Intelligent warning method and system for face risk based on infrared temperature variance

Abstract

The present application relates to the technical field of tunnel face risk intelligent early warning, in particular to a face risk intelligent early warning method and system based on infrared temperature variance, which comprises the following steps: calculating a first difference value between a current infrared temperature variance and an initial infrared temperature variance of each grid area; if the first difference value exceeds a first set threshold, calculating a second difference value between a current average infrared temperature and an initial average infrared temperature of each grid area, if the second difference value exceeds a set threshold, indicating that the current grid area is a breakage risk area, otherwise indicating that the current grid area is a water inrush risk area; determining a breakage risk surface and a water inrush risk surface; according to the intersection of the breakage risk surface, the water inrush risk surface and the unexcavated face, confirming a breakage risk area and a water inrush risk area of the unexcavated face. The abnormal change of the face surface temperature is represented by the infrared temperature variance, so as to analyze the possible risk of the face.

Description

Technical Field

[0001] This invention relates to the field of intelligent early warning technology for tunnel face risks, and in particular to an intelligent early warning method and system for tunnel face risks based on infrared temperature variance. Background Technology

[0002] In tunnel engineering, monitoring the stability of the tunnel face is crucial for construction safety. Early warning systems for tunnel face risks can promptly identify potential safety hazards during construction, allowing for timely preventative and mitigation measures. This helps avoid casualties, equipment damage, and project delays caused by geological disasters, thereby reducing economic losses and ensuring the safety of construction workers. Furthermore, it minimizes construction interruptions due to handling emergencies, improving construction efficiency.

[0003] During tunnel excavation, analyzing the risk conditions of a series of excavated tunnel faces can reveal the location of adverse geological bodies ahead of the tunnel face and the integrity of the surrounding rock structure, predict the likelihood of subsequent risks at the tunnel face, and provide a basis for the design of support parameters and the optimization of construction plans.

[0004] However, due to the harsh construction environment at the tunnel face, with high noise and dust levels, and the frequent operation of large machinery, traditional early warning and monitoring systems are not suitable for the construction site of the tunnel face. They can only provide risk warnings for the current face and cannot intelligently predict the future risks based on the risks that have occurred at the already excavated faces during tunnel advancement. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a method and system for intelligent early warning of risks at the working face based on infrared temperature variance;

[0006] On the one hand, a method for intelligent early warning of tunnel face risks based on infrared temperature variance is provided, including:

[0007] Acquire infrared images of the tunnel face; preprocess the infrared images of the tunnel face; perform gridding on the preprocessed images of the tunnel face to obtain several grid regions; calculate the average infrared temperature and infrared temperature variance of each grid region;

[0008] Calculate the first difference between the current infrared temperature variance and the initial infrared temperature variance for each grid region; determine whether the first difference exceeds a first set threshold; if so, calculate the second difference between the current average infrared temperature and the initial average infrared temperature for each grid region; determine whether the second difference exceeds a second set threshold; if it exceeds, it indicates that the current grid region is a rupture risk region; if it does not exceed, it indicates that the current grid region is a water inrush risk region.

[0009] During tunnel construction, the rupture risk areas and water inrush risk areas at different tunnel faces were recorded, resulting in sequences of rupture risk areas and water inrush risk areas. Spatial surface fitting was performed on both sequences to obtain rupture risk surfaces and water inrush risk surfaces. The rupture risk areas of the unexcavated tunnel faces were identified based on the intersection of the rupture risk surfaces with the unexcavated tunnel faces. Similarly, the water inrush risk areas of the unexcavated tunnel faces were identified based on the intersection of the water inrush risk surfaces with the unexcavated tunnel faces.

[0010] On the other hand, an intelligent early warning system for tunnel face risks based on infrared temperature variance is provided, including:

[0011] The preprocessing module is configured to: acquire infrared images of the working face; preprocess the infrared images of the working face; perform gridding on the preprocessed working face images to obtain several grid regions; and calculate the average infrared temperature and infrared temperature variance of each grid region.

[0012] The calculation module is configured to: calculate a first difference between the current infrared temperature variance and the initial infrared temperature variance of each grid region; determine whether the first difference exceeds a first set threshold; if so, calculate a second difference between the current average infrared temperature and the initial average infrared temperature of each grid region; determine whether the second difference exceeds a second set threshold; if so, it indicates that the current grid region is a rupture risk region; if not, it indicates that the current grid region is a water inrush risk region.

[0013] The output module is configured to: record the rupture risk areas and water inrush risk areas at different tunnel faces during tunnel construction, obtaining a sequence of rupture risk areas and a sequence of water inrush risk areas at the tunnel faces; obtain rupture risk surfaces and water inrush risk surfaces by performing spatial surface fitting on the two sequences respectively; confirm the rupture risk areas of the unexcavated tunnel faces based on the intersection of the rupture risk surfaces and the unexcavated tunnel faces; and confirm the water inrush risk areas of the unexcavated tunnel faces based on the intersection of the water inrush risk surfaces and the unexcavated tunnel faces.

[0014] The above technical solution has the following advantages or beneficial effects:

[0015] Rock fracturing involves the accumulation and release of energy, especially when the rock breaks, releasing a large amount of energy and causing the temperature of the rock mass ahead to rise. However, before a water inrush occurs at the tunnel face, the rock mass ahead of the water source will cool down. Infrared thermal imaging technology is used to capture the infrared temperature information of the tunnel face surface, and the infrared temperature variance is used to represent abnormal changes in the surface temperature, thereby analyzing potential risks at the tunnel face. Simultaneously, risks occurring on the excavated tunnel face are recorded, and risks on the unexcavated tunnel face are predicted using three-dimensional fitting. Attached Figure Description

[0016] 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.

[0017] Figure 1 This is a flowchart of the method in Example 1.

[0018] Figure 2 This is a schematic diagram illustrating how the working face is divided into several regions of the same size, as shown in Example 1.

[0019] Figure 3 This is a schematic diagram of the fitting results of the fracture risk surface in Example 1.

[0020] Figure 4 This is a schematic diagram of the fracture risk area at the unexcavated working face in Example 1.

[0021] Figure 5 This is a schematic diagram of the fitting results for the water inrush risk surface in Example 1.

[0022] Figure 6 This is a schematic diagram of the water inrush risk area at the unexcavated working face in Example 1. Detailed Implementation

[0023] It should be noted that the following detailed descriptions are exemplary and intended to provide further illustration of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0024] Example 1, as Figure 1 As shown, this embodiment provides an intelligent early warning method for tunnel face risks based on infrared temperature variance, including:

[0025] S101: Acquire infrared images of the working face; preprocess the infrared images of the working face; perform gridding on the preprocessed working face images to obtain several grid regions; calculate the average infrared temperature and infrared temperature variance of each grid region;

[0026] S102: Calculate the first difference between the current infrared temperature variance and the initial infrared temperature variance of each grid region; determine whether the first difference exceeds the first set threshold; if so, calculate the second difference between the current average infrared temperature and the initial average infrared temperature of each grid region; determine whether the second difference exceeds the second set threshold; if it exceeds the threshold, it indicates that the current grid region is a rupture risk area; if it does not exceed the threshold, it indicates that the current grid region is a water inrush risk area.

[0027] S103: Record the rupture risk areas and water inrush risk areas at different tunnel faces during tunnel construction to obtain the rupture risk area sequence and the water inrush risk area sequence; obtain the rupture risk surface and the water inrush risk surface by performing spatial surface fitting on the two sequences respectively; confirm the rupture risk area of ​​the unexcavated tunnel face based on the intersection of the rupture risk surface and the unexcavated tunnel face; confirm the water inrush risk area of ​​the unexcavated tunnel face based on the intersection of the water inrush risk surface and the unexcavated tunnel face.

[0028] Further, step S101: acquiring an infrared image of the working face includes:

[0029] An infrared camera is installed at a set distance from the working face to monitor the working face, and an infrared image of the working face is collected at set intervals.

[0030] For example, an infrared camera is fixed at a certain distance from the working face to continuously monitor the working face and store a thermal image every 0.1 seconds.

[0031] Further, step S101: preprocessing the infrared image of the working face, including:

[0032] For the infrared image of the tunnel face, delete the top area, bottom area, and sides of the tunnel, and only keep the arched area of ​​the tunnel face.

[0033] For example, the tunnel face area is delineated based on the engineering design and on-site measurement results. The top, bottom and sides of the tunnel in the image are removed, and only the arched area of ​​the tunnel face is retained.

[0034] Further, in step S101: the preprocessed face image is meshed to obtain several mesh regions; the size of each mesh region is 0.5m × 0.5m.

[0035] Meanwhile, a rectangular coordinate system is established on the preprocessed face image, with the bottom edge of the face as the X-axis, the center point of the bottom edge of the face as the origin, and the line perpendicular to the X-axis as the Y-axis.

[0036] For example, such as Figure 2 As shown, the infrared image is standardized, and the tunnel face is divided into several regions of the same size, with each region measuring 0.5m × 0.5m. Regions whose edges intersect with only a portion of the tunnel face are considered as one region. The origin is taken as the midpoint of the bottom edge of the tunnel face, and each region is represented by coordinates, such as region A(1, 1).

[0037] Further, S101: Calculating the average infrared temperature and infrared temperature variance of each grid region includes:

[0038] When infrared monitoring begins, the average infrared temperature and infrared temperature variance obtained will be set as initial values.

[0039] The temperature of region A(1,1) consists of the pixels within its range and the temperature values ​​of those pixels, and can be represented by the following temperature matrix:

[0040]

[0041] Among them, T(L y ,L x ) indicates that it is located at coordinate (L) x L y The temperature value of the pixel at ().

[0042] Calculate the average infrared temperature AT of the grid region A(1,1):

[0043]

[0044] The infrared temperature variance TV of the grid region A(1,1) is obtained as follows:

[0045]

[0046] Further, S102: Calculating the first difference between the current infrared temperature variance and the initial infrared temperature variance for each grid region includes:

[0047] An infrared temperature variance threshold is set. When the increase in the infrared temperature variance of a certain area relative to the initial variance value, ΔTV, exceeds the threshold θ, an early warning is issued.

[0048] ΔTV=TV t -TV0;

[0049] Among them, TV t Let t be the infrared temperature contrast of the region, and TV0 be the initial infrared temperature variance at the start of monitoring.

[0050] Further, S102: Calculate the second difference between the current average infrared temperature and the initial average infrared temperature of each grid region, and determine whether the second difference exceeds a second preset threshold. If it exceeds, the current grid region is a rupture risk region; if it does not exceed, the current grid region is a water inrush risk region. This includes:

[0051] When the infrared temperature variance of a certain grid area exceeds the threshold θ, it indicates that the temperature in that area has changed significantly. Further comparison is made between the current average infrared temperature in the current grid area and the initial average infrared temperature to determine whether the current grid area is a rupture risk area or a water inrush risk area, thereby realizing real-time monitoring of the current face anomaly. When ΔAT is greater than 0, the area is marked as having a rupture risk; when ΔAT is less than 0, the area is marked as having a water inrush risk.

[0052] ΔAT=AT t -AT0;

[0053] Among them, AT t Let t be the average infrared temperature of the region at time t, and AT0 be the initial average infrared temperature variance when monitoring begins.

[0054] Further, S103: Recording the rupture risk areas and water inrush risk areas at different tunnel faces during tunnel construction, obtaining a sequence of rupture risk areas and a sequence of water inrush risk areas at the tunnel faces, including:

[0055] Record the coordinates (x, y) of the areas where ruptures and water seepage occur at different tunnel faces during tunnel advancement, forming a sequence of tunnel face rupture risk areas (x, y). i ,y i ,S i ) and the sequence of areas at risk of sudden flooding (x j ,y j ,S j ).

[0056] Further, in S103: by performing spatial surface fitting on the two sequences respectively, the rupture risk surface and the water inrush risk surface are obtained. The fitting process of the rupture risk surface is as follows:

[0057] The three-dimensional surface of the fracture risk surface can be expressed by the following formula:

[0058] S = ax 2 +by 2 +cxy+dx+ey+f;

[0059] Where a, b, c, d, e, and f are undetermined coefficients;

[0060] For a known number of fracture risk points (x) on the working face i ,y i ,S i The error function is:

[0061]

[0062] To find the coefficients a, b, c, d, e, and f that minimize the error function, we take the partial derivative of each coefficient and set it to zero, which yields the system of linear equations:

[0063]

[0064] A series of known fracture risk points (x) on the working face. i ,y i ,S i Input the values ​​and obtain the undetermined coefficients a, b, c, d, e, and f, thus forming the rupture risk surface.

[0065] like Figure 3 and Figure 5 As shown, the fitting process for the rupture risk surface and the water inrush risk surface is the same, the difference being that the input sequences are different; the input sequence for the fitting process of the water inrush risk surface is the water inrush risk region sequence.

[0066] Further, S103: Based on the intersection of the rupture risk surface and the unexcavated working face, the rupture risk area of ​​the unexcavated working face is identified; based on the intersection of the water inrush risk surface and the unexcavated working face, the water inrush risk area of ​​the unexcavated working face is identified, including:

[0067] The area where the fracture risk surface intersects with the unexcavated face is defined as the fracture risk zone of the unexcavated face; the fracture risk zone of the unexcavated face, such as... Figure 4 As shown;

[0068] The area where the water inrush risk face intersects with the uncracked working face is defined as the water inrush risk zone of the uncracked working face. The water inrush risk zone of the uncracked working face, such as... Figure 6 As shown.

[0069] The rupture and water inrush situation in the working face can be predicted based on the intersection of the unexcavated working face with the rupture risk face and the water inrush risk face.

[0070] Based on the fracture and water inrush risks of the first six excavated working faces, fracture risk surfaces and water inrush risk surfaces are fitted. Based on the intersection of the two fitted surfaces with the unexcavated working faces, the fracture and water inrush risk areas on the seventh unexcavated working face can be predicted.

[0071] Based on the fracturing and water outflow situation after the excavation of the seventh working face, the fracturing risk area sequence and water inrush risk area sequence data can be supplemented, and the fracturing and water inrush risk areas of the next working face to be excavated can be further predicted.

[0072] The deep integration of infrared thermal imaging technology and spatial fitting methods not only enables real-time early warning of current tunnel face risks but also allows for intelligent prediction of potential risks at the next tunnel face based on historical data. Infrared thermal imaging, as a non-contact monitoring technology, possesses good penetration and wide-area real-time monitoring capabilities. Infrared cameras can acquire real-time, continuous, and high-resolution infrared temperature information of the tunnel face; infrared temperature variance can sensitively capture abnormal temperature changes in various areas of the tunnel face, allowing for comparison of temperature rises and falls to determine the type of risk; and a three-dimensional spatial fitting algorithm enables intelligent prediction of tunnel face risks, presenting historical risk warning information in a three-dimensional format, intuitively and vividly displaying the risk changes at the tunnel face, and accurately identifying the location, scale, and type of risks. Together, these technologies contribute to intelligent early warning of current and future risks at the tunnel face.

[0073] Example 2

[0074] This embodiment provides an intelligent early warning system for tunnel face risks based on infrared temperature variance, including:

[0075] The preprocessing module is configured to: acquire infrared images of the working face; preprocess the infrared images of the working face; perform gridding on the preprocessed working face images to obtain several grid regions; and calculate the average infrared temperature and infrared temperature variance of each grid region.

[0076] The calculation module is configured to: calculate a first difference between the current infrared temperature variance and the initial infrared temperature variance of each grid region; determine whether the first difference exceeds a first set threshold; if so, calculate a second difference between the current average infrared temperature and the initial average infrared temperature of each grid region; determine whether the second difference exceeds a second set threshold; if so, it indicates that the current grid region is a rupture risk region; if not, it indicates that the current grid region is a water inrush risk region.

[0077] The output module is configured to: record the rupture risk areas and water inrush risk areas at different tunnel faces during tunnel construction, obtaining a sequence of rupture risk areas and a sequence of water inrush risk areas at the tunnel faces; obtain rupture risk surfaces and water inrush risk surfaces by performing spatial surface fitting on the two sequences respectively; confirm the rupture risk areas of the unexcavated tunnel faces based on the intersection of the rupture risk surfaces and the unexcavated tunnel faces; and confirm the water inrush risk areas of the unexcavated tunnel faces based on the intersection of the water inrush risk surfaces and the unexcavated tunnel faces.

[0078] 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 face risk intelligent early warning method based on infrared temperature variance, characterized in that, The application relates to a tunnel construction risk area prediction method and device. The method comprises the following steps: acquiring an infrared image of a tunnel face; preprocessing the infrared image of the tunnel face; carrying out grid processing on the preprocessed tunnel face image to obtain a plurality of grid areas; calculating the average infrared temperature and infrared temperature variance of each grid area; calculating a first difference value between the current infrared temperature variance and the initial infrared temperature variance of each grid area; judging whether the first difference value exceeds a first set threshold value; if yes, calculating a second difference value between the current average infrared temperature and the initial average infrared temperature of each grid area; judging whether the second difference value exceeds a second set threshold value; if yes, indicating that the current grid area is a breakage risk area; if not, indicating that the current grid area is a water inrush risk area; recording the breakage risk areas and water inrush risk areas of different tunnel faces in the tunnel construction process to obtain a tunnel face breakage risk area sequence and a tunnel face water inrush risk area sequence; carrying out spatial curved surface fitting on the two sequences respectively to obtain a breakage risk surface and a water inrush risk surface; confirming the breakage risk areas of an unexcavated tunnel face according to the intersection of the breakage risk surface and the unexcavated tunnel face; confirming the water inrush risk areas of the unexcavated tunnel face according to the intersection of the water inrush risk surface and the unexcavated tunnel face; the fitting process of the breakage risk surface is as follows: ； wherein , , , , and are indeterminate coefficients; For several points of rupture risk on the known face The error function is: ； to find the coefficients that minimize the error function value , , , , and Taking the partial derivative of each coefficient and setting it to zero gives a system of linear equations: ； A series of points of fracture risk on a known face Input, to obtain the undetermined coefficients , , , , and , thereby forming a fracture risk surface.

2. The infrared temperature variance-based face risk intelligent early warning method according to claim 1, characterized in that, the three-dimensional spatial curved surface of the breakage risk surface is expressed by the following formula: the infrared image of the tunnel face is acquired, comprising the following steps: installing an infrared camera at a position with a set distance from the tunnel face; monitoring the tunnel face by using the infrared camera; and collecting the infrared image of the tunnel face every set time interval; the preprocessing of the infrared image of the tunnel face comprises the following steps:

3. The infrared temperature variance-based face risk intelligent early warning method according to claim 1, characterized in that, deleting the tunnel top area, the tunnel bottom area and the tunnel side areas in the infrared image of the tunnel face, and only keeping the arch-shaped area of the tunnel face. the average infrared temperature and the infrared temperature variance of each grid area are calculated, comprising the following steps: ； wherein, represents a temperature value of a pixel point located at coordinate ( L x , L y ) Computing the average infrared temperature of the grid region A (1,1) setting the average infrared temperature and the infrared temperature variance obtained when the infrared monitoring is started as initial values; the temperature of the region A (1, 1) is composed of the pixel points in the region and the temperature values of the pixel points, and is expressed by the following temperature matrix: : ； The infrared temperature variance of the grid area A (1,1) is obtained AT : 。 4. The infrared temperature variance-based face risk intelligent early warning method according to claim 3, characterized in that, TV An infrared temperature variance threshold is set, and when the infrared temperature variance of a certain region increases by a certain amount compared to the initial variance value When the threshold θ is exceeded, a warning is issued; ； wherein, is t the infrared temperature variance of the region at the moment, is the initial infrared temperature variance at the start of monitoring.

5. The infrared temperature variance-based face risk intelligent early warning method according to claim 3, characterized in that, the first difference value between the current infrared temperature variance and the initial infrared temperature variance of each grid area is calculated, comprising the following steps: When greater than 0, the area is marked as having a risk of fracture, when less than 0, the area is marked as having a risk of water inrush; ； wherein, is t the average infrared temperature of the area at the moment, is the initial average infrared temperature variance at the start of monitoring.

6. The infrared temperature variance-based face risk intelligent pre-warning method according to claim 1, characterized in that, the second difference value between the current average infrared temperature and the initial average infrared temperature of each grid area is calculated, and whether the second difference value exceeds a second set threshold value is judged; if yes, indicating that the current grid area is a breakage risk area; if not, indicating that the current grid area is a water inrush risk area, comprising the following steps: The coordinates of the areas where the different tunnel faces break and water emerges during the forward advance of the tunnel are recorded x , y ), forming a sequence of face breakage risk areas and a sequence of water inrush risk areas .

7. The infrared temperature variance-based face risk intelligent early warning method according to claim 1, characterized in that, the breakage risk areas and the water inrush risk areas of different tunnel faces in the tunnel construction process are recorded to obtain a tunnel face breakage risk area sequence and a tunnel face water inrush risk area sequence, comprising the following steps: the breakage risk areas of the unexcavated tunnel face are confirmed according to the intersection of the breakage risk surface and the unexcavated tunnel face; the water inrush risk areas of the unexcavated tunnel face are confirmed according to the intersection of the water inrush risk surface and the unexcavated tunnel face, comprising the following steps: The intersection region of the water inrush risk surface and the unexcavated tunnel face is taken as the water inrush risk region of the unexcavated tunnel face. The intersection region of the water inrush risk surface and the unexcavated tunnel face is taken as the water inrush risk region of the unexcavated tunnel face.

8. The infrared temperature variance-based face risk intelligent early warning method according to claim 7, characterized in that, The preprocessed tunnel face image is grid processed to obtain a plurality of grid regions; meanwhile, a rectangular coordinate system is established on the preprocessed tunnel face image, the bottom edge of the tunnel face is taken as the X axis, the center point of the bottom edge of the tunnel face is taken as the origin, and a line perpendicular to the X axis is taken as the Y axis.

9. The intelligent warning system of the face risk based on the infrared temperature variance, characterized in that, The preprocessed tunnel face image is grid processed to obtain a plurality of grid regions; meanwhile, a rectangular coordinate system is established on the preprocessed tunnel face image, the bottom edge of the tunnel face is taken as the X axis, the center point of the bottom edge of the tunnel face is taken as the origin, and a line perpendicular to the X axis is taken as the Y axis. The preprocessed tunnel face image is grid processed to obtain a plurality of grid regions; meanwhile, a rectangular coordinate system is established on the preprocessed tunnel face image, the bottom edge of the tunnel face is taken as the X axis, the center point of the bottom edge of the tunnel face is taken as the origin, and a line perpendicular to the X axis is taken as the Y axis. The preprocessed tunnel face image is grid processed to obtain a plurality of grid regions; meanwhile, a rectangular coordinate system is established on the preprocessed tunnel face image, the bottom edge of the tunnel face is taken as the X axis, the center point of the bottom edge of the tunnel face is taken as the origin, and a line perpendicular to the X axis is taken as the Y axis. The preprocessed tunnel face image is grid processed to obtain a plurality of grid regions; meanwhile, a rectangular coordinate system is established on the preprocessed tunnel face image, the bottom edge of the tunnel face is taken as the X axis, the center point of the bottom edge of the tunnel face is taken as the origin, and a line perpendicular to the X axis is taken as the Y axis. The preprocessed tunnel face image is grid processed to obtain a plurality of grid regions; meanwhile, a rectangular coordinate system is established on the preprocessed tunnel face image, the bottom edge of the tunnel face is taken as the X axis, the center point of the bottom edge of the tunnel face is taken as the origin, and a line perpendicular to the X axis is taken as the Y axis. The preprocessed tunnel face image is grid processed to obtain a plurality of grid regions; meanwhile, a rectangular coordinate system is established on the preprocessed tunnel face image, the bottom edge of the tunnel face is taken as the X axis, the center point of the bottom edge of the tunnel face is taken as the origin, and a line perpendicular to the X axis is taken as the Y axis. The preprocessed tunnel face image is grid processed to obtain a plurality of grid regions; meanwhile, a rectangular coordinate system is established on the preprocessed tunnel face image, the bottom edge of the tunnel face is taken as the X axis, the center point of the bottom edge of the tunnel face is taken as the origin, and a line perpendicular to the X axis is taken as the Y axis. The preprocessed tunnel face image is grid processed to obtain a plurality of grid regions; meanwhile, a rectangular coordinate system is established on the preprocessed tunnel face image, the bottom edge of the tunnel face is taken as the X axis, the center point of the bottom edge of the tunnel face is taken as the origin, and a line perpendicular to the X axis is taken as the Y axis. ​ ； wherein , , , , and are indeterminate coefficients; For several points of rupture risk on the known face The error function is: ； To find the coefficients that minimize the error function value , , , , and Take the partial derivative of each coefficient and set it to zero to get a system of linear equations: ； A series of points of fracture risk on a known face Input, to obtain the pending coefficients , , , , and , thereby forming a fracture risk surface.

Images