A method and system for predicting TBM cutterhead jam in weathered granite strata

Abstract

The present invention discloses a method and system for predicting TBM cutterhead jamming in weathered granite formations, comprising: obtaining mechanical parameters that affect TBM cutterhead jamming during TBM excavation; establishing a relationship model between geophysical parameters and mechanical parameters, collecting geophysical parameters ahead of the tunnel face through advanced geological prediction of the tunnel, obtaining corresponding mechanical parameters using the relationship model, and calculating the surrounding rock integrity coefficient; based on the mechanical parameters, surrounding rock integrity coefficient, initial geostress, and mechanical parameters, obtaining TBM torque using a trained fully connected neural network model, comparing the TBM torque with the rated torque value, and determining whether the TBM cutterhead will jam. The present invention addresses the problem of TBM cutterhead jamming, establishes a cutterhead jam prediction model, and determines the mechanical and mechanical parameters that affect TBM cutterhead jamming, capable of predicting the TBM cutterhead torque, comparing the TBM cutterhead torque with the torque rating, and predicting whether the cutterhead will jam.

Description

Technical Field

[0001] The present invention relates to the field of geological exploration technology, and in particular to a method and system for predicting a TBM cutterhead stuck in a weathered granite stratum. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] Currently, TBM construction is increasingly being adopted for tunnel excavation due to its safety and efficiency. Weathered rock layers have lower mechanical strength, higher permeability, and are easily softened into mud when exposed to water. TBMs are less adaptable to weathered rock layers during excavation. Once encountering weathered granite strata, they are prone to geological disasters such as surrounding rock collapse, water and mud inrush, and other hazards. These can lead to TBM failure, abnormal damage, or even machine and personnel loss, resulting in serious economic losses and casualties. TBM jams have become a major engineering challenge that urgently needs to be addressed during tunnel construction.

[0004] Existing technology mainly studies TBM cutterhead sticking by establishing mechanical models. However, there are many factors affecting TBM cutterhead sticking, and there are many reasons for TBM cutterhead sticking. Mechanical models alone cannot well express the many factors and reasons that affect TBM cutterhead sticking. Summary of the Invention

[0005] In order to solve the above problems, the present invention proposes a method and system for predicting TBM cutterhead jam in weathered granite strata, which can predict TBM cutterhead jam in front of the tunnel face in advance, ensure construction safety and improve construction efficiency.

[0006] In some embodiments, the following technical solutions are adopted:

[0007] A method for predicting cutterhead jamming of a TBM in weathered granite strata, comprising:

[0008] Obtain the mechanical parameters that affect TBM cutterhead sticking during TBM excavation;

[0009] Establish a relationship model between geophysical parameters and mechanical parameters. Collect geophysical parameters ahead of the tunnel face through advanced geological prediction. Use the relationship model to obtain the corresponding mechanical parameters and calculate the surrounding rock integrity coefficient.

[0010] Based on the mechanical parameters, surrounding rock integrity coefficient, initial ground stress, and mechanical parameters, the trained fully connected neural network model is used to obtain the TBM torque, which is then compared with the rated torque value to determine whether the TBM cutterhead will jam.

[0011] As an optional solution, the mechanical parameters that affect TBM cutterhead sticking include: cutterhead rotation speed and penetration rate.

[0012] As an optional solution, a relationship model between geophysical parameters and mechanical parameters is established, specifically including:

[0013] Through indoor tests, the water content, resistivity and longitudinal wave velocity of the core are measured; the tensile strength and shear strength of the standard core are tested;

[0014] By conducting relevant tests on multiple rock cores, the relationship models between resistivity and water content, the relationship models between shear strength and water content, and the relationship models between tensile strength and longitudinal wave velocity were established respectively.

[0015] As an optional solution, geophysical parameters ahead of the tunnel face can be collected through advanced geological prediction of the tunnel, including:

[0016] The resistivity parameters in front of the tunnel face are obtained by the induced polarization method, the longitudinal wave velocity of the rock mass in front of the tunnel face is obtained by the seismic wave method, and the longitudinal wave velocity of the rock core is obtained by obtaining the rock core through advance drilling.

[0017] As an optional solution, the corresponding mechanical parameters are obtained using the relational model, specifically:

[0018] Based on the relationship model between resistivity parameter, resistivity and moisture content, moisture content data is obtained; through the relationship model between moisture content data, shear strength and moisture content, shear strength data is obtained;

[0019] Based on the relationship model between the longitudinal wave velocity of the rock core and the tensile strength and longitudinal wave velocity, the tensile strength data of the rock mass are obtained.

[0020] As an optional solution, the surrounding rock integrity coefficient is calculated, which is specifically the square of the ratio of the longitudinal wave velocity of the rock mass to the longitudinal wave velocity of the core.

[0021] As an optional solution, the TBM torque is compared with the rated torque value to determine whether the TBM cutterhead will jam, specifically including:

[0022] When the TBM torque is greater than the rated torque value, it is determined that the TBM is stuck.

[0023] In other embodiments, the following technical solutions are adopted:

[0024] A TBM cutterhead jam prediction system for weathered granite strata, comprising:

[0025] The data acquisition module is used to obtain the mechanical parameters that affect the TBM cutterhead jam during TBM excavation;

[0026] The parameter calculation module is used to establish a relationship model between geophysical parameters and mechanical parameters. The geophysical parameters ahead of the tunnel face are collected through advanced geological prediction of the tunnel. The corresponding mechanical parameters are obtained using the relationship model to calculate the surrounding rock integrity coefficient.

[0027] The cutterhead sticking judgment module is used to obtain the TBM torque based on the mechanical parameters, surrounding rock integrity coefficient, initial ground stress and mechanical parameters using a trained fully connected neural network model, compare the TBM torque with the rated torque value, and judge whether the TBM cutterhead will stick.

[0028] In other embodiments, the following technical solutions are adopted:

[0029] A terminal device includes a processor and a memory, wherein the processor is used to implement various instructions; the memory is used to store multiple instructions, wherein the instructions are suitable for being loaded and executed by the processor for the above-mentioned method for predicting cutterhead jam of a TBM in weathered granite formation.

[0030] In other embodiments, the following technical solutions are adopted:

[0031] A computer-readable storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded and executed by a processor of a terminal device to predict the cutterhead jam of a TBM in a weathered granite formation.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] (1) The present invention addresses the problem of TBM cutterhead sticking by establishing a cutterhead sticking prediction model and determining the mechanical and mechanical parameters that affect TBM cutterhead sticking. Based on these parameters, the TBM cutterhead torque is predicted, and the TBM cutterhead torque is compared with the torque rating to predict whether the cutterhead will stick.

[0034] (2) The present invention establishes a relationship model between geophysical parameters and mechanical parameters through indoor experiments, and obtains geophysical parameters in front of the tunnel face through geophysical methods (seismic wave method, induced polarization method). The mechanical parameters that affect the TBM cutterhead jam are obtained through the relationship model, providing accurate data support for the TBM cutterhead jam, ensuring safe and efficient TBM construction.

[0035] Other features and 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

[0036] Figure 1 This is a flow chart of a method for predicting cutterhead jamming in a weathered granite formation TBM according to an embodiment of the present invention;

[0037] Figure 2 Schematic diagram of a fully connected neural network in an embodiment of the present invention. DETAILED DESCRIPTION

[0038] It should be noted that the following detailed description is illustrative and is intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used in the present invention have the same meaning as commonly understood by those skilled in the art to which the present application belongs.

[0039] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or combinations thereof.

[0040] Example 1

[0041] In one or more embodiments, a method for predicting cutterhead jamming of a TBM in a weathered granite formation is disclosed, referring to Figure 1 , specifically including the following process:

[0042] S101: Acquire mechanical parameters that affect TBM cutterhead jamming during TBM excavation;

[0043] In this embodiment, the mechanical parameters that affect the TBM cutterhead jam include the cutterhead rotation speed and penetration rate; these two data are directly obtained from the data records during the TBM construction process.

[0044] S102: Establish a relationship model between geophysical parameters and mechanical parameters. Collect geophysical parameters ahead of the tunnel face through advanced geological prediction of the tunnel. Use the relationship model to obtain corresponding mechanical parameters and calculate the surrounding rock integrity coefficient.

[0045] Specifically, through laboratory testing, the water content, resistivity, and longitudinal wave velocity of the core rock were first measured. The tensile and shear strengths of the standard core rock were then tested. Related tests were conducted on multiple core rock samples to establish relationship models between resistivity and water content, between shear strength and water content, and between tensile strength and longitudinal wave velocity. These models were established by acquiring experimental data and fitting the data using a spreadsheet. The fitting methods may vary, but can include linear fitting, power exponential fitting, and other methods, and then obtaining correlation coefficients.

[0046] The resistivity parameters ahead of the tunnel face are obtained by the induced polarization method, the longitudinal wave velocity of the rock mass ahead of the tunnel face is obtained by the seismic wave method, and the longitudinal wave velocity of the rock core is obtained by advance drilling.

[0047] Based on the relationship model between resistivity parameters, resistivity and water content, water content data is obtained; through the relationship model between water content data, shear strength and water content, shear strength data is obtained; based on the relationship model between core longitudinal wave velocity, tensile strength and longitudinal wave velocity, rock mass tensile strength data is obtained.

[0048] The method for calculating the surrounding rock integrity coefficient is: the square of the ratio of the longitudinal wave velocity of the rock mass to the longitudinal wave velocity of the core.

[0049] S103: Based on the mechanical parameters, surrounding rock integrity coefficient, initial ground stress and mechanical parameters, the trained fully connected neural network model is used to obtain the TBM torque, and the TBM torque is compared with the rated torque value to determine whether the TBM cutterhead will jam.

[0050] In this example, the obtained tensile strength, shear strength, and surrounding rock integrity coefficient, along with the ground stress values ​​ahead of the tunnel face, TBM rotational speed, and penetration rate obtained from the construction company, are fed into a trained neural network model. The output is then compared with the TBM's rated torque to determine whether the TBM will experience cutterhead jam. A TBM jam is determined when the torque during tunneling exceeds the rated torque.

[0051] In this embodiment, the neural network model adopts Figure 2 The fully connected neural network model shown in FIG. 1 is a fully connected neural network model. The training process of the fully connected neural network model includes:

[0052] Based on numerous field cases of TBM cutterhead sticking and literature research and analysis, this example proposes mechanical and mechanical parameters that influence TBM cutterhead sticking. Mechanical parameters include tensile strength, shear strength, in-situ stress, and surrounding rock integrity coefficient; mechanical parameters include cutterhead speed and penetration rate.

[0053] On this basis, multiple in-tunnel tests were conducted to obtain the mechanical and mechanical parameters that affect TBM cutterhead sticking and to establish a sample data set for neural network training.

[0054] The fully connected neural network model is trained by collecting mechanical parameters and mechanical parameters. The input parameters are the mechanical parameters and mechanical parameters that affect the TBM cutterhead sticking, and the output parameter is the TBM cutterhead torque.

[0055] This embodiment determines the mechanical and mechanical parameters that affect cutterhead sticking and obtains a cutterhead sticking prediction result through a neural network prediction model. The obtained result is accurate and reliable, can provide protection for TBM tunnel construction, and ensures safe and efficient TBM construction.

[0056] Example 2

[0057] In one or more embodiments, a system for predicting cutterhead jamming of a TBM in weathered granite formations is disclosed, specifically comprising:

[0058] The data acquisition module is used to obtain the mechanical parameters that affect the TBM cutterhead jam during TBM excavation;

[0059] The parameter calculation module is used to establish a relationship model between geophysical parameters and mechanical parameters. The geophysical parameters ahead of the tunnel face are collected through advanced geological prediction of the tunnel. The corresponding mechanical parameters are obtained using the relationship model to calculate the surrounding rock integrity coefficient.

[0060] The cutterhead sticking judgment module is used to obtain the TBM torque based on the mechanical parameters, surrounding rock integrity coefficient, initial ground stress and mechanical parameters using a trained fully connected neural network model, compare the TBM torque with the rated torque value, and judge whether the TBM cutterhead will stick.

[0061] It should be noted that the specific implementation of the above modules has been described in Example 1 and will not be described in detail here.

[0062] Example 3

[0063] In one or more embodiments, a terminal device is disclosed, including a server. The server includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the method for predicting cutterhead jam of a TBM in weathered granite formations described in Example 1 is implemented. For the sake of brevity, this description is omitted here.

[0064] It should be understood that in this embodiment, the processor may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), off-the-shelf field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0065] The memory may include a read-only memory and a random access memory, and provides instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0066] During implementation, each step of the above method may be completed by an integrated logic circuit of hardware in a processor or by instructions in the form of software.

[0067] Example 4

[0068] In one or more embodiments, a computer-readable storage medium is disclosed, storing a plurality of instructions suitable for being loaded and executed by a processor of a terminal device for the method for predicting cutterhead jam of a TBM in weathered granite formations described in Example 1.

[0069] Although the above describes the specific embodiments 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 any creative work are still within the scope of protection of the present invention.

Claims

1. A method for predicting cutterhead jamming of a TBM in weathered granite strata, characterized in that: include: Obtain the mechanical parameters that affect TBM cutterhead sticking during TBM excavation; Establish a relationship model between geophysical parameters and mechanical parameters. Collect geophysical parameters ahead of the tunnel face through advanced geological prediction. Use the relationship model to obtain the corresponding mechanical parameters and calculate the surrounding rock integrity coefficient. Based on the mechanical parameters, surrounding rock integrity coefficient, initial ground stress, and mechanical parameters, a trained fully connected neural network model is used to obtain the TBM torque, and the TBM torque is compared with the rated torque value to determine whether the TBM cutterhead will jam. Establish a relationship model between geophysical parameters and mechanical parameters, including: Through indoor tests, the water content, resistivity and longitudinal wave velocity of the core are measured; the tensile strength and shear strength of the standard core are tested; Through relevant tests on multiple cores, the relationship models between resistivity and water content, the relationship models between shear strength and water content, and the relationship models between tensile strength and longitudinal wave velocity were established respectively; The corresponding mechanical parameters are obtained using the relational model, specifically: Based on the relationship model between resistivity parameter, resistivity and moisture content, moisture content data is obtained; through the relationship model between moisture content data, shear strength and moisture content, shear strength data is obtained; Based on the relationship model between the longitudinal wave velocity of the rock core and the tensile strength and longitudinal wave velocity, the tensile strength data of the rock mass are obtained.

2. The method for predicting cutterhead jamming of a TBM in weathered granite strata according to claim 1, wherein: The mechanical parameters that affect TBM cutterhead sticking include cutterhead rotation speed and penetration rate.

3. The method for predicting cutterhead jamming of a TBM in a weathered granite formation according to claim 1, wherein: The geophysical parameters ahead of the tunnel face are collected through advanced geological prediction of the tunnel, including: The resistivity parameters in front of the tunnel face are obtained by the induced polarization method, the longitudinal wave velocity of the rock mass in front of the tunnel face is obtained by the seismic wave method, and the longitudinal wave velocity of the rock core is obtained by obtaining the rock core through advance drilling.

4. The method for predicting cutterhead jamming of a TBM in a weathered granite formation according to claim 3, wherein: Calculate the surrounding rock integrity coefficient, which is the square of the ratio of the longitudinal wave velocity of the rock mass to the longitudinal wave velocity of the core.

5. The method for predicting cutterhead jamming of a TBM in a weathered granite formation according to claim 1, wherein: Comparing the TBM torque with the rated torque value to determine whether the TBM cutterhead will jam, specifically including: When the TBM torque is greater than the rated torque value, it is determined that the TBM is stuck.

6. A system for predicting cutterhead jam of a TBM in weathered granite strata, using the method for predicting cutterhead jam of a TBM in weathered granite strata according to any one of claims 1 to 5, characterized in that: include: The data acquisition module is used to obtain the mechanical parameters that affect the TBM cutterhead jam during TBM excavation; The parameter calculation module is used to establish a relationship model between geophysical parameters and mechanical parameters. The geophysical parameters ahead of the tunnel face are collected through advanced geological prediction of the tunnel. The corresponding mechanical parameters are obtained using the relationship model to calculate the surrounding rock integrity coefficient. The cutterhead sticking judgment module is used to obtain the TBM torque based on the mechanical parameters, surrounding rock integrity coefficient, initial ground stress and mechanical parameters using a trained fully connected neural network model, compare the TBM torque with the rated torque value, and judge whether the TBM cutterhead will stick.

7. A terminal device comprising a processor and a memory, wherein the processor is used to implement various instructions; the memory is used to store multiple instructions, characterized in that: The instructions are suitable for being loaded by a processor and executing the method for predicting cutterhead jam of a TBM in a weathered granite formation according to any one of claims 1 to 5.

8. A computer-readable storage medium storing a plurality of instructions, characterized in that: The instructions are suitable for being loaded by a processor of a terminal device and executing the method for predicting cutterhead jam of a TBM in a weathered granite formation according to any one of claims 1 to 5.

Images