Tunnel boring machine spatial dynamic compensation seismic wave advanced detection method and system

Abstract

The application discloses a tunnel boring machine space dynamic compensation seismic wave advanced detection method and system, comprising: receiving the reflection echo data of the current space position; compensating the reflection echo data according to the attenuation compensation factor of the current space position, wherein the attenuation compensation factor of the current space position is obtained by a trained neural network, and the prediction process comprises: after curve fitting of the attenuation compensation factor of the reflection echo data of the detected space position, the attenuation compensation factor of the next space position is predicted by using the trained neural network; the compensated reflection echo data is subjected to geological body imaging by using the equal travel time imaging method, and the geological body detection result is obtained according to the amplitude difference on the imaging profile. The space dynamic compensation algorithm of the mechanical wave attenuation is used to adaptively correct the attenuation compensation factor at the next tunneling surface, so as to compensate the received reflection echo data and enhance the identification ability of the reflection echo.

Description

Technical Field

[0001] This invention relates to the field of advanced geological prediction technology, and in particular to a method and system for advanced seismic wave detection using spatial dynamic compensation for tunnel boring machines. Background Technology

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

[0003] Early tunnel advance detection methods mainly included horizontal advance drilling and pilot tunnels. These methods were slow, required frequent operation, had short detection distances, and the results only reflected the geological conditions of a small area, unable to assess the entire space. Furthermore, these methods interfered with the tunnel boring machine's operation, failing to meet the requirements of rapid tunneling. In the development of advance detection methods, various methods gradually emerged, such as seismic wave methods, ground-penetrating radar, and induced polarization methods. However, the limited tunnel space and the constant close contact between the cutterhead and the tunnel face would affect the normal operation of the tunnel boring machine.

[0004] In addition, since the underground medium is not a perfectly elastic medium, even after compensation for attenuation caused by factors such as transmission loss and geometric diffusion, the energy in the middle and deep layers of the seismic profile is still weaker than that in the shallow layer. In other words, energy loss will occur during wave propagation.

[0005] Meanwhile, due to noise interference during tunneling machine construction, the attenuation compensation factor of the reflected echo data received by the advance detection changes with the spatial location of the detection. The attenuation compensation factor of the reflected echo data obtained from advance detection at a single spatial location is prone to large errors due to noise interference. If a single attenuation compensation factor is used to compensate for the reflected echo data received by advance detection at different spatial locations, the detection results will inevitably have large errors, resulting in inaccurate imaging. Summary of the Invention

[0006] To address the aforementioned issues, this invention proposes a spatial dynamic compensation method and system for seismic wave advance detection in tunnel boring machines. It employs a spatial dynamic compensation algorithm for mechanical wave attenuation to adaptively correct the attenuation compensation factor at the next tunnel face, thereby compensating for the received reflected echo data, enhancing the identification capability of the reflected echo, and laying the foundation for further accurate imaging.

[0007] To achieve the above objectives, the present invention adopts the following technical solution:

[0008] In a first aspect, the present invention provides a method for advance seismic wave detection with spatial dynamic compensation for tunnel boring machines, comprising:

[0009] Receive reflected echo data from the current spatial location;

[0010] The attenuation compensation factor for the current spatial location is used to compensate the reflected echo data. The attenuation compensation factor for the current spatial location is predicted by a trained neural network. The prediction process includes: after curve fitting of the attenuation compensation factor of the reflected echo data of the detected spatial location, the trained neural network is used to predict the attenuation compensation factor for the next spatial location.

[0011] The geological bodies were imaged using the isochronous travel time imaging method on the compensated reflected echo data. Based on the amplitude differences on the imaging profile, the geological body detection results were obtained.

[0012] As an alternative implementation, an array of sensors is used to emit seismic waves and receive reflected echo data from in front of the tunnel face, with the sensors emitting seismic waves and receiving reflected echo data being different sensors.

[0013] As an alternative implementation, attenuation compensation factors for different spatial locations are obtained based on the reflected echo amplitude values ​​received by the sensor, the reflected echo amplitude values ​​received by adjacent sensors, and the distance between adjacent sensors, thereby training the neural network.

[0014] As an alternative implementation, spatial compensation is performed on the reflected echo data at the current spatial location by taking the reciprocal of the predicted attenuation compensation factor.

[0015] As an alternative implementation, the compensated reflected echo data is spatially superimposed based on the differences in travel time. If the superimposed imaging amplitude is greater than a set threshold, it is an abnormal geological body; if the superimposed imaging amplitude is less than the set threshold, there is no abnormality.

[0016] In a second aspect, the present invention provides a seismic wave advance detection system for spatial dynamic compensation of tunnel boring machines, comprising: a mechanical wave transmitting and receiving device and a main control system;

[0017] The mechanical wave transmitting and receiving device is mounted on the cutterhead of the tunneling machine and is used to transmit seismic waves and receive reflected echo data reflected from in front of the tunnel face.

[0018] The main control system receives reflected echo data from the current spatial location, compensates the reflected echo data according to the attenuation compensation factor of the current spatial location, and uses the equal travel time imaging method to image the geological body on the compensated reflected echo data. The geological body detection results are obtained based on the amplitude differences on the imaging profile.

[0019] The attenuation compensation factor of the current spatial location is predicted by a trained neural network. The prediction process includes: after curve fitting of the attenuation compensation factor of the reflected echo data of the detected spatial location, the trained neural network is used to predict the attenuation compensation factor of the next spatial location.

[0020] As an alternative implementation, the mechanical wave transmitting and receiving device includes a metal protective shell and mechanical wave transmitting and receiving sensors disposed within the metal protective shell, arranged in an array, wherein the sensor transmitting seismic waves and the sensor receiving reflected echo data are different sensors.

[0021] As an alternative implementation, a pressure sensor is also provided inside the metal protective shell. The pressure sensor is attached to the inner side of the metal protective shell and is used to detect the contact stress between the front end of the metal protective shell and the working face.

[0022] As an alternative implementation, the height of the metal protective shell is level with the outermost edge of the tunneling machine cutterhead.

[0023] As an alternative implementation, the mechanical wave transmitting and receiving devices are installed on the cutterhead of the tunneling machine at equal intervals and in the form of a two-dimensional array.

[0024] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0025] This invention proposes a seismic wave advance detection method with spatial dynamic compensation for tunnel boring machines. By sparsely transmitting and receiving sensors, redundancy in the observation data is eliminated, effectively reducing the amount of data storage and improving the efficiency of transmission and post-processing.

[0026] This invention proposes a spatial dynamic compensation method for seismic wave advance detection using tunnel boring machines. It employs a spatial dynamic compensation algorithm for mechanical wave attenuation to adaptively correct the attenuation compensation factor at the next tunnel face, thereby compensating for the received reflected echo data. This improves the speed and stability of attenuation factor calculation, enhances the identification capability of reflected echoes, and lays the foundation for further accurate imaging.

[0027] This invention proposes a seismic wave advance detection method with spatial dynamic compensation for tunnel boring machines. Based on obtaining the step dynamic attenuation compensation of the tunnel boring machine, it achieves accurate imaging with equal travel time, improves the resolution of anomalous geological bodies, and reduces false anomaly imaging caused by noise and other interference factors.

[0028] This invention proposes a spatial dynamic compensation seismic wave advance detection system for tunnel boring machines (TBMs), which integrates the TBM with mechanical wave detection instruments. It features high automation, high efficiency, and high detection resolution, without interfering with the TBM's construction, thus meeting the safety and efficiency requirements of the TBM.

[0029] Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0030] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0031] Figure 1 This is a flowchart of the seismic wave advance detection method for spatial dynamic compensation of tunnel boring machines provided in Embodiment 1 of the present invention;

[0032] Figure 2 This is a schematic diagram of the seismic wave advance detection system for spatial dynamic compensation of tunnel boring machines provided in Embodiment 2 of the present invention;

[0033] Figure 3 This is a schematic diagram of the seismic wave advance detection system for spatial dynamic compensation of tunnel boring machines provided in Embodiment 2 of the present invention;

[0034] The components include: 1. Tunneling machine cutterhead; 2. Mechanical wave transmitting and receiving device; 3. Tunneling machine trolley; 4. Metal protective shell; 5. Mechanical wave transmitting and receiving sensor; 6. Pressure sensor; 7. Seismic wave probe group; 8. Sealing oil; 9. Flat rod; 10. Data transmission cable; and 11. Bolts. Detailed Implementation

[0035] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0036] It should be noted that the following detailed descriptions are exemplary and intended to provide further illustration of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0037] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments of the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. Furthermore, it should be understood that the terms “comprising” and “having”, and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0038] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0039] Example 1

[0040] like Figure 1 As shown, this embodiment provides a seismic wave advance detection method with spatial dynamic compensation for tunnel boring machines, including:

[0041] Receive reflected echo data from the current spatial location;

[0042] The attenuation compensation factor for the current spatial location is used to compensate the reflected echo data. The attenuation compensation factor for the current spatial location is predicted by a trained neural network. The prediction process includes: after curve fitting of the attenuation compensation factor of the reflected echo data of the detected spatial location, the trained neural network is used to predict the attenuation compensation factor for the next spatial location.

[0043] The geological bodies were imaged using the isochronous travel time imaging method on the compensated reflected echo data. Based on the amplitude differences on the imaging profile, the geological body detection results were obtained.

[0044] In this embodiment, several mechanical wave transmitting and receiving sensors are set up. By changing the excitation time of each sensor, a directional beam can be emitted. This beam has strong energy, strong penetration, and high resolution. Simultaneously, the observation method is optimized by proposing a sparse transmitting and receiving sensor observation method. This method can effectively reduce data storage, improve transmission efficiency, and enhance data post-processing efficiency.

[0045] This embodiment employs 169 mechanical wave transmitting and receiving sensors. Following a full-matrix data acquisition observation method, each sensor is excited individually, and all sensors receive reflected echoes. This process is repeated for all 169 sensors, resulting in 28,561 sets of reflected echo data. The more mechanical wave transmitting and receiving sensors there are, the more reflected echoes are received. Considering the dissimilarity of sensor transmission and reception, the reflected echo data received by sensor Y after a seismic wave is excited by sensor X is consistent with the reflected echo data received by sensor X after a seismic wave is excited by sensor Y.

[0046] For example, the following formula:

[0047]

[0048] The reflected echo data (1, 1, 13, 13) transmitted by the sensor in row 1, column 1 and received by the sensor in row 13, column 13 is consistent with the reflected echo data (13, 13, 1, 1) transmitted by the sensor in row 13, column 13 and received by the sensor in row 1, column 1. Therefore, the reflected echo data obtained using the above observation method has redundancy.

[0049] In order to eliminate redundancy and reduce the number of reflected echo data, this embodiment proposes a sparse transmission and reception sensor observation method. Considering that the transmission and reception of the sensors are mutually exclusive, only sensor X needs to transmit seismic waves and sensor Y needs to receive reflected echo data during observation, which effectively improves the efficiency of data transmission and post-processing.

[0050] Because seismic wave signals exhibit strong attenuation characteristics under shield tunneling conditions, specifically manifested as reduced amplitude and phase misalignment in the reflected echoes. Furthermore, due to noise interference during tunneling, the attenuation compensation factor of the reflected echo data received by advance detection changes with the spatial location of the detection. The attenuation compensation factor of reflected echo data obtained from advance detection at a single spatial location is prone to significant errors due to noise interference. Therefore, it is necessary to reduce these errors and determine an accurate attenuation compensation factor for compensation.

[0051] Therefore, this embodiment proposes a spatial dynamic compensation algorithm for seismic wave attenuation. It records the lithological information of the tunnel boring machine during excavation, and adaptively corrects the attenuation compensation factor at the next excavation face based on the spatial changes in lithological attenuation characteristics. On this basis, it performs dynamic compensation of the reflected echo signal to obtain a more accurate reflection position and a higher anomaly resolution.

[0052] In this embodiment, attenuation compensation factors are fitted to the reflected echo data from multiple detected spatial locations. A Long-Short-Term Memory (LSTM) artificial neural network is used to predict the attenuation compensation factor for the reflected echo data from the next spatial location being tunneled by the tunnel boring machine. This allows for dynamic spatial compensation of the lithological attenuation characteristics ahead of the tunnel boring machine. When the tunnel boring machine reaches this spatial location, a forward detection is performed, and the predicted attenuation compensation factor is used to compensate for the reflected echo data, enhancing the identification capability of the reflected echo data and improving imaging resolution. Compared to the traditional method of using a single attenuation compensation factor to compensate for reflected echo data received from forward detection at different spatial locations, the method in this embodiment can dynamically predict the attenuation compensation factor for the next spatial location based on the differences in spatial location, thereby achieving dynamic compensation, reducing errors, and improving imaging resolution.

[0053] In this embodiment, the formula for calculating the attenuation compensation factor β is as follows:

[0054]

[0055] Where x is the distance between adjacent sensors, A1 is the amplitude value of the reflected echo received by the mechanical wave transmitting and receiving sensor, and A2 is the amplitude value of the reflected echo received by the adjacent mechanical wave transmitting and receiving sensor.

[0056] In this embodiment, 13*13 mechanical wave transmitting and receiving sensors are used. The anomalous geological body is blocky and located in the normal direction of the tunnel face. The initial spatial position of the tunneling machine is set at 10 meters from the anomalous body to conduct a preliminary detection. The mechanical wave transmitting and receiving sensors in the 7th row and 7th column are controlled to excite seismic waves, and 169 mechanical wave transmitting and receiving sensors receive them simultaneously, obtaining a total of 169 sets of reflected echo data.

[0057] The amplitude value of the direct wave received by the mechanical wave transmitting and receiving sensor in the i-th row and j-th column, and the amplitude value received by the mechanical wave transmitting and receiving sensor in the i-th row and (j-1)-th column adjacent to it, are respectively taken as A1 and A2, where the values ​​of i and j are in the range of 1≤i≤85, 2≤i≤85, i,j∈N. The distance between adjacent sensors is taken as the propagation distance x. The attenuation compensation factor of the seismic wave at this location can be solved by this method, and 7140 attenuation compensation factors can be obtained. Since the range of spacing variation is small, the average value is taken as the attenuation compensation factor at this spatial location.

[0058] The tunneling machine advances 1 meter each time, and the above steps are repeated to solve for the attenuation compensation factor at the corresponding spatial location, resulting in a total of 10 attenuation compensation factors at spatial locations.

[0059] LSTM is used to predict the attenuation compensation factor at the next spatial location.

[0060] LSTM mainly consists of three stages, as follows:

[0061] The first stage is the input stage, which inputs attenuation compensation factors at multiple spatial locations into the LSTM; the second stage is the forgetting stage, which mainly selectively forgets the input data, forgetting unimportant information and retaining important information; the third stage is the output stage, which mainly controls the number of output values ​​from the previous state to the current output value of the LSTM.

[0062] The attenuation compensation factor obtained by using the LSTM network at the next spatial location has a small error and is used to compensate for the reflected echo data at the next spatial location. Based on this, the spatial location and scale of the anomalous geological body are obtained by using the isochronous imaging method with spatial dynamic attenuation compensation.

[0063] In this embodiment, after taking the reciprocal of the predicted attenuation compensation factor, spatial compensation is performed on the reflected echo data of the current spatial location. Then, according to the isochronous travel time imaging method, the attenuated reflected echo data is spatially superimposed based on the difference in travel time to perform geological body imaging.

[0064] Based on the amplitude differences on the imaging profile, the geological body detection results are obtained. Specifically, when there is a reflection point at the spatial location, the received reflected echo data has temporal consistency. After superposition, the imaging amplitude is large. If it exceeds the set threshold, it is considered an abnormal geological body. If there is no reflection point, the reflected echo time is different. After superposition, the amplitude is less than the set threshold, or even non-existent, so the medium is not abnormal.

[0065] Example 2

[0066] like Figure 2-3 As shown, this embodiment provides a seismic wave advance detection system with spatial dynamic compensation for tunnel boring machines, including: a mechanical wave transmitting and receiving device and a main control system connected by a data transmission cable;

[0067] The mechanical wave transmitting and receiving device is mounted on the cutterhead of the tunneling machine and is used to transmit seismic waves and receive reflected echo data reflected from in front of the tunnel face.

[0068] The main control system receives reflected echo data from the current spatial location, compensates the reflected echo data according to the attenuation compensation factor of the current spatial location, and uses the isochronous travel time imaging method to image the geological body from the compensated reflected echo data. Based on the amplitude difference on the imaging profile, the geological body detection result is obtained.

[0069] The attenuation compensation factor for the current spatial location is predicted by a trained neural network. The prediction process includes: after curve fitting of the attenuation compensation factor of the reflected echo data of the detected spatial location, the trained neural network is used to predict the attenuation compensation factor for the next spatial location.

[0070] In this embodiment, the mechanical wave transmitting and receiving device 2 is installed on the cutterhead 1 of the tunneling machine and includes a seismic wave probe group 7. The seismic wave probe group 7 includes multiple mechanical wave transmitting and receiving sensors 5. Each mechanical wave transmitting and receiving sensor 5 has the function of independently transmitting seismic waves and receiving reflected echoes. Under the control of the main control system, it realizes directional focusing mechanical wave transmission.

[0071] In this embodiment, the mechanical wave transmitting and receiving device 2 includes a metal protective shell 4, and inside the metal protective shell are a seismic wave probe group 7 composed of multiple mechanical wave transmitting and receiving sensors 5 and a pressure sensor 6.

[0072] As an alternative implementation, the surface of the metal protective shell 4 is a smooth curved surface without sharp edges. This is to avoid the sharp edges colliding and rubbing with the soil, gravel, or working face generated during the tunneling process, which could cause damage to the device.

[0073] As an alternative implementation, the metal protective shell 4 is filled with sealing oil 8.

[0074] As an alternative implementation, multiple mechanical wave transmitting and receiving sensors 5 are installed on the inner front end of the metal protective shell 4, which can be used to detect whether the wear of the metal protective shell has reached the point where it needs to be replaced.

[0075] As an alternative implementation, a pressure sensor 6 is installed inside the metal protective shell 4. The pressure sensor 6 is tightly fitted to the inner side of the metal protective shell 4 and is used to measure the contact stress between the front end of the metal protective shell and the working face to detect whether the mechanical wave transmitting and receiving device and the working face are in good contact.

[0076] Furthermore, the seismic wave probe group 7 and the pressure sensor 6 are connected to the main control system via the data transmission cable 10.

[0077] As an alternative implementation method, the metal protective case is made of a metal with high wear resistance to extend the service life of the protective case.

[0078] Furthermore, the metal protective shell is made of high-manganese steel, which can withstand severe impact loads or contact stresses and has strong wear resistance.

[0079] As an alternative implementation, the metal protective shell is connected to the cutterhead of the tunneling machine by bolts 11. The height of the metal protective shell is level with the outermost edge of the cutterhead, ensuring good contact between the metal protective shell and the tunnel face, and facilitating the disassembly and replacement of the device.

[0080] As an alternative implementation, the mechanical wave transmitting and receiving devices are installed on the cutterhead of the tunneling machine at equal intervals and in the form of a two-dimensional array, without changing the original position of the cutterhead and making full use of the cutterhead space.

[0081] As an alternative implementation, the flat end of the metal protective shell is welded to two outwardly extending flat rods (9 pieces), and adjacent flat rods are connected by bolts. The metal protective shell, the cutter head, and the flat rods are all connected by bolts.

[0082] In this embodiment, the detection method of the seismic wave advance detection system with spatial dynamic compensation for tunnel boring machines includes:

[0083] Step 1) The tunneling machine stops the tunneling process and checks whether the metal protective shell is in good contact with the working face. The contact stress between the metal protective shell and the working face is measured using a pressure sensor. When the contact stress reaches the preset value, it is considered that the two are in good contact and observation work can be carried out.

[0084] Step 2): Based on the established observation system, the main control system controls whether each seismic wave probe group excites seismic waves, the excitation time, and whether to receive reflected echoes. After the observation is completed, the reflected echo data is transmitted to the main control system via a data transmission cable for post-processing imaging.

[0085] Step 3): The main control system sequentially activates the mechanical wave transmitting and receiving sensors inside the metal protective shell. Using a self-excitation and self-reception observation method, the thickness of the metal protective shell at each location is calculated from the received reflected echo data. The minimum thickness of the metal protective shell at all sensing locations is taken. If this value is less than the set minimum thickness, the metal protective shell is considered excessively worn and needs to be replaced. This step is performed once a week.

[0086] Step 4): After the observation is completed, no other operations are required, and the tunneling machine can continue the tunneling process.

[0087] In this embodiment, the mechanical wave transmitting and receiving device is mounted on the cutterhead of the tunnel boring machine. During advance detection, the front end of the metal protective shell is tightly fitted to the tunnel face. The probe group emits seismic waves and receives reflected wave signals carrying geological information from in front of the tunnel face. This solves the problems of low resolution in tunnel advance geological prediction imaging, severe seismic wave energy attenuation, and low automation, improves data transmission and post-processing efficiency, and meets the requirements of safe, fast, and efficient construction of tunnel boring machines.

[0088] While the specific embodiments of the present invention have been described above in conjunction with the accompanying drawings, this 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 without creative effort based on the technical solutions of the present invention are still within the scope of protection of the present invention.

Claims

1. A seismic wave advance detection method with spatial dynamic compensation for tunnel boring machines, characterized in that, include: Receive reflected echo data from the current spatial location; The attenuation compensation factor for the current spatial location is used to compensate the reflected echo data. The attenuation compensation factor for the current spatial location is predicted by a trained neural network. The prediction process includes: after curve fitting of the attenuation compensation factor of the reflected echo data of the detected spatial location, the trained neural network is used to predict the attenuation compensation factor for the next spatial location. Attenuation compensation factor The calculation formula is as follows: in, The distance between adjacent sensors. This refers to the amplitude value of the reflected echo received by the mechanical wave transmitting and receiving sensor. The amplitude value of the reflected echo received by the adjacent mechanical wave transmitting and receiving sensors; The attenuation compensation factor for different spatial locations is obtained based on the reflected echo amplitude value received by the sensor, the reflected echo amplitude value received by the adjacent sensor, and the distance between the adjacent sensors, and the neural network is trained accordingly. After taking the reciprocal of the predicted attenuation compensation factor, spatial compensation is performed on the reflected echo data at the current spatial location. The geological body is then imaged using the isochronous travel time imaging method based on the amplitude differences on the imaging profile. The geological body detection results are obtained based on these amplitude differences.

2. The seismic wave advance detection method with spatial dynamic compensation for tunnel boring machines as described in claim 1, characterized in that, The array of sensors emits seismic waves and receives reflected echo data from in front of the tunnel face. The sensors that emit seismic waves and the sensors that receive reflected echo data are different.

3. The seismic wave advance detection method for spatial dynamic compensation of tunnel boring machines as described in claim 1, characterized in that, The compensated reflected echo data are spatially superimposed based on the differences in travel time. If the superimposed imaging amplitude is greater than a set threshold, it is an abnormal geological body; if the superimposed imaging amplitude is less than the set threshold, there is no abnormality.

4. A seismic wave advance detection system with spatial dynamic compensation for tunnel boring machines, employing the seismic wave advance detection method with spatial dynamic compensation for tunnel boring machines as described in claim 1, characterized in that... include: Mechanical wave transmitting and receiving device and main control system; The mechanical wave transmitting and receiving device is mounted on the cutterhead of the tunneling machine and is used to transmit seismic waves and receive reflected echo data reflected from in front of the tunnel face; the mechanical wave transmitting and receiving device is installed on the cutterhead of the tunneling machine at equal intervals and in the form of a two-dimensional array. The main control system receives reflected echo data from the current spatial location, compensates the reflected echo data according to the attenuation compensation factor of the current spatial location, and uses the equal travel time imaging method to image the geological body on the compensated reflected echo data. The geological body detection results are obtained based on the amplitude differences on the imaging profile. The attenuation compensation factor of the current spatial location is predicted by a trained neural network. The prediction process includes: after curve fitting of the attenuation compensation factor of the reflected echo data of the detected spatial location, the trained neural network is used to predict the attenuation compensation factor of the next spatial location.

5. The seismic wave advance detection system with spatial dynamic compensation for tunnel boring machines as described in claim 4, characterized in that, The mechanical wave transmitting and receiving device includes a metal protective shell and mechanical wave transmitting and receiving sensors installed inside the metal protective shell. The sensors are arranged in an array, and the sensors that transmit seismic waves and the sensors that receive reflected echo data are different sensors.

6. The seismic wave advance detection system with spatial dynamic compensation for tunnel boring machines as described in claim 5, characterized in that, The metal protective shell is also equipped with a pressure sensor, which is attached to the inner side of the metal protective shell and is used to detect the contact stress between the front end of the metal protective shell and the working face.

7. The seismic wave advance detection system with spatial dynamic compensation for tunnel boring machines as described in claim 5, characterized in that, The height of the metal protective shell is level with the outermost edge of the tunneling machine cutterhead.

Images