Shield tunnel synchronous grouting optimization control method and system based on ground surface settlement value

By using surface settlement value and formation parameters, combined with grouting volume prediction model, the grouting parameters of shield tunnel are accurately adjusted, the problems of uneven grouting and safety hazards are solved, the grouting efficiency and quality are improved, and the shield tunnel is ensured. Safety of construction.

CN118933901APending Publication Date: 2024-11-12SHANDONG UNIV +1

Patent Information

Application Number
CN202411300786.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-18
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

In the existing shield tunnel synchronous grouting technology, grouting parameter control depends on experience, resulting in uneven grouting, forming hollows, and posing a major safety hazard.

Method used

Based on the surface settlement value and formation parameters, the pre-trained grouting volume prediction model is used to calculate the grouting volume per unit time, and the grouting pump is controlled according to the grouting pressure, and the grouting parameters are accurately adjusted.

Benefits of technology

The precise adjustment of grouting parameters is achieved, the grouting efficiency and quality is optimized, the grouting uneven grouting and hollowing problems are reduced, and the safety of shield construction is improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118933901A_ABST
    Figure CN118933901A_ABST
Patent Text Reader

Abstract

The invention provides a shield tunnel synchronous grouting optimization control method and system based on a ground surface settlement value, and relates to the technical field of tunnel grouting control. Comprising the following steps that the ground surface settlement value and stratum parameters of a to-be-predicted tunnel section are obtained, and the stratum parameters comprise the tunnel burial depth, the stratum permeability coefficient and the stratum stress value measured through segment grouting; inputting the ground surface settlement value and the stratum parameters into a pre-trained grouting amount prediction model to obtain the missing grouting amount of the to-be-predicted tunnel section; adding the missing grouting amount of the to-be-predicted tunnel section and the actual grouting amount to obtain the grouting amount per unit time; and the grouting pressure is determined based on the grouting amount per unit time, and the grouting pump is controlled based on the grouting pressure. During synchronous grouting of the shield tunnel, grouting parameters can be accurately adjusted, and the requirement for synchronous grouting of the shield in the urban underground space is met.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention belongs to the technical field of tunnel grouting control, and in particular relates to a shield tunnel synchronous grouting optimization control method and system based on surface settlement values. Background Art

[0002] Modern shield tunneling machines integrate optical, mechanical, electrical, hydraulic, sensor and information technologies. They have the functions of excavating and cutting soil, transporting soil and ballast, assembling tunnel linings, measuring and guiding deviation correction, etc. They are also called "sharp tools" for subway construction. At present, shield machines have been widely used in subway, railway, highway, municipal pipeline network, cross-river tunnel, hydropower and other tunnel projects. When the shield machine is excavating, since the diameter of the shield machine shell is larger than the diameter of the segment, as the shield machine continues to advance and detach from the segment, an annular gap will be formed between the segment and the surrounding rock. At this time, the surrounding rock and soil are in a hollow state, which may induce deformation of the stratum under the action of ground stress, and synchronous grouting is required to fill the gap in time.

[0003] In the prior art, grouting operators generally control relevant parameters of grouting according to their own experience, which may cause a large deviation between the grouting effect and the ideal state, resulting in problems such as uneven grouting, forming voids, and bringing great safety hazards. Summary of the invention

[0004] In order to overcome the shortcomings of the above-mentioned prior art, the present invention provides a shield tunnel synchronous grouting optimization control method and system based on surface settlement values. During the synchronous grouting of the shield tunnel, the grouting parameters can be accurately adjusted to meet the needs of synchronous grouting of shield tunnels in urban underground spaces.

[0005] To achieve the above objectives, one or more embodiments of the present invention provide the following technical solutions:

[0006] A first aspect of the present invention provides a shield tunnel synchronous grouting optimization control method based on surface settlement values.

[0007] The shield tunnel synchronous grouting optimization control method based on surface settlement value includes the following steps:

[0008] Obtaining the surface settlement value and formation parameters of the tunnel section to be predicted, wherein the formation parameters include tunnel burial depth, formation permeability coefficient, and formation stress value measured by segment grouting;

[0009] The surface settlement value and formation parameters are input into the pre-trained grouting volume prediction model to obtain the missing grouting volume of the tunnel section to be predicted;

[0010] The missing grouting volume of the tunnel section to be predicted is added to the actual grouting volume to obtain the grouting volume per unit time;

[0011] The grouting pressure is determined based on the grouting volume per unit time, and the grouting pump is controlled based on the grouting pressure.

[0012] The second aspect of the present invention provides a shield tunnel synchronous grouting optimization control system based on surface settlement values.

[0013] The shield tunnel synchronous grouting optimization control system based on surface settlement value includes:

[0014] The data acquisition module is configured to: acquire the surface settlement value and formation parameters of the tunnel section to be predicted, wherein the formation parameters include tunnel burial depth, formation permeability coefficient and formation stress value measured by segment grouting;

[0015] The missing grouting volume prediction module is configured to: input the surface settlement value and the formation parameters into the pre-trained grouting volume prediction model to obtain the missing grouting volume of the tunnel section to be predicted;

[0016] The unit time grouting volume calculation module is configured to: add the missing grouting volume of the tunnel section to be predicted to the actual grouting volume to obtain the unit time grouting volume;

[0017] The grouting pressure calculation module is configured to determine the grouting pressure based on the grouting volume per unit time, and control the grouting pump based on the grouting pressure.

[0018] The third aspect of the present invention provides a computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the steps in the shield tunnel synchronous grouting optimization control method based on surface settlement values ​​as described in the first aspect of the present invention.

[0019] The fourth aspect of the present invention provides an electronic device, including a memory, a processor, and a program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in the shield tunnel synchronous grouting optimization control method based on surface settlement values ​​as described in the first aspect of the present invention are implemented.

[0020] One or more of the above technical solutions have the following beneficial effects:

[0021] The present invention provides a method and system for optimizing and controlling synchronous grouting of a shield tunnel based on ground settlement values. The method and system are based on a pre-trained grouting volume prediction model, and the grouting volume per unit time of the shield synchronous grouting is obtained according to the ground settlement values ​​and formation parameters, and then the grouting pressure is obtained. The grouting pump is controlled based on the grouting pressure, and the grouting parameters of the synchronous grouting of the shield tunnel can be accurately adjusted to meet the needs of synchronous grouting of shield tunnels in urban underground spaces.

[0022] The present invention obtains an accurate grouting plan based on the predicted grouting volume and grouting pressure per unit time, optimizes the grouting speed and grouting pressure parameters, greatly improves the grouting efficiency and quality of synchronous grouting, reduces problems such as voids caused by uneven and insufficient grouting, and ensures safe shield construction.

[0023] The present invention takes tunnel burial depth, stratum permeability coefficient, stratum stress measured by segment grouting, surface settlement value, subsequent secondary grouting amount and tunnel ring number as input features, takes the missing grouting amount as the target variable, trains the BP neural network model, and predicts the missing grouting amount of the predicted tunnel section based on the trained BP neural network model. The missing grouting amount taking into account the surface settlement value can be obtained, and the prediction result is more accurate.

[0024] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0026] Figure 1 This is a flow chart of the method of the first embodiment. DETAILED DESCRIPTION

[0027] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0028] It should be noted that the terms used herein are for describing specific embodiments only and are not intended to be limiting of exemplary embodiments according to the present invention.

[0029] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0030] Embodiment 1

[0031] This embodiment discloses a shield tunnel synchronous grouting optimization control method based on surface settlement value, which is used to solve the problem of poor precision of current shield machine synchronous grouting technology.

[0032] like Figure 1 As shown, the shield tunnel synchronous grouting optimization control method based on the surface settlement value includes the following steps:

[0033] Obtaining the surface settlement value and formation parameters of the tunnel section to be predicted, wherein the formation parameters include tunnel burial depth, formation permeability coefficient, and formation stress value measured by segment grouting;

[0034] The surface settlement value and formation parameters are input into the pre-trained grouting volume prediction model to obtain the missing grouting volume of the tunnel section to be predicted;

[0035] The missing grouting volume of the tunnel section to be predicted is added to the actual grouting volume to obtain the grouting volume per unit time;

[0036] The grouting pressure is determined based on the grouting volume per unit time, and the grouting pump is controlled based on the grouting pressure.

[0037] In this embodiment, the grouting volume prediction model is a BP neural network model, and pre-training the grouting volume prediction model includes the following steps:

[0038] 1. Data Collection

[0039] 1.1 Collect actual construction parameter data during the construction of multiple operating tunnels and divide the data sets. The actual construction parameter data includes:

[0040] (1) Tunnel depth: refers to the depth of the tunnel, usually measured in meters.

[0041] (2) Formation permeability coefficient: describes the permeability of the formation, with the unit of m / s.

[0042] (3) Formation stress measured during segment grouting: refers to the formation stress measured during the segment grouting process, the unit can be kPa.

[0043] (4) Surface settlement value: the surface settlement after tunnel construction or grouting, in mm.

[0044] (5) Subsequent secondary grouting volume: The amount of additional grouting required after the initial grouting to achieve the desired effect, in kg.

[0045] (6) Tunnel ring number: indicates the number of the current tunnel ring.

[0046] 1.2 Target Variable

[0047] The target variable to be predicted is the amount of grouting missing per ring under various formation parameters, usually in kg.

[0048] 1.3 Divide the data into training set, validation set and test set to facilitate subsequent model training and evaluation:

[0049] Training set: used to train the model, usually accounting for 70%.

[0050] Validation set: used for parameter adjustment and model selection during training, about 15%.

[0051] Test set: used for final evaluation of model performance, about 15%.

[0052] 2. Construct BP neural network model

[0053] 2.1 Determine the network structure, which generally includes input layer, hidden layer and output layer:

[0054] Input layer: The number of nodes is equal to the number of features (6 features).

[0055] Hidden layers: Select 2 hidden layers and 15 nodes

[0056] Output layer: One node, representing the predicted missing grouting amount for each ring.

[0057] 2.2 Choosing an activation function

[0058] Hidden layer: Use ReLU activation function, the form is

[0059] f(x)=max(0,x)

[0060] Output layer: Use linear activation function.

[0061] 3. Model training

[0062] 3.1 Select the loss function as mean square error (MSE):

[0063]

[0064] 3.2 Select optimization algorithm:

[0065] Using Adam optimizer

[0066] 3.3 Execute the training process:

[0067] 3.3.1, forward propagation:

[0068] (1) Input features are passed to the hidden layer through the input layer.

[0069] (2) Calculate the weighted sum in each hidden layer node and apply the activation function.

[0070] (3) The output of the hidden layer is passed to the output layer to calculate the final prediction value.

[0071] 3.3.2, Back Propagation:

[0072] (1) Calculate the error of the output layer and pass it back to the network.

[0073] (2) Update the weights and biases of each layer and adjust them using gradient descent.

[0074] (3) Repeat this process for multiple rounds (e.g., 1,000 times) until the loss value converges to a preset threshold or reaches the maximum number of iterations.

[0075] 3.4 Monitoring the Training Process

[0076] The loss value is recorded at the end of each epoch, and the validation set is used to monitor overfitting.

[0077] 4. Model Evaluation

[0078] Use mean square error (MSE), root mean square error (RMSE), and mean absolute error (MAE) indicators to evaluate the model effect. Draw a scatter plot of actual values ​​and predicted values ​​to intuitively understand the model's predictive ability.

[0079] 5. Prediction and output

[0080] Use the trained model to predict the new formation parameters and obtain the missing grouting volume for each ring;

[0081] Compare the predicted results with the actual measured values ​​and record the flaws in the prediction and room for improvement.

[0082] Since the above grouting volume prediction model outputs the missing grouting volume of each ring, the sum of the missing grouting volume plus the current grouting volume per unit time maintained by the shield is the optimized grouting volume per unit time.

[0083] Next, the grouting pressure is determined based on the grouting volume per unit time:

[0084] The grouting pump adjusts the grouting speed, that is, the grouting volume per unit time, through the grouting pressure. According to the grouting volume per unit time obtained above, the grouting pressure is specifically:

[0085]

[0086] ΔP is pressure; f is friction coefficient; L is length of grouting pipe; D is pipe diameter; ρ is slurry density; V is grouting speed, V = grouting volume per unit time / grouting pipe cross-sectional area. For example: grouting volume per unit time 0.5m 3 / s, the grouting pipe area is determined, for example, 0.1m 2 , then the grouting speed is 0.5 / 0.1=5m / s.

[0087] Also includes:

[0088] According to the predicted grouting volume and grouting pressure per unit time, an accurate grouting plan is obtained, which is as follows:

[0089] Real-time acquisition of grouting pressure during shield tunneling;

[0090] Compare the predicted grouting pressure with the received real-time grouting pressure, and adjust the actual grouting pressure during the construction process in real time;

[0091] Real-time acquisition of the actual injection volume per unit time of synchronous grouting slurry;

[0092] The predicted grouting volume per unit time is compared with the actual grouting volume per unit time, and the actual grouting volume per unit time during the construction process is adjusted in real time.

[0093] The grouting pressure can be obtained through the above-mentioned predicted grouting volume per unit time, and then the grouting pressure of the grouting pump can be adjusted, thereby completing the adjustment of the grouting volume and optimizing the synchronous grouting construction during the construction process. The synchronous grouting optimization control method of this embodiment can optimize the grouting speed and grouting pressure parameters, greatly improve the grouting efficiency and quality of synchronous grouting, reduce the problems of cavities caused by uneven and insufficient grouting, and escort the safe construction of the shield.

[0094] Embodiment 2

[0095] This embodiment discloses a shield tunnel synchronous grouting optimization control system based on surface settlement values.

[0096] The shield tunnel synchronous grouting optimization control system based on surface settlement value includes:

[0097] The data acquisition module is configured to: acquire the surface settlement value and formation parameters of the tunnel section to be predicted, wherein the formation parameters include tunnel burial depth, formation permeability coefficient and formation stress value measured by segment grouting;

[0098] The missing grouting volume prediction module is configured to: input the surface settlement value and the formation parameters into the pre-trained grouting volume prediction model to obtain the missing grouting volume of the tunnel section to be predicted;

[0099] The unit time grouting volume calculation module is configured to: add the missing grouting volume of the tunnel section to be predicted to the actual grouting volume to obtain the unit time grouting volume;

[0100] The grouting pressure calculation module is configured to determine the grouting pressure based on the grouting volume per unit time, and control the grouting pump based on the grouting pressure.

[0101] Embodiment 3

[0102] The purpose of this embodiment is to provide a computer-readable storage medium.

[0103] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the shield tunnel synchronous grouting optimization control method based on surface settlement values ​​as described in Example 1 of the present disclosure.

[0104] Embodiment 4

[0105] The purpose of this embodiment is to provide an electronic device.

[0106] An electronic device includes a memory, a processor, and a program stored in the memory and executable on the processor. When the processor executes the program, the steps in the shield tunnel synchronous grouting optimization control method based on surface settlement values ​​as described in Example 1 of the present disclosure are implemented.

[0107] The steps involved in the apparatuses of the above embodiments 2, 3 and 4 correspond to the method embodiment 1, and the specific implementation methods can refer to the relevant description part of embodiment 1. The term "computer-readable storage medium" should be understood as a single medium or multiple media including one or more instruction sets; it should also be understood to include any medium that can store, encode or carry an instruction set for execution by a processor and enable the processor to execute any method in the present invention.

[0108] Those skilled in the art should understand that the modules or steps of the present invention described above can be implemented by a general-purpose computer device, or alternatively, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. The present invention is not limited to any specific combination of hardware and software.

[0109] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A shield tunnel synchronous grouting optimization control method based on surface settlement value, characterized in that: The following steps are involved: Obtaining the surface settlement value and formation parameters of the tunnel section to be predicted, wherein the formation parameters include tunnel burial depth, formation permeability coefficient, and formation stress value measured by segment grouting; The surface settlement value and formation parameters are input into the pre-trained grouting volume prediction model to obtain the missing grouting volume of the tunnel section to be predicted; The missing grouting volume of the tunnel section to be predicted is added to the actual grouting volume to obtain the grouting volume per unit time; The grouting pressure is determined based on the grouting volume per unit time, and the grouting pump is controlled based on the grouting pressure.

2. The shield tunnel synchronous grouting optimization control method based on surface settlement value according to claim 1 is characterized in that: The grouting volume prediction model is a BP neural network model, and pre-training the grouting volume prediction model includes: Obtain historical construction parameter data during the construction of multiple operating tunnels, including tunnel burial depth, ground permeability coefficient, ground stress measured by segment grouting, surface settlement value, subsequent secondary grouting amount and number of tunnel rings; The historical construction parameter data is input into the BP neural network model as input features, the input features are transferred from the input layer to the hidden layer through forward propagation, and the output of the hidden layer is transferred to the output layer to obtain the predicted missing grouting amount; The parameters of the BP neural network model are updated through back propagation and gradient descent method until the loss value converges to the preset threshold or reaches the maximum number of iterations to obtain a trained BP neural network model.

3. The shield tunnel synchronous grouting optimization control method based on surface settlement value according to claim 2 is characterized in that: The loss function is the mean square error, specifically: Among them, y true Indicates the actual missing grouting volume; y pred represents the predicted missing grouting volume; n represents the number of iterations; i represents the i-th iteration.

4. The shield tunnel synchronous grouting optimization control method based on surface settlement value according to claim 1 is characterized in that: Based on the grouting volume per unit time, the grouting pressure is determined as follows: Among them, ΔP is the pressure; f is the friction coefficient; L is the length of the grouting pipe; D is the pipe diameter; ρ is the slurry density; V is the grouting volume per unit time / cross-sectional area of ​​the grouting pipe.

5. The shield tunnel synchronous grouting optimization control method based on surface settlement value according to claim 1 is characterized in that: It also includes obtaining an accurate grouting plan based on the predicted grouting volume and grouting pressure per unit time, specifically: Real-time acquisition of grouting pressure during shield tunneling; Compare the predicted grouting pressure with the received real-time grouting pressure, and adjust the actual grouting pressure during the construction process in real time; Real-time acquisition of the actual injection volume per unit time of synchronous grouting slurry; The predicted grouting volume per unit time is compared with the actual grouting volume per unit time, and the actual grouting volume per unit time during the construction process is adjusted in real time.

6. The shield tunnel synchronous grouting optimization control method based on surface settlement value according to claim 2 is characterized in that: The ReLU activation function is used in the hidden layer of the BP neural network model, and the linear activation function is used in the output layer.

7. The shield tunnel synchronous grouting optimization control method based on surface settlement value according to claim 2 is characterized in that: The surface settlement value is the actual settlement value of the tunnel caused by shield excavation during the construction process, and the tunnel ring number represents the number of the current tunnel ring.

8. The shield tunnel synchronous grouting optimization control system based on the surface settlement value is characterized by: include: The data acquisition module is configured to: acquire the surface settlement value and formation parameters of the tunnel section to be predicted, wherein the formation parameters include tunnel burial depth, formation permeability coefficient and formation stress value measured by segment grouting; The missing grouting volume prediction module is configured to: input the surface settlement value and the formation parameters into the pre-trained grouting volume prediction model to obtain the missing grouting volume of the tunnel section to be predicted; The unit time grouting volume calculation module is configured to: add the missing grouting volume of the tunnel section to be predicted to the actual grouting volume to obtain the unit time grouting volume; The grouting pressure calculation module is configured to determine the grouting pressure based on the grouting volume per unit time, and control the grouting pump based on the grouting pressure.

9. A computer-readable storage medium having a program stored thereon, characterized in that: When the program is executed by a processor, the steps of the shield tunnel synchronous grouting optimization control method based on surface settlement values ​​as described in any one of claims 1 to 7 are implemented.

10. An electronic device comprising a memory, a processor, and a program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps in the shield tunnel synchronous grouting optimization control method based on surface settlement values ​​as described in any one of claims 1-7 are implemented.

Citation Information

Patent Citations

  • Method for predicting ground surface settlement caused by shield construction based on neural fuzzy inference system

    CN107239599A

  • Prediction method and device for ground surface settlement value and computer readable storage medium

    CN111639468A

  • Synchronous grouting prediction method for shield construction of water-rich sandy gravel mudstone interactive composite stratum

    CN114626287A

  • Shield tunneling machine synchronous grouting control method and system

    CN115539059A

  • Shield synchronous grouting amount setting method and system based on knowledge data dual drive

    CN118008330A

Cited By

  • Grouting pressure intelligent adjusting method and system based on deep learning

    CN120066139A

  • Intelligent prediction method and system for settlement of TBM passing through pebble stratum

    CN120579463A

  • Intelligent prediction method and system for settlement of TBM crossing pebble stratum

    CN120579463B

  • High-performance shield intelligent synchronous grouting control system based on solid waste residue soil resource utilization, grouting material and preparation method

    CN120669590A

  • Small-clear-distance parallel shield low-disturbance cooperative control method based on preceding tunnel protection

    CN121556878A