TBM tunnel weak broken zone jamming risk prediction and active reinforcement decision-making method

Abstract

The invention relates to the technical field of tunnel monitoring, in particular to a TBM tunnel weak broken zone jamming risk prediction and active reinforcement decision-making method. According to the method, the TBM shield pressure prediction sub-model and the multiple TBM feature data are used for prediction, Dropout operation is introduced, and model overfitting is reduced; according to the method, the deviation degree is utilized for risk grading, the risk grades can be rapidly and effectively obtained, different supporting modes are selected according to the different risk grades, and the problem that a reinforcement treatment method and the surrounding rock condition cannot be effectively matched under the condition that the machine jamming risk exists is solved; the system is simple in structure and high in applicability, a proper active reinforcement decision is made, resource waste is reduced, workers are assisted in completing tunnel construction, TBM equipment is prevented from being damaged, and the occurrence rate of engineering accidents is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel monitoring, and in particular to a method for risk prediction and active reinforcement decision-making of a weak and broken belt jammer in a TBM tunnel. Background Art

[0002] Tunnel boring machines (TBMs), as high-end intelligent equipment for tunnel and underground engineering construction, are currently widely used in tunnel (hole) construction and underground space development in various fields, including transportation, energy, and water conservancy. They have demonstrated excellent excavation performance in good rock mass. However, as tunnel construction environments have become increasingly complex in recent years, the geological conditions faced by TBMs during excavation have also become increasingly complex. Weak and fractured surrounding rock, represented by altered rock, faults, and densely jointed zones, are common. TBMs are prone to large deformations and machine jams when excavating in such surrounding rock. Once a machine jam occurs, it can cost a considerable amount of time, manpower, and material resources to resolve. In severe cases, it can lead to damage to the TBM equipment, resulting in significant economic losses and engineering accidents. Furthermore, surrounding rock with a risk of machine jams often requires reinforcement to reduce the risk. However, if the reinforcement method is not suitable for the surrounding rock conditions, the reinforcement effect may be poor or excessive.

[0003] The prior art discloses a method for assessing and treating the risk of a machine stuck in an open TBM tunnel (publication number: CN114692457A), comprising the following steps: obtaining the physical and mechanical parameters of the tunnel surrounding rock; constructing a stratum-structure model to extract the settlement deformation value u0 of the tunnel vault surrounding rock; when the settlement deformation value u0 of the tunnel vault surrounding rock is less than the reserved deformation δR, it is determined that the open TBM has no risk of machine stuck; otherwise, there may be a machine stuck risk; then, the horizontal stress σx and the vertical stress σz are calculated, and the radial stress σr acting on the TBM shield, the surrounding rock pressure P, and the frictional resistance Rp between the TBM shield and the surrounding rock are obtained; the ratio k of the frictional resistance Rp between the TBM shield and the surrounding rock to the TBM excavation thrust FI is calculated; and based on the P and k values, it is determined that the open TBM has a machine stuck risk. The corresponding relationship between the tunnel surrounding rock-shield friction and TBM thrust was established by using the physical and mechanical parameters of the on-site surrounding rock. A quantitative TBM tunnel jam risk assessment standard was proposed, which is highly accurate and practical.

[0004] However, the existing technology only assesses the risk of machine jamming, and the risk assessment and subsequent processing methods are not consistent enough. Faced with the increasingly complex geological conditions currently faced during the excavation process, large deformation and machine jamming are very likely to occur. Summary of the Invention

[0005] The purpose of the present invention is to overcome the problems of large deformation and machine jamming faced by the existing technology in increasingly complex geological conditions, and to provide a method for predicting the risk of machine jamming in the weak and broken zone of a TBM tunnel and making active reinforcement decisions.

[0006] In a first aspect, the present invention provides a method for predicting the risk of a weak and broken belt jam in a TBM tunnel and making active reinforcement decisions, comprising: S1. Inputting characteristic data of a full-face tunnel boring machine (TBM) into a TBM shield pressure prediction sub-model to obtain a shield cylinder pressure value for the next process of the full-face tunnel boring machine (TBM); S2. Inputting the shield cylinder pressure value of the next process of the full-face tunnel boring machine (TBM) into the card processing module to obtain an active reinforcement decision; S3. Based on the active reinforcement decision, adjust the operating parameters of the full-face tunnel boring machine (TBM) of the next process. Preferably, the characteristic data of the full-section tunnel boring machine (TBM) specifically include: the propulsion speed, cutterhead speed, thrust, torque and penetration of the full-section tunnel boring machine (TBM); Before inputting the characteristic data of the full-face tunnel boring machine (TBM) into the TBM shield pressure prediction sub-model, preprocessing is required, and the preprocessing specifically includes normalization.

[0007] Preferably, a risk decision model needs to be constructed before S1, and the risk decision model specifically includes: the TBM shield pressure prediction sub-model and the card machine processing module.

[0008] Further preferably, the TBM shield pressure prediction sub-model includes at least two residual modules connected in series; the residual module includes a first convolution layer and a convolution sub-module connected in parallel; the convolution sub-module includes a first convolution unit and a second convolution unit connected in series; the first convolution unit and the second convolution unit both include a causal convolution layer, a weight normalization layer, an activation function layer and a Dropout block; the activation function layer adopts a ReLU function; The card machine processing module includes: a deviation calculation submodule, a risk classification submodule and a decision solution processing submodule connected in series.

[0009] Preferably, the S1 specifically includes: S11. Calculate the initial causal convolution result in the first residual module ; S12, the initial causal convolution result Perform weight normalization to obtain the normalized initial causal convolution result ; S13, based on the normalized initial causal convolution result , use the activation function to calculate the initial causal convolution result after processing ; S14, the processed initial causal convolution result Input to the Dropout block for random regularization to obtain the regularized initial causal convolution result; S15, repeating S11 to S14 to obtain the final causal convolution result; S16, performing nonlinear mapping on the normalized feature data of the full-face tunnel boring machine (TBM), and concatenating the result with the final causal convolution result to obtain an initial training prediction result; S17. Input the initial training prediction result into the next residual module connected to the first residual module, and repeat S11 to S16 to obtain the shield cylinder pressure value of the next process of the full-section tunnel boring machine TBM.

[0010] Preferably, the S2 specifically includes: S21. Obtain the shield cylinder pressure value of the current process; S22: Input the shield cylinder pressure value of the current process and the shield cylinder pressure value of the next process into the deviation calculation submodule for calculation to obtain the deviation ; S23, based on the risk judgment standard, use the risk grading submodule to Make judgments and obtain risk results; S24: Based on the risk result, the decision-making scheme processing submodule is used to process the risk result to obtain the active reinforcement decision.

[0011] Further preferably, the risk judgment standard in S43 is: If the deviation , then the risk result is determined to be at a risk-free level; If the deviation , then the risk result is determined to be a low risk level; If the deviation , then the risk result is determined to be a high risk level; If the deviation , then the risk result is determined to be the surrounding rock level.

[0012] Further preferably, the active reinforcement decision corresponding to the risk result includes: If the risk result is the no-risk level, the corresponding active reinforcement strategy is to maintain the operating parameters of the current process; If the risk result is the low risk level, the corresponding active reinforcement strategy is to adjust the excavation parameters; If the risk result is the high risk level and the surrounding rock levels IV and V, it is necessary to construct a three-dimensional tunnel numerical model to simulate the tunneling process of the full-section tunnel boring machine (TBM) and calculate the difference between the thrust of the full-section tunnel boring machine (TBM) and the shield friction resistance. If the difference is greater than 0, the corresponding active reinforcement strategy is to maintain the operating parameters of the current process; if the difference is less than 0, the corresponding active reinforcement strategy is to select a corresponding support form. If the surrounding rock level is not IV or V, the corresponding active reinforcement strategy is to maintain the operating parameters of the current process.

[0013] Preferably, the S3 specifically includes: If the active reinforcement strategy is to maintain the operating parameters of the current process, then the current operating parameters are not changed; If the active reinforcement strategy is to adjust the excavation parameters, the speed is reduced to , the thrust is controlled between 4~6MN, and the torque is controlled at 50% of the normal tunneling torque; If the active reinforcement strategy is to select a corresponding support form, flac3 is used to construct a surrounding rock-advance support model. Based on the surrounding rock-advance support model, the deformation of the full-section tunnel boring machine (TBM) during excavation and the settlement of the surrounding rock inside the shield are calculated; based on the deformation and the settlement of the surrounding rock inside the shield, a surrounding rock deformation diagram is obtained; the gap value between the shield tail and the surrounding rock of the cave top in the current process is obtained; and the corresponding support form is selected according to the surrounding rock deformation diagram and the gap value.

[0014] Further preferably, the support methods include: advanced small pipe, advanced medium pipe shed, advanced large pipe shed, and double-layer advanced large pipe shed.

[0015] Compared with the prior art, the present invention has the following beneficial effects: The present invention provides a method for predicting the risk of machine jamming in weak and broken zones of a TBM tunnel and making active reinforcement decisions. Compared with the existing technology, the present invention can reduce model overfitting by referring to the characteristic data of a full-section tunnel boring machine (TBM) and a TBM shield pressure prediction sub-model. The present invention calculates the deviation degree through a machine jam processing module to achieve risk grading, and can quickly and effectively obtain the risk level. Different active reinforcement strategies are selected for different risk levels, thus solving the problem of being unable to effectively match the reinforcement treatment method with the surrounding rock conditions when there is a risk of machine jamming. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1This is a flow chart of a method for risk prediction and active reinforcement decision-making for a weak and broken belt jam in a TBM tunnel in Example 1.

[0017] Figure 2 Schematic diagram of the structure of the TBM shield pressure prediction sub-model in Example 1.

[0018] Figure 3 This is a diagram of the surrounding rock deformation acting on the shield under different support conditions in Example 1.

[0019] Figure 4 This is the deformation diagram of the surrounding rock acting on the shield under support condition 1 in Example 1.

[0020] Figure 5 This is the deformation diagram of the surrounding rock acting on the shield under support condition 2 in Example 1.

[0021] Figure 6 This is a result diagram of surrounding rock settlement and void value under different support conditions in Example 2.

[0022] Figure 7 Graph showing the original operating parameters and optimized parameters of the TBM in Example 2. DETAILED DESCRIPTION

[0023] The present invention will be further described in detail below with reference to specific embodiments. However, this should not be construed as limiting the scope of the present invention to the following embodiments, as all technologies implemented based on the present invention fall within the scope of the present invention.

[0024] Unless otherwise specified, in the description of the specific embodiments of the present invention, the terms indicating the orientation or positional relationship, such as "upper", "lower", "left", "right", "center", "inside", and "outside", are based on the expressions of the orientation or positional relationship shown in the accompanying drawings, or are the orientation or positional relationship in which the invented product / device / apparatus is placed when it is conventionally used. These terms of orientation or positional relationship are merely for the purpose of facilitating the description of the scheme of the present invention or simplifying the description of the specific embodiments to facilitate the rapid understanding of the scheme by technicians, and do not indicate or imply that a specific device / component / element must have a specific orientation, or be constructed and operated in a specific positional relationship, and therefore should not be understood as limiting the present invention.

[0025] In addition, if the terms "horizontal", "vertical", "overhanging", "parallel" and the like appear, it does not mean that the corresponding devices / components / elements are required to be absolutely horizontal or vertical or overhanging or parallel, but may be slightly tilted or have deviations. For example, "horizontal" only means that its direction is more horizontal relative to "vertical", and does not mean that the structure must be completely horizontal, but may be slightly tilted. Alternatively, it can be simply understood that the corresponding devices / components / elements are set in directions such as "horizontal", "vertical", "overhanging", and "parallel", and can have an error / deviation of ±10% relative to the corresponding direction setting, more preferably an error / deviation within ±8%, more preferably an error / deviation within ±6%, more preferably an error / deviation within ±5%, and more preferably an error / deviation within ±4%. As long as the corresponding device / component / element is within the error / deviation range, it can still achieve its role in the solution of the present invention.

[0026] In addition, the expressions “first”, “second”, “third”, etc. in the terms are merely used to distinguish the description of the same or similar components, and should not be understood as emphasizing or implying the relative importance of specific components.

[0027] In addition, in the description of the embodiments of the present invention, "several," "plurality," and "a number" represent at least two. It can also be any number such as two, three, four, five, six, seven, eight, nine, or even more than nine.

[0028] Furthermore, in the description of the technical solution of the present invention, unless otherwise expressly specified, defined, or restricted, the terms "disposed," "installed," "connected," "connected," "provided with," "laid," and "arranged" should be understood broadly. For example, they may refer to fixed, removable, or integral connections, and may include welding, riveting, bolting, threading, and other commonly used connection methods in the field of tunnel monitoring technology. Such connections may be mechanical, electrical, or communication; they may be direct, indirect via an intermediate medium, or internally connected between two components.

[0029] Example 1 A flowchart of a TBM jam risk prediction and active reinforcement decision-making method in weak fracture zones is shown below: Figure 1 As shown, the specific steps include: S1. Obtain characteristic data of the full-face tunnel boring machine (TBM) in the current process and perform preprocessing; The characteristic data in step S1 include the propulsion speed, cutterhead speed, thrust, torque, and penetration of the full-section tunnel boring machine (TBM). In surrounding rock with good stability, there is a good correspondence between the shield pressure and the propulsion speed, cutterhead speed, thrust, torque, and penetration. However, in poor surrounding rock, the shield pressure will vary. Therefore, the propulsion speed, cutterhead speed, thrust, torque, and penetration of the full-section tunnel boring machine (TBM) are selected as the input of the prediction model.

[0030] The preprocessing in step S1 includes normalization, and the corresponding formula is:

[0031] Where: represents the normalized feature data, Represents feature data, Indicates the minimum value of the feature data, Indicates the maximum value of the feature data.

[0032] S2. Constructing a risk decision model; the risk decision model includes a TBM shield pressure prediction sub-model and a card processing module; The schematic diagram of the structure of the TBM shield pressure prediction sub-model in step S2 is as follows: Figure 2 As shown, the TBM shield pressure prediction submodel includes at least two residual modules connected in series. The residual module includes a first convolutional layer and a convolutional submodule connected in parallel. The convolutional submodule includes a first convolutional unit and a second convolutional unit connected in series. The first convolutional unit and the second convolutional unit each include a causal convolutional layer, a weight normalization layer, an activation function layer, and a dropout block connected in series. The activation function layer uses the Reluctant Unified Unit (ReLU) function. Causal convolution ensures causal relationships between data, meaning that input information at the current moment is only related to information before the current moment and not to information at future moments, thus preventing information leakage. The model weights are normalized (weight normalization), and a dropout block is added to avoid overfitting. During model training, the dropout block inactivates some neurons with a certain probability, thereby achieving a certain degree of regularization. When the model's input and output dimensions differ, the first convolutional layer performs nonlinear mapping, adjusting the input data dimensions so that the model has the same input and output dimensions.

[0033] The card machine processing module in step S2 includes a deviation calculation submodule, a risk classification submodule and a decision solution processing submodule which are connected in series.

[0034] S3. Input the pre-processed characteristic data into the TBM shield pressure prediction sub-model to obtain the shield cylinder pressure value of the next process of the full-face tunnel boring machine TBM, i.e., the prediction result; The training process of the TBM shield pressure prediction sub-model is as follows: S31. According to the formula:

[0035] Where: represents the initial causal convolution result; where, represents the total number of filters, represents the summation function, Represents the number of normalized feature data, represents the normalized feature data, They represent the normalized propulsion speed, cutterhead speed, thrust, torque and penetration of the full-face tunnel boring machine TBM, represents the total filter, Represents each filter, Indicates the filters, Indicates the Preprocessed feature data; S32. Initial causal convolution results Perform weight normalization to obtain the normalized initial causal convolution result; S33. According to the formula:

[0036] Where: Represents the initial causal convolution result after processing; represents the activation function, represents the weight parameter of the TBM shield pressure prediction sub-model, represents the bias term of the TBM shield pressure prediction sub-model, represents the normalized initial causal convolution result; S34, the processed initial causal convolution result Input to the Dropout block for random regularization to obtain the regularized initial causal convolution result; S35. Repeat steps S31 to S34 to obtain the final causal convolution result; S36, performing nonlinear mapping on the normalized feature data and concatenating it with the final causal convolution result to obtain the initial training prediction result; S37: Input the initial training prediction result to the next residual module, and repeat steps S31 to S36 until all residual modules complete data processing to obtain the final training prediction result, i.e., the shield cylinder pressure value for the next process of the full-face tunnel boring machine (TBM); S38. Adjust the parameters of the TBM shield pressure prediction sub-model based on the final training prediction result to complete the training of the TBM shield pressure prediction sub-model.

[0037] S4. Input the shield cylinder pressure value of the next process into the card machine processing module to obtain an active reinforcement decision; Step S4 includes the following steps: S41. Obtain the shield cylinder pressure value of the current process; S42: Input the shield cylinder pressure value of the current process and the shield cylinder pressure value of the next process into the deviation calculation submodule for calculation to obtain the deviation; The calculation formula of the deviation calculation submodule in step S42 is:

[0038] Where: Indicates the degree of deviation, Indicates the shield cylinder pressure value of the next process, Indicates the shield cylinder pressure value of the current process.

[0039] S43. Based on the risk judgment standard, the risk grading submodule is used to judge the deviation degree and obtain the risk result; The risk judgment criteria in step S43 are: If the deviation , then the risk result is determined to be at a risk-free level; If the deviation , then the risk result is determined to be a low risk level; If the deviation , then the risk result is determined to be a high risk level; If the deviation , then the risk result is determined to be the surrounding rock level.

[0040] S44. Based on the risk results, the decision-making scheme processing submodule is used to process and obtain the corresponding active reinforcement decision.

[0041] Step S44 includes the following steps: S44-1, determine whether the risk result is at the no-risk level; if so, actively strengthen the decision to maintain the operating parameters of the current process and proceed to step S5; otherwise, proceed to step S44-2; S44-2, determine whether the risk result is low risk level; if so, the active reinforcement decision is to adjust the excavation parameters and reduce the speed. , the thrust is controlled between 4 and 6 MN, the torque is controlled at 50% of the normal excavation torque, and the process goes to step S5; otherwise, the process goes to step S44-3; S44-3, determine whether the risk result is the surrounding rock level; if so, proceed to step S44-4; otherwise, proceed to step S44-5; S44-4: Obtain on-site tunnel geological data. Based on this data and the shield cylinder pressure value for the next process, determine whether the surrounding rock mass is Class IV or V. If so, proceed to Step S44-5. Otherwise, the risk determination is no risk, and the active reinforcement decision is to maintain the operating parameters of the current process, proceeding to Step S5. The on-site tunnel geological data is obtained through data research, field testing, and other methods. This on-site tunnel geological data includes, but is not limited to, stratigraphic information, fault information, lithologic interface information, and initial stress and strain information. The specific geological data will be determined based on the project's specific circumstances.

[0042] S44-5. Construct a three-dimensional tunnel numerical model using flac3 based on field geological data; wherein the three-dimensional tunnel numerical model includes a shield and contact surface elements on the outside of the shield; the three-dimensional tunnel numerical model uses solid elements to establish the shield and contact surface elements on the outside of the shield; the shield includes a top shield, top side shields, side shields, bottom shield, and bottom shield; S44-6. Use a three-dimensional tunnel numerical model to simulate the tunneling process of a full-face tunnel boring machine (TBM) to obtain the shield friction resistance. The calculation formula of shield friction resistance is:

[0043] Where: represents the summation function, Indicates the The pressure on the shield, represents the area of ​​the contact element, Indicates the Normal stress of the block shield acting on the contact element, Indicates the pressure on all shields. 、 、 、 、 Respectively represents the pressure on each shield, represents the friction coefficient, Indicates the shield friction resistance.

[0044] S44-7. Calculate the difference between the thrust and shield friction resistance of the full-face tunnel boring machine (TBM), and determine whether the difference is less than 0. If so, determine that the full-face tunnel boring machine (TBM) is stuck, and proceed to step S44-8. Otherwise, make an active reinforcement decision to maintain the operating parameters of the current process, and proceed to step S5. S44-8. Use flac3 to construct a surrounding rock-advance support model. In this model, different support forms such as advance small pipe, advance medium pipe shed, advance large pipe shed, and double-layer advance large pipe shed are considered. The Hooke equation is used to calculate the deformation of the surrounding rock under different support conditions during the excavation process and the settlement of the surrounding rock within the shield range. S44-9. Obtain a surrounding rock deformation map based on the deformation condition and the surrounding rock settlement value within the shield; The deformation diagram of surrounding rock acting on the shield under different support conditions is shown in the figure below. Figure 3 As shown in Figure 2, at the tunnel face position, a certain shield length is set, and the surrounding rock settlement values ​​inside the shield corresponding to different support conditions are different.

[0045] S44-10, get the gap value between the shield tail and the surrounding rock of the cave top in the current process ; S44-11. According to the surrounding rock deformation diagram under different support conditions and the gap value between the shield tail and the surrounding rock at the top of the cave, the corresponding support form is selected, that is, the active reinforcement decision. Among them, the surrounding rock settlement value inside the shield corresponding to the surrounding rock deformation diagram under different support conditions is ,choose Corresponding support form.

[0046] The deformation diagram of surrounding rock acting on the shield under support condition 1 is shown in the figure below: Figure 4 As shown in the figure, the deformation diagram of the surrounding rock acting on the shield under support condition 2 is as follows Figure 5 As shown in the figure, the settlement values ​​of the surrounding rock within the shield range are different in different situations, so it is necessary to select an appropriate support method to ensure that the full-section tunnel boring machine (TBM) of the next process will not be damaged during operation and will not cause tunnel collapse, thereby ensuring the safety of the workers and reducing the occurrence of accidents.

[0047] The support methods of step S44-11 include advanced small pipe shed, advanced medium pipe shed, advanced large pipe shed, and double-layer advanced large pipe shed.

[0048] S5. Based on the active reinforcement decision, adjust the operating parameters of the full-face tunnel boring machine (TBM) for the next process.

[0049] In summary, this invention utilizes a TBM shield pressure prediction submodel and multiple TBM feature data points for prediction, introducing a dropout operation to reduce model overfitting. It also uses deviation to perform risk grading, quickly and effectively determining risk levels. Different support methods are then selected for each risk level, resolving the issue of effectively matching reinforcement treatment methods with surrounding rock conditions when there is a risk of machine jamming. This system boasts a simple structure and strong applicability, enabling appropriate proactive reinforcement decisions to be made, reducing resource waste, assisting personnel in completing tunnel construction, preventing TBM equipment damage, and lowering the incidence of engineering accidents.

[0050] Example 2 This example uses a tunnel project in a mountainous area in which a TBM passes through a Grade V weak and fractured zone surrounding rock as an example. Data such as the dramatic fluctuations in shield pressure and the abnormal increase in cutterhead torque that occurred when the TBM passed through a large fault area are selected.

[0051] The TBM's working data in this section was obtained and preprocessed. The initial TBM excavation data was weighted and normalized, with key parameters such as thrust and torque given higher weights (weight coefficient ω = 1.5).

[0052] Three residual modules are connected in series, along with a causal convolution layer, a weight normalization layer, an activation function layer, and a dropout block. The causal convolution layer uses a kernel size of 5, a stride of 1, and 64 channels. Group Normalization with 8 groups is used for weight normalization. The activation function layer uses ReLU + Swish to enhance nonlinear fitting capabilities. A dropout block with a dynamically adjusted dropout rate is set, with an initial dropout rate of 20% that increases linearly to 30% over training rounds.

[0053] The current cylinder pressure is 16.8 MPa. The model predicts the shield cylinder pressure for the next stage to be 19.5 MPa, with a deviation of 16.1%, placing it at a high risk. Using flac3d, a 3D tunnel numerical model was constructed to simulate the excavation process and calculate the difference between thrust and shield friction resistance: thrust F = 7.0 MN, shield friction resistance Rp = 8.2 MN; the difference F - Rp = -1.2 MN (less than 0, indicating a risk of machine jamming and requiring support measures).

[0054] The surrounding rock-advance support model was constructed using flac3d, and the surrounding rock settlement and void values ​​under different support conditions were calculated as follows: Figure 6 shown.

[0055] Considering the economic and safety considerations, the advanced large pipe shed + high pressure grouting + steel arch temporary support solution was selected to ensure that the surrounding rock deformation meets the standard and retain 34% safety redundancy. Based on the active reinforcement decision, the operating parameters of the full-section tunnel boring machine (TBM) in the next process were adjusted. The original operating parameters of the TBM and the optimized parameters are as follows: Figure 7 shown.

[0056] After risk prediction and active reinforcement decision-making were carried out through the method of the present invention, abnormal working conditions were responded to in a timely and effective manner, the accident rate was reduced, and the excavation speed was improved, which shows that the method of the present invention is effective.

Claims

1. A TBM tunnel weak and broken belt jam risk prediction and active reinforcement decision-making method, characterized by: include: S1. Inputting characteristic data of a full-face tunnel boring machine (TBM) into a TBM shield pressure prediction sub-model to obtain a shield cylinder pressure value for the next process of the full-face tunnel boring machine (TBM); S2. Inputting the shield cylinder pressure value of the next process of the full-face tunnel boring machine (TBM) into the card processing module to obtain an active reinforcement decision; S3. Based on the active reinforcement decision, adjust the operating parameters of the full-face tunnel boring machine (TBM) of the next process.

2. A TBM tunnel weak broken belt jam risk prediction and active reinforcement decision-making method according to claim 1, characterized in that: The characteristic data of the full-face tunnel boring machine (TBM) specifically include: the propulsion speed, cutterhead speed, thrust, torque and penetration of the full-face tunnel boring machine (TBM); Before inputting the characteristic data of the full-face tunnel boring machine (TBM) into the TBM shield pressure prediction sub-model, preprocessing is required, and the preprocessing specifically includes normalization.

3. The method for risk prediction and active reinforcement decision-making of weak and broken belt jammers in TBM tunnels according to claim 1 is characterized in that: Before S1, a risk decision model needs to be constructed. The risk decision model specifically includes: the TBM shield pressure prediction sub-model and the card machine processing module.

4. A TBM tunnel weak broken belt jam risk prediction and active reinforcement decision-making method according to claim 3, characterized in that: The TBM shield pressure prediction submodel includes at least two residual modules connected in series; the residual module includes a first convolution layer and a convolution submodule connected in parallel; the convolution submodule includes a first convolution unit and a second convolution unit connected in series; the first convolution unit and the second convolution unit each include a causal convolution layer, a weight normalization layer, an activation function layer and a Dropout block; the activation function layer uses a ReLU function; The card machine processing module includes: a deviation calculation submodule, a risk classification submodule and a decision solution processing submodule connected in series.

5. The method for risk prediction and active reinforcement decision-making of weak and broken belt jammers in TBM tunnels according to claim 1 is characterized in that: Said S1 specifically includes: S11. Calculate the initial causal convolution result in the first residual module ; S12, the initial causal convolution result Perform weight normalization to obtain the normalized initial causal convolution result ; S13, based on the normalized initial causal convolution result , use the activation function to calculate the initial causal convolution result after processing ; S14, the processed initial causal convolution result Input to the Dropout block for random regularization to obtain the regularized initial causal convolution result; S15, repeating S11 to S14 to obtain the final causal convolution result; S16, performing nonlinear mapping on the normalized feature data of the full-face tunnel boring machine (TBM), and concatenating the result with the final causal convolution result to obtain an initial training prediction result; S17. Input the initial training prediction result into the next residual module connected to the first residual module, and repeat S11 to S16 to obtain the shield cylinder pressure value of the next process of the full-section tunnel boring machine TBM.

6. The method for risk prediction and active reinforcement decision-making of weak and broken belt jammers in TBM tunnels according to claim 1 is characterized in that: The S2 specifically includes: S21. Obtain the shield cylinder pressure value of the current process; S22: Input the shield cylinder pressure value of the current process and the shield cylinder pressure value of the next process into the deviation calculation submodule for calculation to obtain the deviation ; S23, based on the risk judgment standard, use the risk grading submodule to Make judgments and obtain risk results; S24: Based on the risk result, the decision-making scheme processing submodule is used to process the risk result to obtain the active reinforcement decision.

7. A TBM tunnel soft broken belt jam risk prediction and active reinforcement decision-making method according to claim 6, characterized in that: The risk judgment criteria in S23 are: If the deviation , then the risk result is determined to be at a risk-free level; If the deviation , then the risk result is determined to be a low risk level; If the deviation , then the risk result is determined to be a high risk level; If the deviation , then the risk result is determined to be the surrounding rock level.

8. A TBM tunnel soft broken belt jam risk prediction and active reinforcement decision-making method according to claim 7, characterized in that: The active reinforcement decision obtained based on the risk result includes: If the risk result is the no-risk level, the corresponding active reinforcement strategy is to maintain the operating parameters of the current process; If the risk result is the low risk level, the corresponding active reinforcement strategy is to adjust the excavation parameters; If the risk result is the high risk level and the surrounding rock levels IV and V, it is necessary to construct a three-dimensional tunnel numerical model to simulate the tunneling process of the full-section tunnel boring machine (TBM) and calculate the difference between the thrust of the full-section tunnel boring machine (TBM) and the shield friction resistance. If the difference is greater than 0, the corresponding active reinforcement strategy is to maintain the operating parameters of the current process; if the difference is less than 0, the corresponding active reinforcement strategy is to select a corresponding support form. If the surrounding rock level is not IV or V, the corresponding active reinforcement strategy is to maintain the operating parameters of the current process.

9. The method for risk prediction and active reinforcement decision-making of weak and broken belt jammers in TBM tunnels according to claim 1 is characterized in that: The S3 specifically includes: If the active reinforcement strategy is to maintain the operating parameters of the current process, then the current operating parameters are not changed; If the active reinforcement strategy is to adjust the excavation parameters, the speed is reduced to , the thrust is controlled between 4~6MN, and the torque is controlled at 50% of the normal tunneling torque; If the active reinforcement strategy is to select a corresponding support form, flac3 is used to construct a surrounding rock-advance support model. Based on the surrounding rock-advance support model, the deformation of the full-section tunnel boring machine (TBM) during excavation and the settlement of the surrounding rock inside the shield are calculated; based on the deformation and the settlement of the surrounding rock inside the shield, a surrounding rock deformation diagram is obtained; the gap value between the shield tail and the surrounding rock of the cave top in the current process is obtained; and the corresponding support form is selected according to the surrounding rock deformation diagram and the gap value.

10. A TBM tunnel weak broken belt jam risk prediction and active reinforcement decision-making method according to claim 9, characterized in that: Support methods include: advanced small pipe shed, advanced medium pipe shed, advanced large pipe shed, and double-layer advanced large pipe shed.

Images