Geological prediction and early warning closed-loop control method for earth pressure balance shield construction

Abstract

This disclosure presents a geological prediction and early warning closed-loop control method for earth pressure balance (EPB) shield tunneling. One specific implementation of this method includes: acquiring a two-dimensional refined geological prediction map of the tunnel face, a geological prediction map of the preset longitudinal distance ahead, geological assessment results, and the current construction status; extracting geological boundary parameters, tunnel face grid position parameters, and forward longitudinal prediction node position parameters; generating a control strategy instruction set; adjusting the EPB shield parameters; determining the observation deviation vector; performing reverse correction processing on the geological assessment results, geological boundary parameters, tunnel face grid position parameters, and forward longitudinal prediction node position parameters; determining graded early warning information; and sending the graded early warning information to the construction management terminal. This implementation is related to the field of closed-loop control in EPB shield tunneling, improving the safety, stability, and intelligence level of EPB shield tunneling.

Description

Technical Field

[0001] The embodiments disclosed herein relate to the field of closed-loop control in earth pressure balance shield tunnel construction, specifically to a geological prediction and early warning closed-loop control method for earth pressure balance shield tunnel construction. Background Technology

[0002] During tunnel boring machine (TBM) construction, abrupt changes in geological conditions (such as uneven strata, water-rich sand layers, karst development zones, etc.) can easily lead to risks such as excavation face instability, surface subsidence, gushing, or cutterhead mud cake formation. Traditional control methods rely on manual experience to set earth pressure parameters, which are difficult to dynamically respond to geological changes, resulting in control lag or over-adjustment.

[0003] In the prior art, patent CN113361824B discloses a method for predicting the propulsion speed of an earth pressure balance shield tunneling machine. This method trains an autoregressive model with exogenous variables using historical input-output data and fits the model parameters using a multilayer perceptron to predict the shield's propulsion speed. This solution primarily focuses on the dynamic prediction and adaptive adjustment of the propulsion speed subsystem, falling under the category of operational parameter prediction and control. While it can improve construction safety, it does not aim for rapid geological prediction, does not disclose a reverse correction mechanism for the prediction results, and does not establish an integrated linkage framework between the prediction results and closed-loop control.

[0004] Patent CN114370284B discloses a method and system for real-time sensing of strata properties and adjustment of tunneling parameters at a shield tunneling face. It establishes a mapping model between tunneling parameters and soil properties by acquiring shield tunneling parameters and excavated soil engineering parameters, and then predicts and adjusts the tunneling parameters accordingly. While this solution involves the linkage between strata property sensing and construction parameter adjustment, its core lies in establishing the mapping relationship between tunneling parameters and soil properties; however, it does not disclose a reverse correction mechanism for the prediction results.

[0005] Patent CN113255990A discloses a real-time soil quality prediction system and method for shield tunnel construction. It constructs predictors based on soil characteristic information and slag images obtained from the construction data processing module, and then fuses the two prediction results to achieve real-time soil quality prediction. This solution involves multi-source information fusion for soil quality prediction, which is closer to the present invention than single-modal recognition methods. However, its output mainly focuses on soil category prediction, failing to establish a unified data relationship network between the face grid nodes and the forward longitudinal prediction nodes, and also failing to form a closed-loop control chain of prediction-control-feedback-correction-re-prediction.

[0006] However, existing publicly available patents and research still have at least the following shortcomings: even though some solutions involve stratum perception and parameter adjustment, a complete closed-loop technical system of "spatial prediction - control strategy generation - feedback correction - hierarchical early warning" has not been formed. Therefore, it is still necessary to propose a rapid geological prediction method for the face and the forward longitudinal three-dimensional geological conditions of earth pressure balance shield tunneling to improve the accuracy, timeliness, interpretability, and engineering reliability of geological prediction under complex strata conditions.

[0007] The information disclosed in this background section is only intended to enhance the understanding of the background of the inventive concept, and therefore may contain information that does not form prior art known to those skilled in the art. Summary of the Invention

[0008] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0009] Some embodiments of this disclosure propose a geological prediction and early warning closed-loop control method, device, electronic equipment, and computer-readable medium for earth pressure balance shield tunneling to solve the technical problems mentioned in the background section above.

[0010] In a first aspect, some embodiments of this disclosure provide a closed-loop control method for geological prediction and early warning in earth pressure balance shield tunneling. The method includes: acquiring a two-dimensional refined geological prediction map of the tunnel face, a geological prediction map of the pre-set longitudinal distance ahead, geological assessment results, and the current construction status; extracting geological boundary parameters, tunnel face grid position parameters, and pre-set longitudinal prediction node position parameters based on the aforementioned two-dimensional refined geological prediction map of the tunnel face and the aforementioned geological prediction map of the pre-set longitudinal distance ahead; and generating a control strategy instruction set based on the aforementioned two-dimensional refined geological prediction map of the tunnel face, the aforementioned geological prediction map of the pre-set longitudinal distance ahead, and the aforementioned current construction status. Based on the aforementioned control strategy instruction set, the earth pressure balance shield parameters for earth pressure balance shield construction are adjusted to collect feedback data. In response to the collected feedback data, an observation deviation vector is determined based on the feedback data, the aforementioned two-dimensional geological refinement prediction map of the tunnel face, the aforementioned geological prediction map of the forward longitudinal preset distance, and the aforementioned current construction status. Based on the aforementioned observation deviation vector, the aforementioned geological judgment results, the aforementioned geological boundary parameters, the aforementioned tunnel face grid position parameters, and the aforementioned forward longitudinal predicted node position parameters are subjected to reverse correction processing to generate correction results. Based on the aforementioned correction results, graded early warning information is determined and sent to the construction management terminal.

[0011] Secondly, some embodiments of this disclosure provide a geological prediction and early warning closed-loop control device for earth pressure balance shield tunneling. The device includes: an acquisition unit configured to acquire a two-dimensional refined geological prediction map of the tunnel face, a geological prediction map of the preset longitudinal distance ahead, geological judgment results, and the current construction status; an extraction unit configured to extract geological boundary parameters, tunnel face grid position parameters, and the predicted longitudinal node position parameters based on the aforementioned two-dimensional refined geological prediction map of the tunnel face and the aforementioned geological prediction map of the preset longitudinal distance ahead; a generation unit configured to generate a control strategy instruction set based on the aforementioned two-dimensional refined geological prediction map of the tunnel face, the aforementioned geological prediction map of the preset longitudinal distance ahead, and the aforementioned current construction status; and an adjustment unit configured to... Based on the aforementioned control strategy instruction set, the earth pressure balance shield tunneling parameters are adjusted to collect feedback data. A first determining unit is configured to, in response to the collected feedback data, determine an observation deviation vector based on the feedback data, the aforementioned two-dimensional refined geological prediction map of the tunnel face, the aforementioned geological prediction map of the forward longitudinal preset distance, and the aforementioned current construction status. A reverse correction unit is configured to, based on the aforementioned observation deviation vector, perform reverse correction processing on the aforementioned geological judgment results, the aforementioned geological boundary parameters, the aforementioned tunnel face grid position parameters, and the aforementioned forward longitudinal predicted node position parameters to generate a correction result. A second determining unit is configured to, based on the aforementioned correction result, determine graded early warning information and send the graded early warning information to the construction management terminal.

[0012] Thirdly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.

[0013] Fourthly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

[0014] The above-described embodiments of this disclosure have the following beneficial effects: Through the geological prediction and early warning closed-loop control method for earth pressure balance shield tunneling construction according to some embodiments of this disclosure, the geological judgment results are used for construction parameter recommendation, closed-loop control, feedback correction, graded early warning and emergency response, forming an integrated technical chain of "prediction-control-feedback-correction-re-prediction", which solves the problem of the disconnect between prediction results and on-site control in the prior art, and improves the safety, stability and intelligence level of earth pressure balance shield tunneling construction. Attached Figure Description

[0015] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0016] Figure 1 This is a flowchart of some embodiments of the geological prediction and early warning closed-loop control method for earth pressure balance shield tunneling according to the present disclosure;

[0017] Figure 2 These are schematic diagrams of two-dimensional geological precision prediction maps of the tunnel face, geological prediction maps of the forward longitudinal preset distance, and geological judgment results, based on some embodiments of the geological prediction and early warning closed-loop control method for earth pressure balance shield tunneling according to this disclosure.

[0018] Figure 3 This is a flowchart illustrating the prediction-control-feedback-correction-repreneurial closed-loop control process according to some embodiments of the geological prediction and early warning closed-loop control method for earth pressure balance shield tunneling according to this disclosure.

[0019] Figure 4 This is a structural schematic diagram of some embodiments of the geological prediction and early warning closed-loop control device for earth pressure balance shield tunneling according to the present disclosure.

[0020] Figure 5 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure.

[0021] Figure 4 and Figure 5 The markings are explained below:

[0022] 400- Geological prediction and early warning closed-loop control device for earth pressure balance shield tunneling; 401- Acquisition unit; 402- Extraction unit; 403- Generation unit; 404- Adjustment unit; 405- First determination unit; 406- Reverse correction unit; 407- Second determination unit; 500- Electronic equipment; 501- Processing device; 502- Read-only memory; 503- Random access memory; 504- Bus; 505- Input / output interface; 506- Input device; 507- Output device; 508- Storage device; 509- Communication device. Detailed Implementation

[0023] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0024] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0025] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0026] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0027] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0028] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0029] Figure 1 A flow chart 100 of some embodiments of the geological prediction and early warning closed-loop control method for earth pressure balance shield tunneling according to this disclosure is shown. The geological prediction and early warning closed-loop control method for earth pressure balance shield tunneling includes the following steps:

[0030] Step 101: Obtain the two-dimensional geological refinement prediction map of the working face, the geological prediction map of the preset longitudinal distance ahead, the geological judgment results, and the current construction status.

[0031] In some embodiments, the implementing entity of the geological prediction and early warning closed-loop control method for earth pressure balance shield tunneling can acquire a two-dimensional refined geological prediction map of the tunnel face, a geological prediction map of the pre-set longitudinal distance ahead, geological assessment results, and the current construction status from the shield machine control system, construction monitoring system, or geological prediction system via wired or wireless connection. Here, the shield machine control system can be a system for generating the two-dimensional refined geological prediction map of the tunnel face and the geological prediction map of the pre-set longitudinal distance ahead. The construction monitoring system can be a system for monitoring the current construction status. The geological prediction system can be a system for predicting the geological assessment results. Specifically, the two-dimensional refined geological prediction map of the tunnel face can characterize the spatial coordinates, geological category, water-bearing capacity level, permeability level, and stability level of each grid node in the two-dimensional region of the tunnel face. The geological prediction map of the pre-set longitudinal distance ahead can characterize the spatial coordinates, geological category, water-bearing capacity level, permeability level, and stability level of each pre-set longitudinal prediction node within the pre-set distance ahead in the shield tunneling direction. The geological assessment results can characterize the results obtained after fusing and assessing each node in the two-dimensional refined geological prediction map of the tunnel face and the geological prediction map of the pre-set longitudinal distance ahead. The geological assessment results can characterize the comprehensive geological attributes (which may include: geological category, engineering attribute level) and risk level of each node. The current construction status can characterize the current state during earth pressure balance shield tunneling. Here, the current construction status may include, but is not limited to, at least one of the following: earth chamber pressure, cutterhead rotation speed, cutterhead torque, total thrust, zone thrust, propulsion speed, screw conveyor rotation speed, actual soil discharge volume, foam agent injection volume, polymer injection volume, and shield attitude parameters. Shield attitude parameters are used to characterize the spatial attitude of the shield machine relative to the design axis. Shield attitude parameters may include, but are not limited to, at least one of the following: horizontal deviation, vertical deviation, pitch angle, yaw angle, roll angle, and attitude correction rate.

[0032] Here, geological categories can be, but are not limited to: high-permeability sand layers, water-rich sand layers, gravel layers, boulder-rich layers, and composite strata with soft upper layers and hard lower layers. Engineering attribute levels can characterize the engineering classification results of the degree of influence of strata or nodes on the safety of earth pressure balance shield tunneling construction. Engineering attribute levels can include, but are not limited to, at least one of the following: water-bearing capacity level, permeability level, and stability level. The stability level is used to characterize the risk of instability, collapse, or deformation of the tunnel face or surrounding rock. The water-bearing capacity level is used to characterize the water content of the strata and the risk of water inrush. The permeability level is used to characterize the seepage capacity of the strata and the risk of gushing. For example, the water-bearing capacity level can be: Water-bearing I (Level 1), Water-bearing II (Level 2), Water-bearing III (Level 3), Water-bearing IV (Level 4). The permeability level can be: Permeability I, Permeability II, Permeability III, Permeability IV. The stability level can be: Stability I, Stability II, Stability III, Stability IV. Here, a higher level indicates a higher corresponding risk.

[0033] In practice, this invention establishes a shield tunneling coordinate system, using the cutterhead center as a local coordinate reference point, defining the tunneling direction as the X-axis, the vertical direction as the Y-axis, and the horizontal direction as the Z-axis. The two-dimensional area of ​​the tunnel face is divided into several grid nodes (i.e., tunnel face grid nodes) according to a preset resolution (e.g., a preset resolution of 16×16), with each grid node corresponding to a unique spatial location code. Forward longitudinal prediction nodes are set along the tunneling direction at preset intervals (e.g., a preset interval of 0.5m) (each forward longitudinal prediction node constitutes an area within a preset distance in front of the shield tunneling direction), and a spatial propagation relationship is established with the tunnel face grid nodes.

[0034] As an example, the two-dimensional area of ​​the tunnel face is divided into 16×16 tunnel face grid nodes, and 20 nodes are arranged at a spacing of 0.5m along the tunnel boring direction, corresponding to a preset distance of 10m in the tunnel boring direction ahead; the present invention is not limited to this, the tunnel face grid nodes can be 8×8 to 24×24, and the preset distance in the tunnel boring direction ahead can be 5m to 15m.

[0035] As an example, the two-dimensional detailed geological prediction map of the working face, the geological prediction map of the preset longitudinal distance ahead, and the geological assessment results can be used as a reference. Figure 2 , Figure 2 The diagram illustrates a two-dimensional geological precision prediction map of the tunnel face, a geological prediction map of the forward longitudinal preset distance, and a schematic diagram of the geological determination results, according to some embodiments of the geological prediction and early warning closed-loop control method for earth pressure balance shield tunneling based on the present disclosure.

[0036] It should be noted that the aforementioned wireless connection methods may include, but are not limited to, 3G / 4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other currently known or future wireless connection methods.

[0037] Step 102: Based on the two-dimensional geological refinement prediction map of the working face and the geological prediction map of the forward longitudinal preset distance, extract the geological boundary parameters, the grid position parameters of the working face, and the position parameters of the forward longitudinal prediction nodes.

[0038] In some embodiments, the executing entity can extract geological boundary parameters, face grid position parameters, and forward longitudinal prediction node position parameters based on the two-dimensional geological refinement prediction map of the working face and the geological prediction map with a preset longitudinal distance. In practice, the executing entity can extract these parameters based on the two-dimensional geological refinement prediction map of the working face and the geological prediction map with a preset longitudinal distance using the following steps:

[0039] The first step is to identify the set of nodes where geological attributes of the working face change abruptly in the aforementioned two-dimensional geological refinement prediction map, and to form the working face boundary line based on this set. In practice, firstly, the executing entity can identify each grid node in the aforementioned two-dimensional geological refinement prediction map that meets the preset abrupt change conditions as the set of nodes where geological attributes of the working face change abruptly. Secondly, the executing entity can use a polygon fitting algorithm to fit the set of nodes where geological attributes of the working face change abruptly to generate the working face boundary line. The preset abrupt change conditions can be: nodes that exhibit abrupt changes in geological category, stability level, water abundance level, and permeability level compared to adjacent nodes. Here, the abrupt change can be: a difference of two or more levels in stability level, water abundance level, or permeability level. The abrupt change can also be: a direct change in geological category from high-permeability sand layer / water-rich sand layer to boulder-rich layer / soft-over-hard composite strata. Another abrupt change can be: a direct change in geological category from sand and gravel layer to high-permeability sand layer / water-rich sand layer.

[0040] The second step involves identifying the set of abrupt changes in geological attributes in the aforementioned forward longitudinal preset distance geological prediction map, and forming a forward longitudinal geological boundary line based on this set. In practice, the executing entity can determine the set of forward longitudinal geological attribute abrupt changes in each of the forward longitudinal preset distance geological prediction maps that meets the preset abrupt change conditions. Furthermore, the executing entity can use a polygon fitting algorithm to fit the set of forward longitudinal geological attribute abrupt changes to generate the forward longitudinal boundary line.

[0041] The third step involves parameterizing the aforementioned face boundary line and the forward longitudinal boundary line to generate geological boundary parameters. In practice, the implementing entity can parameterize the face boundary line and the forward longitudinal boundary line using polylines, polylines, spline curves, or control point sequences to obtain the geological boundary parameters.

[0042] The fourth step involves determining the horizontal left-hand coordinates, vertical coordinates, and node offset of each geological attribute abrupt change node in the aforementioned two-dimensional geological refinement prediction map of the tunnel face as the tunnel face grid position parameters. Here, the node offset can be the static deviation value between the actual construction position and the theoretical design position of the tunnel face grid node.

[0043] The fifth step involves determining the mileage position, node spacing correction, and start and end positions of the abnormal section for each forward longitudinal geological attribute abrupt change node corresponding to the aforementioned forward longitudinal preset distance geological prediction map as the forward longitudinal prediction node position parameters. Here, the mileage position can be the distance from the shield tunneling starting point to the forward longitudinal predicted node. The node spacing correction can be the difference between the actual measured spacing between adjacent longitudinal predicted nodes and the designed preset spacing. The starting position of the abnormal section can be the mileage position of the first forward longitudinal geological attribute abrupt change node, and the ending position of the abnormal section can be the mileage position of the last forward longitudinal geological attribute abrupt change node.

[0044] Optionally, the aforementioned implementing entity can also determine the spatial location, area, number of nodes, forward longitudinal length, spatial proportion, and distance from the current position of the tunnel boring machine (TBM) as spatial parameters of the anomaly candidate region. Here, the anomaly candidate region can be: the range extending two grid node spacings outwards from the core of the abrupt geological attribute change node on the two-dimensional geological refinement prediction map of the tunnel face. Alternatively, the anomaly candidate region can be: the range extending two grid node spacings outwards to both sides from the core of the forward longitudinal geological attribute change node on the geological prediction map with a preset forward longitudinal distance.

[0045] Step 103: Based on the two-dimensional geological refinement prediction map of the working face, the geological prediction map of the preset longitudinal distance ahead, and the current construction status, generate a set of control strategy instructions.

[0046] In some embodiments, the execution entity may generate a set of control strategy instructions based on the two-dimensional geological refinement prediction map of the working face, the geological prediction map of the preset longitudinal distance ahead, and the current construction status.

[0047] In practice, the aforementioned implementing entity can generate a control strategy instruction set based on the aforementioned two-dimensional geological refinement prediction map of the working face, the aforementioned geological prediction map of the pre-set longitudinal distance, and the aforementioned current construction status through the following steps:

[0048] The first step is to determine the initial control parameters based on the current construction status and the pre-acquired historical geological case library. The historical geological case library can include multiple historical geological cases. These cases may include, but are not limited to, at least one of the following: historical two-dimensional geological refinement prediction maps of the working face, historical geological prediction maps of the pre-set longitudinal distance ahead, historical geological judgment results, historical construction status, historical control parameters, and historical feedback data. Historical control parameters may include, but are not limited to, at least one of the following: soil chamber pressure setpoint, cutterhead rotation speed, propulsion speed, screw conveyor rotation speed, foaming agent injection volume, polymer injection volume, zone thrust, and attitude control parameters. Here, historical feedback data can be the construction status collected after executing the historical control parameters.

[0049] The second step is to construct a multi-objective optimization model using the following formula:

[0050] ,

[0051] in, Represents the target vector. Represents the control variable vector. This represents the objective function for the stability risk at the working face. Represent the objective function for matching excavated materials with deviation. This represents the objective function relating equipment load and energy consumption. This represents the objective function for controlling the adjustment range. Indicates the lower limit of the control variable. This indicates the upper limit of the control variable. This represents the current control variable vector. This represents the maximum allowable adjustment amount per cycle. Here, the tunnel face stability risk objective function characterizes the risk level of tunnel face instability, collapse, gushing, or soil pressure imbalance under the influence of control variables. The tunnel face stability risk objective function can be a function calculated using arithmetic methods to determine the deviation between the soil pressure setpoint and the target soil pressure, the stability level, the water-bearing capacity level, and the permeability level. The soil discharge matching deviation objective function characterizes the degree of matching between the actual soil discharge and the theoretical soil discharge. The soil discharge matching deviation objective function can be a function calculated using arithmetic methods to determine the theoretical soil discharge and the actual soil discharge. The equipment load and energy consumption objective function characterizes the shield tunneling equipment load and energy consumption levels under the influence of control variables. The equipment load and energy consumption objective function can be a function calculated using arithmetic methods to determine at least one of the cutterhead torque, total thrust, and cutterhead speed. The objective function for control adjustment magnitude characterizes the adjustment magnitude of the target control variable relative to the current control variable. This objective function can be calculated using arithmetic methods based on changes in the soil chamber pressure setpoint, cutterhead speed, propulsion speed, screw conveyor speed, foaming agent injection volume, polymer injection volume, zonal thrust, or attitude control parameters. Therefore, the multi-objective optimization model can achieve a comprehensive balance between reducing the risk of face instability, improving soil removal matching, reducing equipment load and energy consumption, and avoiding drastic fluctuations in control parameters.

[0052] Here, the control variable vector can be a pre-defined construction state. The control variable vector can represent the target value to be set. The control variable vector may include: target soil pressure.

[0053] The third step involves solving the multi-objective optimization model based on the initial control parameters to generate a set of candidate control parameters. In practice, the executing entity can use a preset solution algorithm to solve the multi-objective optimization model based on the initial control parameters to generate a set of candidate control parameters. For example, the preset solution algorithm could be the NSGA-II (Non-dominated sorting genetic algorithm II) algorithm. The parameters of the preset solution algorithm could be: initial control parameters as the initial population, population size of 80, number of iterations of 60, crossover probability of 0.9, and mutation probability of 0.1. As an example, the initial control parameters can be used as the initial population center, combined with the allowable range of control variables to generate the initial population; then, non-dominated sorting, crowding calculation, selection, crossover, and mutation operations can be performed to obtain multiple non-dominated solutions; these multiple non-dominated solutions are then determined as the set of candidate control parameters. Each candidate control parameter in the set of candidate control parameters can correspond to a feasible control scheme.

[0054] The fourth step involves constraining and screening the candidate control parameter set and performing comprehensive scoring to generate the target control parameter. In practice, firstly, the executing entity can pre-set a screening algorithm to constrain and screen the candidate control parameter set to generate a filtered parameter set. Secondly, by pre-setting a candidate score formula, the candidate score set corresponding to the filtered parameter set is determined. Then, the candidate score with the smallest value in the candidate score set and its corresponding filtered parameter are determined as the target control parameter. For example, the preset screening algorithm could be: eliminating candidate control parameters that do not meet the following conditions: upper and lower limits of soil chamber pressure (e.g., upper limit of soil chamber pressure could be 0.2 MPa, upper limit of soil chamber pressure could be 0.3 MPa), cutterhead torque limit (e.g., upper limit of cutterhead torque could be 150 kN·m), propulsion speed limit (e.g., upper limit of propulsion speed could be 50 mm / min), attitude correction rate limit (e.g., upper limit of attitude correction rate could be 0.5‰ / ring), screw conveyor speed limit (e.g., screw conveyor speed could be 20 rpm), and soil conditioner injection rate limit (e.g., soil conditioner injection rate range could be 50-100 L / min). The preset candidate score formula could be:

[0055] ,

[0056] in, Indicates the candidate control parameter number. Indicates the first Candidate scores for each candidate control parameter Indicates risk score, Indicates load score, Indicates the control deviation score. This indicates a score for the range of parameter adjustments. , , , They represent the weights, .

[0057] The fifth step involves generating a control strategy instruction set based on the aforementioned target control parameters. As an example, the target parameters included in the control strategy instructions within the instruction set can be determined based on geological category, engineering attribute level, historical geological case database, and multi-objective optimization results. For instance, in water-rich sand layers, the target cutterhead rotation speed can be 1.0 rpm to 1.5 rpm, and the target advance speed can be 20 mm / min to 35 mm / min; in gravel or boulder-rich layers, the target cutterhead rotation speed can be 0.8 rpm to 1.2 rpm, and the target advance speed can be 15 mm / min to 30 mm / min; in homogeneous clay layers, the target advance speed can be 30 mm / min to 50 mm / min. These values ​​are exemplary and can be adjusted according to the tunnel boring machine model, geological conditions, and construction management requirements, and do not constitute a limitation on the scope of protection of this application.

[0058] In practice, the aforementioned implementing entities can determine the initial control parameters based on the current construction status and the pre-acquired historical geological case database through the following steps:

[0059] The first step is to perform similarity matching between the current construction status and the historical geological case in the acquired historical geological case database, using the following formula, to generate a similarity score:

[0060] ,

[0061] in, Indicates similarity. Indicates the similarity of geological categories. Indicates the similarity of project attribute levels. Indicates the similarity of construction conditions. , , These represent the weights of geological category similarity, engineering attribute level similarity, and construction status similarity, respectively. , Indicates the node sequence number. Indicates the number of nodes. Indicates an indicator function, Indicates the current construction status of the first... The geological category of each node, Indicating the first case in historical geological cases The geological category of each node, Indicates the project attribute level number. Indicates the stability level. Indicates the water-bearing capacity level. Indicates the level of permeability. Indicates the first Project-related attribute weights , Indicates the current construction status of the first... The node of the first Class project attribute level coding, Indicating the first case in historical geological cases The node of the first Class project attribute level coding, Indicates the construction status sequence number. Indicates the number of construction status parameters. Indicates the first Weights of each construction status parameter Indicates the first The scaling factor of each construction state parameter Indicates the current construction status of the first... Normalized values ​​of each construction status parameter. Indicating the first case in historical geological cases Normalized values ​​of each construction status parameter. .For example, It can be 0.4. It can be 0.3. It can be 0.3. This indicates that the value is 1 if the condition within the parentheses is true, and 0 otherwise. The stability level, water abundance level, and permeability level can all be coded as 1, 2, 3, and 4 according to Level I, Level II, Level III, and Level IV, respectively.

[0062] The second step involves extracting a target geological case set from the historical geological case database based on the generated similarities. In practice, firstly, the executing entity can determine the target similarity set as the set of the highest-ranking similarities among the generated similarities (a preset number of similarities). Secondly, the target geological case set corresponding to the target similarity set is extracted from the historical geological case database. For example, the preset number of similarities could be 3.

[0063] The third step is to extract initial control parameters from the above target geological case using the following formula:

[0064] ,

[0065] in, Indicates the initial control parameters. Indicates the target geological case number. This indicates the number of target geological cases in the target geological case set. Indicates the first The similarity between each target geological case Indicates the first Historical control parameters in a target geological case.

[0066] Step 104: Based on the control strategy instruction set, adjust the earth pressure balance shield parameters for earth pressure balance shield construction to collect feedback data.

[0067] In some embodiments, the aforementioned executing entity can adjust the earth pressure balance shield parameters for earth pressure balance shield tunneling based on the aforementioned control strategy instruction set, in order to collect feedback data. In practice, the aforementioned executing entity can execute the aforementioned control strategy instruction set to adjust the earth pressure balance shield parameters for earth pressure balance shield tunneling and collect feedback data. The earth pressure balance shield parameters may include, but are not limited to, at least one of the following: earth chamber pressure, cutterhead rotation speed, cutterhead torque, total thrust, propulsion speed, screw conveyor rotation speed, actual excavated soil volume, foam agent injection volume, polymer injection volume, and shield attitude parameters. Here, the feedback data can be the current measured data collected within the current control cycle after executing the aforementioned control strategy instruction set and adjusting the earth pressure balance shield parameters for earth pressure balance shield tunneling. For example, the feedback data may include, but is not limited to, at least one of the following: measured earth chamber pressure, measured cutterhead torque, measured cutterhead rotation speed, measured propulsion speed, measured screw conveyor rotation speed, theoretical excavated soil volume, actual excavated soil volume, soil particle composition, foam agent injection volume, polymer injection volume, and shield attitude deviation. The attitude deviation of the tunnel boring machine may include, but is not limited to, at least one of the following: horizontal deviation, vertical deviation, pitch angle, yaw angle, and roll angle.

[0068] Step 105: In response to the collected feedback data, determine the observation deviation vector based on the feedback data, the two-dimensional geological refinement prediction map of the working face, the geological prediction map of the forward longitudinal preset distance, and the current construction status.

[0069] In some embodiments, the execution entity may, in response to the collection of feedback data, determine the observation deviation vector based on the feedback data, the two-dimensional geological refinement prediction map of the working face, the geological prediction map of the forward longitudinal preset distance, and the current construction status.

[0070] In practice, the aforementioned implementing entity can determine the observation deviation vector based on the aforementioned feedback data, the aforementioned two-dimensional geological refinement prediction map of the working face, the aforementioned geological prediction map of the forward longitudinal preset distance, and the aforementioned current construction status through the following steps:

[0071] The first step, based on the feedback data above, is to construct the observation vector using the following formula:

[0072] ,

[0073] in, Represents the observation vector. This represents the measured value of the earth pressure chamber. This represents the measured value of the cutterhead torque. This represents the measured propulsion speed. This represents the measured value of the screw conveyor speed. Indicates the theoretical amount unearthed. This indicates the actual amount of excavated material. Indicates the amount of foaming agent injected. Indicates the amount of polymer injected. This indicates the deviation in the shield tunnel's attitude.

[0074] The second step involves combining the aforementioned geological boundary parameters, the aforementioned face grid location parameters, and the aforementioned forward longitudinal predicted node location parameters into a parameter vector to be corrected. Here, the parameter vector to be corrected can be expressed as:

[0075] ,

[0076] in, Represents the vector of parameters to be corrected. This indicates the mesh position parameters at the tunnel face. This indicates the position parameters of the forward longitudinal predicted nodes. Indicates geological boundary parameters.

[0077] The third step involves constructing a prediction vector based on the aforementioned parameter vector to be corrected, the aforementioned two-dimensional geological refinement prediction map of the tunnel face, the aforementioned geological prediction map of the preset longitudinal distance ahead, and the aforementioned current construction status, using the following formula:

[0078] ,

[0079] in, Represents the prediction vector. Represents the vector of parameters to be corrected. This section describes the construction response prediction model. A construction response prediction model can be a prediction model that maps geological assessment results and the current construction state to the construction response. As an example, the prediction vector represents the predicted construction response under the conditions of the current geological assessment results, the current construction state, and the parameter vector to be corrected; the parameter vector to be corrected represents a parameter vector formed by the combination of geological boundary parameters, face grid position parameters, and forward longitudinal prediction node position parameters; the construction response prediction model is a prediction model used to characterize the mapping relationship between geological assessment results, the current construction state, control parameters, and the construction response. In practice, the construction response prediction model can be trained based on a historical geological case database and historical feedback data. The inputs to the construction response prediction model can include historical geological assessment results, historical face grid position parameters, historical forward longitudinal prediction node position parameters, historical geological boundary parameters, and historical control parameters; the outputs of the construction response prediction model can include soil chamber pressure, cutterhead load, excavated soil volume, advance speed, screw conveyor speed, and shield attitude response. The construction response prediction model can employ regression models, neural network models, random forest models, support vector regression models, or prediction models that combine physical constraints with data-driven approaches.

[0080] Fourth, based on the above observation vector and the above prediction vector, the observation bias vector is determined using the following formula:

[0081] ,

[0082] in, This represents the observation bias vector. As an example, the observation bias vector is used to characterize the difference between the measured response and the predicted response. If only one feedback sample is collected within a control period, then... A single deviation vector is used. If feedback samples are collected at multiple times within a control cycle, multiple deviation vectors can be formed, and these multiple deviation vectors can be stacked in chronological order to form a deviation matrix or an extended deviation vector.

[0083] Step 106: Based on the observation deviation vector, perform reverse correction processing on the geological judgment results, geological boundary parameters, face grid location parameters and forward longitudinal prediction node location parameters to generate correction results.

[0084] In some embodiments, the execution entity may perform reverse correction processing on the geological determination results, the geological boundary parameters, the face grid position parameters, and the forward longitudinal prediction node position parameters based on the observation deviation vector to generate correction results.

[0085] In practice, the aforementioned implementing entity can perform reverse correction processing on the aforementioned geological determination results, geological boundary parameters, face grid location parameters, and forward longitudinal prediction node location parameters based on the aforementioned observation deviation vector through the following steps to generate correction results:

[0086] The first step is to construct the boundary sensitivity matrix.

[0087] The second step involves determining the parameter correction amount based on the aforementioned boundary sensitivity matrix and observation bias vector using the following formula:

[0088] ,

[0089] in, Indicates the parameter correction amount. Represents the boundary sensitivity matrix. Represents the regularization coefficient. Represents the observation weight matrix. Represents the identity matrix.

[0090] Therefore, the boundary correction amount can be solved using the least squares method and the dynamic boundary update algorithm.

[0091] The third step involves updating the parameter vector to be corrected using the following formula, based on the aforementioned parameter correction amounts, to generate the parameter update vector:

[0092] ,

[0093] in, This represents the parameter update vector.

[0094] The fourth step involves generating, based on the parameter update vector, the aforementioned two-dimensional geological refinement prediction map of the working face, the aforementioned geological prediction map of the preset longitudinal distance ahead, the corrected two-dimensional geological refinement prediction map of the working face corresponding to the aforementioned geological assessment result, the corrected geological prediction map of the preset longitudinal distance ahead, and the corrected geological assessment result. In practice, the executing entity can generate the aforementioned two-dimensional geological refinement prediction map of the working face, the aforementioned geological prediction map of the preset longitudinal distance ahead, the corrected two-dimensional geological refinement prediction map of the working face corresponding to the aforementioned geological assessment result, the corrected geological prediction map of the preset longitudinal distance ahead, and the corrected geological assessment result through the following sub-steps based on the parameter update vector:

[0095] The first sub-step involves updating the spatial coordinates of the face grid nodes, the spatial coordinates of the forward longitudinal prediction nodes, and the geological boundary parameters based on the parameter update vector, resulting in updated spatial coordinates of the face grid nodes, updated spatial coordinates of the forward longitudinal prediction nodes, and updated geological boundary parameters. In practice, the aforementioned execution entity can update the parameters corresponding to the parameter update vector in the face grid node spatial coordinates, forward longitudinal prediction node spatial coordinates, and geological boundary parameters to the parameters included in the parameter update vector, thus obtaining updated spatial coordinates of the face grid nodes, updated spatial coordinates of the forward longitudinal prediction nodes, and updated geological boundary parameters.

[0096] The second sub-step involves re-determining the geological category, water-bearing capacity, permeability, and stability level of each grid node in the two-dimensional region of the tunnel face, based on the updated spatial coordinates of the face grid nodes and the updated geological boundary parameters, to generate a corrected two-dimensional geological refinement prediction map of the tunnel face. In practice, the aforementioned executing entity can send the updated spatial coordinates of the face grid nodes and the updated geological boundary parameters to the aforementioned tunnel boring machine (TBM) control system, and receive the corrected two-dimensional geological refinement prediction map of the face sent by the TBM control system.

[0097] The third sub-step involves re-determining the geological category, water-bearing capacity, permeability, and stability level of each forward longitudinal prediction node within a preset distance in the tunnel boring machine's direction, based on the updated spatial coordinates of the forward longitudinal prediction nodes and the updated geological boundary parameters, to generate a corrected forward longitudinal preset distance geological prediction map. In practice, the aforementioned executing entity can send the updated spatial coordinates of the forward longitudinal prediction nodes and the updated geological boundary parameters to the aforementioned tunnel boring machine control system, and receive the corrected forward longitudinal preset distance geological prediction map sent by the aforementioned tunnel boring machine control system.

[0098] The fourth sub-step involves fusing and determining the geological category, water-bearing capacity, permeability, and stability level of each node based on the corrected two-dimensional geological refinement prediction map of the working face and the corrected longitudinal preset distance geological prediction map, to generate the corrected geological determination result. In practice, the aforementioned executing entity can send the corrected two-dimensional geological refinement prediction map of the working face and the corrected longitudinal preset distance geological prediction map to the aforementioned geological prediction system, and receive the corrected geological determination result sent by the aforementioned geological prediction system.

[0099] As an example, based on the corrected geological categories and engineering attribute levels of each node, nodes that meet the preset anomaly judgment conditions are selected, and the spatial coordinates of the corrected geological anomaly area are determined through spatial connectivity analysis. The preset anomaly judgment conditions may include, but are not limited to, at least one of the following: the geological category is a water-rich sand layer, a high-permeability sand layer, a gravel layer, a boulder-rich layer, or a soft-over-hard composite stratum; the stability level reaches level III or IV; the water-richness level reaches level III or IV; the permeability level reaches level III or IV; and there is a sudden change in the geological category or engineering attribute level between adjacent nodes. Therefore, the correction results include not only the corrected two-dimensional refined geological prediction map of the working face, the corrected geological prediction map of the preset longitudinal distance ahead, and the corrected geological judgment results, but also the spatial coordinates of the corrected geological anomaly area.

[0100] The fifth step is to determine the above-mentioned two-dimensional geological refinement prediction map of the corrected working face, the above-mentioned geological prediction map of the longitudinal preset distance ahead of the correction, and the above-mentioned geological judgment results as the correction results.

[0101] In practice, the aforementioned implementing entity can construct the boundary sensitivity matrix through the following steps:

[0102] The first step is to apply a small perturbation to the parameter vector to be corrected.

[0103] In practice, the aforementioned execution entity can use the parameter vector to be corrected. The first in One parameter to be corrected Apply small perturbations As an example, a small perturbation can be between 0.05m and 0.10m. A small perturbation can also be 1% to 3% of the corresponding mesh size or node spacing.

[0104] The second step is to determine the set of predicted response vectors corresponding to the set of parameters to be perturbed after applying a small perturbation. The predicted response vectors in the predicted response vector set can be determined by the following formula:

[0105] ,

[0106] in, Indicates the first A predicted response vector, This represents the predicted response without any perturbation. This represents the predicted response after applying a small perturbation. This indicates a small perturbation. Indicates the first Unit perturbation vector. Here, the first... The predicted response vector can be the boundary sensitivity matrix. The List.

[0107] The third step involves combining the predicted response vector set to generate a boundary sensitivity matrix. In practice, the executing entity can combine the predicted response vectors in the predicted response vector set column-wise to form the boundary sensitivity matrix.

[0108] Step 107: Based on the correction results, determine the graded early warning information and send the graded early warning information to the construction management terminal.

[0109] In some embodiments, the aforementioned executing entity may determine graded early warning information based on the aforementioned correction results, and send the graded early warning information to the construction management terminal. Here, the construction management terminal may be a terminal that performs alarm processing on the graded early warning information. Here, alarm processing may involve displaying warning text or issuing warning sounds.

[0110] In practice, the aforementioned implementing entities can determine the tiered early warning information based on the above correction results through the following steps:

[0111] The first step, based on the above-mentioned corrected geological assessment results, is to select anomaly nodes that meet the preset anomaly assessment conditions from the above-mentioned corrected two-dimensional geological refinement prediction map of the working face and the above-mentioned corrected longitudinal preset distance geological prediction map, thereby obtaining an anomaly node set. The preset anomaly assessment conditions may include, but are not limited to, at least one of the following: the geological category is water-rich sand layer, high-permeability sand layer, gravel layer, boulder-rich layer, or a soft-over-hard composite stratum; the stability level reaches level III or IV; the water-richness level reaches level III or IV; the permeability level reaches level III or IV; and there is a sudden change in the geological category or engineering attribute level between adjacent nodes.

[0112] The second step involves performing spatial connectivity analysis on the aforementioned set of anomalous nodes to generate a set of geological anomaly regions. In practice, the executing entity can merge spatially adjacent anomalous nodes or nodes within a preset distance threshold into the same geological anomaly region. For example, the preset distance threshold could be, but is not limited to, 0.5 meters, 1 meter, or 2 meters. Therefore, there can be one or multiple geological anomaly regions. When multiple geological anomaly regions exist, each geological anomaly region corresponds to a set of spatial coordinates.

[0113] Third, for each of the aforementioned geological anomaly regions, perform the following processing sub-steps:

[0114] The first sub-step involves determining the stability score, water abundance score, permeability score, tunneling speed score, estimated arrival time score, and anomaly impact range score corresponding to the aforementioned geological anomaly areas.

[0115] The second sub-step involves determining the comprehensive risk score based on the aforementioned stability score, water abundance score, permeability score, tunneling speed score, estimated arrival time score, and abnormal impact range score, using the following formula:

[0116] ,

[0117] in, Indicates the sequence number of the geological anomaly region. Indicates the first The comprehensive risk score of each geologically anomalous area Indicates the first Stability scores for each geologically anomalous region Indicates the first Water-bearing fraction of each geologically anomalous region Indicates the first Permeability score of each geologically anomalous region Indicates the first The tunneling speed score for each geologically anomalous area Indicates the first The estimated time of arrival fraction for each geological anomaly region Indicates the first The score of the anomalous influence range of each geological anomaly region , , , , , They represent the weights, .For example, It can be 0.3. It can be 0.2. It can be 0.2. It can be 0.1. It can be 0.1. It can be 0.1.

[0118] As an example, the geological risk contribution value can be expressed as: The risk contribution value of equipment or construction status can be expressed as: .when ≥15, or When the value is ≥1.25, the geological risk contribution value can be considered significantly higher than the equipment or construction status risk contribution value, and in this case, it can be appropriately increased. , , , Corresponding weights; when ≥15, or When the value is ≥1.25, the risk contribution value of the equipment or construction status can be considered significantly higher than the geological risk contribution value, and in this case, it can be appropriately increased. , Corresponding weights.

[0119] The third sub-step involves determining the target comprehensive risk score based on the aforementioned comprehensive risk score using the following formula:

[0120] ,

[0121] in, Indicates the first The target comprehensive risk score for each geologically anomalous area This represents a compound anomaly correction term. Here, The number of composite anomalies is determined. For example, when there is one type of construction feedback anomaly, Take 5; when there are two types of construction feedback anomalies, Take 10; when there are 3 or more types of construction feedback anomalies, Take 15. When no composite anomaly is detected, Take 0.

[0122] Here, composite anomalies can refer to the simultaneous existence of geological anomalies and construction feedback anomalies within the same geological anomaly area or the same pre-defined spatial neighborhood. Geological anomalies can include, but are not limited to, at least one of the following: water-rich anomalies, high permeability anomalies, stability anomalies, and unfavorable strata anomalies. For example, water-rich anomalies can refer to high stratum water content, with a water-richness level of III or IV, or phenomena such as increased fluctuations in soil pressure in the soil chamber, increased moisture content of excavated soil, and the excavated soil from the screw conveyor exhibiting a fluid plastic state in the feedback data. High permeability anomalies can refer to stratum permeability level of III or IV, or phenomena such as difficulty in maintaining soil pressure in the soil chamber, water and sand mixed in the excavated soil from the screw conveyor, and an abnormally increased actual excavation rate in the feedback data. Stability anomalies can refer to stability level of III or IV, or the presence of risks of collapse, deformation, instability, or soil pressure imbalance at the working face, surrounding rock, or excavation face. Unfavorable geological formations can refer to geological categories such as sand and gravel layers, boulder-rich layers, composite strata with soft upper layers and hard lower layers, fault fracture zones, karst fissure zones, or other strata that adversely affect the safety of earth pressure balance shield tunneling. Construction feedback anomalies may include, but are not limited to, at least one of the following: abnormal fluctuations in soil chamber pressure, abnormal increases in cutterhead load, abnormal actual soil removal rate, abnormal soil particle size distribution, abnormal shield posture, and abnormal soil improvement effects. For example, abnormal fluctuations in soil chamber pressure can refer to a continuous deviation or drastic fluctuation in the measured soil chamber pressure relative to the target soil chamber pressure; abnormal increases in cutterhead load can refer to the cutterhead torque exceeding a preset torque threshold or the total thrust exceeding a preset total thrust threshold (for example, the preset torque threshold could be 150 kN·m, and the preset total thrust threshold could be 1000 kN (kilonewtons)); abnormal actual soil discharge rate can refer to the deviation between the actual soil discharge and the theoretical soil discharge exceeding a preset deviation threshold (for example, the preset deviation threshold could be 10%); abnormal soil particle count can refer to abnormal changes in the content of coarse particles, pebbles, boulders, or fine particles in the soil (for example, the proportion of coarse particles is greater than 15%, pebbles are greater than 15%), etc. The following are considered abnormal conditions: The proportion of stone or boulders is greater than 50%, or the proportion of fine particles is less than 15%; abnormal shield attitude can refer to horizontal deviation, vertical deviation, pitch angle, yaw angle, or roll angle exceeding the preset allowable range (for example, the preset allowable range can be: horizontal and vertical deviation less than 50 mm, pitch angle, yaw angle, and roll angle less than 1); abnormal soil improvement effect can refer to soil slump, moisture content, or foaming agent injection amount, polymer injection amount not meeting the preset requirements (for example, the preset requirements can be: soil slump greater than 160 mm and less than 180 mm, moisture content greater than 12% and less than 18%, foaming agent injection amount and polymer injection amount of 10%-20% of soil volume).

[0123] The fourth step is to determine the target with the highest overall risk score among all identified targets as the target early warning risk score.

[0124] Fifth, in response to the determination that the aforementioned target warning risk score meets the first preset warning condition, the first preset warning information is identified as graded warning information. The first preset warning condition can be: the target warning risk score is greater than or equal to the first preset warning score. For example, the first preset warning score can be 85. The first preset warning information can represent a Level I warning.

[0125] Step 6: In response to determining that the target warning risk score meets the second preset warning condition, the second preset warning information is identified as graded warning information. The second preset warning condition can be: the target warning risk score is less than the first preset warning score and greater than or equal to the second preset warning score. For example, the second preset warning score can be 60. The second preset warning information can represent a Level II warning.

[0126] Step 7: In response to determining that the target warning risk score meets the third preset warning condition, the third preset warning information is identified as graded warning information. The third preset warning condition can be that the target warning risk score is less than the second preset warning score and greater than or equal to the third preset warning score. For example, the third preset warning score could be 40. The third preset warning information can represent a Level III warning.

[0127] Therefore, by clarifying the weighting and scoring criteria for stability, water abundance, permeability, tunneling speed, expected arrival time, and scope of abnormal impact, the repeatability, interpretability, and engineering feasibility of graded early warning can be improved.

[0128] As an example, the emergency response process for a Level I warning should at least include immediately reducing the advance speed, increasing the soil pressure setpoint, suspending the advance under high-risk conditions, increasing the amount of amendment injected, and organizing on-site verification; the emergency response process for a Level II warning should at least include reducing the advance speed, locally adjusting the soil pressure and screw conveyor speed, increasing the monitoring frequency, and preparing emergency response measures; the emergency response process for a Level III warning should at least include maintaining controlled advance, strengthening monitoring, dynamically assessing the warning level, and continuously pushing risk alerts to the construction management terminal.

[0129] In practice, the aforementioned implementing entities can determine the stability score, water-bearing capacity score, permeability score, tunneling speed score, estimated arrival time score, and anomaly impact range score corresponding to the aforementioned geological anomaly areas through the following steps:

[0130] The first step is to determine the estimated arrival time by the ratio of the shield boundary distance to the current tunneling speed. The shield boundary distance can be the distance from the current position of the shield to the nearest boundary of the aforementioned geological anomaly area.

[0131] The second step is to determine the tunneling speed fraction. In practice, the aforementioned implementing entity can determine the tunneling speed fraction through the following steps: First, determine the ratio of the current tunneling speed to the preset ground safety reference speed as the shield speed ratio. Second, in response to determining that the shield speed ratio is less than or equal to a first preset speed ratio, determine the first preset speed fraction as the tunneling speed fraction. Third, in response to determining that the shield speed ratio is greater than the first preset speed ratio and less than or equal to a second preset speed ratio, determine the second preset speed fraction as the tunneling speed fraction. Fourth, in response to determining that the shield speed ratio is greater than the second preset speed ratio and less than or equal to a third preset speed ratio, determine the third preset speed fraction as the tunneling speed fraction. Fifth, in response to determining that the shield speed ratio is greater than the third preset speed ratio, determine the fourth preset speed fraction as the tunneling speed fraction. For example, the first preset speed ratio can be 0.6. The second preset speed ratio can be 0.8. The third preset speed ratio can be 1.0. The first preset speed fraction can be 20. The second preset speed fraction can be 40. The third preset speed fraction can be 70. The fourth preset speed score can be 90. For example, for water-rich sand layers, the preset safe reference speed for the strata can be 20 mm / min to 35 mm / min; for gravel layers, it can be 15 mm / min to 30 mm / min; and for homogeneous clay layers, it can be 30 mm / min to 50 mm / min. These values ​​can be adjusted according to engineering geological conditions, tunnel boring machine (TBM) models, and construction management requirements. Here, the highest possible tunneling speed score is 90 points to characterize the risks associated with excessively high tunneling speeds; if it is necessary to further emphasize the risks of high-speed tunneling, the tunneling speed score when the TBM speed ratio is >1.20 can be set to 100 points.

[0132] The third step is to determine the estimated arrival time fraction based on the aforementioned estimated arrival time. In practice, the executing entity can determine the estimated arrival time fraction based on the aforementioned estimated arrival time through the following steps: First, in response to determining that the aforementioned estimated arrival time is greater than a first preset arrival time, the first preset time fraction is determined as the estimated arrival time fraction. Second, in response to determining that the aforementioned estimated arrival time is less than or equal to the first preset arrival time and greater than a second preset arrival time, the second preset time fraction is determined as the estimated arrival time fraction. Third, in response to determining that the aforementioned estimated arrival time is less than or equal to the second preset arrival time and greater than a third preset arrival time, the third preset time fraction is determined as the estimated arrival time fraction. Fourth, in response to determining that the aforementioned estimated arrival time is less than or equal to the third preset arrival time, the fourth preset time fraction is determined as the estimated arrival time fraction. For example, the first preset arrival time can be 180 minutes. The second preset arrival time can be 90 minutes. The third preset arrival time can be 30 minutes. The first preset time fraction can be 20. The second preset time fraction can be 40. The third preset time fraction can be 70. The fourth preset time fraction can be 100.

[0133] The fourth step is to determine the score of the anomaly's impact range. In practice, the implementing entity can determine the score of the anomaly's impact range based on the aforementioned geological anomaly area using the following steps: First, determine the area of ​​the anomaly region corresponding to the geological anomaly region using coordinate analysis. Second, determine the ratio of the anomaly region area to the total area of ​​the working face as the anomaly impact ratio. The total area of ​​the working face can be the total area of ​​the two-dimensional region of the working face. Third, in response to determining that the anomaly impact ratio is less than or equal to a first preset anomaly ratio, determine the first preset anomaly impact score as the initial anomaly impact range score. Fourth, in response to determining that the anomaly impact ratio is greater than the first preset anomaly ratio and less than or equal to a second preset anomaly ratio, determine the second preset anomaly impact score as the initial anomaly impact range score. Fifth, in response to determining that the anomaly impact ratio is greater than the second preset anomaly ratio and less than or equal to a third preset anomaly ratio, determine the third preset anomaly impact score as the initial anomaly impact range score. Sixth, in response to determining that the anomaly impact ratio is greater than the third preset anomaly ratio, determine the fourth preset anomaly impact score as the initial anomaly impact range score. For example, the first preset anomaly ratio could be 10%, and the second preset anomaly ratio could be 25%. The third preset anomaly ratio can be 50%. The first preset anomaly impact score can be 20. The second preset anomaly impact score can be 40. The third preset anomaly impact score can be 70. The fourth preset anomaly impact score can be 100. Seventh, in response to determining that the length of the anomaly region corresponding to the geological anomaly region (the anomaly region length can be: the difference between the end position and the start position of the anomaly segment corresponding to the geological anomaly region) is greater than the preset length, the sum of the initial anomaly impact range score and the preset length score is determined as the target anomaly impact range score. For example, the preset length can be 5 meters. The preset length score can be 10. Eighth, in response to determining that the above target anomaly impact range score is less than or equal to the fourth preset anomaly impact score, the above target anomaly impact score is determined as the anomaly impact score. Ninth, in response to determining that the above target anomaly impact range score is greater than the fourth preset anomaly impact score, the fourth preset anomaly impact score is determined as the anomaly impact score.

[0134] Step 5: Determine the stability score. In practice, the implementing entity can determine the stability score based on the above-mentioned corrected geological assessment results through the following steps: First, in response to determining that the stability level corresponding to the above-mentioned geological anomaly area included in the above-mentioned corrected geological assessment results is stability level I, a first preset stability score is determined as the stability score. Second, in response to determining that the stability level corresponding to the above-mentioned geological anomaly area included in the above-mentioned corrected geological assessment results is stability level II, a second preset stability score is determined as the stability score. Third, in response to determining that the stability level corresponding to the above-mentioned geological anomaly area included in the above-mentioned corrected geological assessment results is stability level III, a third preset stability score is determined as the stability score. Fourth, in response to determining that the stability level corresponding to the above-mentioned geological anomaly area included in the above-mentioned corrected geological assessment results is stability level IV, a fourth preset stability score is determined as the stability score. For example, the first preset stability score can be 25. The second preset stability score can be 50. The third preset stability score can be 75. The fourth preset stability score can be 100.

[0135] Step 6: Determine the water-bearing score. In practice, the implementing entity can determine the water-bearing score based on the above-mentioned corrected geological assessment results through the following steps: First, in response to determining that the water-bearing level corresponding to the above-mentioned geological anomaly area included in the above-mentioned corrected geological assessment results is water-bearing level I, the first preset water-bearing score is determined as the water-bearing score. Second, in response to determining that the water-bearing level corresponding to the above-mentioned geological anomaly area included in the above-mentioned corrected geological assessment results is water-bearing level II, the second preset water-bearing score is determined as the water-bearing score. Third, in response to determining that the water-bearing level corresponding to the above-mentioned geological anomaly area included in the above-mentioned corrected geological assessment results is water-bearing level III, the third preset water-bearing score is determined as the water-bearing score. Fourth, in response to determining that the water-bearing level corresponding to the above-mentioned geological anomaly area included in the above-mentioned corrected geological assessment results is water-bearing level IV, the fourth preset water-bearing score is determined as the water-bearing score. For example, the first preset water-bearing score can be 20. The second preset water-bearing score can be 45. The third preset water-bearing score can be 75. The fourth preset water-bearing score can be 100.

[0136] Step 7: Determine the permeability score. In practice, the implementing entity can determine the permeability score based on the above-mentioned corrected geological assessment results through the following steps: First, in response to determining that the permeability level corresponding to the above-mentioned geological anomaly area included in the above-mentioned corrected geological assessment results is permeability level I, a first preset permeability score is determined as the permeability score. Second, in response to determining that the permeability level corresponding to the above-mentioned geological anomaly area included in the above-mentioned corrected geological assessment results is permeability level II, a second preset permeability score is determined as the permeability score. Third, in response to determining that the permeability level corresponding to the above-mentioned geological anomaly area included in the above-mentioned corrected geological assessment results is permeability level III, a third preset permeability score is determined as the permeability score. Fourth, in response to determining that the permeability level corresponding to the above-mentioned geological anomaly area included in the above-mentioned corrected geological assessment results is permeability level IV, a fourth preset permeability score is determined as the permeability score. For example, the first preset permeability score can be 20. The second preset permeability score can be 45. The third preset permeability score can be 75. The fourth preset permeability score can be 100.

[0137] As an example, if a geological anomaly area comprises multiple nodes, each node can correspond to a stability level, a water-bearing level, and a permeability level. Therefore, a score can be calculated separately for each geological anomaly area. For a given geological anomaly area, the corresponding score can be determined using the highest risk level of each anomaly node within the area, or it can be determined using an area-weighted average or a node-number-weighted average. Preferably, to ensure construction safety, the highest risk level can be used to determine the corresponding score.

[0138] Optionally, the aforementioned implementing entity may also use the corrected two-dimensional geological refinement prediction map of the tunnel face, the corrected longitudinal preset distance geological prediction map, and the corrected geological judgment result, including the correction results, as the two-dimensional geological refinement prediction map of the tunnel face, the forward longitudinal preset distance geological prediction map, and the geological judgment result for the next control cycle, so as to execute the aforementioned geological prediction and early warning closed-loop control method for earth pressure balance shield tunneling again.

[0139] Therefore, the aforementioned executing entity can collect feedback data after executing the control strategy instruction set, and correct the two-dimensional geological refinement prediction map of the working face, the geological prediction map of the forward longitudinal preset distance, and the geological judgment result based on the feedback data. The corrected two-dimensional geological refinement prediction map of the working face, the geological prediction map of the forward longitudinal preset distance, and the geological judgment result are used as the two-dimensional geological refinement prediction map of the working face, the geological prediction map of the forward longitudinal preset distance, and the geological judgment result for the next control cycle, so as to generate the control strategy instruction set again, thereby forming a closed-loop control chain of prediction-control-feedback-correction-reprediction. As an example, the process of prediction-control-feedback-correction-reprediction closed-loop control can be referred to Figure 3 , Figure 3A schematic flowchart illustrating the prediction-control-feedback-correction-repreneurial closed-loop control process of some embodiments of the geological prediction and early warning closed-loop control method for earth pressure balance shield tunneling according to the present disclosure is shown.

[0140] As an example, the present invention will be further illustrated below with reference to the Zhuchong Tunnel and Xialou Tunnel in the Chushandian Reservoir Irrigation Area Project.

[0141] Both the Zhuchong Tunnel and the Xialou Tunnel fall under the category of earth pressure balance shield tunneling for water conveyance. Compared to shield tunneling sections in urban rail transit, these projects are characterized by long continuous tunneling distances, high requirements for tunnel quality and lining seepage prevention, frequent changes in surrounding rock types, and significant impacts of local water-rich strata on tunnel face stability. In this scenario, in addition to conventional mechanical load parameters such as cutterhead torque, total thrust, and propulsion speed, factors such as soil chamber pressure stability, the continuity of soil discharge by the screw conveyor, the matching degree between theoretical and actual soil discharge rates, the effect of spoil remediation, changes in the particle composition of discharged soil, and the risks of rock jamming and gushing all significantly affect tunnel face stability control, geological identification accuracy, and tunneling safety. Therefore, this invention, targeting the earth pressure balance shield tunneling characteristics of the Zhuchong Tunnel and Xialou Tunnel in the Chushandian Reservoir irrigation area, establishes an implementation scheme for closed-loop control based on two-dimensional and three-dimensional geology at the tunnel face and in the forward longitudinal direction.

[0142] In this embodiment, a historical case library is invoked for similarity matching, and initial control parameters adapted to the current geological scenarios of the Zhuchong Tunnel and the Xialou Tunnel are generated. When a water-rich sand layer and a local high-permeability anomaly zone are identified ahead, the following control strategy instruction set is generated: the soil chamber pressure setpoint is increased by 12 kPa to 18 kPa, the foam agent injection amount is increased by 10% to 20%, the polymer injection amount is increased by 5% to 15%, the propulsion speed is reduced by 10% to 25%, and the cutterhead rotation speed is reduced by 5% to 15% to enhance the face support capacity and the plastic flow stability of the excavated soil. When an alternating zone of interbedded rock mass and Class V surrounding rock is identified, zonal thrust control and attitude adjustment instructions are further generated to limit the thrust difference between the upper and lower zones to within 12%, control the attitude correction rate, and dynamically adjust the screw conveyor speed according to the changes in excavated soil particles and the actual soil discharge rate deviation to reduce the risk of cutterhead overload, attitude instability, and screw conveyor jamming.

[0143] After the control strategy instruction set is executed, control execution feedback data is collected in real time and compared with the two-dimensional geological refinement prediction map of the tunnel face and the geological prediction map of the preset longitudinal distance ahead. The least squares method and dynamic boundary update algorithm are used to perform reverse correction on the grid position parameters of the tunnel face, the predicted node position parameters of the longitudinal distance ahead, and the geological boundary parameters, obtaining the corrected spatial coordinates of the geological anomaly area. After one reverse correction, the water-rich anomaly boundary ahead of the Zhuchong Tunnel is corrected forward by approximately 0.30m relative to the original prediction result, and the boundary of the local unstable zone at the Xialou Tunnel tunnel face is corrected downward by approximately 0.25m, thereby further improving the identification accuracy of complex strata boundary locations.

[0144] As the tunnel boring machine (TBM) continued its excavation, on-site findings revealed a localized anomalous zone in the section ahead of the Zhuchong Tunnel, where homogeneous clay transitioned into water-rich sand. In the section ahead of the Xialou Tunnel, alternating layers of interbedded rock and Class V surrounding rock were observed. During construction, a comprehensive risk score was calculated based on the corrected spatial coordinates of the geological anomaly areas, the real-time TBM location, and the estimated arrival time. Corresponding graded early warning information was generated and simultaneously pushed to the construction management terminal. This guided timely adjustments to soil chamber pressure, screw conveyor parameters, spoil remediation parameters, propulsion parameters, and attitude control parameters, thereby reducing construction risks caused by sudden geological changes.

[0145] Therefore, when applied to the earth pressure balance shield tunneling construction scenarios of the Zhuchong Tunnel and Xialou Tunnel in the Chushandian Reservoir Irrigation Area Project, this invention can fully utilize the coupling characteristics between soil pressure control, spiral soil discharge continuity, slag improvement state, and tunnel face stability control in the earth pressure balance shield tunneling construction of water conservancy water conveyance tunnels. It can achieve closed-loop linkage of parameter recommendation, feedback correction, and graded early warning for typical geological scenarios such as homogeneous clay, interbedded rock mass, Class V surrounding rock, and water-rich sand layers, and has good engineering applicability and promotion value.

[0146] Further reference Figure 4 As an implementation of the methods shown in the above figures, this disclosure provides some embodiments of a geological prediction and early warning closed-loop control device for earth pressure balance shield tunneling. These device embodiments are similar to... Figure 1 Corresponding to the method embodiments shown, this geological prediction and early warning closed-loop control device for earth pressure balance shield tunneling can be specifically applied to various electronic devices.

[0147] like Figure 4As shown in some embodiments, a geological prediction and early warning closed-loop control device 400 for earth pressure balance shield tunneling includes: an acquisition unit 401, an extraction unit 402, a generation unit 403, an adjustment unit 404, a first determination unit 405, a reverse correction unit 406, and a second determination unit 407. The acquisition unit 401 is configured to acquire a two-dimensional refined geological prediction map of the tunnel face, a geological prediction map of the preset longitudinal distance ahead, geological judgment results, and the current construction status of the earth pressure balance shield tunneling. The extraction unit 402 is configured to extract geological boundary parameters, tunnel face grid position parameters, and forward longitudinal prediction node position parameters based on the aforementioned two-dimensional refined geological prediction map of the tunnel face and the aforementioned geological prediction map of the preset longitudinal distance ahead. The generation unit 403 is configured to generate a control strategy instruction set based on the aforementioned two-dimensional refined geological prediction map of the tunnel face, the aforementioned geological prediction map of the preset longitudinal distance ahead, and the aforementioned current construction status. The adjustment unit 404 is configured to adjust the earth pressure balance shield tunneling based on the aforementioned control strategy instruction set. The earth pressure balance shield tunneling parameters during construction are collected and feedback data is collected. The first determining unit 405 is configured to determine the observation deviation vector based on the collected feedback data, the two-dimensional geological refinement prediction map of the tunnel face, the geological prediction map of the forward longitudinal preset distance, and the current construction status. The reverse correction unit 406 is configured to perform reverse correction processing on the geological judgment result, the geological boundary parameters, the tunnel face grid position parameters, and the forward longitudinal prediction node position parameters based on the observation deviation vector to generate a correction result. The second determining unit 407 is configured to determine the graded early warning information based on the correction result and send the graded early warning information to the construction management terminal.

[0148] It is understandable that the various units and references recorded in the geological prediction and early warning closed-loop control device 400 for earth pressure balance shield tunneling are related to... Figure 1 The steps described in the method correspond to each other. Therefore, the operations, features, and beneficial effects described above for the method are also applicable to the geological prediction and early warning closed-loop control device 400 and its constituent units for earth pressure balance shield tunneling, and will not be repeated here.

[0149] The following is for reference. Figure 5 It shows a schematic diagram of the structure of an electronic device (e.g., a computing device) 500 suitable for implementing some embodiments of the present disclosure. Figure 5 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0150] like Figure 5As shown, the electronic device 500 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory 502 or a program loaded from a storage device 508 into a random access memory 503. The random access memory 503 also stores various programs and data required for the operation of the electronic device 500. The processing unit 501, the read-only memory 502, and the random access memory 503 are interconnected via a bus 504. An input / output interface 505 is also connected to the bus 504.

[0151] Typically, the following devices can be connected to the input / output interface 505: input devices 506 including, for example, a touchscreen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 507 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 508 including, for example, magnetic tape, hard disk, etc.; and communication devices 509. Communication device 509 allows electronic device 500 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 5 An electronic device 500 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 5 Each box shown can represent a device or multiple devices as needed.

[0152] In particular, according to some embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 509, or installed from a storage device 508, or installed from a read-only memory 502. When the computer program is executed by the processing device 501, it performs the functions defined above in the methods of some embodiments of this disclosure.

[0153] It should be noted that, in some embodiments of this disclosure, the computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In some embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0154] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0155] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: acquire a two-dimensional refined geological prediction map of the tunnel face, a geological prediction map of the pre-set longitudinal distance ahead, geological assessment results, and the current construction status of the earth pressure balance shield tunneling; extract geological boundary parameters, tunnel face grid position parameters, and pre-set longitudinal prediction node position parameters based on the aforementioned two-dimensional refined geological prediction map of the tunnel face and the aforementioned geological prediction map of the pre-set longitudinal distance ahead; and generate a control strategy instruction set based on the aforementioned two-dimensional refined geological prediction map of the tunnel face, the aforementioned geological prediction map of the pre-set longitudinal distance ahead, and the aforementioned current construction status. Based on the aforementioned control strategy instruction set, the earth pressure balance shield parameters for earth pressure balance shield construction are adjusted to collect feedback data. In response to the collected feedback data, an observation deviation vector is determined based on the feedback data, the aforementioned two-dimensional geological refinement prediction map of the tunnel face, the aforementioned geological prediction map of the forward longitudinal preset distance, and the aforementioned current construction status. Based on the aforementioned observation deviation vector, the aforementioned geological judgment results, the aforementioned geological boundary parameters, the aforementioned tunnel face grid position parameters, and the aforementioned forward longitudinal predicted node position parameters are subjected to reverse correction processing to generate correction results. Based on the aforementioned correction results, graded early warning information is determined and sent to the construction management terminal.

[0156] Computer program code for performing operations of some embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0157] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0158] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0159] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. A closed-loop control method for geological prediction and early warning in earth pressure balance shield tunneling, characterized in that, include: Obtain a two-dimensional detailed geological prediction map of the tunnel face, a geological prediction map of the preset longitudinal distance ahead, geological assessment results, and the current construction status of the earth pressure balance shield tunneling project. Based on the two-dimensional geological refinement prediction map of the working face and the geological prediction map of the forward longitudinal preset distance, geological boundary parameters, working face grid position parameters, and forward longitudinal prediction node position parameters are extracted. Based on the two-dimensional geological refinement prediction map of the working face, the geological prediction map of the preset longitudinal distance ahead, and the current construction status, a set of control strategy instructions is generated; Based on the control strategy instruction set, adjust the earth pressure balance shield parameters during earth pressure balance shield construction to collect feedback data; In response to the collected feedback data, the observation deviation vector is determined based on the feedback data, the two-dimensional geological refinement prediction map of the working face, the geological prediction map of the forward longitudinal preset distance, and the current construction status. Based on the observation deviation vector, the geological determination result, the geological boundary parameters, the face grid position parameters, and the forward longitudinal prediction node position parameters are subjected to reverse correction processing to generate correction results; Based on the correction results, graded early warning information is determined, and the graded early warning information is sent to the construction management terminal.

2. The geological prediction and early warning closed-loop control method for earth pressure balance shield tunneling according to claim 1, characterized in that, The correction results include: a corrected two-dimensional geological refinement prediction map of the working face, a corrected geological prediction map of the forward longitudinal preset distance, and corrected geological determination results; and the method further includes: The correction results, including the corrected two-dimensional geological refinement prediction map of the tunnel face, the corrected geological prediction map of the preset longitudinal distance ahead, and the corrected geological judgment results, are used as the two-dimensional geological refinement prediction map of the tunnel face, the geological prediction map of the preset longitudinal distance ahead, and the geological judgment results for the next control cycle, so as to allow the geological prediction and early warning closed-loop control method for earth pressure balance shield construction to be executed again.

3. The geological prediction and early warning closed-loop control method for earth pressure balance shield tunneling according to claim 1, characterized in that, The control strategy instruction set generated based on the two-dimensional refined geological prediction map of the working face, the geological prediction map of the preset longitudinal distance ahead, and the current construction status includes: Based on the current construction status and the pre-acquired historical geological case database, the initial control parameters are determined; A multi-objective optimization model is constructed using the following formula: ， in, Represents the target vector. Represents the control variable vector. This represents the objective function for the stability risk at the working face. Represent the objective function for matching excavated materials with deviation. This represents the objective function relating equipment load and energy consumption. This represents the objective function for controlling the adjustment range. Indicates the lower limit of the control variable. This indicates the upper limit of the control variable. This represents the current control variable vector. Indicates the maximum allowable adjustment amount per cycle; Based on the initial control parameters, the multi-objective optimization model is solved to generate a set of candidate control parameters; The candidate control parameter set is subjected to constraint screening and comprehensive scoring to generate target control parameters; Based on the target control parameters, a control strategy instruction set is generated.

4. The geological prediction and early warning closed-loop control method for earth pressure balance shield tunneling according to claim 3, characterized in that, The determination of initial control parameters based on the current construction status and a pre-acquired historical geological case database includes: For each historical geological case included in the acquired historical geological case database, the current construction status and the historical geological case are matched for similarity using the following formula to generate a similarity score: ， in, Indicates similarity. Indicates the similarity of geological categories. Indicates the similarity of project attribute levels. Indicates the similarity of construction conditions. , , These represent the weights of geological category similarity, engineering attribute level similarity, and construction status similarity, respectively. , Indicates the node sequence number. Indicates the number of nodes. Indicates an indicator function, Indicates the current construction status of the first... The geological category of each node, Indicating the first case in historical geological cases The geological category of each node, Indicates the project attribute level number. Indicates the stability level. Indicates the water-bearing capacity level. Indicates the level of permeability. Indicates the first Project-related attribute weights , Indicates the current construction status of the first... The node of the first Class project attribute level coding, Indicating the first case in historical geological cases The node of the first Class project attribute level coding, Indicates the construction status sequence number. Indicates the number of construction status parameters. Indicates the first Weights of each construction status parameter Indicates the first The scaling factor of each construction state parameter Indicates the current construction status of the first... Normalized values ​​of each construction state parameter. Indicating the first case in historical geological cases Normalized values ​​of each construction state parameter. ; Based on the generated similarities, a set of target geological cases is extracted from the historical geological case database; Initial control parameters are extracted from the target geological case set using the following formula: ， in, Indicates the initial control parameters. Indicates the target geological case number. This indicates the number of target geological cases in the target geological case set. Indicates the first The similarity between each target geological case Indicates the first Historical control parameters in a target geological case.

5. The geological prediction and early warning closed-loop control method for earth pressure balance shield tunneling according to claim 1, characterized in that, The determination of the observation deviation vector based on the feedback data, the two-dimensional geological refinement prediction map of the working face, the geological prediction map of the preset longitudinal distance ahead, and the current construction status includes: Based on the feedback data, the observation vector is constructed using the following formula: ， in, Represents the observation vector. This represents the measured value of the earth pressure chamber. This represents the measured value of the cutterhead torque. This represents the measured propulsion speed. This represents the measured value of the screw conveyor speed. Indicates the theoretical amount unearthed. This indicates the actual amount of excavated material. Indicates the amount of foaming agent injected. Indicates the amount of polymer injected. Indicates the deviation in the shield tunnel's attitude; The geological boundary parameters, the face grid location parameters, and the forward longitudinal prediction node location parameters are combined into a parameter vector to be corrected. Based on the parameter vector to be corrected, the two-dimensional geological refinement prediction map of the working face, the geological prediction map of the preset longitudinal distance ahead, and the current construction status, the prediction vector is constructed using the following formula: ， in, Represents the prediction vector. Represents the vector of parameters to be corrected. This represents the construction response prediction model; Based on the observation vector and the prediction vector, the observation bias vector is determined using the following formula: ， in, This represents the observation bias vector.

6. The geological prediction and early warning closed-loop control method for earth pressure balance shield tunneling according to claim 5, characterized in that, The process of performing reverse correction on the geological determination result, the geological boundary parameters, the face grid position parameters, and the forward longitudinal prediction node position parameters based on the observation deviation vector to generate a correction result includes: Construct the boundary sensitivity matrix; Based on the boundary sensitivity matrix and the observation bias vector, the parameter correction amount is determined using the following formula: ， in, Indicates the parameter correction amount. Represents the boundary sensitivity matrix. Represents the regularization coefficient. Represents the observation weight matrix. Represents the identity matrix; Based on the parameter correction amount, the parameter vector to be corrected is updated using the following formula to generate a parameter update vector: ， in, This represents the parameter update vector; Based on the parameter update vector, the following are generated: a two-dimensional geological refinement prediction map of the working face, a geological prediction map of the preset longitudinal distance ahead, a corrected two-dimensional geological refinement prediction map of the working face corresponding to the geological judgment result, a corrected geological prediction map of the preset longitudinal distance ahead, and a corrected geological judgment result. The two-dimensional geological refinement prediction map of the corrected working face, the geological prediction map of the longitudinal preset distance ahead of the correction, and the correction geological judgment result are determined as the correction results.

7. The geological prediction and early warning closed-loop control method for earth pressure balance shield tunneling according to claim 6, characterized in that, The construction of the boundary sensitivity matrix includes: Apply a small perturbation to the parameter vector to be corrected; Determine the set of predicted response vectors corresponding to the parameter vectors to be corrected after applying a small perturbation; The predicted response vector set is combined to generate a boundary sensitivity matrix.

8. The geological prediction and early warning closed-loop control method for earth pressure balance shield tunneling according to claim 1, characterized in that, The correction results include: a corrected two-dimensional geological refinement prediction map of the working face, a corrected geological prediction map of the forward longitudinal preset distance, and corrected geological determination results; And the determination of graded early warning information based on the correction results includes: Based on the geological assessment results, abnormal nodes that meet the preset anomaly assessment conditions are selected from the two-dimensional geological refinement prediction map of the corrected working face and the geological prediction map of the longitudinal preset distance ahead of the correction to obtain an abnormal node set; the abnormal node set is subjected to spatial connectivity analysis to generate a geological anomaly region set. For each geological anomaly region in the aforementioned geological anomaly region set, the following processing steps are performed: Determine the stability score, water-bearing capacity score, permeability score, tunneling speed score, estimated arrival time score, and anomaly impact range score corresponding to the geological anomaly area; Based on the stability score, water abundance score, permeability score, tunneling speed score, estimated time of arrival score, and anomaly impact range score, the comprehensive risk score is determined using the following formula: ， in, Indicates the sequence number of the geological anomaly region. Indicates the first The comprehensive risk score of each geologically anomalous area Indicates the first Stability scores for each geologically anomalous region Indicates the first Water-bearing fraction of each geologically anomalous region Indicates the first Permeability score of each geologically anomalous region Indicates the first The tunneling speed score for each geologically anomalous area Indicates the first The estimated time of arrival fractions for each geological anomaly region Indicates the first The score of the anomalous influence range of each geological anomaly region , , , , , They represent the weights, ; Based on the comprehensive risk score, the target comprehensive risk score is determined using the following formula: ， in, Indicates the first The target comprehensive risk score for each geologically anomalous area Indicates a compound anomaly correction term; The target with the highest overall risk score among all identified targets is determined as the target early warning risk score. In response to determining that the target early warning risk score meets the first preset early warning condition, the first preset early warning information is determined as graded early warning information; In response to determining that the target early warning risk score meets the second preset early warning condition, the second preset early warning information is determined as graded early warning information; In response to determining that the target early warning risk score meets the third preset early warning condition, the third preset early warning information is determined as graded early warning information.

9. A geological prediction and early warning closed-loop control device for earth pressure balance shield tunneling, characterized in that, include: The acquisition unit is configured to acquire a two-dimensional detailed geological prediction map of the tunnel face, a geological prediction map of the preset longitudinal distance ahead, geological judgment results, and the current construction status of the earth pressure balance shield tunneling construction. The extraction unit is configured to extract geological boundary parameters, face grid position parameters, and forward longitudinal prediction node position parameters based on the two-dimensional geological refinement prediction map of the working face and the geological prediction map of the preset longitudinal distance in front. The generation unit is configured to generate a set of control strategy instructions based on the two-dimensional geological refinement prediction map of the working face, the geological prediction map of the preset longitudinal distance ahead, and the current construction status. The adjustment unit is configured to adjust the earth pressure balance shield parameters during earth pressure balance shield construction based on the control strategy instruction set, in order to collect feedback data. The first determining unit is configured to, in response to the collected feedback data, determine the observation deviation vector based on the feedback data, the two-dimensional geological refinement prediction map of the working face, the geological prediction map of the forward longitudinal preset distance, and the current construction status; The reverse correction unit is configured to perform reverse correction processing on the geological determination result, the geological boundary parameters, the face grid position parameters, and the forward longitudinal prediction node position parameters based on the observation deviation vector, so as to generate a correction result; The second determining unit is configured to determine graded early warning information based on the correction results, and to send the graded early warning information to the construction management terminal.

10. An electronic device, characterized in that, include: One or more processors; A storage device on which one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 8.

Images