Subway shield tunnel circular seam identification method

Abstract

A subway shield tunnel circular seam identification method comprises the following steps: converting a three-dimensional tunnel point cloud obtained through mobile three-dimensional laser scanning into a two-dimensional plane tunnel point cloud according to a cylinder projection principle; dividing the two-dimensional plane tunnel point cloud into a plurality of sections according to the scanning line characteristics of the point cloud; calculating an average value of all point cloud reflection intensity values in each section, and storing the average value in a data container M according to a mileage value in an ascending order; traversing all data in the M, calculating the difference between the mean values of the reflection intensity values of each section and the adjacent section, and storing the difference in a new point cloud P if a condition is met; and clustering the point cloud P by using a DBSCAN clustering algorithm, and identifying the tunnel circular seam according to a clustering result. According to the method, the position of the circular seam in the tunnel can be rapidly and accurately positioned, the position of the circular seam can be accurately identified and positioned in the tunnel in a complex environment without bolt hole characteristics, the accuracy and efficiency of subway tunnel deformation detection are improved, and the safety of subway operation is improved.

Description

Technical Field

[0001] The invention relates to a method for identifying annular seams in a subway shield tunnel, and belongs to the technical field of subway tunnel point cloud processing and application. Background Art

[0002] At present, subways have become the main means for many large cities to relieve ground traffic pressure, improve traffic efficiency, and facilitate residents' lives. Subway tunnels are buried deep underground in the city and are located in the geological environment of the environment. They are affected by natural factors such as geological movement, groundwater changes, seismic activities, and extreme climate for a long time. Construction on the ground and the long-term movement of trains also affect the structural safety of subway tunnels. If the deformation of the subway tunnel structure exceeds a certain limit, it will cause serious safety hazards such as cracks in the inner wall of the tunnel, lining peeling, and track deformation, which will lead to safety accidents. It is of great significance to conduct regular deformation detection and maintenance of subway tunnels.

[0003] Compared with traditional single-point measuring instruments, LiDAR can quickly, efficiently and accurately collect three-dimensional point cloud data of the measurement target. It has gradually been applied to subway tunnel inspection tasks. The collected point cloud data can accurately reflect the real three-dimensional conditions in the tunnel. However, subway tunnels are often shield tunnels built using the shield method, and the arrangement of their segments has a strong regularity. The deformation of subway tunnels is mainly caused by the relative misalignment between these regularly arranged segments, which in turn causes a series of structural diseases. Therefore, how to accurately identify and locate the position of the annular seam without losing the accuracy of the subway tunnel point cloud data has become a key issue that needs to be solved urgently for tunnel deformation.

[0004] Existing tunnel annular joint identification methods based on advanced algorithms and neural network models mainly include tunnel annular joint identification methods based on the arrangement rules of bolt holes in the tunnel, tunnel annular joint identification methods using image grayscale transformation and straight line fitting after appropriately projecting the tunnel point cloud into a grayscale image, and tunnel annular joint identification methods using deep neural networks to identify tunnel regularity features in tunnel grayscale images. These methods directly or indirectly rely on the bolt hole features in the tunnel point cloud and have low efficiency. When faced with a complex tunnel environment without bolt holes, it is difficult to accurately identify and locate the annular joints, and cannot meet the needs of overall structural detection of subway tunnels. Summary of the invention

[0005] In view of the problems existing in the above-mentioned prior art, the present invention provides a method for identifying annular joints in a subway shield tunnel. The method can identify and locate the annular joints of the tunnel in a complex tunnel environment without bolt holes, thereby improving the accuracy and efficiency of deformation detection of the subway tunnel and ensuring safe operation of the subway.

[0006] In order to achieve the above object, the present invention provides a method for identifying annular seams in a subway shield tunnel, comprising the following steps:

[0007] S1. According to the cylindrical projection principle, the three-dimensional tunnel point cloud obtained by mobile three-dimensional laser scanning is converted into a two-dimensional plane tunnel point cloud;

[0008] S2, dividing the two-dimensional plane tunnel point cloud into N sections according to the scan line features of the tunnel point cloud obtained by mobile three-dimensional laser scanning;

[0009] S3. Calculate the average value M of all point cloud reflection intensity values ​​in each section i (i=1,2,...,N), saved in data container M in ascending order according to mileage value;

[0010] S4, traverse all the data in M, calculate the difference between the mean value of the reflection intensity value of each section and the adjacent sections, and if the conditions are met, save the point cloud in the corresponding section into a new point cloud P;

[0011] S5. Use the DBSCAN clustering algorithm to cluster P, and identify the tunnel annular gap based on the clustering results.

[0012] Furthermore, the process of converting the three-dimensional tunnel point cloud into the two-dimensional plane tunnel point cloud in step S1 is:

[0013] S1.1. The scan line point cloud of the tunnel point cloud refers to all points with the same mileage value, i.e., the same y coordinate. Ellipse fitting is performed on each scan line point cloud in the tunnel point cloud. Ellipse correction is performed based on the parameters of the fitted ellipse, and the center of the scan line is moved to the origin. The specific process is as follows:

[0014] Let the general equation of the ellipse be: Ax 2 ++Bxy++Cy 2 ++Dx++Ey++F=0, A, B, C, D, E, F are unknown parameters, constraint B 2 -4AC<0 ensures that the fitting curve is an ellipse; construct the design matrix:

[0015]

[0016] Construct the distribution matrix S = D T D; construct constraint matrix:

[0017]

[0018] Solve the generalized eigenvalue problem: Sp = λRp, where p = [ABCDEF] T , λ is the eigenvalue to be solved, S is the distribution matrix; the coordinates of the center point in According to the coordinates of the center point, move the point cloud data center on the scan line to the origin, and modify the coordinates of any point to

[0019] S1.2. Project the ellipse-corrected 3D tunnel point cloud data onto a 2D plane and calculate the angle between any point p on the scan line and the line connecting the origin and the Z axis.

[0020] S1.3. Calculate the corresponding arc length l = θ × r, where r is the tunnel design radius; modify the coordinates of p to Project the 3D tunnel point cloud onto the Z=r plane.

[0021] Furthermore, the specific process of extracting the tunnel point cloud section in step S2 is as follows:

[0022] S2.1. According to the mileage coordinates, i.e., the y coordinates, of each point in the point cloud, the point clouds with the same y coordinates are divided and saved together, i.e., a scan line point cloud;

[0023] S2.2. Calculate the average spacing s between all scan lines using the following formula: Where n represents the total number of scan lines, represents the i-th scan line, represents the i-1th scan line;

[0024] S2.3, according to the annular gap width W during tunnel design s Calculate the section width W d ,

[0025] S2.4, according to the section width W d Divide the tunnel point cloud into sections, round() represents the rounding function, y max Indicates the maximum value of y in the tunnel point cloud, y min Indicates the minimum y value in the tunnel point cloud.

[0026] Furthermore, in step S3, the average value M of the reflection intensity values ​​of all the point clouds in each section is calculated. i The specific process of (i=1,2,...,N) is: traverse all points in each cross-section point cloud and calculate the sum of the intensity values ​​of all points Where j represents the total number of point clouds at the cross section, and the mean value of the intensity of the cross section point cloud is Save the mean value of the point cloud intensity at the i-th section as M i .

[0027] Furthermore, the specific process of step S4 is as follows:

[0028] S4.1. Calculation of section M i Difference from the mean strength value of the previous section i=2,3,4,...,N-1,where M i represents the mean intensity value of the point cloud at the i-th section, M i-1 represents the mean intensity value of the point cloud at the i-1th section;

[0029] S4.2. Calculation of section M i Difference from the mean strength value of the next section i=2,3,4,...,N-1,where M i represents the mean intensity value of the point cloud at the i-th section, M i++1 Represents the mean intensity value of the point cloud at the i+1th section;

[0030] S4.3. Determine whether D1 and D2 satisfy If satisfied, it will be combined with M i The corresponding cross-section point cloud is saved in P, where t is a threshold that can be set freely.

[0031] Furthermore, the specific process of step S5 is as follows:

[0032] S5.1. Set the neighborhood radius Eps of the DBSCAN algorithm to 0.1-0.3, and the number of points within the neighborhood radius MinPts>=5;

[0033] S5.2. Use the DBSCAN algorithm to cluster P, save each class in the clustering result separately, and obtain f classes of results after clustering P;

[0034] S5.3. Calculate the coordinates of the center point of each type of result Where i = 1, 2, ..., T, T represents the point cloud contained in each result; the coordinate range of the i-th clustering result on the y-axis is i=1,2,3,...,f;

[0035] S5.4, if Δy i <0.3, calculate separately and Where W r represents the width of the lining ring in a tunnel design, r i The difference between the y coordinate of the center point of the i-th result and the y coordinate of the center point of the i-1-th result and the integer multiple of the ring width, r i ′ represents the difference between the y coordinate of the center point of the i-th result and the y coordinate of the center point of the i+1-th result and the integer multiple of the ring width, and round(x) represents rounding x; if 0 <r i <0.1 and 0 <r i ′<0.1, then p i (x i ,yi ,z i ) is recorded as the position coordinate of the annular seam;

[0036] S5.5, according to the annular seam position coordinates p i (x i ,y i ,z i ) and W r Calculate the position coordinates p of the previous ring gap i (x i ,y i -W r ,z i ) and the next annular gap position coordinate p i (x i ,y i ++W r ,z i ), and so on to calculate the position coordinates of all the annular seams. According to the position coordinates of all the annular seams, find the points belonging to each annular seam, and the points in the annular seam satisfy Where p y represents the y coordinate of any point p in the tunnel point cloud, y i represents the y coordinate of the i-th ring gap position, W s is the annular gap width, and the annular gap identification of the tunnel is completed here.

[0037] The present invention converts three-dimensional tunnel point cloud data into two-dimensional plane data through cylindrical projection and retains the corresponding relationship, then uses a section extraction module to divide the two-dimensional tunnel point cloud into sections, and realizes tunnel annular seam identification by calculating the mean value of the point cloud intensity value in the section and capturing the difference in the point cloud intensity value at the annular seam. The present invention can quickly and accurately locate the annular seam position in the tunnel, and can also accurately identify and locate the annular seam position in a complex environment tunnel without bolt hole features, thereby improving the accuracy and efficiency of subway tunnel deformation detection and improving the safety of subway operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 is a flow chart of the method of the present invention;

[0039] Figure 2 It is a schematic diagram of converting a three-dimensional tunnel point cloud into a two-dimensional plane point cloud in the present invention;

[0040] Figure 3 It is a schematic diagram of the result of cross-section extraction of a two-dimensional plane point cloud in the present invention;

[0041] Figure 4 It is a schematic diagram of the result after the cross-section extraction results are clustered using the DBSCAN algorithm in the present invention;

[0042] Figure 5It is a schematic diagram of the annular seam identification result after inverting the clustering result in the present invention;

[0043] Figure 6 These are the experimental result diagrams of the method of the present invention on the characteristic tunnel point cloud with bolt holes and the characteristic point cloud without bolt holes. DETAILED DESCRIPTION

[0044] The present invention will be further described below in conjunction with the accompanying drawings.

[0045] like Figure 1 As shown, a method for identifying annular seams in a subway shield tunnel comprises the following steps:

[0046] S1. According to the cylindrical projection principle, the three-dimensional tunnel point cloud obtained by mobile three-dimensional laser scanning is converted into a two-dimensional plane tunnel point cloud;

[0047] S2, dividing the two-dimensional plane tunnel point cloud into N sections according to the scan line features of the tunnel point cloud obtained by mobile three-dimensional laser scanning;

[0048] S3. Calculate the average value M of all point cloud reflection intensity values ​​in each section i (i=1,2,...,N), saved in data container M in ascending order according to mileage value;

[0049] S4, traverse all the data in M, calculate the difference between the mean strength value of each section and the adjacent sections, and if the conditions are met, save the point cloud in the corresponding section into a new point cloud P;

[0050] S5. Use the DBSCAN clustering algorithm to cluster P, and identify the tunnel annular gap based on the clustering results.

[0051] Furthermore, the process of converting the three-dimensional tunnel point cloud into the two-dimensional plane tunnel point cloud in step S1 is:

[0052] S1.1. The scan line point cloud in the tunnel point cloud refers to all points with the same mileage value, i.e., the same y coordinate. Ellipse fitting is performed on each scan line point cloud in the tunnel point cloud. Ellipse correction is performed based on the parameters of the fitted ellipse, and the center of the scan line is moved to the origin. The specific process is as follows:

[0053] Let the general equation of the ellipse be: Ax 2 +Bxy++Cy 2 +Dx+Ey+F=0, A, B, C, D, E, F are unknown parameters, constraint B 2 -4AC<0 ensures that the fitting curve is an ellipse; construct the design matrix:

[0054]

[0055] Construct the distribution matrix S = D T D; construct constraint matrix:

[0056]

[0057] Solve the generalized eigenvalue problem: Sp = λRp, where p = [ABCDEF] T , λ is the eigenvalue to be solved, S is the distribution matrix; the coordinates of the center point in According to the coordinates of the center point, move the point cloud data center on the scan line to the origin, and modify the coordinates of any point to

[0058] S1.2. Project the ellipse-corrected 3D tunnel point cloud data onto a 2D plane and calculate the angle between any point p on the scan line and the line connecting the origin and the Z axis.

[0059] S1.3. Calculate the corresponding arc length l = θ × r, where r is the tunnel design radius; modify the coordinates of p to Project the 3D tunnel point cloud onto the Z=r plane, as Figure 2 As shown;

[0060] Furthermore, the specific process of extracting the tunnel point cloud section in step S2 is as follows:

[0061] S2.1. According to the mileage coordinates, i.e., the y coordinates, of each point in the point cloud, the point clouds with the same y coordinates are divided and saved together, i.e., a scan line point cloud;

[0062] S2.2. Calculate the average spacing s between all scan line point clouds. The calculation formula is: Where n represents the total number of scan lines, represents the i-th scan line, represents the i-1th scan line;

[0063] S2.3, according to the annular gap width W during tunnel design s Calculate the section width W d ,

[0064] S2.4, such as Figure 3 As shown, according to the section width W d Divide the tunnel point cloud into sections, round() represents the rounding function, y max Indicates the maximum value of y in the tunnel point cloud, y min Indicates the minimum y value in the tunnel point cloud.

[0065] Furthermore, in step S3, the average value M of the reflection intensity values ​​of all the point clouds in each section is calculated. i The specific process of (i=1,2,...,N) is: traverse all points in each cross-section point cloud and calculate the sum of the intensity values ​​of all points Where j represents the total number of point clouds at the cross section, and the mean value of the intensity of the cross section point cloud is Save the mean value of the point cloud intensity at the i-th section as M i .

[0066] Furthermore, the specific process of step S4 is as follows:

[0067] S4.1. Calculation of section M i Difference from the mean strength value of the previous section i=2,3,4,...,N-1,where M i represents the mean intensity value of the point cloud at the i-th section, M i-1 Represents the mean intensity value of the point cloud at the i-1th section

[0068] S4.2. Calculation of section M i Difference from the mean strength value of the next section i=2,3,4,...,N-1,where M i represents the mean intensity value of the point cloud at the i-th section, M i++1 Represents the mean intensity value of the point cloud at the i+1th section;

[0069] S4.3. Determine whether D1 and D2 satisfy If satisfied, it will be combined with M i The corresponding cross-section point cloud is saved in P, where t is a threshold value that can be set freely. Further, the specific process of step S5 is:

[0070] S5.1. Set the neighborhood radius Eps of the DBSCAN algorithm to 0.1-0.3, and the number of points within the neighborhood radius MinPts>5;

[0071] S5.2, such as Figure 4 As shown, the DBSCAN algorithm is used to cluster P, and each class in the clustering result is saved separately. After clustering, P obtains f class results;

[0072] S5.3. Calculate the coordinates of the center point of each type of result Where i = 1, 2, ..., T, T represents the total number of points contained in each type of result, and the coordinate range of the i-th clustering result on the y-axis is i=1,2,3,...,f;

[0073] S5.4, if Δy i<0.3, calculate separately and

[0074] Where W r represents the width of the lining ring in a tunnel design, r i The difference between the y coordinate of the center point of the i-th result and the y coordinate of the center point of the i-1-th result and the integer multiple of the ring width, r i ′ represents the difference between the y coordinate of the center point of the i-th result and the y coordinate of the center point of the i+1-th result and the integer multiple of the ring width, and round(x) represents rounding x; if 0 <r i <0.1 and 0 <r i ′<0.1, then p i (x i ,y i ,z i ) is recorded as the position coordinate of the annular seam;

[0075] S5.5, if Figure 5 As shown, according to the annular seam position coordinate p i (x i ,y i ,z i ) and W r Calculate the position coordinates p of the previous ring gap i (x i ,y i -W r ,z i ) ring and the next ring gap position coordinate p i (x i ,y i +W r ,z i ), and so on to calculate the coordinates of all the annular seams. According to the coordinates of all the annular seams, find the points belonging to each annular seam. The points in the annular seam should satisfy In the formula, p y represents the y coordinate of any point p in the tunnel point cloud, y i represents the y coordinate of the i-th ring gap position, W s is the annular gap width, which completes the annular gap identification of the tunnel.

[0076] like Figure 6 As shown, in order to make the result more intuitive, the tunnel point cloud is converted into a grayscale image and the annular seam recognition result is marked with a red line. Figure 6 (a) is a diagram showing the annular seam recognition result on a point cloud of a tunnel with bolt hole features according to the present invention. Figure 6(b) is the result diagram of the annular seam recognition on the point cloud without bolt hole features of the present invention. It can be seen that the present invention does not rely on the bolt hole features in the tunnel point cloud. When facing complex and diverse tunnel environments, it can realize tunnel annular seam recognition and positioning with high efficiency and high precision, providing more reliable technical support for subsequent tunnel structure analysis and safety monitoring.

Claims

1. A method for identifying annular seams in a subway shield tunnel, characterized in that: The following steps are involved: S1. According to the cylindrical projection principle, the three-dimensional tunnel point cloud obtained by mobile three-dimensional laser scanning is converted into a two-dimensional plane tunnel point cloud; S2, dividing the two-dimensional plane tunnel point cloud into N sections according to the scan line features of the tunnel point cloud obtained by mobile three-dimensional laser scanning; S3. Calculate the average value M of all point cloud reflection intensity values ​​in each section i (i=1,2,...,N), saved in data container M in ascending order according to mileage value; S4, traverse all the data in M, calculate the difference between the mean value of the reflection intensity value of each section and the adjacent sections, and if the conditions are met, save the point cloud in the corresponding section into a new point cloud P; S5. Use the DBSCAN clustering algorithm to cluster P, and identify the tunnel annular gap based on the clustering results.

2. The method for identifying annular seams in a subway shield tunnel according to claim 1, characterized in that: The process of converting the three-dimensional tunnel point cloud into a two-dimensional plane tunnel point cloud in step S1 is as follows: S1.

1. The scan line point cloud of the tunnel point cloud refers to all points with the same mileage value, i.e., the same y coordinate. Ellipse fitting is performed on each scan line point cloud in the tunnel point cloud. Ellipse correction is performed based on the parameters of the fitted ellipse, and the center of the scan line is moved to the origin. The specific process is as follows: Let the general equation of the ellipse be: Ax 2 ++Bxy++Cy 2 ++Dx++Ey++F=0, A, B, C, D, E, F are unknown parameters, constraint B 2 -4AC<0 ensures that the fitting curve is an ellipse; construct the design matrix: Construct the distribution matrix S = D T D; construct constraint matrix: Solve the generalized eigenvalue problem Sp = λRp, where p = [ABCDEF] T , λ is the eigenvalue to be solved, S is the distribution matrix; the coordinates of the center point in According to the coordinates of the center point, move the point cloud data center on the scan line to the origin, and modify the coordinates of any point to S1.

2. Project the ellipse-corrected 3D tunnel point cloud data onto a 2D plane and calculate the angle between any point p on the scan line and the line connecting the origin and the Z axis. S1.

3. Calculate the corresponding arc length l = θ × r, where r is the tunnel design radius; modify the coordinates of p to Project the 3D tunnel point cloud onto the Z=r plane.

3. The method for identifying annular seams in a subway shield tunnel according to claim 1, characterized in that: The specific process of step S2 is: S2.

1. According to the mileage coordinates, i.e., the y coordinates, of each point in the point cloud, the point clouds with the same y coordinates are divided and saved together, i.e., a scan line point cloud; S2.

2. Calculate the average spacing s between all scan line point clouds. The calculation formula is: Where n represents the total number of scan lines, represents the i-th scan line, represents the i-1th scan line; S2.3, according to the annular gap width W during tunnel design s Calculate the section width W d , S2.4, according to the section width W d Divide the tunnel point cloud into sections, round() represents the rounding function, y max Indicates the maximum value of the y coordinate in the tunnel point cloud, y min Indicates the minimum y coordinate in the tunnel point cloud.

4. The method for identifying annular seams in a subway shield tunnel according to claim 1, characterized in that: In step S3, the average value M of the reflection intensity values ​​of all the point clouds in each section is calculated. i The specific process of (i=1,2,...,N) is: traverse all points in each cross-section point cloud and calculate the sum of the intensity values ​​of all points Where j represents the total number of point clouds at the cross section, and the mean value of the intensity of the cross section point cloud is Save the mean value of the point cloud intensity at the i-th section as M i .

5. The method for identifying annular seams in a subway shield tunnel according to claim 1, characterized in that: The specific process of step S4 is as follows: S4.

1. Calculation of section M i Difference from the mean strength value of the previous section i=2,3,4,...,N-1,where M i represents the mean value of the reflection intensity of the point cloud at the i-th section, M i-1 Represents the reflection intensity value of the point cloud at the i-1th section; S4.

2. Calculation of section M i The difference between the mean reflection intensity value of the next section i=2,3,4,...,N-1,where M i represents the mean intensity value of the point cloud at the i-th section, M i++1 Represents the reflection intensity value of the point cloud at the i+1th section; S4.

3. Determine whether D1 and D2 satisfy If satisfied, it will be combined with M i The corresponding cross-section point cloud is saved in P, where t is the set threshold.

6. The method for identifying annular seams in a subway shield tunnel according to claim 1, characterized in that: The specific process of step S5 is as follows: S5.

1. Set the neighborhood radius Eps of the DBSCAN algorithm to 0.1-0.3, and the number of points within the neighborhood radius MinPts>5; S5.

2. Use the DBSCAN algorithm to cluster P, save each class in the clustering result separately, and obtain f classes of results after clustering P; S5.

3. Calculate the coordinates of the center point of each type of result Where k = 1, 2, ..., T, T represents the point cloud contained in each type of result; the coordinate range of the i-th clustering result on the y-axis is i=1,2,3,...,f; S5.4, if Δy i <0.3, calculate separately and Where W r represents the width of the lining ring in tunnel design, r i The difference between the y coordinate of the center point of the i-th result and the y coordinate of the center point of the i-1-th result and the integer multiple of the ring width, r i ′ represents the difference between the y coordinate of the center point of the i-th result and the y coordinate of the center point of the i+1-th result and the integer multiple of the ring width, and round(x) represents rounding x; if 0 <r i <0.1 and 0 <r i ′<0.1, then p i (x i ,y i ,z i ) is recorded as the position coordinate of the annular seam; S5.5, according to the annular seam position coordinates p i (x i ,y i ,z i ) and the tunnel lining ring design width W r Calculate the position coordinates p of the previous ring gap i (x i ,y i -W r ,z i ) and the next annular gap position coordinate p i (x i ,y i ++W r ,z i ), and so on to calculate the position coordinates of all the ring seams; according to the position coordinates of all the ring seams, find the points belonging to each ring seam, and the points in the ring seams satisfy In the formula, p y represents the y coordinate of any point p in the tunnel point cloud, y i represents the y coordinate of the i-th ring gap position, W s It is the annular gap width, which completes the annular gap identification of the tunnel.

Images