A Method and System for In-situ Volume Inversion of Shield Tunnel Excavated Soil Based on Multiphase Material Equilibrium

Abstract

This invention relates to the field of underground engineering construction monitoring technology, and provides a method and system for in-situ volume inversion of shield tunnel excavated soil based on multiphase material balance. The method includes: acquiring three-dimensional point cloud data of the excavated soil surface and the conveyor belt speed; for each moment, projecting the three-dimensional point cloud data onto a direction perpendicular to the conveyor belt reference plane, and calculating the effective area of ​​the cross-section using the polygon area formula; within the time period of one tunneling ring, calculating the integral of the product of the effective area of ​​the cross-section and the conveyor belt speed at each moment to obtain the cumulative loose volume; and using a multiphase material balance correction model, inverting the cumulative loose volume into the in-situ soil volume. This eliminates the influence of soil conditioner and accurately inverts the true in-situ soil volume.

Description

Technical Field

[0001] This invention belongs to the field of underground engineering construction monitoring technology, and in particular relates to a method and system for in-situ volume inversion of shield tunnel excavation soil based on multiphase material balance. 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] In shield tunnel construction, accurate measurement of excavated soil is a core aspect of ensuring construction safety. Existing measurement methods mainly suffer from two types of problems: Limited measurement accuracy: Traditional monocular laser scanners are easily affected by belt vibration, dust interference, and obstruction by slag accumulation, resulting in distorted measurement data; Lack of physical model: Most existing technologies directly measure the volume of loose excavated soil on the conveyor belt, ignoring the large amount of foam, water, bentonite and other modifiers injected during the shield tunneling process, as well as the loosening effect after the soil is broken. The excavated soil on the conveyor belt is actually a three-phase mixture of "soil + water + air". Directly using this volume to judge over-excavation and under-excavation will produce huge errors. Summary of the Invention

[0004] To address the technical problems mentioned above, this invention provides a method and system for in-situ volume inversion of shield tunnel slag based on multiphase material balance. It calculates the loose volume using high-precision point clouds, combined with a rigorous geometric optical model and integral algorithm. Furthermore, it introduces a multiphase material balance correction model to eliminate the influence of amendments and accurately invert the real in-situ soil volume.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: The first aspect of the present invention provides a method for in-situ volume inversion of shield tunnel excavation soil based on multiphase material equilibrium, comprising: Acquire 3D point cloud data of the slag surface and conveyor belt speed; For each moment, the three-dimensional point cloud data is projected onto a direction perpendicular to the belt reference plane, and the effective area of ​​the cross section is calculated using the polygon area formula. During the time period of tunneling one ring, the integral of the product of the effective cross-sectional area and the belt running speed at each moment is calculated to obtain the cumulative loose volume. The cumulative loose volume is then converted into the in-situ soil volume using a multiphase material balance correction model.

[0006] Furthermore, the method for acquiring the three-dimensional point cloud data of the soil surface is as follows: a line laser emitter and two parallel cameras are set above the belt conveyor of the tunnel boring machine. The line laser emitter projects blue light onto the surface of the slag, with the laser line projection direction perpendicular to the belt running direction. The two cameras synchronously acquire images. After converting the images from camera image pixel coordinates to world coordinates, stereo matching verification is performed to obtain the three-dimensional point cloud data of the slag surface.

[0007] Furthermore, when the injection amount is available, the multiphase material balance correction model is: ; in, This represents the in-situ soil volume obtained through inversion. For the cumulative loose volume; This represents the cumulative volume of water injected into the current ring. The cumulative volume of bentonite slurry injected into the current ring; residual foam volume. ; The residual foam coefficient is a function of the soil chamber pressure P and the foam duration t. This indicates the cumulative foam injection volume of the current tunneling ring; This is the soil loosening coefficient.

[0008] Furthermore, when the injection volume cannot be obtained, the multiphase material balance correction model is as follows: ; in, This represents the in-situ soil volume obtained through inversion. For the cumulative loose volume; To determine the dynamic volume correction factor value using the table lookup method.

[0009] Furthermore, the injection volume includes the cumulative injected water volume, bentonite slurry volume, and foam injection volume.

[0010] Furthermore, after preprocessing the three-dimensional point cloud data of the slag surface, the three-dimensional point cloud data is projected onto a direction perpendicular to the belt reference plane. The preprocessing includes noise filtering based on reflection intensity and vibration compensation based on belt edge characteristics.

[0011] Furthermore, it also includes: calculating the deviation rate between the in-situ soil volume and the theoretical excavation volume, and triggering a graded over-excavation and under-excavation warning when the deviation rate exceeds a preset threshold.

[0012] A second aspect of the present invention provides an in-situ volume inversion system for shield tunneling excavated soil based on multiphase material equilibrium, comprising: The data acquisition module is configured to acquire three-dimensional point cloud data of the slag surface and the conveyor belt speed. The area calculation module is configured to: at each time step, project the three-dimensional point cloud data onto a direction perpendicular to the belt reference plane and calculate the effective area of ​​the cross section using the polygon area formula; The volume calculation module is configured to: calculate the integral of the product of the effective cross-sectional area and the belt running speed at each moment during the time period of tunneling one ring, obtain the cumulative loose volume, and invert the cumulative loose volume into the in-situ soil volume through the multiphase material balance correction model.

[0013] A third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the above-described method for in-situ volume inversion of shield tunnel slag based on multiphase material equilibrium.

[0014] A fourth aspect of the present invention provides a computer device including a computer-readable storage medium, a processor, and a computer program stored on the computer-readable storage medium and executable on the processor, wherein the processor executes the program to implement the steps in the above-described method for in-situ volume inversion of shield tunnel slag based on multiphase material equilibrium.

[0015] Compared with the prior art, the beneficial effects of the present invention are: This invention calculates loose volume based on high-precision point cloud, combined with a rigorous geometric optical model and integral algorithm, and further introduces a multiphase material balance correction model to eliminate the influence of amendments and accurately invert the real in-situ soil volume.

[0016] The invention's left camera can capture the area obscured on the left side of the slag heap, while the right camera can capture the blind spot on the right side. The fields of view of the two cameras overlap in the central area of ​​the conveyor belt, forming a "binocular complementary area," which effectively solves the visual shadow problem existing in monocular cameras. Attached Figure Description

[0017] 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.

[0018] Figure 1 This is a flowchart of the shield tunneling slag insitu volume inversion method based on multiphase material balance in Embodiment 1 of the present invention. Figure 2 This is a schematic diagram of the structure of a computer device according to Embodiment 4 of the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings.

[0020] It should be noted that the following detailed description is illustrative and intended to provide further explanation 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.

[0021] Example 1 This embodiment provides a method for in-situ volume inversion of shield tunnel slag based on multiphase material balance.

[0022] The in-situ volume inversion method for shield tunneling excavation based on multiphase material balance provided in this embodiment utilizes active vision binocular laser technology to collect point clouds and dynamically corrects them in conjunction with shield tunneling construction parameters to achieve excavation volume inversion and early warning.

[0023] The in-situ volume inversion method for shield tunneling slag based on multiphase material balance provided in this embodiment uses a binocular laser 3D camera based on active vision to acquire high-precision point clouds of slag on the conveyor belt, and calculates the loose volume through a geometric optical model and the infinitesimal integral method; at the same time, it combines a noise reduction algorithm based on reflection intensity and a conveyor belt edge locking algorithm to eliminate environmental interference.

[0024] The shield tunneling excavation soil in-situ volume inversion method based on multiphase material balance provided in this embodiment constructs a multiphase material balance correction model, comprehensively considers the injection volume of foam, water, bentonite and the loosening coefficient of the stratum, calculates the dynamic volume correction coefficient, inverts the measured loose volume into the in-situ soil volume, and compares it with the theoretical excavation volume to realize over-excavation and under-excavation early warning.

[0025] The in-situ volume inversion method for shield tunneling excavation based on multiphase material balance provided in this embodiment solves the measurement error problems caused by neglecting the volume of the amendment and belt vibration in the existing technology, and improves the safety of shield tunneling construction.

[0026] The in-situ volume inversion method for shield tunneling spoil based on multiphase material balance provided in this embodiment is as follows: Figure 1 As shown, it includes the following steps: Step S1: Data Acquisition and Synchronization. Based on the active vision binocular laser triangulation principle, a non-contact shield tunneling excavation real-time monitoring system is constructed. A binocular laser 3D camera projects laser lines onto the excavation surface on the belt conveyor and simultaneously acquires images of laser line deformation. An incremental photoelectric encoder (1024 P / R resolution) is installed at the driven wheel axle of the belt conveyor to acquire the belt running speed in real time, achieving microsecond-level synchronization between point cloud data and belt displacement. The current ring injection volume, including the cumulative injected water volume, is obtained in real time through the shield machine PLC interface. Bentonite slurry volume and foam injection volume .

[0027] Specifically, the non-contact shield tunneling muck real-time monitoring system mainly includes a monitoring unit installed above the shield tunneling machine's belt conveyor and a data processing unit located in the main control room.

[0028] Specifically, the monitoring unit is installed on a gantry support above the No. 1 belt conveyor of the tunnel boring machine (about 3-5 meters behind the auger excavator outlet). The slag at this location has been initially stabilized and avoids the gushing area of ​​the auger excavator outlet.

[0029] Specifically, the monitoring unit is a binocular line laser 3D camera, which integrates a line laser emitter and two parallel high-resolution global exposure CMOS cameras with an interpupillary distance of 320mm. The line laser emitter emits blue light with a wavelength of 450nm or infrared light with a wavelength of 850nm / 940nm. The camera has a maximum frame rate of 3000 lines / second and a maximum single-line point cloud density of 2048 points. The camera is installed at a height of approximately 1200mm from the surface of the belt, and the laser line projection direction is perpendicular to the belt running direction.

[0030] Specifically, the binocular complementary field of view: The camera integrates two CMOS cameras with an interpupillary distance of 320mm. The left camera's field of view covers the left and middle areas of the belt, while the right camera's field of view covers the right and middle areas of the belt. When a tall pile of slag is piled up on the belt, the left camera can capture the area on the left side of the slag pile that is blocked, while the right camera can capture the blind spot on the right side. The fields of view of the two cameras overlap in the central area of ​​the belt, forming a "binocular complementary area," which effectively solves the visual shadow problem of monocular cameras.

[0031] Specifically, after startup, the line laser emitter projects blue light with a wavelength of 450nm onto the surface of the slag; dual cameras simultaneously acquire images, and 3D matching is performed through FPGA hardware acceleration.

[0032] Step S2: 3D Reconstruction. Establish a mapping model from camera image pixel coordinates to world coordinates, and perform stereo matching and 3D reconstruction based on epipolar constraints and laser plane constraints to obtain high-density 3D point cloud data of the slag surface.

[0033] Specifically, the high-density 3D point cloud data of the slag surface based on the combination of stereo vision and line structured light includes: (1) Imaging model: Each camera follows the pinhole model. For the left camera, the image pixels are... relative to camera coordinate system space points satisfy: ; in, This is the camera intrinsic parameter matrix; These represent the horizontal and vertical pixel coordinates in the left camera image coordinate system, respectively; These represent the three-dimensional spatial coordinates in the left camera coordinate system. This represents the depth value from the spatial point to the camera's optical center.

[0034] (2) Coordinate transformation: using the rotation matrix obtained from calibration Translation vector Establish the transformation relationship between the left and right camera coordinate systems, and the right camera coordinate system points Point relative to the left camera coordinate system (set as the world coordinate system) satisfy: ; (3) Solving for laser plane constraints: combining laser plane equations For the pixels on the laser line in the left image By combining the camera imaging model and the laser plane equations, the depth value can be directly solved. .

[0035] The equation of the plane of light projected by a line laser is: By substituting the imaging relationship of the left camera into the plane equation, the depth value can be directly calculated. : ; Where A, B, C, and D are the plane equation coefficients of the line laser plane in the left camera coordinate system obtained through calibration; This represents the depth value (Z-axis coordinate) of the target point in the left camera coordinate system. The horizontal and vertical pixel coordinates of the extracted laser feature points on the left camera image; , These are the equivalent focal lengths (camera intrinsic parameters) of the left camera in the horizontal and vertical directions, respectively. , The pixel coordinates (camera intrinsics) of the principal point (optical center) of the left camera image.

[0036] (4) Then, the world coordinates are obtained. And using the corresponding points in the right image Stereo matching verification was performed to eliminate mismatched points and ensure robustness of measurements under strong light and on surfaces with complex reflectivity. Specifically, based on the pinhole imaging model of the left camera, the depth value was... Substitute the values ​​to obtain the three-dimensional spatial coordinates of the point in the left camera coordinate system. Subsequently, using the extrinsic parameter matrices (rotation matrix R and translation vector T) obtained from system calibration, a rigid body transformation of the coordinate system is performed to obtain the three-dimensional coordinates of the point in the world coordinate system. And use the right camera to perform stereo matching verification. The specific verification process is as follows: the obtained world coordinates By combining the intrinsic and extrinsic parameters of the right camera, the image is reprojected onto the right camera image plane, and the theoretical projection pixel point p2′(u2′,v2′) is calculated. The Euclidean distance between the theoretical projection point p2′ and the corresponding laser feature point p2(u2,v2) actually extracted from the right image is calculated. If the distance is less than a preset pixel threshold (e.g., 1 to 2 pixels), it is determined to be a valid matching point. If the distance is greater than or equal to the preset threshold, it is determined to be a mismatched point caused by strong light reflection or complex materials and is removed, thereby ensuring the robustness of the measurement on complex reflective surfaces.

[0037] Specifically, a point is retained only when the depth value calculated from the matching points in the left and right images deviates by less than 0.5 mm, thus ensuring the high density of the point cloud.

[0038] Step S3: Point cloud preprocessing and cleaning. The 3D point cloud data is preprocessed, including noise filtering based on reflection intensity and vibration compensation based on belt edge features, to obtain the corrected point cloud of the slag surface.

[0039] (1) Noise filtering method based on reflection intensity. This method utilizes the reflection intensity information collected by the camera. Set intensity threshold and Remove Low reflectivity dust particles and High reflectivity and noise.

[0040] Specifically, the point cloud output by the camera contains reflection intensity information. Construction waste is a diffuse reflective material, while water mist in the air reflects laser light very weakly, and metal parts reflect light very strongly; the noise filtering algorithm reads the grayscale value of each point. ,reserve The point effectively filters out dust noise and metallic highlight noise in the air.

[0041] (2) Belt edge locking and vibration compensation method. The RANSAC algorithm is used to extract the edge point sets on both sides of the belt from the point cloud of each frame, and the belt cross-section baseline equation of the current frame is fitted. Calculate the vertical displacement of the baseline relative to the initial calibration zero line. and tilt angle Inverse transformation correction was performed on the dust point cloud to eliminate the influence of conveyor belt vibration.

[0042] , , for The normal vector components of the belt reference plane obtained by fitting at any time; is the distance constant from the plane to the origin; x, y, z are the three-dimensional coordinates of the extracted belt edge point cloud.

[0043] Specifically, due to the severe vibrations during the operation of the belt conveyor, the belt reference plane undergoes vertical displacement. and tilt The RANSAC algorithm is used to search for belt edge feature points at both ends of the point cloud in each frame, fit the straight line containing these two points, and calculate the vertical offset of the line relative to the calibration zero point. and tilt angle Construct the rigid body transformation matrix Set the coordinates of all construction waste point clouds in the current frame. Transform into : ; After this transformation, the dust point cloud is always corrected to a uniform static reference plane, eliminating vibration errors.

[0044] Step S4: Volume calculation and mass balance correction.

[0045] Step S401: Using the infinitesimal integral method and combined with the belt running speed, calculate the loose accumulation volume of the slag on the belt at the current moment.

[0046] Specifically, for a certain moment A frame of contour point cloud is projected onto a direction perpendicular to the belt reference plane, and the effective area of ​​the cross section is calculated using the polygon area formula. : ; In the formula: for The effective area of ​​the slag cross section at any given time; This represents the total number of valid slag point clouds in the current frame's cross-sectional profile. The index of the point cloud (k=1,2,...,n); Let x be the horizontal coordinate of the k-th point in the world coordinate system; The height coordinates of the k-th point after vibration compensation correction are given; in particular, when k=n, k+1 points to the first point, that is, the two points are connected to form a closed polygon.

[0047] The instantaneous speed of the belt is obtained through an encoder. During the time period of tunneling one ring Internally, combined with the instantaneous speed of the belt Numerical integration is performed to obtain the cumulative loose volume. That is, the total loose volume of slag and soil. The integral of the product of area and velocity at each time step: ; in, This represents the time interval between the acquisition of point cloud data from two adjacent frames (i.e., the reciprocal of the camera sampling frequency). In order to be in The total number of frames collected within the time period.

[0048] Step S402: Taking one ring of tunneling by the tunnel boring machine as a unit, simultaneously acquire construction parameters and geological parameters during the tunneling process, construct a multiphase material balance correction model, calculate the dynamic volume correction coefficient, and adjust the loose accumulation volume. The volume of the soil in situ is inverted.

[0049] Specifically, measurements obtained using existing technology Comprising soil, water, and air, this embodiment uses the following logic to reconstruct the actual in-situ soil volume. The multiphase equilibrium correction formula is defined as follows: ; in: This represents the in-situ soil volume obtained through inversion. The loosely packed volume measured in step S401; This represents the current cumulative volume of water injected into the ring. This represents the cumulative volume of bentonite slurry injected into the current ring. The residual volume of the foam is calculated using the following formula: , The residual foam coefficient is a function of the pressure P in the soil chamber and the time t that the foam has been exposed to (the foam will dissipate and burst under pressure and time). This indicates the cumulative foam injection volume of the current tunneling ring; This is the dynamic volume correction factor; This is the soil loosening coefficient, which is determined based on the current lithology of the strata.

[0050] The cumulative water volume injected into the tunnel boring machine (TBM) can be obtained in real time via the TBM's PLC interface. Bentonite slurry volume and foam injection volume .

[0051] Among them, the dynamic volume correction coefficient Defined as Specifically, to facilitate rapid application on-site, a dynamic volume correction coefficient lookup table based on formation lithology and modifier injection volume is pre-set. When the precise injection volume cannot be obtained in real time, the dynamic volume correction coefficient value is determined by looking up the table, and the calculation is performed directly. As shown in Table 1.

[0052] Table 1. Dynamic volumetric correction coefficient lookup table for different formation lithologies and amendment injection amounts

[0053] Step S5: Over-excavation / Under-excavation warning. Calculate the theoretical excavation volume at the current tunneling mileage, calculate the deviation rate between the in-situ soil volume and the theoretical excavation volume, and trigger a graded over-excavation / under-excavation warning when the deviation rate exceeds a preset threshold.

[0054] Specifically, reports are output in cycles of "rings".

[0055] Specifically, calculate the deviation rate. ; like Green status, normal tunneling; like Yellow alert, indicating a need to adjust the screw conveyor speed; like Red alert: This indicates a potential risk of over-excavation and voids. It is recommended to stop the machine and perform grouting to fill the voids.

[0056] Specifically, let's assume the theoretical excavation volume per ring of a certain shield tunnel section. .

[0057] Case 1: Measured value If not corrected: Deviation False alarms indicate severe over-excavation. This invention (for gravel and sand conditions) is used to correct this. ): .deviation The result is normal.

[0058] Case 2: Measured value After modification using this invention: .deviation The system was determined to be over-excavated, triggering a red alert. It is recommended to stop the machine and perform grouting and filling.

[0059] As can be seen from the above embodiments, the present invention achieves the "true and false" verification of the amount of soil excavated by the tunnel boring machine through hardware binocular complementarity and software material balance correction, which greatly improves the accuracy of early warning.

[0060] The in-situ volume inversion method for shield tunneling spoil based on multiphase material balance provided in this embodiment uses an industrial-grade binocular laser 3D camera to acquire high-precision point clouds, combines a rigorous geometric optical model and integral algorithm to calculate the loose volume, and further introduces a multiphase material balance correction model to eliminate the influence of amendments and invert the true in-situ soil volume.

[0061] Example 2 The shield tunneling spoil in-situ volume inversion system based on multiphase material balance provided in this embodiment includes: The data acquisition module is configured to acquire three-dimensional point cloud data of the slag surface and the conveyor belt speed. The area calculation module is configured to: at each time step, project the three-dimensional point cloud data onto a direction perpendicular to the belt reference plane and calculate the effective area of ​​the cross section using the polygon area formula; The volume calculation module is configured to: calculate the integral of the product of the effective cross-sectional area and the belt running speed at each moment during the time period of tunneling one ring, obtain the cumulative loose volume, and invert the cumulative loose volume into the in-situ soil volume through the multiphase material balance correction model.

[0062] It should be noted that each module in this embodiment corresponds one-to-one with each step in Embodiment 1, and their specific implementation processes are the same, so they will not be repeated here.

[0063] Example 3 This embodiment provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps in the shield tunneling spoil in-situ volume inversion method based on multiphase material balance as described in Embodiment 1 above.

[0064] Example 4 This embodiment provides a computer device, such as... Figure 2 As shown, the system includes a computer-readable storage medium 1003, a processor 1001, a communication interface 1002, and a computer program stored on the computer-readable storage medium 1003 and executable on the processor 1001. The processor 1001, communication interface 1002, and computer-readable storage medium 1003 can be connected via a bus or other means. The communication interface 1002 is used to receive and send data. When the processor 1001 executes the program, it implements the steps in the in-situ volume inversion method for shield tunneling spoil based on multiphase material balance as described in Embodiment 1 above.

[0065] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. 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 in-situ volume inversion of shield tunnel excavation soil based on multiphase material equilibrium, characterized in that, include: Acquire 3D point cloud data of the slag surface and conveyor belt speed; For each moment, the three-dimensional point cloud data is projected onto a direction perpendicular to the belt reference plane, and the effective area of ​​the cross section is calculated using the polygon area formula. During the time period of tunneling one ring, the integral of the product of the effective cross-sectional area and the belt running speed at each moment is calculated to obtain the cumulative loose volume. The cumulative loose volume is then converted into the in-situ soil volume using a multiphase material balance correction model.

2. The in-situ volume inversion method for shield tunneling spoil based on multiphase material balance as described in claim 1, characterized in that, The method for acquiring the three-dimensional point cloud data of the soil surface is as follows: a line laser emitter and two parallel cameras are set above the belt conveyor of the tunnel boring machine. The line laser emitter projects blue light onto the surface of the slag, with the laser line projection direction perpendicular to the belt running direction. The two cameras synchronously acquire images. After converting the images from camera image pixel coordinates to world coordinates, stereo matching verification is performed to obtain the three-dimensional point cloud data of the slag surface.

3. The in-situ volume inversion method for shield tunneling spoil based on multiphase material balance as described in claim 1, characterized in that, When the injection volume is available, the multiphase material balance correction model is as follows: ； in, This represents the in-situ soil volume obtained through inversion. For the cumulative loose volume; This represents the cumulative volume of water injected into the current ring. The cumulative volume of bentonite slurry injected into the current ring; residual foam volume. , The residual foam coefficient is a function of the soil chamber pressure P and the foam duration t. This indicates the cumulative foam injection volume of the current tunneling ring; This is the soil loosening coefficient.

4. The in-situ volume inversion method for shield tunneling spoil based on multiphase material balance as described in claim 1, characterized in that, When the injection volume cannot be obtained, the multiphase material balance correction model is as follows: ； in, This represents the in-situ soil volume obtained through inversion. For the cumulative loose volume; To determine the dynamic volume correction factor value using the table lookup method.

5. The in-situ volume inversion method for shield tunneling spoil based on multiphase material balance as described in claim 3 or 4, characterized in that, The injection volume includes the cumulative injected water volume, bentonite slurry volume, and foam injection volume.

6. The in-situ volume inversion method for shield tunneling spoil based on multiphase material balance as described in claim 1, characterized in that, After preprocessing the three-dimensional point cloud data of the slag surface, the three-dimensional point cloud data is projected onto a direction perpendicular to the belt reference plane. The preprocessing includes noise filtering based on reflection intensity and vibration compensation based on belt edge characteristics.

7. The in-situ volume inversion method for shield tunneling spoil based on multiphase material balance as described in claim 1, characterized in that, Also includes: Calculate the deviation rate between the in-situ soil volume and the theoretical excavation volume. When the deviation rate exceeds a preset threshold, trigger a graded over-excavation and under-excavation warning.

8. A shield tunneling spoil in-situ volume inversion system based on multiphase material equilibrium, characterized in that, include: The data acquisition module is configured to acquire three-dimensional point cloud data of the slag surface and the conveyor belt speed. The area calculation module is configured to: at each time step, project the three-dimensional point cloud data onto a direction perpendicular to the belt reference plane and calculate the effective area of ​​the cross section using the polygon area formula; The volume calculation module is configured to: calculate the integral of the product of the effective cross-sectional area and the belt running speed at each moment during the time period of tunneling one ring, obtain the cumulative loose volume, and invert the cumulative loose volume into the in-situ soil volume through the multiphase material balance correction model.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps in the in-situ volume inversion method for shield tunneling spoil based on multiphase material balance as described in any one of claims 1-7.

10. A computer device comprising a computer-readable storage medium, a processor, and a computer program stored on the computer-readable storage medium and executable on the processor, characterized in that, When the processor executes the program, it implements the steps in the shield tunneling spoil in-situ volume inversion method based on multiphase material balance as described in any one of claims 1-7.

Images