TBM tunnel strip identification method based on DBSCAN clustering algorithm

Abstract

The invention provides a TBM tunnel strip identification method based on a DBSCAN clustering algorithm, and the method comprises the steps: selecting a micro-seismic event screening space range, obtaining the coordinates of the micro-seismic events in the space range, carrying out the clustering of the micro-seismic events in the space range through employing the DBSCAN clustering algorithm, calculating the mean value of the coordinates of the micro-seismic events, obtaining a main shaft through employing singular value decomposition, and carrying out the recognition of a TBM tunnel strip. The method comprises the steps of obtaining a minimum tangent cuboid, calculating the length, width and height of the minimum tangent cuboid to obtain a length-height ratio and an aspect ratio, judging whether a strip exists or not, establishing a threshold value of a mean value of the length-height ratio and the aspect ratio of a soft strip and a hard strip according to the length-height ratio and the aspect ratio of the minimum tangent cuboid, and judging the property of the strip. And according to the direction vector of each axis of the minimum tangent cuboid and the included angle of the original XOY coordinate system, obtaining the included angle between the strip trend and the tunnel axis determined by the minimum tangent cuboid according to the micro-seismic event. Whether the strip exists or not, the position, the trend and the property can be identified when the surrounding rock is not exposed, and the accuracy of strip judgment is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel microseismic monitoring, and in particular to a TBM tunnel stripe recognition method based on a DBSCAN clustering algorithm. Background Art

[0002] Rockburst is a dynamic phenomenon in which the elastic deformation potential accumulated in the rock mass of underground engineering is suddenly released under excavation or other external disturbances, resulting in the explosion and ejection of surrounding rocks. With the increase of ground stress and the increasing complexity of geological structure, rockbursts occurred multiple times in the same area during the construction of underground engineering. Among them, rockbursts that occurred multiple times along the radial direction of the tunnel are called radial chain rockbursts. In the statistical analysis of radial chain rockburst cases in TBM tunnels, it was found that there were many weak bands controlling the occurrence of radial chain rockbursts. The weak bands included alteration bands, biotite schist bands, and other bands with properties weaker than bedrock granite. In addition, during the construction of TBM tunnels, radial chain rockbursts lasted for a long time, posing a great safety threat to construction equipment and personnel. Therefore, it is urgent to establish a radial chain rockburst prediction method under the influence of weak bands in TBM granite tunnels, to identify radial chain rockbursts in advance, to lay the foundation for radial chain rockburst prevention and control, and to ensure the safety of construction personnel and construction progress.

[0003] Research on rockburst type identification has been conducted at home and abroad and some results have been achieved. The Chinese invention patent "Method for Predicting Rockburst Type", publication number CN110456413A, discloses a method for identifying the rockburst type in the warning area based on microseismic information. This method can be used to determine whether the rockburst in the warning area is a strain-type rockburst or a strain-structural surface sliding rockburst. Current research on rockburst type identification mainly focuses on single rockbursts, and a method for identifying radial chain rockbursts that occur multiple times in the same area has not yet been established. Summary of the invention

[0004] According to the technical problems raised above, a TBM tunnel stripe identification method based on DBSCAN clustering algorithm is provided to realize automatic identification of the existence, location, direction and nature of TBM tunnel stripes, which can provide a basis for comprehensive and automated geological advance identification and provide a scientific basis for disaster warning and prevention and control under the influence of stripes.

[0005] The technical means adopted by the present invention are as follows:

[0006] A TBM tunnel stripe identification method based on DBSCAN clustering algorithm, comprising:

[0007] S1. Select a microseismic event screening spatial range, obtain the coordinates of the microseismic events within the spatial range, and use the DBSCAN clustering algorithm to cluster the microseismic events within the obtained spatial range;

[0008] S2, calculate the coordinate mean of microseismic events;

[0009] S3, use singular value decomposition to obtain the principal axis and obtain the minimum tangent cuboid;

[0010] S4, calculate the length, width and height of the minimum tangent cuboid;

[0011] S5, calculating the aspect ratio and width ratio of the minimum tangent cuboid;

[0012] S6. judging whether a stripe exists according to the length-to-height ratio and the width-to-height ratio of the minimum tangent cuboid;

[0013] S7. Identify the properties of the strip according to the average of the length-to-height ratio and the width-to-height ratio of the minimum tangent cuboid;

[0014] S8. According to the angles between the direction vectors of the axes of the minimum tangent cuboid and the original XOY coordinate system, the angle between the strip direction determined by the minimum tangent cuboid of the microseismic event and the tunnel axis is obtained.

[0015] Furthermore, in step S1, the microseismic event screening space range is selected to include:

[0016] The screening space range in front and behind the heading, the screening space range on the left and right sides perpendicular to the tunnel axis, and the screening space range above and below perpendicular to the tunnel axis.

[0017] Furthermore, step S2 specifically includes:

[0018] According to the microseismic event coordinates obtained in step S1, assume that A1, A2, ...A n represents the coordinates of a certain direction of the microseismic event, [A1, A2, ...A n ] is a 1×n observation matrix, and the coordinate mean of the microseismic event is calculated using the following formula:

[0019]

[0020] Where M represents the mean coordinate of one direction of the microseismic event, and n represents the number of microseismic events.

[0021] Furthermore, step S3 specifically includes:

[0022] S31, according to the microseismic event coordinates obtained in step S1, calculate the average deviation form matrix of the microseismic event coordinates, and the calculation formula is as follows:

[0023]

[0024] Among them, A k represents one direction coordinate of each microseismic event, M represents the mean value of one direction coordinate of the microseismic event, represents the amount of deviation from the coordinate mean, B represents the mean deviation form matrix, and n represents the number of microseismic events;

[0025] S32, using singular value decomposition to obtain the principal axis, decomposing the singular value of the average deviation form matrix B into:

[0026] B=UΣV T

[0027] From the mean deviation form matrix B, we can get B T B and BB T , and further get B T B and BB T The eigenvalues ​​and eigenvectors of , where U is a left singular vector, U = {U1 U2 ... U n},U1 U2 ... U n For BB T The characteristic vector of T is the right singular vector, V T = {V T1 V T2 ... V Tn}, T T1 V T2 ... V Tn For B T The eigenvector of B; Σ is the singular value matrix, λ i is the matrix composed of eigenvalues;

[0028] S33, calculate the average deviation form matrix B in V T The projection B′ on the XOY space is transformed into B′ by the following formula:

[0029]

[0030] Further, step S4 specifically includes:

[0031] Calculate the length, width, and height of the minimum tangent cuboid using the following formula:

[0032] L = max(a,b,c)

[0033] W=mid(a,b,c)

[0034] H=min(a,b,c)

[0035] a=a max -a min

[0036] b=b max -b min

[0037] c=c max -c min

[0038] Among them, L, W, and H are the length, width, and height of the minimum tangent cuboid respectively; a, b, and c are the lengths of the principal axes of the minimum tangent cuboid respectively; a max and a min , b max and b min 、c max and c min They are the maximum and minimum coordinates of each principal axis of the minimum tangent cuboid respectively.

[0039] Furthermore, step S5 specifically includes:

[0040] Calculate the aspect ratio and width ratio of the minimum tangent cuboid using the following formula:

[0041]

[0042] Wherein, A represents the aspect ratio of the minimum tangent cuboid, and B represents the aspect ratio of the minimum tangent cuboid.

[0043] Further, step S6 specifically includes:

[0044] S61, comparing the length-to-height ratio and the width-to-height ratio of the minimum tangent cuboid obtained by clustering the microseismic events of the existing stripes and the non-existing stripes in the excavated and exposed tunnel section, and establishing a threshold for whether the stripes exist;

[0045] S62, a comprehensive discrimination method, after obtaining microseismic information, compares the length-to-height ratio and the width-to-height ratio of the minimum tangent cuboid obtained after clustering the microseismic events with the established threshold value. If the length-to-height ratio and the width-to-height ratio of the minimum tangent cuboid reach the threshold value, it is predicted that a strip exists in the area, otherwise, it is predicted that no strip exists in the area.

[0046] Further, step S7 specifically includes:

[0047] S71. Establishing a threshold value for the average value of the length-to-height ratio and the aspect-to-height ratio of the weak strip and the hard strip according to the length-to-height ratio and the aspect-to-height ratio of the minimum tangent cuboid;

[0048] S72. If the average of the aspect ratio and the width ratio reaches a threshold, it is a hard strip; if the average of the aspect ratio and the width ratio does not reach the threshold, it is a weak strip.

[0049] Further, step S8 specifically includes:

[0050] S81, according to the original coordinate B transformed into B' rotation matrix V T, obtain the angle between the direction vector of each axis of the minimum tangent cuboid and the original XOY coordinate system, and then select the angle between the strip distribution direction of the minimum tangent cuboid and the original X-axis, that is, the angle between the strip direction and the tunnel axis determined by the minimum tangent cuboid of the microseismic event;

[0051] S82. Calculate the angle between the direction vector of each axis of the minimum tangent cuboid and the original XOY coordinate system. The calculation formula is as follows:

[0052] θ=arccos -1 V Tk ,k=1,2,…,n

[0053] Among them, θ represents the angle between the direction vector of each axis of the minimum tangent cuboid and the original XOY coordinate system, V Tk Represents the corresponding element in the rotation matrix that transforms the original coordinate B to B′.

[0054] Compared with the prior art, the present invention has the following advantages:

[0055] 1. The present invention provides a TBM tunnel stripe identification method based on the DBSCAN clustering algorithm. The aspect ratio and width-to-height ratio of the minimum tangent cuboid obtained after clustering microseismic events are compared with a known threshold value to determine whether the area has a stripe. The mean of the aspect ratio and width-to-height ratio of the minimum tangent cuboid obtained is compared with a known threshold value to determine the nature of the stripe. According to the angle between the direction vector of each axis of the minimum tangent cuboid and the original XOY coordinate system, the angle between the stripe direction determined by the minimum tangent cuboid of the microseismic event and the tunnel axis is obtained.

[0056] 2. The present invention provides a TBM tunnel stripe identification method based on the DBSCAN clustering algorithm, which can identify the existence, location, direction and nature of the stripe when the surrounding rock is not exposed, improve the accuracy of stripe identification, and provide a scientific basis for disaster warning and prevention and control under the influence of the stripe.

[0057] Based on the above reasons, the present invention can be widely promoted in hard rock TBM tunnel construction in various water conservancy, hydropower, transportation, mining and the like. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0059] Figure 1 The figure is a flow chart of the method of the present invention.

[0060] Figure 2 The spatial distribution of microseismic events provided by the embodiment of the present invention.

[0061] Figure 3 This is a microseismic event screening area provided in an embodiment of the present invention.

[0062] Figure 4 This is the microseismic event clustering result provided by the embodiment of the present invention.

[0063] Figure 5 The minimum tangent cuboid provided by the embodiment of the present invention.

[0064] Figure 6 The aspect ratio and length-to-height ratio results provided by the embodiments of the present invention.

[0065] Figure 7 The comparison result of the aspect ratio of the existing stripes and the non-existing stripes provided in the embodiment of the present invention.

[0066] Figure 8 The comparison result of width-to-height ratio between the existing stripe and the non-existing stripe provided in the embodiment of the present invention.

[0067] Fig. 9 The results of the comparison of the average length-to-height ratio and width-to-height ratio of the weak strips and the hard strips provided in the embodiments of the present invention.

[0068] Fig.10 A schematic diagram of the direction vectors of each axis of the minimum tangent cuboid and the original XOY coordinate system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0069] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0070] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0071] like Figure 1 As shown, the present invention provides a TBM tunnel stripe identification method based on the DBSCAN clustering algorithm, comprising:

[0072] S1. Select a microseismic event screening spatial range, obtain the coordinates of the microseismic events within the spatial range, and use the DBSCAN clustering algorithm to cluster the microseismic events within the obtained spatial range;

[0073] S2, calculate the coordinate mean of microseismic events;

[0074] S3, use singular value decomposition to obtain the principal axis and obtain the minimum tangent cuboid;

[0075] S4, calculate the length, width and height of the minimum tangent cuboid;

[0076] S5, calculating the aspect ratio and width ratio of the minimum tangent cuboid;

[0077] S6. judging whether a stripe exists according to the average of the length-to-height ratio and the width-to-height ratio of the minimum tangent cuboid;

[0078] S7. Identify the properties of the strip based on the length-to-height ratio and width-to-height ratio of the minimum tangent cuboid;

[0079] S8. According to the angles between the direction vectors of the axes of the minimum tangent cuboid and the original XOY coordinate system, the angle between the strip direction determined by the minimum tangent cuboid of the microseismic event and the tunnel axis is obtained.

[0080] In specific implementation, as a preferred embodiment of the present invention, in step S1, selecting a microseismic event screening space range includes:

[0081] The screening space range in front and behind the tunnel face, the screening space range on the left and right sides perpendicular to the tunnel axis, and the screening space range above and below the tunnel axis. Figure 2 As shown in Figure 1, this is the spatial distribution of microseismic events. Figure 3As shown in Figure 1, it is the microseismic event screening area. Figure 4 The following is the clustering result of microseismic events.

[0082] In specific implementation, as a preferred embodiment of the present invention, step S2 specifically includes:

[0083] According to the microseismic event coordinates obtained in step S1, assume that A1, A2, ...A n represents the coordinates of a certain direction of the microseismic event, [A1, A2, ...A n ] is a 1×n observation matrix, and the coordinate mean of the microseismic event is calculated using the following formula:

[0084]

[0085] Where M represents the mean coordinate of one direction of the microseismic event, and n represents the number of microseismic events.

[0086] In specific implementation, as a preferred embodiment of the present invention, step S3 specifically includes:

[0087] S31, according to the microseismic event coordinates obtained in step S1, calculate the average deviation form matrix of the microseismic event coordinates, and the calculation formula is as follows:

[0088]

[0089] Among them, A k represents one direction coordinate of each microseismic event, M represents the mean value of one direction coordinate of the microseismic event, represents the amount of deviation from the coordinate mean, B represents the mean deviation form matrix, and n represents the number of microseismic events;

[0090] S32, using singular value decomposition to obtain the principal axis, decomposing the singular value of the average deviation form matrix B into:

[0091] B=UΣV T

[0092] From the mean deviation form matrix B, we can get B T B and BB T , and further get B T B and BB T The eigenvalues ​​and eigenvectors of , where U is a left singular vector, U = {U1 U2 ... U n},U1 U2 ... U n For BB T The characteristic vector of T is the right singular vector, V T = {V T1 V T2 … V Tn},V T1 V T2 … V Tn For B T The eigenvector of B; Σ is the singular value matrix, λ i is a matrix composed of eigenvalues; Figure 5 As shown, it is the minimum tangent cuboid.

[0093] S33, calculate the average deviation form matrix B in V T The projection B′ on the XOY space is transformed into B′ by the following formula:

[0094]

[0095] In specific implementation, as a preferred embodiment of the present invention, step S4 specifically includes:

[0096] Calculate the length, width, and height of the minimum tangent cuboid using the following formula:

[0097] L = max(a,b,c)

[0098] W=mid(a,b,c)

[0099] H=min(a,b,c)

[0100] a=a max -a min

[0101] b=b max -b min

[0102] c=c max -c min

[0103] Among them, L, W, and H are the length, width, and height of the minimum tangent cuboid respectively; a, b, and c are the lengths of the principal axes of the minimum tangent cuboid respectively; a max and a min , b max and b min 、c max and c min They are the maximum and minimum coordinates of each principal axis of the minimum tangent cuboid respectively.

[0104] In specific implementation, as a preferred embodiment of the present invention, step S5 specifically includes:

[0105] Calculate the aspect ratio and width ratio of the minimum tangent cuboid using the following formula:

[0106]

[0107] Among them, A represents the aspect ratio of the minimum tangent cuboid, and B represents the width ratio of the minimum tangent cuboid. Figure 6 Shown are the aspect ratio and length ratio results.

[0108] In specific implementation, as a preferred embodiment of the present invention, step S6 specifically includes:

[0109] S61, comparing the length-to-height ratio and the width-to-height ratio of the minimum tangent cuboid obtained by clustering the microseismic events of the existing stripes and the non-existing stripes in the excavated and exposed tunnel section, and establishing a threshold for whether the stripes exist;

[0110] S62, comprehensive discrimination method, after obtaining microseismic information, compare the length-to-height ratio and width-to-height ratio of the minimum tangent cuboid obtained after clustering the microseismic events with the established threshold value, if the length-to-height ratio and width-to-height ratio of the minimum tangent cuboid reach the threshold value, it is predicted that there is a strip in the area, otherwise, there is no strip in the area. Figure 7 , 8 Shown are the comparison results of the length-to-height ratio and the width-to-height ratio of the presence and absence of the stripes.

[0111] In specific implementation, as a preferred embodiment of the present invention, step S7 specifically includes:

[0112] S71. Establishing a threshold value for the average value of the length-to-height ratio and the aspect-to-height ratio of the weak strip and the hard strip according to the length-to-height ratio and the aspect-to-height ratio of the minimum tangent cuboid;

[0113] S72: If the average of the aspect ratio and the width ratio reaches a threshold, it is a hard stripe; if the average of the aspect ratio and the width ratio does not reach the threshold, it is a weak stripe. Fig. 9 Shown are the comparison results of the average length-to-height ratio and width-to-height ratio of the weak strips and the hard strips.

[0114] In specific implementation, as a preferred embodiment of the present invention, step S8 specifically includes:

[0115] S81, according to the original coordinate B transformed into B' rotation matrix V T , obtain the angle between the direction vector of each axis of the minimum tangent cuboid and the original XOY coordinate system, and then select the angle between the strip distribution direction of the minimum tangent cuboid and the original X-axis (the direction of the tunnel axis), that is, the angle between the strip direction and the tunnel axis determined by the minimum tangent cuboid of the microseismic event;

[0116] S82. Calculate the angle between the direction vector of each axis of the minimum tangent cuboid and the original XOY coordinate system. The calculation formula is as follows:

[0117] θ=arccos -1 V Tk,k=1,2,…,n

[0118] Among them, θ represents the angle between the direction vector of each axis of the minimum tangent cuboid and the original XOY coordinate system, V Tk Represents the corresponding element in the rotation matrix that transforms the original coordinate B into B′. Fig.10 As shown, it is a schematic diagram of the direction vectors of each axis of the minimum tangent cuboid and the original XOY coordinate system.

[0119] Example

[0120] The following is an explanation of the process of stripe identification using the present invention in actual engineering:

[0121] First, during the construction of this project, the distribution characteristics of existing microseismic events were comprehensively analyzed, such as Figure 2 As shown in the figure, the distribution range of microseismic events is statistically analyzed to obtain the microseismic event screening area, such as Figure 3 As shown in Figure 1, the distribution range of microseismic events in the X direction is [K33+155, K33+115], the distribution range of microseismic events in the Y direction is [-20, 20], and the distribution range of microseismic events in the Z direction is [-10, 15]. The coordinates of microseismic events in the spatial range are obtained, and then the DBSCAN clustering algorithm is used to cluster the microseismic events, as shown in Figure 1. Figure 4 As shown, the coordinate mean of the microseismic event is calculated, the principal axis is obtained using singular value decomposition, the minimum tangent cuboid is obtained, the length, width and height of the minimum tangent cuboid are calculated, and the length-to-height ratio and the width-to-height ratio are obtained;

[0122] Figure 5 is the minimum tangent cuboid obtained after clustering microseismic events, and the aspect ratio and width ratio can be calculated (such as Figure 6 shown);

[0123] Select the case where the stripes exist in the project area and the case where the stripes do not exist in the area. Using the above method, the aspect ratio threshold is 3.7 and the width-to-height ratio threshold is 2.6, as shown in Figure 7 , 8 As shown;

[0124] Select the cases with weak strips and hard strips in the project area, and use the above method to obtain the average threshold of the aspect ratio and width ratio as 16.8, such as Fig. 9 As shown;

[0125] According to the angle between the direction vector of each axis of the minimum tangent cuboid and the original XOY coordinate system, the angle between the strip direction determined by the minimum tangent cuboid of the microseismic event and the tunnel axis is obtained, as follows: Fig.10 As shown;

[0126] During the subsequent construction of this project, microseismic monitoring was carried out to obtain microseismic events in the screening area. After clustering the microseismic events, the minimum tangent cuboid was obtained, and the length-to-height ratio and the width-to-height ratio were calculated. The results showed that both the length-to-height ratio and the width-to-height ratio met the conditions, so it was determined that the area had a strip. The mean of the length-to-height ratio and the width-to-height ratio did not meet the conditions, so it was determined that the area had a weak strip. According to the angle between the minimum tangent cuboid strip distribution direction and the tunnel axis, the angle between the direction of the identified weak strip and the tunnel axis was 83°.

[0127] During the subsequent excavation process, data collected through on-site surveys showed that there were weak strips in the area and the angle between the direction of the weak strips and the axis of the tunnel was 80°. The identification results were basically consistent with the actual situation.

[0128] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A TBM tunnel stripe identification method based on DBSCAN clustering algorithm, characterized in that: include: S1. Select a microseismic event screening spatial range, obtain the coordinates of the microseismic events within the spatial range, and use the DBSCAN clustering algorithm to cluster the microseismic events within the obtained spatial range; S2, calculate the coordinate mean of microseismic events; S3, use singular value decomposition to obtain the principal axis and obtain the minimum tangent cuboid; S4, calculate the length, width and height of the minimum tangent cuboid; S5, calculating the aspect ratio and width ratio of the minimum tangent cuboid; S6. judging whether a stripe exists according to the length-to-height ratio and the width-to-height ratio of the minimum tangent cuboid; S7. Identify the properties of the strip according to the average of the length-to-height ratio and the width-to-height ratio of the minimum tangent cuboid; S8. According to the angles between the direction vectors of the axes of the minimum tangent cuboid and the original XOY coordinate system, the angle between the strip direction determined by the minimum tangent cuboid of the microseismic event and the tunnel axis is obtained.

2. According to claim 1, a TBM tunnel stripe identification method based on DBSCAN clustering algorithm is characterized in that: In step S1, the microseismic event screening space range is selected to include: The screening space range in front and behind the heading, the screening space range on the left and right sides perpendicular to the tunnel axis, and the screening space range above and below perpendicular to the tunnel axis.

3. The TBM tunnel stripe identification method based on DBSCAN clustering algorithm according to claim 1 is characterized in that: Step S2 specifically includes: According to the microseismic event coordinates obtained in step S1, assume that A1, A2, ...A n represents the coordinates of a certain direction of the microseismic event, [A1, A2, ...A n ] is a 1×n observation matrix, and the coordinate mean of the microseismic event is calculated using the following formula: Where M represents the mean coordinate of one direction of the microseismic event, and n represents the number of microseismic events.

4. The TBM tunnel stripe identification method based on DBSCAN clustering algorithm according to claim 1 is characterized in that: Step S3 specifically includes: S31, according to the microseismic event coordinates obtained in step S1, calculate the average deviation form matrix of the microseismic event coordinates, and the calculation formula is as follows: Among them, A k represents one direction coordinate of each microseismic event, M represents the mean value of one direction coordinate of the microseismic event, represents the amount of deviation from the coordinate mean, B represents the mean deviation form matrix, and n represents the number of microseismic events; S32, using singular value decomposition to obtain the principal axis, decomposing the singular value of the average deviation form matrix B into: B=UΣV T From the mean deviation form matrix B, we can get B T B and BB T , and further get B T B and BB T The eigenvalues ​​and eigenvectors of , where U is a left singular vector, U = {U1 U2 ... U n },U1 U2 ... U n For BB T The characteristic vector of T is the right singular vector, V T = {V T1 V T2 … V Tn },V T1 V T2 … V Tn For B T The eigenvector of B; Σ is the singular value matrix, λ i is the matrix composed of eigenvalues; S33, calculate the average deviation form matrix B in V T The projection B′ on the XOY space is transformed into B′ by the following formula:

5. The TBM tunnel stripe identification method based on DBSCAN clustering algorithm according to claim 1 is characterized in that: Step S4 specifically includes: Calculate the length, width, and height of the minimum tangent cuboid using the following formula: L=max(a,b,c) W=mid(a,b,c) H=min(a,b,c) a=a max -a min b=b max -b min c=c max -c min Among them, L, W, and H are the length, width, and height of the minimum tangent cuboid respectively; a, b, and c are the lengths of the principal axes of the minimum tangent cuboid respectively; a max and a min , b max and b min 、c max and c min They are the maximum and minimum coordinates of each principal axis of the minimum tangent cuboid respectively.

6. The TBM tunnel stripe identification method based on DBSCAN clustering algorithm according to claim 1 is characterized in that: Step S5 specifically includes: Calculate the aspect ratio and width ratio of the minimum tangent cuboid using the following formula: Wherein, A represents the aspect ratio of the minimum tangent cuboid, and B represents the aspect ratio of the minimum tangent cuboid.

7. The TBM tunnel stripe identification method based on DBSCAN clustering algorithm according to claim 1 is characterized in that: Step S6 specifically includes: S61, comparing the length-to-height ratio and the width-to-height ratio of the minimum tangent cuboid obtained by clustering the microseismic events of the existing stripes and the non-existing stripes in the excavated and exposed tunnel section, and establishing a threshold for whether the stripes exist; S62, a comprehensive discrimination method, after obtaining microseismic information, compares the length-to-height ratio and the width-to-height ratio of the minimum tangent cuboid obtained after clustering the microseismic events with the established threshold value. If the length-to-height ratio and the width-to-height ratio of the minimum tangent cuboid reach the threshold value, it is predicted that a strip exists in the area, otherwise, it is predicted that no strip exists in the area.

8. The method for identifying TBM tunnel stripes based on DBSCAN clustering algorithm according to claim 1, characterized in that: Step S7 specifically includes: S71. Establishing a threshold value for the average value of the length-to-height ratio and the aspect-to-height ratio of the weak strip and the hard strip according to the length-to-height ratio and the aspect-to-height ratio of the minimum tangent cuboid; S72. If the average of the aspect ratio and the width ratio reaches a threshold, it is a hard strip; if the average of the aspect ratio and the width ratio does not reach the threshold, it is a weak strip.

9. The method for identifying TBM tunnel stripes based on DBSCAN clustering algorithm according to claim 1, characterized in that: Step S8 specifically includes: S81, according to the original coordinate B transformed into B' rotation matrix V T , obtain the angle between the direction vector of each axis of the minimum tangent cuboid and the original XOY coordinate system, and then select the angle between the strip distribution direction of the minimum tangent cuboid and the original X-axis, that is, the angle between the strip direction and the tunnel axis determined by the minimum tangent cuboid of the microseismic event; S82. Calculate the angle between the direction vector of each axis of the minimum tangent cuboid and the original XOY coordinate system. The calculation formula is as follows: θ = arccos -1 V Tk ,k=1,2,…,n Among them, θ represents the angle between the direction vector of each axis of the minimum tangent cuboid and the original XOY coordinate system, V Tk Represents the corresponding element in the rotation matrix that transforms the original coordinate B to B′.

Images