TBM tunnel advanced detection wave velocity parameter correction method and device

Abstract

The application discloses a TBM tunnel advanced detection wave velocity parameter correction method and device, and relates to the technical field of tunnel construction, wherein the method comprises the following steps: determining first position information of an adverse geological body in front of a working face by an advanced detection method; acquiring a plurality of construction parameters of a heading machine in tunnel excavation construction in real time; inputting the plurality of construction parameters of the heading machine into a pre-established adverse geological body identification model to output a geological type of the current working face, wherein the adverse geological body identification model is obtained by training a machine learning model; if the geological type of the current working face is an adverse geological body, determining second position information of the current working face; correcting the advanced detection wave velocity parameter according to the difference between the second position information and the first position information; and detecting the adverse geological body in front of the working face by using the corrected advanced detection wave velocity parameter. The application can improve the efficiency of the advanced detection wave velocity parameter and improve the position detection precision of the adverse geological body.

Description

Technical Field

[0001] This invention relates to the field of tunnel construction technology, and in particular to a method and device for correcting wave velocity parameters in advance detection of TBM tunnels. Background Technology

[0002] This section is intended to provide background or context for the embodiments of the invention set forth in the claims. The description herein is not an admission that it is prior art simply because it is included in this section.

[0003] In TBM (tunnel boring machine) tunnel construction, advanced detection of adverse geological features is a prerequisite for implementing advanced support measures. Advanced detection methods are widely used for this purpose. Wavelength-based advanced detection primarily relies on the relative distance difference between the adverse geological feature and the detector. The location of the adverse geological feature is obtained by multiplying the time difference between the received signals from the transmitter and detector by a wave velocity parameter. However, the selection of the wave velocity parameter is largely empirical, leading to poor accuracy in detecting the location of adverse geological features and hindering effective guidance for support measures and safe tunneling.

[0004] Existing technologies typically require the calibration of wave velocity parameters, but wave velocity parameter calibration is costly and has a large time lag due to shield obstruction. This results in problems such as expensive equipment and complex data processing, making it unsuitable for timely detection during the construction of long-distance tunnels. Summary of the Invention

[0005] This invention provides a method for correcting wave velocity parameters in advance detection of TBM tunnels, to improve the speed and efficiency of wave velocity parameter correction and enhance the accuracy of detecting the location of adverse geological bodies. The method includes:

[0006] The initial location information of adverse geological bodies in front of the tunnel face was determined by the advanced detection method;

[0007] Multiple construction parameters of the tunnel boring machine during tunnel excavation are acquired in real time, and these construction parameters reflect the geological conditions of the tunnel face.

[0008] Multiple construction parameters of the tunnel boring machine are input into a pre-established adverse geological body identification model, and the geological type of the current tunnel face is output. The geological type includes adverse geological bodies and non-adverse geological bodies. The adverse geological body identification model is obtained by training a machine learning model using multiple construction parameters of the tunnel boring machine and geological types of the tunnel face in the past tunnel excavation construction.

[0009] If the geological type of the current working face is an unfavorable geological body, determine the second location information of the current working face;

[0010] Based on the difference between the second and first position information, the advanced detection wave velocity parameters are corrected.

[0011] The modified advanced detection wave velocity parameters are used to detect unfavorable geological bodies ahead of the tunnel face.

[0012] This invention also provides a device for correcting wave velocity parameters in advance detection of TBM tunnels, to improve the speed and efficiency of wave velocity parameter correction in advance detection and to improve the accuracy of detecting the location of adverse geological bodies. The device includes:

[0013] The advanced detection and prediction module is used to determine the first location information of adverse geological bodies in front of the tunnel face through advanced detection methods;

[0014] The tunnel boring machine (TBM) construction parameter acquisition module is used to acquire multiple construction parameters of the TBM during tunnel excavation in real time. These construction parameters reflect the geological conditions of the tunnel face.

[0015] The tunnel boring machine (TBM) construction parameter prediction module is used to input multiple construction parameters of the TBM into a pre-established adverse geological body identification model and output the geological type of the current tunnel face. The geological type includes adverse geological bodies and non-adverse geological bodies. The adverse geological body identification model is obtained by training a machine learning model using multiple construction parameters of the TBM and geological types of the tunnel face in the past.

[0016] The wave velocity parameter correction module is used to determine the second location information of the current working face if the geological type of the current working face is an unfavorable geological body; and to correct the advanced detection wave velocity parameters based on the difference between the second location information and the first location information.

[0017] The advanced detection and prediction module is also used to detect adverse geological bodies in front of the tunnel face using the corrected advanced detection wave velocity parameters.

[0018] This invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-described TBM tunnel advance detection wave velocity parameter correction method.

[0019] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for correcting wave velocity parameters in advance detection of TBM tunnels.

[0020] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-described TBM tunnel advance detection wave velocity parameter correction method.

[0021] In this embodiment of the invention, the first location information of unfavorable geological bodies in front of the tunnel face is determined by an advanced detection method; multiple construction parameters of the tunnel boring machine during tunnel excavation are acquired in real time, the construction parameters reflecting the geological conditions of the tunnel face; the multiple construction parameters of the tunnel boring machine are input into a pre-established unfavorable geological body identification model, and the geological type of the current tunnel face is output, the geological type including unfavorable geological bodies and non-unfavorable geological bodies, the unfavorable geological body identification model is trained on a machine learning model using historical data: multiple construction parameters of the tunnel boring machine during tunnel excavation and the geological type of the tunnel face; if the geological type of the current tunnel face is an unfavorable geological body, the second location information of the current tunnel face is determined; the advanced detection wave velocity parameters are corrected according to the difference between the second location information and the first location information; the corrected advanced detection wave velocity parameters are used to detect unfavorable geological bodies in front of the tunnel face. In this embodiment of the invention, an advanced detection method is used to determine unfavorable geological bodies in front of the tunnel face. Combined with the intelligent judgment of the geological type of the current tunnel face, the wave velocity parameter in the advanced detection method is corrected. Compared with the complex and time-consuming calibration in the prior art, the correction of the wave velocity parameter is faster, more efficient, more real-time, and less costly, which greatly improves the accuracy of detecting the location of unfavorable geological bodies in tunnel construction. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:

[0023] Figure 1 This is a flowchart illustrating the method for correcting wave velocity parameters in advance detection of TBM tunnels in an embodiment of the present invention.

[0024] Figure 2 This is a specific embodiment of the TBM tunnel advance detection wave velocity parameter correction method in the present invention;

[0025] Figure 3 This is a specific embodiment of the TBM tunnel advance detection wave velocity parameter correction method in the present invention;

[0026] Figure 4 This is a schematic diagram of the TBM tunnel advance detection wave velocity parameter correction device in an embodiment of the present invention;

[0027] Figure 5 This is a schematic diagram of a computer device in an embodiment of the present invention. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0029] It should be noted that the acquisition, storage, use, and processing of data in the technical solution of this application all comply with the relevant provisions of national laws and regulations.

[0030] The applicant found that advanced detection is currently an essential system for TBM tunnel construction, but the calibration of wave velocity parameters using advanced detection is costly and has significant time delays, making it unsuitable for long-distance tunnel construction. Existing methods for determining rock mass wave velocity suffer from problems such as expensive equipment and complex data processing, failing to effectively improve the wave velocity parameter correction results. Therefore, developing a dynamic correction method for wave velocity parameters in advanced detection using TBM tunnel wave methods is extremely necessary.

[0031] Figure 1 This is a flowchart illustrating the method for correcting wave velocity parameters in TBM tunnel advance detection according to an embodiment of the present invention. Figure 1 As shown, the method includes:

[0032] Step 101: Determine the initial location information of the unfavorable geological body in front of the tunnel face using the advanced detection method;

[0033] Step 102: Real-time acquisition of multiple construction parameters of the tunnel boring machine during tunnel excavation, wherein the construction parameters reflect the geological conditions of the tunnel face;

[0034] Step 103: Input multiple construction parameters of the tunnel boring machine into the pre-established adverse geological body identification model, and output the geological type of the current tunnel face. The geological type includes adverse geological bodies and non-adverse geological bodies. The adverse geological body identification model is obtained by training the machine learning model using multiple construction parameters of the tunnel boring machine and the geological type of the tunnel face in the past tunnel excavation construction.

[0035] Step 104: If the geological type of the current working face is an unfavorable geological body, determine the second location information of the current working face;

[0036] Step 105: Correct the advanced detection wave velocity parameters based on the difference between the second position information and the first position information;

[0037] Step 106: Use the corrected advanced detection wave velocity parameters to detect unfavorable geological bodies in front of the tunnel face.

[0038] from Figure 1As shown in the flowchart, in this embodiment of the invention, the first location information of the unfavorable geological body in front of the tunnel face is determined by the advanced detection method; multiple construction parameters of the tunnel boring machine during tunnel excavation are acquired in real time, and the construction parameters reflect the geological conditions of the tunnel face; the multiple construction parameters of the tunnel boring machine are input into a pre-established unfavorable geological body identification model, and the geological type of the current tunnel face is output, the geological type including unfavorable geological body and non-unfavorable geological body, the unfavorable geological body identification model is obtained by training a machine learning model using historical data: multiple construction parameters of the tunnel boring machine during tunnel excavation and the geological type of the tunnel face; if the geological type of the current tunnel face is unfavorable geological body, the second location information of the current tunnel face is determined; the advanced detection wave velocity parameters are corrected according to the difference between the second location information and the first location information; and the corrected advanced detection wave velocity parameters are used to detect unfavorable geological bodies in front of the tunnel face. In this embodiment of the invention, an advanced detection method is used to determine unfavorable geological bodies in front of the tunnel face. Combined with the intelligent judgment of the geological type of the current tunnel face, the wave velocity parameter in the advanced detection method is corrected. Compared with the complex and time-consuming calibration in the prior art, the correction of the wave velocity parameter is faster, more efficient, more real-time, and less costly, which greatly improves the accuracy of detecting the location of unfavorable geological bodies in tunnel construction.

[0039] The following section provides a detailed explanation of the wave velocity parameter correction method for TBM tunnel advance detection in this application.

[0040] First, in step 101, the location of unfavorable geological bodies identified through advanced exploration is interpreted. In this embodiment of the invention, the type of advanced exploration method is not limited; most seismic wave methods can be used to implement this embodiment.

[0041] Figure 2 This is a specific embodiment of the TBM tunnel advance detection wave velocity parameter correction method in the present invention, such as... Figure 2 As shown, determining the initial location information of adverse geological bodies ahead of the tunnel face using the advanced detection method can include:

[0042] Step 201: Obtain geological exploration data in front of the tunnel face using a geophone. The geophone is deployed in front of the tunnel face to receive the reflected waves of the vibration signal emitted by the seismic source transmitter into the strata in front of the tunnel face in the adverse geological body.

[0043] Step 202: Based on geological survey data, determine the first location information of the unfavorable geological body in front of the tunnel face.

[0044] During implementation, geological exploration data in front of the tunnel face is obtained by deploying geophones, and geological exploration results are obtained by data interpretation software. The location information of adverse geological bodies is identified using the exploration results.

[0045] In steps 102 and 103, the adverse geological conditions are monitored by combining multiple construction parameters of the tunneling machine.

[0046] First, multiple construction parameters of the tunnel boring machine (TBM) during tunnel excavation are acquired in real time using various sensors installed on the TBM or parameters obtainable by the TBM itself. These construction parameters reflect the geological conditions at the tunnel face, such as thrust F, torque T, and penetration depth p. Real-time acquisition can be understood as continuously updating and acquiring these parameters at a certain frequency.

[0047] After obtaining multiple construction parameters of the tunnel boring machine, the geological type of the current working face is determined by using a pre-established adverse geological body identification model. The geological type includes adverse geological bodies and non-adverse geological bodies, such as good geological bodies.

[0048] Among them, the adverse geological body identification model is obtained by training the machine learning model using historical data: multiple construction parameters of the tunnel boring machine and the geological type of the tunnel face during tunnel excavation.

[0049] In one embodiment, the adverse geological body identification model employs the K-nearest neighbor algorithm.

[0050] Figure 3 This is a specific embodiment of the TBM tunnel advance detection wave velocity parameter correction method in the present invention, such as... Figure 3 As shown, the adverse geological body identification model can be trained in the following manner:

[0051] Step 301: Collect historical data on multiple construction parameters of the tunnel boring machine and the geological type of the tunnel face during tunnel excavation.

[0052] Step 302: Mark multiple construction parameters of the tunnel boring machine and geological types of the tunnel face during historical tunnel excavation to form training samples; the marking process includes marking according to different geological types;

[0053] Step 303: Using training samples, train the machine model using the K-nearest neighbor algorithm to obtain the adverse geological body identification model.

[0054] During implementation, a sample database of excavated tunnels can be established. By recording the surrounding rock conditions revealed during excavation, the characteristics of the supporting surrounding rock of collapsed and fractured zones with unfavorable geological bodies can be recorded, enabling the identification of the location information of unfavorable geological bodies. Geological bodies are marked according to their characteristics, with unfavorable geological bodies marked as 1 and favorable geological bodies marked as 0. For the identification of unfavorable geological body characteristics at the tunneling face, the tunneling machine's excavation parameter information method is used to extract features from parameters such as thrust F, torque T, and penetration depth p. Indices such as FPI (FPI = F / p, field penetration index) and TPI (TPI = T / p, torque penetration index) are calculated, forming a sample database of tunneling construction parameter characteristics.

[0055] The KNN intelligent identification algorithm is introduced to establish an intelligent identification model for unfavorable geological bodies. Based on the distribution patterns of unfavorable geological bodies and FPI and TPI indices, the FPI and TPI indices are used as input features, and the geological body codes (0 and 1) are used as output features. The KNN unfavorable geological body intelligent identification model is established through algorithm training.

[0056] In step 104, the location of the actual excavated unfavorable geological body is interpreted. Based on the multiple construction parameters of the tunnel boring machine, these parameters are input into the unfavorable geological body identification model to identify the geological body status information. If the geological type of the current working face is an unfavorable geological body, the second location information x2 of the current working face is determined.

[0057] In step 105, the advanced detection wave velocity parameters are corrected based on the difference between the second position information and the first position information.

[0058] Based on the difference between the second and first location information, the location deviation value is determined. For the location x1 of the unfavorable geological body obtained from the advance exploration and the location x2 of the unfavorable geological body revealed by actual excavation, the location deviation Δx = x1 - x2 is calculated.

[0059] Using the time difference Δt between the vibration signal emitted by the seismic source transmitter and the reflected wave received by the detector, and the position deviation value Δx, the advanced detection wave velocity parameters are corrected as follows:

[0060] v = 2Δx / Δt

[0061] Where v is the corrected advanced detection wave velocity parameter.

[0062] Next, the accuracy of detecting adverse geological bodies can be verified. Using the corrected wave velocity parameter v, advance detection is conducted ahead of the tunnel face, and the result is verified in conjunction with the actual excavation and exposure of the surrounding rock. When the detection and actual exposure results are accurate, it indicates that the wave velocity parameter correction is appropriate. When there is an error between the detection and actual exposure results, the wave velocity parameter is dynamically corrected based on the positional error, thereby improving the accuracy of detecting adverse geological bodies.

[0063] Finally, the modified advanced detection wave velocity parameters were used to detect adverse geological bodies ahead of the tunnel face.

[0064] In summary, this embodiment of the invention combines advanced detection prediction with prediction based on tunneling machine construction parameters. This allows for the rapid determination of the location of adverse geological bodies based on advanced detection data and tunneling machine construction parameters. The advanced detection wave velocity parameters are then corrected based on the positional deviation between the two methods. As a result, the location of adverse geological bodies can be determined without manual intervention. The dynamic correction of the wave velocity parameters improves the accuracy of adverse geological body location detection during subsequent tunneling, providing a basis for decision-making regarding advanced support ahead of the tunnel face. Furthermore, it enables the rational setting of tunneling parameters during construction in adverse geological conditions, thereby enhancing construction safety.

[0065] The embodiments of the present invention can realize automated and accurate identification of the location of adverse geological bodies. Compared with traditional methods such as identifying adverse geological bodies through surrounding rock images and core drilling, it has the characteristics of high real-time performance and low cost. By combining the location identification results of adverse geological bodies with advanced detection and correcting the wave velocity parameters under the premise of location error discrimination, the location identification accuracy of adverse geological bodies can be improved, and it has the characteristics of simple operation.

[0066] This invention also provides a device for correcting wave velocity parameters in TBM tunnel advance detection, as described in the following embodiments. Since the principle behind this device is similar to the method for correcting wave velocity parameters in TBM tunnel advance detection, its implementation can be found in the implementation of the method for correcting wave velocity parameters in TBM tunnel advance detection; repeated details will not be elaborated further.

[0067] Figure 4 This is a schematic diagram of the TBM tunnel advance detection wave velocity parameter correction device in an embodiment of the present invention, as shown below. Figure 4 As shown, the device includes:

[0068] The advanced detection and prediction module 401 is used to determine the first location information of the unfavorable geological body in front of the tunnel face through the advanced detection method.

[0069] The tunnel boring machine construction parameter acquisition module 402 is used to acquire multiple construction parameters of the tunnel boring machine in real time during tunnel excavation, and the construction parameters reflect the geological conditions of the tunnel face.

[0070] The tunnel boring machine construction parameter prediction module 403 is used to input multiple construction parameters of the tunnel boring machine into a pre-established adverse geological body identification model and output the geological type of the current tunnel face. The geological type includes adverse geological bodies and non-adverse geological bodies. The adverse geological body identification model is obtained by training a machine learning model using multiple construction parameters of the tunnel boring machine and the geological type of the tunnel face in the past tunnel excavation construction.

[0071] The wave velocity parameter correction module 404 is used to determine the second location information of the current working face if the geological type of the current working face is an unfavorable geological body; and to correct the advanced detection wave velocity parameter according to the difference between the second location information and the first location information.

[0072] The advanced detection and prediction module 401 is also used to detect adverse geological bodies in front of the tunnel face using the corrected advanced detection wave velocity parameters.

[0073] In one embodiment, the advanced detection and prediction module 401 is specifically used for:

[0074] Geological exploration data in front of the tunnel face is obtained by a geophone. The geophone is deployed in front of the tunnel face to receive the reflection wave of the vibration signal emitted by the seismic source transmitter into the strata in front of the tunnel face in the adverse geological body.

[0075] Based on geological survey data, the primary location information of the unfavorable geological body in front of the tunnel face was determined.

[0076] In one embodiment, the wave velocity parameter correction module 404 is specifically used for:

[0077] Based on the difference between the second position information and the first position information, the position deviation value Δx is determined;

[0078] Using the time difference Δt between the vibration signal emitted by the seismic source transmitter and the reflected wave received by the detector, and the position deviation value Δx, the advanced detection wave velocity parameters are corrected as follows:

[0079] v = 2Δx / Δt

[0080] Where v is the corrected advanced detection wave velocity parameter.

[0081] In one embodiment, the adverse geological body identification model employs the K-nearest neighbor algorithm.

[0082] In one embodiment, the adverse geological body identification model is trained as follows:

[0083] Collecting historical data: multiple construction parameters of tunnel boring machines and geological types of the tunnel face during tunnel excavation;

[0084] For historical data, multiple construction parameters of the tunnel boring machine and geological types of the tunnel face during tunnel excavation are tagged to form training samples; the tagging process includes tagging according to different geological types.

[0085] Using training samples, a machine model employing the K-nearest neighbor algorithm is trained to obtain an adverse geological body identification model.

[0086] In one embodiment, the advanced detection method includes: the seismic wave method.

[0087] Figure 5 This is a schematic diagram of a computer device in an embodiment of the present invention, such as... Figure 5As shown, this embodiment of the invention also provides a computer device 500, including a processor 501, a memory 502, and a computer program 503 stored in the memory 502 and executable on the processor 501. When the processor 501 executes the computer program 503, it implements the above-mentioned TBM tunnel advance detection wave velocity parameter correction method.

[0088] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for correcting wave velocity parameters in advance detection of TBM tunnels.

[0089] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-described TBM tunnel advance detection wave velocity parameter correction method.

[0090] In this embodiment of the invention, the first location information of unfavorable geological bodies in front of the tunnel face is determined by an advanced detection method; multiple construction parameters of the tunnel boring machine during tunnel excavation are acquired in real time, the construction parameters reflecting the geological conditions of the tunnel face; the multiple construction parameters of the tunnel boring machine are input into a pre-established unfavorable geological body identification model, and the geological type of the current tunnel face is output, the geological type including unfavorable geological bodies and non-unfavorable geological bodies, the unfavorable geological body identification model is trained on a machine learning model using historical data: multiple construction parameters of the tunnel boring machine during tunnel excavation and the geological type of the tunnel face; if the geological type of the current tunnel face is an unfavorable geological body, the second location information of the current tunnel face is determined; the advanced detection wave velocity parameters are corrected according to the difference between the second location information and the first location information; the corrected advanced detection wave velocity parameters are used to detect unfavorable geological bodies in front of the tunnel face. In this embodiment of the invention, an advanced detection method is used to determine unfavorable geological bodies in front of the tunnel face. Combined with the intelligent judgment of the geological type of the current tunnel face, the wave velocity parameter in the advanced detection method is corrected. Compared with the complex and time-consuming calibration in the prior art, the correction of the wave velocity parameter is faster, more efficient, more real-time, and less costly, which greatly improves the accuracy of detecting the location of unfavorable geological bodies in tunnel construction.

[0091] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0092] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0093] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0094] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0095] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for correcting wave velocity parameters in advance detection of TBM tunnels, characterized in that, Applied to tunnel excavation construction, including: The first location information of the unfavorable geological body in front of the tunnel face was determined by the advanced detection method; Multiple construction parameters of the tunnel boring machine during tunnel excavation are acquired in real time, and these construction parameters reflect the geological conditions of the tunnel face. Multiple construction parameters of the tunnel boring machine are input into a pre-established adverse geological body identification model, and the geological type of the current tunnel face is output. The geological type includes adverse geological bodies and non-adverse geological bodies. The adverse geological body identification model is obtained by training a machine learning model using multiple construction parameters of the tunnel boring machine and geological types of the tunnel face in the past tunnel excavation construction. If the geological type of the current working face is an unfavorable geological body, determine the second location information of the current working face; Based on the difference between the second and first position information, the advanced detection wave velocity parameters are corrected. The modified advanced detection wave velocity parameters were used to detect unfavorable geological bodies ahead of the tunnel face; Specifically, the advanced detection wave velocity parameters are corrected based on the difference between the second and first position information, including: Based on the difference between the second position information and the first position information, the position deviation value Δx is determined; Using the time difference Δt between the vibration signal emitted by the seismic source transmitter and the reflected wave received by the detector, and the position deviation value Δx, the advanced detection wave velocity parameters are corrected as follows: v=2Δx / Δt Where v is the corrected advanced detection wave velocity parameter.

2. The method as described in claim 1, characterized in that, The initial location information of adverse geological bodies ahead of the tunnel face is determined by the advanced detection method, including: Geological exploration data in front of the tunnel face is obtained by a geophone. The geophone is deployed in front of the tunnel face to receive the reflection wave of the vibration signal emitted by the seismic source transmitter into the strata in front of the tunnel face in the adverse geological body. Based on geological survey data, the primary location information of the unfavorable geological body in front of the tunnel face was determined.

3. The method as described in claim 1, characterized in that, The adverse geological body identification model uses the K-nearest neighbor algorithm.

4. The method as described in claim 3, characterized in that, The adverse geological body identification model was trained in the following manner: Collecting historical data: multiple construction parameters of tunnel boring machines and geological types of the tunnel face during tunnel excavation; For historical data, multiple construction parameters of the tunnel boring machine and geological types of the tunnel face during tunnel excavation are tagged to form training samples; the tagging process includes tagging according to different geological types. Using training samples, a machine model employing the K-nearest neighbor algorithm is trained to obtain an adverse geological body identification model.

5. The method as described in claim 1, characterized in that, The advanced detection methods include: seismic wave method.

6. A device for correcting wave velocity parameters in advance detection of TBM tunnels, characterized in that, Applied to tunnel excavation construction, including: The advanced detection and prediction module is used to determine the first location information of adverse geological bodies in front of the tunnel face through advanced detection methods; The tunnel boring machine (TBM) construction parameter acquisition module is used to acquire multiple construction parameters of the TBM during tunnel excavation in real time. These construction parameters reflect the geological conditions of the tunnel face. The tunnel boring machine (TBM) construction parameter prediction module is used to input multiple construction parameters of the TBM into a pre-established adverse geological body identification model and output the geological type of the current tunnel face. The geological type includes adverse geological bodies and non-adverse geological bodies. The adverse geological body identification model is obtained by training a machine learning model using multiple construction parameters of the TBM and geological types of the tunnel face in historical tunnel excavation construction. The wave velocity parameter correction module is used to determine the second location information of the current working face if the geological type of the current working face is an unfavorable geological body; and to correct the advanced detection wave velocity parameters based on the difference between the second location information and the first location information. The advanced detection and prediction module is also used to detect adverse geological bodies in front of the tunnel face using the corrected advanced detection wave velocity parameters; The wave velocity parameter correction module is specifically used for: Based on the difference between the second position information and the first position information, the position deviation value Δx is determined; Using the time difference Δt between the vibration signal emitted by the seismic source transmitter and the reflected wave received by the detector, and the position deviation value Δx, the advanced detection wave velocity parameters are corrected as follows: v=2Δx / Δt Where v is the corrected advanced detection wave velocity parameter.

7. The apparatus as claimed in claim 6, characterized in that, The advanced detection and prediction module is specifically used for: Geological exploration data in front of the tunnel face is obtained by a geophone. The geophone is deployed in front of the tunnel face to receive the reflection wave of the vibration signal emitted by the seismic source transmitter into the strata in front of the tunnel face in the adverse geological body. Based on geological survey data, the primary location information of the unfavorable geological body in front of the tunnel face was determined.

8. The apparatus as claimed in claim 6, characterized in that, The adverse geological body identification model uses the K-nearest neighbor algorithm.

9. The apparatus as claimed in claim 8, characterized in that, The adverse geological body identification model was trained in the following manner: Collecting historical data: multiple construction parameters of tunnel boring machines and geological types of the tunnel face during tunnel excavation; For historical data, multiple construction parameters of the tunnel boring machine and geological types of the tunnel face during tunnel excavation are tagged to form training samples; the tagging process includes tagging according to different geological types. Using training samples, a machine model employing the K-nearest neighbor algorithm is trained to obtain an adverse geological body identification model.

10. The apparatus as claimed in claim 6, characterized in that, The advanced detection methods include: seismic wave method.

11. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 5.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1 to 5.

13. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 5.

Images