress release and seepage field simulation calculations on the finite element model for opening the tunnel boring machine at multiple locations, and obtain the simulated opening parameters; the simulated opening parameters include water inflow, shield diameter, tunnel face pressure data, tunnel face displacement data, and surface settlement;

[0046] S3: When the tunnel boring machine reaches the standard for opening the tunnel, acquire the geological data and simulated opening parameters of multiple sections within a preset range in front of the tunnel.

[0047] S4: Input the geological data and the simulated opening parameters into the risk prediction model and obtain the opening risk data of each section output by the risk prediction model;

[0048] S5: Select multiple sections of the opening risk data that meet the preset requirements to form an opening section pool;

[0049] S6: Select at least one optimal opening section from the opening section pool based on the objective conditions and constraints;

[0050] S7: When the opening of the position is completed at the optimal opening section, the actual opening parameters of the opening of the position at the optimal opening section are obtained, and the risk prediction model is trained a second time using the actual opening parameters and the corresponding geological data.

[0051] In the implementation of this application, geological data of different cross-sections can be obtained through methods such as borehole exploration, ground-penetrating radar, and TSP advanced prediction, and a finite element model can be constructed based on this geological data. The finite element model can simulate the opening state at different locations. Specifically, with the seepage field module loaded, the load change of the tunnel face (i.e., the surrounding area) is used to calculate the opening simulation process; after the calculation is completed, the corresponding simulated opening parameters can be obtained. During the tunneling process of the slurry shield machine, the wear degree of the cutterhead can be detected by the cutterhead wear sensor to determine whether the opening operation standard has been met. If the cutter wear reaches 80% of the cutter wear threshold, the opening site selection begins. At this time, geological data and simulated opening parameters of multiple cross-sections within a preset range need to be selected. Specifically, the preset range is the area from the current shield machine position to the position where the cutter wear reaches the cutter wear threshold. Since the cutter wear condition can be calculated through the cutter wear rate, the final position reaching the cutter wear threshold can also be calculated. When obtaining geological data and simulated opening parameters of multiple cross-sections, geological data and simulated opening parameters of all cross-sections within the preset range can be obtained for subsequent risk assessment.

[0052] In this embodiment, the risk data for opening the trench can be calculated for each cross-section using a pre-trained risk prediction model. Multiple cross-sections whose risk data meets the relevant requirements are then selected as candidate cross-sections for safe trench opening. At this point, it is necessary to evaluate which cross-section(s) to provide to the construction party. First, the target conditions and constraints need to be determined. Constraints are generally the hard indicators that must be met during trench opening, while target conditions are the desired conditions. For example, constraints may include hard requirements on the proportion of hard rock and surface subsidence, while target conditions include minimizing the risk prediction index, minimizing the trench opening prediction time, and minimizing the remaining tool life. Cross-sections that do not meet the constraints are then removed from the trench opening cross-section pool, and the target conditions are used to further screen the cross-sections. For example, the screening process is as follows: All sections selected through the constraints are treated as a candidate section set, and the risk prediction index, opening prediction duration, and remaining tool life of all sections in the candidate section set are obtained as target parameters for the sections. A section is randomly selected from the candidate section set as the selected section, and its target parameters are compared with those of other sections. If the target parameters of any other section are greater than those of the selected section, that other section is removed from the candidate section set. If the target parameters of any other section are less than those of the selected section, that selected section is removed from the candidate section set. This selection and comparison process is repeated until all remaining sections in the candidate section set have been selected and compared. The current candidate section set is then provided to the construction party as the optimal opening section. In this embodiment, after one tunnel opening is completed, the corresponding actual opening parameters can be obtained. Based on this, the risk prediction model can be retrained, allowing it to better adapt to the current geological conditions and further improve its prediction accuracy. This embodiment, through the above technical solution, overcomes the limitations of decision-making based on a geology-equipment-environment ternary data fusion architecture. Simultaneously, it reduces the reliance on human experience in the tunnel opening site selection process, effectively improving the intelligence level of tunnel boring machine construction, significantly reducing tunnel opening risks, and exhibiting better real-time performance and applicability.

[0053] In one possible implementation, constructing a finite element model based on the geological data includes:

[0054] Non-uniform B-spline interpolation is performed on the geological data of multiple cross sections based on the cross section mileage to obtain continuous stratigraphic data;

[0055] Finite element modeling was performed based on the continuous stratigraphic data.

[0056] In the implementation of this application embodiment, since the geological data of the cross section is discrete data, it is necessary to generate these discrete data as continuous data through non-uniform B-spline interpolation, so as to facilitate the construction of the finite element model.

[0057] In one possible implementation, the generation of the risk prediction model includes:

[0058] Acquire historical opening data, which includes corresponding risk indicator data, opening duration data, and risk assessment index; the characteristic indicators of the risk indicator data include surface subsidence data, water inflow, shield diameter, tunnel face displacement data, tunnel face pressure data, fissure water pressure, fissure development index, water level data, and hard rock ratio at the time of opening.

[0059] A random forest model is constructed based on the aforementioned feature indicators, and the random forest model is trained using the aforementioned risk indicator data as input data and the aforementioned risk assessment index as output data to generate a risk assessment model.

[0060] Using the risk indicator data as input data and the opening duration data as output data, a neural network model is trained to form an opening duration prediction model;

[0061] The risk prediction model is formed by combining the risk assessment model and the opening duration prediction model.

[0062] In the implementation of this application embodiment, the risk prediction model has two main functions: one is to calculate the corresponding risk level, i.e., risk index data, and the other is to calculate the possible opening duration data. Therefore, in this application embodiment, the risk prediction model is divided into two parts. For the risk index data, a random forest model is used for training and generation. The feature indicators include surface subsidence data, water inflow, shield diameter, tunnel face displacement data, tunnel face pressure data, fracture water pressure, fracture development index, water level data, and hard rock ratio. The risk assessment index in the historical opening data can be obtained through expert scoring. Multiple decision trees are generated by randomly sampling these feature indicators. Each decision tree randomly acquires multiple feature indicators and completes the construction of the random forest model. After training the random forest model with historical opening data, a risk assessment model can be generated. The purpose of the tunnel boring machine (TBM) opening time prediction model is to predict the opening time using data on surface subsidence, water inflow, shield diameter, tunnel face displacement, tunnel face pressure, fissure water pressure, fissure development index, water level, and hard rock ratio. Therefore, a neural network model is used, which has 9 input layer neurons, 1 output layer neuron, and 3 hidden layers for model training.

[0063] In one possible implementation, inputting the geological data and the simulated opening parameters into the risk prediction model and obtaining the opening risk data for each cross-section output by the risk prediction model includes:

[0064] The fracture water pressure, fracture development index, water level data, and hard rock ratio in the stratigraphic data of the cross section, as well as the surface subsidence data, water inflow, shield diameter, tunnel face displacement data, and tunnel face pressure data in the simulated tunnel opening parameters, are used as prediction input data.

[0065] Input the predicted input data into the risk assessment model and receive the risk prediction index output by the risk assessment model; input the predicted input data into the opening position duration prediction model and receive the opening position prediction duration output by the opening position duration prediction model.

[0066] The risk prediction index and the opening position prediction duration are used as the opening position risk data for this section.

[0067] In one possible implementation, selecting multiple cross-sections of the opening risk data that meet preset requirements to form an opening cross-section pool includes:

[0068] The opening position cross-section pool is formed by selecting multiple cross-sections with medium or low risk prediction indices.

[0069] In one possible implementation, secondary training of the risk prediction model using the actual opening parameters and corresponding geological data includes:

[0070] A risk assessment was conducted on this opening process to generate an actual risk index, and the duration of the opening process was recorded as the actual opening duration.

[0071] The risk assessment model is trained a second time using the actual opening parameters as new input data and the actual risk index as new output data.

[0072] The actual opening parameters are used as new input data, and the actual opening duration is used as new output data to perform secondary training on the opening duration prediction model. The actual opening parameters include surface subsidence data, water inflow, shield diameter, tunnel face displacement data, tunnel face pressure data, fissure water pressure, fissure development index, water level data, and hard rock ratio.

[0073] In one possible implementation, the constraints include a hard rock ratio of 40% or more and a surface subsidence of less than 3 mm; the target conditions include minimizing the risk prediction index, minimizing the opening prediction time, and minimizing the remaining tool life.

[0074] In one possible implementation, the calculation of the remaining tool life includes:

[0075] Obtain the cutter wear rate of the tunnel boring machine and calculate the number of rings from the tunnel boring machine to the corresponding section;

[0076] The tool wear amount is calculated based on the tool wear rate and the number of rings;

[0077] Obtain the current remaining lifespan of the tunnel boring machine's cutters, and calculate the difference between the current remaining lifespan of the cutters and the amount of cutter wear as the remaining lifespan of the cutters corresponding to that section.

[0078] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0079] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices or units, or may be electrical, mechanical or other forms of connection.

[0080] The units described as separate components may or may not be physically separate. As will be apparent to those skilled in the art, the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0081] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0082] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or grid device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0083] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A smart decision-making method for slurry shield tunneling opening based on geology-equipment-environment synergy, characterized in that, include: Geological data from multiple sections of the target tunneling area are acquired, and a finite element model is constructed based on the geological data. The geological data includes surrounding rock parameters, water level data, fracture water pressure, fracture development index, and hard rock ratio. The finite element model was used to simulate the stress release and seepage field of the stratum when the tunnel boring machine opened at multiple locations, and the simulated opening parameters were obtained. The simulated opening parameters include water inflow, shield diameter, face pressure data, face displacement data and surface settlement. When the tunnel boring machine reaches the standard for opening the tunnel, the geological data and simulated opening parameters of multiple sections within a preset range in front of the tunnel are acquired. Input the geological data and the simulated opening parameters into the risk prediction model and obtain the opening risk data for each section output by the risk prediction model; Multiple cross-sections that meet preset requirements for the opening risk data are selected to form an opening cross-section pool; Select at least one optimal opening section from the opening section pool based on the objective conditions and constraints; When the opening of the position is completed at the optimal opening section, the actual opening parameters of the opening at the optimal opening section are obtained, and the risk prediction model is trained a second time using the actual opening parameters and the corresponding geological data.

2. The intelligent decision-making method for slurry shield tunneling based on geology-equipment-environment synergy as described in claim 1, characterized in that, Constructing a finite element model based on the geological data includes: Non-uniform B-spline interpolation is performed on the geological data of multiple cross sections based on the cross section mileage to obtain continuous stratigraphic data; Finite element modeling was performed based on the continuous stratigraphic data.

3. The intelligent decision-making method for slurry shield tunneling based on geology-equipment-environment synergy as described in claim 1, characterized in that, The generation of the risk prediction model includes: Acquire historical opening data, which includes corresponding risk indicator data, opening duration data, and risk assessment index; the characteristic indicators of the risk indicator data include surface subsidence data, water inflow, shield diameter, tunnel face displacement data, tunnel face pressure data, fissure water pressure, fissure development index, water level data, and hard rock ratio at the time of opening. A random forest model is constructed based on the aforementioned feature indicators, and the random forest model is trained using the aforementioned risk indicator data as input data and the aforementioned risk assessment index as output data to generate a risk assessment model. Using the risk indicator data as input data and the opening duration data as output data, a neural network model is trained to form an opening duration prediction model; The risk prediction model is formed by combining the risk assessment model and the opening duration prediction model.

4. The intelligent decision-making method for slurry shield tunneling based on geology-equipment-environment synergy as described in claim 3, characterized in that, The geological data and the simulated opening parameters are input into the risk prediction model, and the opening risk data for each cross-section output by the risk prediction model are obtained, including: The fracture water pressure, fracture development index, water level data, and hard rock ratio in the geological data of the cross section, as well as the surface subsidence data, water inflow, shield diameter, tunnel face displacement data, and tunnel face pressure data in the simulated tunnel opening parameters, are used as prediction input data. Input the predicted input data into the risk assessment model and receive the risk prediction index output by the risk assessment model; input the predicted input data into the opening position duration prediction model and receive the opening position prediction duration output by the opening position duration prediction model. The risk prediction index and the opening position prediction duration are used as the opening position risk data for this section.

5. The intelligent decision-making method for slurry shield tunneling based on geology-equipment-environment synergy as described in claim 4, characterized in that, The selection of multiple cross-sections of the opening risk data that meet preset requirements to form an opening cross-section pool includes: The opening position cross-section pool is formed by selecting multiple cross-sections with medium or low risk prediction indices.

6. The intelligent decision-making method for slurry shield tunneling based on geology-equipment-environment synergy as described in claim 4, characterized in that, The risk prediction model is then trained a second time using the actual opening parameters and corresponding geological data, including: A risk assessment was conducted on this opening process to generate an actual risk index, and the duration of the opening process was recorded as the actual opening duration. The risk assessment model is trained a second time using the actual opening parameters as new input data and the actual risk index as new output data. The actual opening parameters are used as new input data, and the actual opening duration is used as new output data to perform secondary training on the opening duration prediction model. The actual opening parameters include surface subsidence data, water inflow, shield diameter, tunnel face displacement data, tunnel face pressure data, fissure water pressure, fissure development index, water level data, and hard rock ratio.

7. The intelligent decision-making method for slurry shield tunneling based on geology-equipment-environment synergy as described in claim 1, characterized in that, The constraints include a hard rock ratio of 40% or more and a surface subsidence of less than 3 mm; the target conditions include minimizing the risk prediction index, minimizing the opening prediction time, and minimizing the remaining tool life.

8. The intelligent decision-making method for slurry shield tunneling based on geology-equipment-environment synergy as described in claim 7, characterized in that, The calculation of the remaining tool life includes: Obtain the cutter wear rate of the tunnel boring machine and calculate the number of rings from the tunnel boring machine to the corresponding section; The tool wear amount is calculated based on the tool wear rate and the number of rings; Obtain the current remaining lifespan of the tunnel boring machine's cutters, and calculate the difference between the current remaining lifespan of the cutters and the amount of cutter wear as the remaining lifespan of the cutters corresponding to that section.

Images