Slurry shield bin opening intelligent decision-making method based on geology-equipment-environment cooperation

Abstract

The invention discloses a slurry shield bin opening intelligent decision-making method based on geology-equipment-environment cooperation, and the method comprises the steps: obtaining geological data, and constructing a finite element model; acquiring simulation bin opening parameters; when the shield tunneling machine reaches the bin opening operation standard, geological data and bin opening simulation parameters are obtained; calculating warehouse opening risk data of each section; selecting an open-bin section pool; selecting at least one optimal bin opening section; when bin opening of the optimal bin opening section is completed, actual bin opening parameters of bin opening of the optimal bin opening section are obtained, and secondary training is conducted on the risk prediction model through the actual bin opening parameters and the corresponding geological data. According to the technical scheme, based on the geological-equipment-environment ternary data fusion architecture, the decision limitation of a single data source is broken through; meanwhile, judgment of human experience in the bin opening site selection process is reduced, the intelligent level of shield construction is effectively improved, the bin opening risk can be well reduced, and better real-time performance and applicability are achieved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to an intelligent decision-making method for opening a slurry shield tunnel based on geology-equipment-environment collaboration. Background Art

[0002] During tunneling, the shield machine's cutters gradually wear out due to friction and impact with the ground. When wear reaches a certain level, the cutter must be opened and replaced to ensure tunneling efficiency and construction quality. However, existing technologies for selecting the opening position present the following problems: 1. Traditional methods rely on manual judgment, lack quantitative data support, and are easily influenced by subjective factors; 2. Geological forecasts are inaccurate, making it difficult to accurately predict risk sources such as the soft-hard interface and fissure water distribution; 3. The timing and location of opening the cutter 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 deficiencies in the prior art, the purpose of this application is to provide an intelligent decision-making method for slurry shield opening based on geology-equipment-environment collaboration.

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

[0005] Acquire geological data of multiple sections of the target excavation 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;

[0006] Simulating the stratum stress release and seepage field of shield machine openings at multiple locations on the finite element model to obtain simulated opening parameters; the simulated opening parameters include water inflow, shield diameter, face pressure data, face displacement data, and surface settlement;

[0007] When the shield machine reaches the opening operation standard, the geological data and the simulated opening parameters of multiple sections within a preset range in front of the shield are obtained;

[0008] Inputting the geological data and the simulated opening parameters into a risk prediction model and obtaining the opening risk data of each section output by the risk prediction model;

[0009] Selecting multiple sections whose opening risk data meet preset requirements to form an opening section pool;

[0010] Select at least one optimal opening section from the opening section pool according to the target conditions and constraint conditions;

[0011] When the optimal opening section completes the opening, the actual opening parameters of the optimal opening section are obtained, and the risk prediction model is trained twice using the actual opening parameters and corresponding geological data.

[0012] When implementing the embodiments of the present application, geological data for different sections can be obtained through methods such as borehole exploration, geological radar, and TSP advance prediction, and a finite element model can be constructed based on this geological data. The finite element model can be used to simulate the state of opening at different locations. Specifically, when the seepage field module is loaded, the load variation of the tunnel face and the surrounding area is applied to realize the calculation of the opening simulation process. After the calculation is completed, the corresponding simulated opening parameters can be obtained. During the excavation process, the slurry shield machine can detect the degree of tool wear through the cutterhead wear sensor to determine whether the opening operation standard has been met. For example, when the tool wear threshold reaches 80%, the opening location selection begins. At this time, geological data and simulated opening parameters for multiple sections within a preset range need to be selected. Specifically, the preset range is the range from the current shield machine position to the position where the tool reaches the tool wear threshold. Since the tool wear condition can be calculated through the tool wear rate, the position where the tool wear threshold is finally reached can also be calculated. When obtaining geological data and simulated opening parameters for multiple sections, geological data and simulated opening parameters for all sections within the preset range can be obtained for subsequent risk assessment.

[0013] In an embodiment of the present application, the opening risk data of each section can be calculated through a pre-trained risk prediction model. At this time, multiple sections whose opening risk data meet the relevant requirements are selected as alternative sections that can be safely opened. At this time, it is necessary to evaluate which section or sections to provide to the construction party; first, it is necessary to determine the target conditions and constraints, where the constraints are generally hard index requirements that need to be met when opening the section, and the target conditions are the conditions expected to be achieved; for example, the constraints use hard requirements on the hard rock ratio and surface settlement, and the target conditions include the minimum risk prediction index, the minimum opening prediction time, and the minimum remaining tool life; at this time, the non-compliant sections are eliminated from the opening section pool through the constraints, and then the sections are screened through the target conditions. For example, the screening process is as follows: all sections that pass the constraint screening are taken as the alternative section set, and the risk prediction index, opening prediction time and tool remaining life of all sections in the alternative section set are obtained as section target parameters; a section is randomly selected from the alternative section set as the selected section, and the section target parameters of the selected section are compared with the section target parameters of other sections; when there is another section whose section target parameters are all greater than the section target parameters of the selected section, the other section is deleted from the alternative section set; when there is another section whose section target parameters are all less than the section target parameters of the selected section, the selected section is deleted from the alternative section set; the selection and comparison of the selected sections are repeated until all remaining sections in the alternative section set are selected and compared, and the alternative section set at this time is provided to the construction party as the optimal opening section. In the embodiment of the present application, after completing an opening, the corresponding actual opening parameters can be obtained, based on which the risk prediction model can be trained a second time, so that the risk prediction model can better adapt to the current formation conditions and further improve the prediction accuracy of the risk prediction model. Through the above technical solution, the embodiment of the present application breaks through the decision-making limitations of a single data source based on the geology-equipment-environment ternary data fusion architecture; at the same time, it reduces the judgment of human experience in the opening site selection process, effectively improves the intelligent level of shield construction, can well reduce the opening risk, and has better real-time and applicability.

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

[0015] Perform non-uniform B-spline interpolation on the geological data of multiple sections according to the section mileage to obtain continuous stratigraphic data;

[0016] A finite element model is built based on the continuous formation data.

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

[0018] Acquire historical opening data, including corresponding risk indicator data, opening duration data, and risk assessment index; characteristic indicators of the risk indicator data include surface settlement 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 at the time of opening;

[0019] Constructing a random forest model based on the characteristic indicators, and using the risk indicator data as input data and the risk assessment index as output data to train the random forest model to generate a risk assessment model;

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

[0021] The risk assessment model and the position opening duration prediction model are used in parallel to form the risk prediction model.

[0022] In a possible implementation, inputting the geological data and the simulated position opening parameters into a risk prediction model and obtaining position opening risk data for each 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 stratum data of the cross section, and the surface settlement data, water inflow, shield diameter, tunnel face displacement data and tunnel face pressure data in the simulation opening parameters are used as prediction input data;

[0024] Inputting the predicted input data into the risk assessment model and receiving the risk prediction index output by the risk assessment model, inputting the predicted input data into the position opening duration prediction model and receiving the position opening prediction duration output by the position opening duration prediction model;

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

[0026] In a possible implementation, selecting multiple sections whose opening risk data meet preset requirements to form an opening section pool includes:

[0027] A plurality of sections with medium or low risk prediction indexes are selected to form the opening section pool.

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

[0029] Conduct a risk assessment on the current position opening process to generate an actual risk index, and record the duration of the position opening process as the actual position opening duration;

[0030] Performing secondary training on the risk assessment model using the actual opening position parameters as newly added input data and the actual risk index as newly added 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 settlement 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.

[0032] In one possible implementation, the constraint conditions include a hard rock ratio greater than or equal to 40% and a surface settlement less than 3 mm; the target conditions include a minimum risk prediction index, a minimum opening prediction time, and a minimum remaining tool life.

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

[0034] Obtaining the tool wear rate of the shield machine and calculating the number of rings from the shield machine to the corresponding section;

[0035] calculating the tool wear amount according to the tool wear rate and the number of rings;

[0036] The current remaining life of the tool of the shield machine is obtained, and the difference between the current remaining life of the tool and the amount of tool wear is calculated as the remaining life of the tool corresponding to the section.

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

[0038] Through the above technical solution, the present invention breaks through the decision-making limitations of a single data source based on the geology-equipment-environment ternary data fusion architecture; at the same time, it reduces the human experience judgment in the site selection process, effectively improves the intelligence level of shield construction, can greatly reduce the site selection risk, and has better real-time and applicability. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of this application, and do not constitute a limitation of the embodiments of the present invention. In the drawings:

[0040] Figure 1 This is a schematic diagram of the method steps of an embodiment of the present application. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of illustration and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate the operations implemented according to some embodiments of the embodiments of the present application. It should be understood that the operations of the flowcharts can be implemented out of sequence, and steps without logical context can be reversed or implemented simultaneously. In addition, those skilled in the art, under the guidance of the contents of this application, can add one or more other operations to the flowchart, or remove one or more operations from the flowchart.

[0042] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed application, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present application.

[0043] Please refer to Figure 1 , which is a flow chart of the intelligent decision-making method for opening a slurry shield based on geology-equipment-environment collaboration provided by an embodiment of the present invention. Furthermore, the intelligent decision-making method for opening a slurry shield based on geology-equipment-environment collaboration can specifically include the contents described in the following steps S1 to S7.

[0044] S1: Acquire geological data of multiple sections of the target excavation 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: simulating the stress release and seepage field of the stratum when the shield machine is opened at multiple positions on the finite element model to obtain 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 shield machine reaches the opening operation standard, the geological data and the simulated opening parameters of multiple sections within a preset range in front of the shield machine are obtained;

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

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

[0049] S6: Select at least one optimal opening section from the opening section pool according to the target condition and the constraint condition;

[0050] S7: When the optimal opening section completes the opening, the actual opening parameters of the optimal opening section are obtained, and the risk prediction model is trained twice using the actual opening parameters and corresponding geological data.

[0051] When implementing the embodiments of the present application, geological data for different sections can be obtained through methods such as borehole exploration, geological radar, and TSP advance prediction, and a finite element model can be constructed based on this geological data. The finite element model can be used to simulate the state of opening at different locations. Specifically, when the seepage field module is loaded, the load variation of the tunnel face and the surrounding area is applied to realize the calculation of the opening simulation process. After the calculation is completed, the corresponding simulated opening parameters can be obtained. During the excavation process, the slurry shield machine can detect the degree of tool wear through the cutterhead wear sensor to determine whether the opening operation standard has been met. For example, when the tool wear threshold reaches 80%, the opening location selection begins. At this time, geological data and simulated opening parameters for multiple sections within a preset range need to be selected. Specifically, the preset range is the range from the current shield machine position to the position where the tool reaches the tool wear threshold. Since the tool wear condition can be calculated through the tool wear rate, the position where the tool wear threshold is finally reached can also be calculated. When obtaining geological data and simulated opening parameters for multiple sections, geological data and simulated opening parameters for all sections within the preset range can be obtained for subsequent risk assessment.

[0052] In an embodiment of the present application, the opening risk data of each section can be calculated through a pre-trained risk prediction model. At this time, multiple sections whose opening risk data meet the relevant requirements are selected as alternative sections that can be safely opened. At this time, it is necessary to evaluate which section or sections to provide to the construction party; first, it is necessary to determine the target conditions and constraints, where the constraints are generally hard index requirements that need to be met when opening the section, and the target conditions are the conditions expected to be achieved; for example, the constraints use hard requirements on the hard rock ratio and surface settlement, and the target conditions include the minimum risk prediction index, the minimum opening prediction time, and the minimum remaining tool life; at this time, the non-compliant sections are eliminated from the opening section pool through the constraints, and then the sections are screened through the target conditions. For example, the screening process is as follows: all sections that pass the constraint screening are taken as the alternative section set, and the risk prediction index, opening prediction time and tool remaining life of all sections in the alternative section set are obtained as section target parameters; a section is randomly selected from the alternative section set as the selected section, and the section target parameters of the selected section are compared with the section target parameters of other sections; when there is another section whose section target parameters are all greater than the section target parameters of the selected section, the other section is deleted from the alternative section set; when there is another section whose section target parameters are all less than the section target parameters of the selected section, the selected section is deleted from the alternative section set; the selection and comparison of the selected sections are repeated until all remaining sections in the alternative section set are selected and compared, and the alternative section set at this time is provided to the construction party as the optimal opening section. In the embodiment of the present application, after completing an opening, the corresponding actual opening parameters can be obtained, based on which the risk prediction model can be trained a second time, so that the risk prediction model can better adapt to the current formation conditions and further improve the prediction accuracy of the risk prediction model. Through the above technical solution, the embodiment of the present application breaks through the decision-making limitations of a single data source based on the geology-equipment-environment ternary data fusion architecture; at the same time, it reduces the judgment of human experience in the opening site selection process, effectively improves the intelligent level of shield construction, can well reduce the opening risk, and has better real-time and applicability.

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

[0054] Perform non-uniform B-spline interpolation on the geological data of multiple sections according to the section mileage to obtain continuous stratigraphic data;

[0055] A finite element model is built based on the continuous formation data.

[0056] When implementing the embodiment of the present application, since the geological data of the cross section are discrete data, it is necessary to generate these discrete data continuously through non-uniform B-spline interpolation, so as to facilitate the construction of the finite element model.

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

[0058] Acquire historical opening data, including corresponding risk indicator data, opening duration data, and risk assessment index; characteristic indicators of the risk indicator data include surface settlement 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 at the time of opening;

[0059] Constructing a random forest model based on the characteristic indicators, and using the risk indicator data as input data and the risk assessment index as output data to train the random forest model to generate a risk assessment model;

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

[0061] The risk assessment model and the position opening duration prediction model are used in parallel to form the risk prediction model.

[0062] When the embodiment of the present application is implemented, the risk prediction model has two main functions, one is to calculate the corresponding risk level, that is, the risk index data, and the other is to calculate the possible opening time data, so in the embodiment of the present application, the risk prediction model is divided into two; for the risk index data, a random forest model is used for training and generation, wherein the characteristic indicators use surface settlement data, water gushing volume, shield diameter, face displacement data, face pressure data, fracture water pressure, fracture development index, water level data and hard rock ratio, and the risk assessment index in the historical opening data can be obtained by expert scoring; multiple decision trees are generated by random sampling of these characteristic indicators, each decision tree randomly obtains multiple characteristic indicators, and completes the construction of the random forest model; a risk assessment model can be generated after training the random forest model with historical opening data. The purpose of the opening time prediction model is to predict the opening time through surface settlement 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. Therefore, a neural network model is used, in which the input layer neurons of the neural network model are defined as 9, the output layer neuron is defined as 1, and the hidden layer is defined as three layers for model training.

[0063] In a possible implementation, inputting the geological data and the simulated position opening parameters into a risk prediction model and obtaining position opening risk data for each 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 stratum data of the cross section, and the surface settlement data, water inflow, shield diameter, tunnel face displacement data and tunnel face pressure data in the simulation opening parameters are used as prediction input data;

[0065] Inputting the predicted input data into the risk assessment model and receiving the risk prediction index output by the risk assessment model, inputting the predicted input data into the position opening duration prediction model and receiving the position opening prediction duration output by the position opening duration prediction model;

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

[0067] In a possible implementation, selecting multiple sections whose opening risk data meet preset requirements to form an opening section pool includes:

[0068] A plurality of sections with medium or low risk prediction indexes are selected to form the opening section pool.

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

[0070] Conduct a risk assessment on the current position opening process to generate an actual risk index, and record the duration of the position opening process as the actual position opening duration;

[0071] Performing secondary training on the risk assessment model using the actual opening position parameters as newly added input data and the actual risk index as newly added 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 settlement 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.

[0073] In one possible implementation, the constraint conditions include a hard rock ratio greater than or equal to 40% and a surface settlement less than 3 mm; the target conditions include a minimum risk prediction index, a minimum opening prediction time, and a minimum remaining tool life.

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

[0075] Obtaining the tool wear rate of the shield machine and calculating the number of rings from the shield machine to the corresponding section;

[0076] calculating the tool wear amount according to the tool wear rate and the number of rings;

[0077] The current remaining life of the tool of the shield machine is obtained, and the difference between the current remaining life of the tool and the amount of tool wear is calculated as the remaining life of the tool corresponding to the section.

[0078] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the composition and steps of each example according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

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

[0080] The units described as separate components may or may not be physically separated. As units, it is obvious that a person of ordinary skill in the art can realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0081] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0082] If the integrated unit is implemented in the form of 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 is essentially 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. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or grid device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0083] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method 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 in the scope of protection of the present invention.

Claims

1. An intelligent decision-making method for slurry shield opening based on geology-equipment-environment collaboration, characterized by: include: Acquire geological data of multiple sections of the target excavation 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; Simulating the stratum stress release and seepage field of shield machine openings at multiple locations on the finite element model to obtain simulated opening parameters; the simulated opening parameters include water inflow, shield diameter, face pressure data, face displacement data, and surface settlement; When the shield machine reaches the opening operation standard, the geological data and the simulated opening parameters of multiple sections within a preset range in front of the shield are obtained; Inputting the geological data and the simulated opening parameters into a risk prediction model and obtaining the opening risk data of each section output by the risk prediction model; Selecting multiple sections whose opening risk data meet preset requirements to form an opening section pool; Select at least one optimal opening section from the opening section pool according to the target conditions and constraint conditions; When the optimal opening section completes the opening, the actual opening parameters of the optimal opening section are obtained, and the risk prediction model is trained twice using the actual opening parameters and corresponding geological data.

2. The intelligent decision-making method for slurry shield opening based on geology-equipment-environment collaboration according to claim 1 is characterized in that: Constructing a finite element model based on the geological data includes: Perform non-uniform B-spline interpolation on the geological data of multiple sections according to the section mileage to obtain continuous stratigraphic data; A finite element model is built based on the continuous formation data.

3. The intelligent decision-making method for slurry shield opening based on geology-equipment-environment collaboration according to claim 1 is characterized in that: The generation of the risk prediction model includes: Acquire historical opening data, including corresponding risk indicator data, opening duration data, and risk assessment index; characteristic indicators of the risk indicator data include surface settlement 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 at the time of opening; Constructing a random forest model based on the characteristic indicators, and using the risk indicator data as input data and the risk assessment index as output data to train the random forest model to generate a risk assessment model; Using the risk indicator data as input data and the position opening duration data as output data, a neural network model is trained to form a position opening duration prediction model; The risk assessment model and the position opening duration prediction model are used in parallel to form the risk prediction model.

4. The intelligent decision-making method for slurry shield opening based on geology-equipment-environment collaboration according to claim 3 is characterized in that: Inputting the geological data and the simulated opening parameters into a risk prediction model and obtaining the opening risk data of each section output by the risk prediction model includes: The fracture water pressure, fracture development index, water level data and hard rock ratio in the stratum data of the cross section, and the surface settlement data, water inflow, shield diameter, tunnel face displacement data and tunnel face pressure data in the simulation opening parameters are used as prediction input data; Inputting the predicted input data into the risk assessment model and receiving the risk prediction index output by the risk assessment model, inputting the predicted input data into the position opening duration prediction model and receiving the position opening prediction duration output by the position opening duration prediction model; The risk prediction index and the position opening prediction duration are used as the position opening risk data of the section.

5. The intelligent decision-making method for slurry shield opening based on geology-equipment-environment collaboration according to claim 4 is characterized in that: Selecting multiple sections whose opening risk data meet preset requirements to form an opening section pool includes: A plurality of sections with medium or low risk prediction indexes are selected to form the opening section pool.

6. The intelligent decision-making method for slurry shield opening based on geology-equipment-environment collaboration according to claim 4 is characterized in that: The secondary training of the risk prediction model using the actual opening parameters and the corresponding geological data includes: Conduct a risk assessment on the current position opening process to generate an actual risk index, and record the duration of the position opening process as the actual position opening duration; Performing secondary training on the risk assessment model using the actual opening parameters as newly added input data and the actual risk index as newly added 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 settlement 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.

7. The intelligent decision-making method for slurry shield opening based on geology-equipment-environment collaboration according to claim 1 is characterized in that: The constraint conditions include that the hard rock ratio is greater than or equal to 40% and the surface settlement is less than 3 mm; the target conditions include that the risk prediction index is minimized, the opening prediction time is minimized, and the remaining life of the tool is minimized.

8. The intelligent decision-making method for slurry shield opening based on geology-equipment-environment collaboration according to claim 6 is characterized in that: The calculation of the remaining tool life includes: Obtaining the tool wear rate of the shield machine and calculating the number of rings from the shield machine to the corresponding section; calculating the tool wear amount according to the tool wear rate and the number of rings; The current remaining life of the tool of the shield machine is obtained, and the difference between the current remaining life of the tool and the amount of tool wear is calculated as the remaining life of the tool corresponding to the section.

Images