Water inrush risk assessment method and system based on while-drilling image and spectrum fusion

Abstract

The present invention belongs to the field of geological exploration technology, and specifically discloses a method and system for assessing the risk of sudden water inrush based on image while drilling and spectrum fusion, the method comprising: if water flows out during drilling, the risk range is identified, and the sudden water inrush hazard level is determined based on the risk range, the solubility of the surrounding rock, and the height difference between the groundwater level and the shaft and tunnel bottom plate; if no water flows out, the sudden water inrush hazard level of each position of the tunnel face is determined based on the solubility of the surrounding rock and the height difference between the groundwater level and the shaft and tunnel bottom plate; for each sudden water inrush hazard level area, the total number of cracks per unit area, the color abnormal area and the water content are obtained; based on the total number of cracks per unit area at different positions in each sudden water inrush hazard level area, whether the color is abnormal and the water content of the rock mass, the risk level of each position in each sudden water inrush hazard level area is further determined. The present invention can timely discover the risk of sudden water inrush, and give early warning, providing a basis for timely taking emergency measures.

Description

Technical Field

[0001] The present invention relates to the field of geological exploration technology, and in particular to a method and system for assessing water inrush risk based on while-drilling image and spectrum fusion. Background Art

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

[0003] Water inrush is an important factor that causes flooding, shutdown, machinery damage, casualties and economic losses during coal mine construction. The source of water inrush, its occurrence form in the geological bodies along the mines and its degree of disaster are jointly determined by multiple factors. With the continuous increase in the mining depth of mines, the complexity and variability of underground hydrogeological conditions make the occurrence of water inrush accidents difficult to predict, posing a serious threat to the safe construction of mines.

[0004] In the actual construction process, water inrush is somewhat sudden, and the lack of effective early warning and emergency response measures often further aggravates the severity of the accident. Therefore, how to effectively identify and assess the risk of water inrush under complex and changeable geological conditions has become a key issue that needs to be urgently solved in the field of coal mine shaft and tunnel engineering safety.

[0005] The existing methods for sudden water inrush risk assessment mainly include geological analysis method, hierarchical analysis method and attribute mathematical theory method. Among them, the geological analysis method mainly evaluates the hydrogeological conditions of mines and predicts the risk of sudden water inrush through geological surveys, data collection, lithological and structural analysis, risk assessment and monitoring feedback. The hierarchical analysis method decomposes the problem into multiple levels such as goals, criteria, and plans, constructs a judgment matrix through pairwise comparison, calculates weights, and performs consistency tests to finally derive the relative importance ranking of each plan or level. The attribute mathematical theory method describes and evaluates the risk of sudden water inrush by constructing mathematical models.

[0006] The above methods still have many limitations when dealing with sudden water risk assessment in complex situations. For example, the geological analysis method relies on the knowledge and experience of geological experts and usually focuses on qualitative description, which may lead to uncertainty in the assessment results. The hierarchical analysis method still relies on the subjective judgment of experts when constructing the judgment matrix and making pairwise comparisons, which is prone to misjudgment and omission. The attribute mathematics theory method describes and evaluates sudden water risks by constructing mathematical models, which may not be able to capture the real-time changes in geological conditions in a timely manner. There may be delays between the output of risk results from the model and the taking of actual measures. These problems have jointly led to the fact that the prevention and control effects of sudden water accidents are far from ideal. Summary of the invention

[0007] In order to solve the above problems, the present invention proposes a sudden water burst risk assessment method and system based on downhole image and spectrum fusion, which determines the risk range through the abnormal points of the borehole water discharge, propulsion force and torque curve, divides the sudden water burst hazard level according to the solubility of the surrounding rock, the risk range and the groundwater level, obtains the number of cracks, color abnormal area and water content data at each position in front of the face, and conducts sudden water burst risk assessment.

[0008] In some embodiments, the following technical solutions are adopted:

[0009] A method for sudden water inrush risk assessment based on while-drilling image and spectrum fusion, comprising:

[0010] Conduct multi-hole drilling on the tunnel face to be tested, analyze and determine the solubility of the surrounding rock, and record the abnormal points of drilling parameters and the corresponding drilling depth during the drilling process;

[0011] If water flows out during drilling, the risk range is identified, and the level of water inrush hazard is determined based on the risk range, the solubility of the surrounding rock, and the height difference between the groundwater level and the bottom plate of the shaft and tunnel. If no water flows out, the level of water inrush hazard at each location of the face is determined based on the solubility of the surrounding rock and the height difference between the groundwater level and the bottom plate of the shaft and tunnel.

[0012] For each water inrush hazard level area, obtain image information of the rock mass in the borehole in the area, process the image to obtain the number and distribution of cracks in the borehole, and obtain the total number of cracks per unit area; cluster the pixels in the image to determine the color abnormal area in the image; obtain the spectral information of the rock mass in the borehole in the area, and invert the water content of the rock mass based on the established spectral water content inversion model;

[0013] Based on the total number of cracks per unit area, whether the color is abnormal and the water content of the rock mass at different locations within each level of sudden water surge hazard area, the risk level of each location within each level of sudden water surge hazard area is further determined.

[0014] As a further approach, if water is leaking during drilling, identify the risk areas, specifically:

[0015] If water flows out during the drilling process, the location of the water outlet point is recorded, and holes are drilled evenly around the water outlet borehole until a water-free borehole is drilled; the horizontal and vertical boundaries of the risk range in the plane direction of the face are determined based on the locations of the water-free boreholes around the water outlet borehole; the depth boundary in the depth direction of the face is determined based on the two drilling parameter anomaly points corresponding to each borehole; and a three-dimensional view of the risk range is formed.

[0016] As a further solution, image information of the rock mass in the borehole is obtained, and the image is processed to obtain the number and distribution of cracks in the borehole, specifically:

[0017] Identify the edge information in the image through edge detection algorithm; remove noise and impurities in the image to highlight the crack features; apply Hough transform to convert the edge information in the image into parameter space, so as to identify the shape of the crack;

[0018] By setting the threshold, the image is divided into foreground and background. The foreground corresponds to the cracks, and the background corresponds to other geological features. A high-pass filter is used to highlight the edges of the cracks in the foreground image, and a low-pass filter is used to remove noise and impurities in the foreground image to make the crack features clearer. Thus, the number and distribution of cracks in the borehole can be obtained.

[0019] As a further solution, the color abnormal area in the image is determined by clustering the pixels in the image, specifically:

[0020] Convert pixels from RGB to HSV or Lab color space through color space conversion;

[0021] The clustering algorithm is applied to classify the pixels in the image, and the areas with large color differences from other clusters in the clustering results are regarded as color abnormal areas, and the location and size of the color abnormal areas are recorded.

[0022] As a further solution, the spectral water content inversion model is specifically:

[0023] Through indoor experiments, the absorption peak intensity characteristic data of the spectrum under different water contents were obtained, the relationship between the water content and the absorption peak intensity characteristics of the spectrum was fitted, and the spectral water content inversion model was obtained.

[0024] As a further solution, the total number of cracks per unit area, whether the color is abnormal, and the water content of the rock mass at different locations in each sudden water hazard level area are obtained by interpolating the known data; the specific process is as follows:

[0025] For a known data point A ( x ki , y ki ) and B ( x kj , y kj ), calculate the distance between data points A and B h , and calculate the square of the numerical difference between data points A and B, that is, ( y ki - y kj ) 2 ; y ki Represents the total number of cracks per unit area, color anomalies after numerical processing, or water content data of rock mass;

[0026] For all pairs of data points with a distance h, the squares of the differences in the values ​​of the data points are averaged to obtain the semivariance γ ( h );

[0027] All the semivariances obtained γ ( h ) are connected into a line in the set order to obtain the variation function curve;

[0028] According to the shape of the variogram curve, select the appropriate Kriging model and determine the parameters of the model;

[0029] Based on the Kriging model, the weight coefficient of each data point for the target position is calculated, the value of each known data point is multiplied by its weight coefficient, and then summed to obtain the interpolation result of the target position; then the total number of cracks per unit area, color anomalies or water content data information of the rock mass are obtained at each location point.

[0030] As a further solution, based on the total number of cracks per unit area, abnormal color and water content of the rock mass at different locations in each sudden water hazard level area, the risk level of each location in each sudden water hazard level area is further determined, specifically:

[0031] If the total number of cracks per unit area and the water content of the rock mass at a certain location point exceed the set threshold and it is an abnormal color area, then the location point is delineated as a high-risk area;

[0032] If the total number of cracks per unit area and the water content of the rock mass at a certain location point both exceed the set thresholds, but it is not a color abnormality area; or if a certain location point is a color abnormality area and one of the total number of cracks per unit area and the water content of the rock mass exceeds the set threshold, then the location point is considered to belong to the medium risk area;

[0033] If the total number of cracks per unit area and the water content of the rock mass at a certain location point do not exceed the set threshold, and the location point is an abnormal color area or a normal color area; or if one of the total number of cracks per unit area and the water content of the rock mass at a certain location point exceeds the set threshold, and the location point is a normal color area, then the area is considered to be a low-risk area.

[0034] In other embodiments, the following technical solutions are adopted:

[0035] A water inrush risk assessment system based on drilling image and spectrum fusion, comprising:

[0036] The drilling parameter acquisition module is used to perform multi-hole drilling on the tunnel face to be tested, analyze and determine the solubility of the surrounding rock, and record the abnormal points of drilling parameters and the corresponding drilling depth during the drilling process;

[0037] The water inrush hazard level determination module is used to identify the risk range if water flows out during drilling, and determine the water inrush hazard level based on the risk range, the solubility of the surrounding rock, and the height difference between the groundwater level and the bottom plate of the shaft and tunnel; if no water flows out, the water inrush hazard level at each position of the tunnel face is determined based on the solubility of the surrounding rock and the height difference between the groundwater level and the bottom plate of the shaft and tunnel;

[0038] The processing module is used to obtain the image information of the rock mass in the regional borehole for each sudden water hazard level area, process the image to obtain the number and distribution of cracks in the borehole, and obtain the total number of cracks per unit area; determine the color abnormal area in the image by clustering the pixels in the image; obtain the spectral information of the rock mass in the regional borehole, and invert the water content of the rock mass based on the established spectral water content inversion model;

[0039] The risk level determination module is used to further determine the risk level of each location in each sudden water hazard level area based on the total number of cracks per unit area, whether the color is abnormal, and the water content of the rock mass at different locations in each sudden water hazard level area.

[0040] In other embodiments, the following technical solutions are adopted:

[0041] A terminal device comprises a processor and a memory, wherein the processor is used to implement instructions; and the memory is used to store a plurality of instructions, wherein the instructions are suitable for being loaded by the processor and executing the above-mentioned sudden water inrush risk assessment method based on while-drilling image and spectrum fusion.

[0042] In other embodiments, the following technical solutions are adopted:

[0043] A computer-readable storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor of a terminal device and executing the above-mentioned sudden water inrush risk assessment method based on while-drilling image and spectrum fusion.

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] (1) The present invention locates the positions of waterless boreholes around water-containing boreholes through multi-hole drilling, and draws a three-dimensional image of the risk area in combination with the abnormal conditions of the propulsion force and torque curves during the drilling process. The position and size of the sudden water risk range can be quickly identified and located, and the hazard level is divided according to the solubility of the surrounding rock and the groundwater level. The risk is then identified by combining the image and spectral information of the rock mass in the borehole, thereby achieving an accurate assessment of the sudden water risk and improving the safety of coal mine shaft and tunnel construction.

[0046] (2) The present invention can timely obtain the number of cracks per unit area, color anomalies, and water content of the rock mass in the borehole by real-time collection and analysis of the spectrum and image information of the rock mass in the borehole. The collected values ​​of different gradients are interpolated to obtain data information of each position in front of the face, and the risk of sudden water inrush can be discovered in time, and an early warning can be issued, providing a basis for timely taking emergency measures.

[0047] (3) The present invention can identify the hazard level of sudden water inrush by surveying the groundwater level and conducting solubility analysis of the surrounding rock and determining the risk range during the drilling process. It can further combine the rock mass image and spectral information analysis in the borehole to make a comprehensive judgment on the sudden water inrush risk within the corresponding level based on multiple factors, overcoming the limitations of single methods such as traditional geological analysis, hierarchical analysis method and attribute mathematical theory method, improving the accuracy and reliability of risk assessment, and realizing real-time monitoring and accurate assessment of the sudden water inrush risk during shaft and tunnel construction.

[0048] Other features and advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 This is a flow chart of a method for assessing water inrush risk based on while-drilling image and spectrum fusion in an embodiment of the present invention;

[0050] Figure 2 A schematic diagram of determining the horizontal and vertical boundaries of a risk range in an embodiment of the present invention;

[0051] Figure 3 A schematic diagram of determining the vertical boundary of a risk range in an embodiment of the present invention;

[0052] Figure 4 Schematic diagram of water inrush risk identification at various hazard levels in an embodiment of the present invention. DETAILED DESCRIPTION

[0053] It should be noted that the following detailed descriptions are illustrative and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used in the present invention have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.

[0054] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0055] Embodiment 1

[0056] In one or more embodiments, a method for assessing water inrush risk based on while-drilling image and spectral fusion is disclosed. Figure 1 , specifically including the following process:

[0057] S101: Multi-hole drilling is performed on the face of the well tunnel to be tested, the solubility of the surrounding rock is analyzed and determined, and the abnormal points of drilling parameters and the corresponding drilling depth during the drilling process are recorded.

[0058] Specifically, this embodiment conducts groundwater level survey on the entire mining area, obtains the specific situation of groundwater level in the mining area, conducts multi-hole drilling on the face in the shaft and tunnel, and collects the rock slag generated during the drilling process. The collected rock slag is subjected to lithological analysis, including observing the appearance, color, texture, hardness and other characteristics of the rock slag, as well as conducting necessary chemical composition analysis and surrounding rock solubility analysis; the solubility of the surrounding rock is determined by analysis, and the solubility of the surrounding rock is divided into non-soluble rock layers, weakly soluble rock layers, moderately soluble rock layers and strongly soluble rock layers according to actual needs and set standards; for example: rocks containing more soluble minerals, such as limestone, dolomite, etc., have strong solubility.

[0059] During the drilling process, the propulsion force and torque of the drilling are recorded in real time, the propulsion force curve and torque curve are obtained, and the abnormal conditions of the curves are observed. Abnormal fluctuations in the propulsion force or torque curve, such as sudden drops or rises, may be a signal of changes in the geological conditions ahead. If the curve suddenly drops, it may indicate that softer rocks or geological structures such as caves and cracks are encountered ahead; if the curve suddenly rises, it means that the geological structure ahead has hardened, indicating that the rock mass is in good condition. Mark the abnormal points and record their corresponding drilling depths for subsequent geological analysis and risk assessment.

[0060] S102: If water flows out during drilling, the risk range is identified, and the hazard level of sudden water inrush is determined based on the risk range, the solubility of the surrounding rock, and the height difference between the groundwater level and the bottom slab of the shaft and tunnel; if no water flows out, the hazard level of sudden water inrush is determined based on the solubility of the surrounding rock and the height difference between the groundwater level and the bottom slab of the shaft and tunnel.

[0061] In this embodiment, during the drilling process, the water output of the borehole is judged: closely observe whether water flows directly out of the borehole. If water is directly pumped out during the drilling process, this may indicate the existence of groundwater or karst channels; at this time, the location and situation of the water output point are recorded, and drilling is carried out around the water output borehole. The distribution of the boreholes forms a grid or semicircular array, which is evenly distributed outward around the water output borehole.

[0062] After the drilling operation begins, record the drilling parameters of each borehole, including the thrust and torque, and observe whether there is water flowing out. If there is water, continue drilling toward the periphery; until a waterless borehole is drilled, it means that the aquifer has been exceeded. Record the location and drilling parameters of each borehole (water-producing borehole + water-free borehole) in detail; based on the location data of the water-producing borehole and the surrounding water-free boreholes, the horizontal and vertical boundaries of the risk range in the plane direction of the face can be drawn through the connection lines of the water-free boreholes drilled around the water-producing boreholes, such as Figure 2 As shown in the figure, the drilling parameters of the water-producing borehole can be analyzed to obtain the longitudinal boundary of the risk range in the depth direction of the face by connecting the boundary points of each borehole risk range. Specifically, each borehole corresponds to two abnormal drilling parameter points. For example, during the drilling process, when the hard rock is drilled into the cave, the force of drilling into the cave will suddenly drop, because it does not take much force to drill into the cave. The drilling force and torque curves will suddenly drop. This is the abnormal drilling parameter point 1, which corresponds to the front boundary of the cave. When the back boundary of the cave is reached, the rock will drop. The experience will become hard, the force of driving in will increase, and the drilling force and torque curve will suddenly rise. This is the drilling parameter abnormal point 2, which corresponds to the rear boundary of the cave; the area between the drilling parameter abnormal point 1 and the drilling parameter abnormal point 2 is the longitudinal range of the risk range corresponding to the borehole (that is, the front boundary and the rear boundary locate the location of the cave and the range along the drilling direction). The line connecting the drilling parameter abnormal point 1 is the front boundary of the risk range that is closer to the face, and the line connecting the drilling parameter abnormal point 2 is the rear boundary of the risk range that is farther from the face. Figure 3 As shown, a three-dimensional view of the risk range can be further drawn, and the risk range can be preliminarily determined. Then, the hazard level can be identified based on the solubility of the surrounding rock, the risk range and the groundwater level obtained from the survey.

[0063] In this embodiment, the groundwater level is obtained through geological survey, and the radial bottom plate height can be obtained according to the design documents, and then the height difference between the groundwater level and the shaft bottom plate can be calculated.

[0064] In this embodiment, the risk range is divided into a small risk range, a medium risk range, a large risk range, a non-risk range, etc. according to the size of the risk range and the set standard.

[0065] If no water flows out, the hazard level will be determined based on the solubility of the surrounding rock and the groundwater level.

[0066] The specific determination method is shown in Table 1. The hazard level is an important indicator for assessing the risk of sudden water inrush, which is used to formulate targeted safety measures and optimize construction plans to reduce the possibility of sudden water inrush accidents and ensure the safety of coal mine shaft and tunnel construction.

[0067] Table 1 Identification of water inrush hazard levels

[0068]

[0069] It should be noted that if there is water outflow, the hazard level should be comprehensively judged based on the three factors of risk range, solubility of surrounding rock and height difference between groundwater level and shaft bottom plate, combined with Table 1; if there is no water outflow, the hazard level should be comprehensively judged based on the two factors of solubility of surrounding rock and height difference between groundwater level and shaft bottom plate, combined with Table 1.

[0070] When various factors meet different classification conditions, they are classified according to the most serious danger level, and finally determined as the highest level classification of each factor; for example: there is a small risk range above the bottom plate near the shaft (corresponding to the medium danger level), but it is in a strong soluble rock layer (corresponding to the extremely high danger level), and the height difference between the groundwater level and the bottom plate of the shaft is greater than 30m and less than 60m (corresponding to the high danger level). If different danger classification levels are met, they are classified according to the most serious danger level, and the danger level is therefore classified as extremely high.

[0071] S103: The risk level within each water inrush hazard level area is further subdivided below.

[0072] For each water inrush hazard level area, image information of the rock mass in the borehole in the area is obtained, and the image is processed to obtain the number and distribution of cracks in the borehole; by clustering the pixels in the image, the color abnormality area in the image is determined.

[0073] In this embodiment, the image information of the rock mass in the borehole is obtained. Ideally, all boreholes are detected. If all boreholes cannot be detected, the more boreholes detected, the better. The more reference points there are during interpolation, the more accurate the interpolated value. The same is true for obtaining the spectral information of the rock mass in the borehole in step S104.

[0074] In this embodiment, a camera is used to obtain image information of the rock mass in the borehole. The obtained information needs to be further preprocessed by applying image processing technology, including:

[0075] S1031: Use edge detection algorithm to identify edge information in the image; in rock mass images, edge information can reflect changes in rock surface texture, such as cracks, faults, joints and other geological structures. Therefore, edge information can serve as an important clue to identify cracks;

[0076] S1032: Apply morphological operations such as dilation and erosion to remove noise and impurities in the image and highlight the crack features; apply Hough transform to convert edge information in the image into parameter space to identify cracks with specific shapes (such as straight lines, circles, etc.);

[0077] S1033: Set the threshold to segment the image into foreground (cracks) and background (other geological features, such as bedding or mineral grains). The threshold can be adjusted based on factors such as the image's grayscale distribution and noise level. Apply a high-pass filter to highlight the edges of cracks in the image, and apply a low-pass filter to remove noise and impurities in the image to make the crack features clearer.

[0078] In this embodiment, both the high-pass filter and the low-pass filter process the foreground (cracks) of the image. Among them, the high-pass filter is used to highlight the edges of the cracks in the image. After the image is divided into the foreground and the background, the high-pass filter can enhance the contrast of the crack edges to make them clearer, which is convenient for subsequent crack identification and counting. The low-pass filter can smooth the image, remove noise and impurities, thereby improving the image quality and avoiding interference with subsequent analysis. The high-pass filter highlights the crack edges, and the low-pass filter removes noise. The two work together to make the crack features clearer, thereby improving the accuracy of crack identification and counting.

[0079] S1034: Use an image segmentation algorithm to separate the cracks from the background, and calculate the total number and distribution of cracks per unit area.

[0080] In addition, in this embodiment, the color abnormal area is also identified, specifically:

[0081] Color space conversion (for example, from RGB to HSV or Lab color space) is used to enhance color contrast and more effectively identify color anomalies. A clustering algorithm is applied to classify pixels in the image. First, the appropriate number of clusters is determined based on experience or prior knowledge. The initial cluster center is calculated using random initialization or the K-means++ algorithm. The distance from each pixel to the cluster center is then calculated. The pixel is assigned to the nearest cluster center and the position of the cluster center is updated. Repeated iterations are performed until the position of the cluster center no longer changes or the maximum number of iterations is reached. The area with a large color difference from other clusters in the clustering results is regarded as a color anomaly area. After the color anomaly area is identified, the position and size of the color anomaly area of ​​the rock mass in the borehole are recorded.

[0082] S104: For each water inrush hazard level area, spectral information of the rock mass in the borehole is obtained, and the water content of the rock mass is inverted based on the established rock spectral water content inversion model.

[0083] The specific spectral water content inversion model is:

[0084] Through indoor experiments, the spectral data of rocks under different water contents are obtained, and preprocessing operations such as noise removal and spectral drift correction are performed; the spectral features are extracted for each spectral data. For example, the intensity of the absorption peak of water molecules at 1400nm and 1900nm is closely related to the water molecule content. The correspondence between different water content data and their corresponding absorption peak intensities can be fitted through data, and then the spectral water content inversion model can be obtained.

[0085] Fissures are natural cracks in rock mass, and their number and distribution directly affect the strength and stability of the rock mass. The more cracks there are, the lower the strength of the rock mass is, and the more likely it is to have a water inrush accident. Abnormal color may indicate the presence of aquifers or weak layers inside the rock mass, and these areas are more likely to have a water inrush accident. For example, for the same rock mass, the darker the color, the higher the water content. The higher the water content of the rock mass, the closer it may be to the water body, and the more likely it is to have a water inrush accident.

[0086] S105: Based on the total number of cracks per unit area, whether the color is abnormal, and the water content of the rock mass at different locations within each water inrush hazard level area, the risk level of each location within each water inrush hazard level area is further determined, thereby achieving further subdivision of the regional hazard level.

[0087] This embodiment combines three factors to jointly judge the risk level of the risk area, which can improve the accuracy of the judgment result.

[0088] This embodiment makes a comprehensive judgment on the risk of sudden water inrush within the corresponding level based on multiple factors. First, the color abnormality is digitized, for example: the color abnormality area is assigned a specific value, such as 1, and the color normal area is assigned 0 or other values. At this time, the color abnormality area and the color normal area have become continuous variables.

[0089] The collected number of cracks per unit area, color anomalies and rock water content are interpolated using an interpolation method (such as Kriging interpolation); in this embodiment, the number of cracks per unit area refers to the total number of cracks within a specific area (such as 1m²).

[0090] The total number of cracks, color anomalies or water content data of the rock mass at each position point on the tunnel face are obtained by data interpolation using the corresponding data of the drilling position; the specific process is as follows:

[0091] For a known data point A (x ki , y ki ) and B ( x kj , y kj ), calculate the distance between data points A and B h , and calculate the square of the numerical difference between data points A and B, that is, ( y ki - y kj ) 2 ; k represents the total number of cracks, color abnormal areas or water content data of rock mass;

[0092] Select all distances to h data points, calculate them ( y ki - y kj ) 2 The mean value of γ ( h ).

[0093] variance γ ( h ) indicates distance h The expected value of the square of the difference between the observed values ​​of two data points.

[0094] All the semivariances obtained γ ( h ) are connected into a line in the set order to obtain the variation function curve;

[0095] According to the shape of the variogram curve, select the appropriate Kriging model (such as the spherical model, exponential model, etc.) for interpolation, and determine the parameters of the Kriging model, such as the nugget, sill, and range. These parameters need to be determined based on the variogram curve.

[0096] According to the Kriging model and the values ​​of the known data points, the weight coefficient of each data point to the target location is calculated: the distance between the target location and each known data point is calculated, and the semivariance of each known data point to the target location is calculated according to the Kriging model and the distance; the weight coefficient of each known data point to the target location is calculated according to the semivariance, and the weight coefficient is inversely proportional to the semivariance.

[0097] The value of each data point is multiplied by its weight coefficient and then summed to obtain the interpolation result of the target position, thereby obtaining the data information of each position in front of the face and performing risk identification.

[0098] This embodiment uses the Kriging interpolation method to effectively expand the limited data collected in the borehole to the entire area in front of the face, thereby achieving a refined assessment of the risk of sudden water inrush and improving the accuracy and reliability of risk assessment.

[0099] The target position can be acquired by using a laser scanner to scan the underground environment, obtain three-dimensional point cloud data, identify the point cloud data, and convert it into spatial coordinates.

[0100] After obtaining the data information of each location, risk identification can be carried out. Figure 4 The specific identification method is as follows:

[0101] If the total number of cracks per unit area and the water content of the rock mass at a certain location point exceed the set threshold and it is an abnormal color area, then the location point is delineated as a high-risk area;

[0102] If the total number of cracks per unit area and the water content of the rock mass at a certain location point both exceed the set thresholds, but it is not a color abnormality area; or if a certain location point is a color abnormality area and one of the total number of cracks per unit area and the water content of the rock mass exceeds the set threshold, then the location point is considered to belong to the medium risk area;

[0103] If the total number of cracks per unit area and the water content of the rock mass at a certain location point do not exceed the set threshold, and the location point is an abnormal color area or a normal color area; or if one of the total number of cracks per unit area and the water content of the rock mass at a certain location point exceeds the set threshold, and the location point is a normal color area, then the area is considered to be a low-risk area.

[0104] Among them, the set risk threshold range can be selected based on actual conditions and needs.

[0105] This embodiment can identify the hazard level of sudden water inrush by surveying the groundwater level and conducting solubility analysis of the surrounding rock and determining the risk range during the drilling process. It can further combine the rock image and spectral information analysis in the borehole to make a comprehensive judgment on the sudden water inrush risk within the corresponding level based on multiple factors, overcome the limitations of single methods such as traditional geological analysis, hierarchical analysis method and attribute mathematical theory method, improve the accuracy and reliability of risk assessment, and realize real-time monitoring and accurate assessment of the sudden water inrush risk during shaft and tunnel construction.

[0106] Embodiment 2

[0107] In one or more embodiments, a water inrush risk assessment system based on while-drilling image and spectrum fusion is disclosed, comprising:

[0108] The drilling parameter acquisition module is used to perform multi-hole drilling on the tunnel face to be tested, analyze and determine the solubility of the surrounding rock, and record the abnormal points of drilling parameters and the corresponding drilling depth during the drilling process;

[0109] The water inrush hazard level determination module is used to identify the risk range if water flows out during drilling, and determine the water inrush hazard level based on the risk range, the solubility of the surrounding rock, and the height difference between the groundwater level and the bottom plate of the shaft and tunnel; if no water flows out, the water inrush hazard level at each position of the tunnel face is determined based on the solubility of the surrounding rock and the height difference between the groundwater level and the bottom plate of the shaft and tunnel;

[0110] The processing module is used to obtain the image information of the rock mass in the regional borehole for each sudden water hazard level area, process the image to obtain the number and distribution of cracks in the borehole, and obtain the total number of cracks per unit area; determine the color abnormal area in the image by clustering the pixels in the image; obtain the spectral information of the rock mass in the regional borehole, and invert the water content of the rock mass based on the established spectral water content inversion model;

[0111] The risk level determination module is used to further determine the risk level of each location in each sudden water hazard level area based on the total number of cracks per unit area, whether the color is abnormal, and the water content of the rock mass at different locations in each sudden water hazard level area.

[0112] It should be noted that the specific implementation method of the above modules is the same as that in Example 1 and will not be described in detail.

[0113] Embodiment 3

[0114] In one or more embodiments, a terminal device is disclosed, which includes a processor and a memory, the processor is used to implement instructions; the memory is used to store multiple instructions, and the instructions are suitable for being loaded by the processor and executing the sudden water inrush risk assessment method based on downhole image and spectral fusion described in Example 1.

[0115] It should be understood that in this embodiment, the processor may be a central processing unit CPU, and the processor may also be other general-purpose processors, digital signal processors DSP, application-specific integrated circuits ASIC, off-the-shelf programmable gate arrays FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0116] The memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0117] In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in a processor or an instruction in the form of software.

[0118] Embodiment 4

[0119] In one or more embodiments, a computer-readable storage medium is disclosed, in which a plurality of instructions are stored, wherein the instructions are suitable for being loaded by a processor of a terminal device and executing the method for sudden water inrush risk assessment based on while-drilling image and spectrum fusion described in Example 1.

[0120] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A method for assessing water inrush risk based on while-drilling image and spectrum fusion, characterized in that: include: Conduct multi-hole drilling on the tunnel face to be tested, analyze and determine the solubility of the surrounding rock, and record the abnormal points of drilling parameters and the corresponding drilling depth during the drilling process; If water flows out during drilling, identify the risk range and determine the level of water inrush hazard based on the risk range, the solubility of the surrounding rock, and the height difference between the groundwater level and the bottom plate of the well; If there is no water outflow, the water inrush hazard level at each location on the tunnel face is determined based on the solubility of the surrounding rock and the height difference between the groundwater level and the bottom plate of the shaft and tunnel; For each water inrush hazard level area, obtain the image information of the rock mass in the borehole in the area, process the image to obtain the number and distribution of cracks in the borehole, and obtain the total number of cracks per unit area; cluster the pixels in the image to determine the color abnormal area in the image; Obtain the spectral information of the rock mass in the regional borehole, and invert the water content of the rock mass based on the established spectral water content inversion model; Based on the total number of cracks per unit area, abnormal color and water content of the rock mass at different locations in each water inrush hazard level area, the risk level of each location in each water inrush hazard level area is further determined; Among them, the total number of cracks per unit area, whether the color is abnormal, and the water content of the rock mass at different locations in each sudden water hazard level area are obtained by interpolating the known data; the specific process is as follows: For a known data point A ( x ki , y ki ) and B ( x kj , y kj ), calculate the distance between data points A and B h , and calculate the square of the numerical difference between data points A and B, that is, ( y ki - y kj ) 2 ; y ki Represents the total number of cracks per unit area, color anomalies after numerical processing, or water content data of rock mass; For all pairs of data points with a distance h, the squares of the differences in the values ​​of the data points are averaged to obtain the semivariance γ ( h ); All the semivariances obtained γ ( h ) are connected into a line in the set order to obtain the variation function curve; According to the shape of the variogram curve, select the appropriate Kriging model and determine the parameters of the model; Based on the Kriging model, the weight coefficient of each data point for the target position is calculated, the value of each known data point is multiplied by its weight coefficient, and then summed to obtain the interpolation result of the target position; then the total number of cracks per unit area, color anomalies or water content data information of the rock mass are obtained at each location point.

2. The method for assessing water inrush risk based on while-drilling image and spectrum fusion according to claim 1, characterized in that: If water flows out during drilling, identify the risk areas, specifically: If water flows out during the drilling process, the location of the water outlet point is recorded, and holes are drilled evenly around the water outlet borehole until a water-free borehole is drilled; the horizontal and vertical boundaries of the risk range in the plane direction of the face are determined based on the locations of the water-free boreholes around the water outlet borehole; the depth boundary in the depth direction of the face is determined based on the two drilling parameter anomaly points corresponding to each borehole; and a three-dimensional view of the risk range is formed.

3. The method for assessing water inrush risk based on while-drilling image and spectrum fusion according to claim 1, characterized in that: Obtain image information of the rock mass in the borehole, and process the image to obtain the number and distribution of cracks in the borehole, specifically: Identify edge information in images through edge detection algorithms; remove noise and impurities in images and highlight crack features; Hough transform is applied to convert edge information in the image into parameter space, thereby identifying the shape of the crack; The image is segmented into foreground and background by setting a threshold, where the foreground corresponds to cracks and the background corresponds to other geological features; A high-pass filter is applied to highlight the edge of the crack in the foreground image, and a low-pass filter is applied to remove noise and impurities in the foreground image to make the crack features clearer; Thus, the number and distribution of cracks in the borehole can be obtained.

4. The method for assessing water inrush risk based on while-drilling image and spectrum fusion according to claim 1, characterized in that: By clustering the pixels in the image, the color abnormal area in the image is determined, specifically: Convert pixels from RGB to HSV or Lab color space through color space conversion; The clustering algorithm is applied to classify the pixels in the image, and the areas with large color differences from other clusters in the clustering results are regarded as color abnormal areas, and the location and size of the color abnormal areas are recorded.

5. The method for assessing water inrush risk based on while-drilling image and spectrum fusion according to claim 1, characterized in that: The spectral water content inversion model is specifically: Through indoor experiments, the absorption peak intensity characteristic data of the spectrum under different water contents were obtained, the relationship between the water content and the absorption peak intensity characteristics of the spectrum was fitted, and the spectral water content inversion model was obtained.

6. The method for assessing water inrush risk based on while-drilling image and spectrum fusion according to claim 1, characterized in that: Based on the total number of cracks per unit area, abnormal color and water content of the rock mass at different locations in each water inrush hazard level area, the risk level of each location in each water inrush hazard level area is further determined, specifically: If the total number of cracks per unit area and the water content of the rock mass at a certain location point exceed the set threshold and it is an abnormal color area, then the location point is delineated as a high-risk area; If the total number of cracks per unit area and the water content of the rock mass at a certain location point both exceed the set thresholds, but it is not a color abnormality area; or if a certain location point is a color abnormality area and one of the total number of cracks per unit area and the water content of the rock mass exceeds the set threshold, then the location point is considered to belong to the medium risk area; If the total number of cracks per unit area and the water content of the rock mass at a certain location point do not exceed the set threshold, and the location point is an abnormal color area or a normal color area; Or if one of the total number of cracks per unit area and the water content of the rock mass at a certain location point exceeds the set threshold, and the location point is a normal color area, then the area is considered to be a low-risk area.

7. A water inrush risk assessment system based on drilling image and spectrum fusion, characterized in that: include: The drilling parameter acquisition module is used to perform multi-hole drilling on the tunnel face to be tested, analyze and determine the solubility of the surrounding rock, and record the abnormal points of drilling parameters and the corresponding drilling depth during the drilling process; The water inrush hazard level determination module is used to identify the risk range if water flows out during drilling, and determine the water inrush hazard level based on the risk range, the solubility of the surrounding rock, and the height difference between the groundwater level and the bottom plate of the well; If there is no water outflow, the water inrush hazard level at each location on the tunnel face is determined based on the solubility of the surrounding rock and the height difference between the groundwater level and the bottom plate of the shaft and tunnel; A processing module is used to obtain image information of the rock mass in the borehole in each area with a sudden water hazard level, process the image to obtain the number and distribution of cracks in the borehole, and obtain the total number of cracks per unit area; and determine the color abnormal area in the image by clustering the pixels in the image; Obtain the spectral information of the rock mass in the regional borehole, and invert the water content of the rock mass based on the established spectral water content inversion model; A risk level determination module, for further determining the risk level of each location within each water inrush hazard level area based on the total number of cracks per unit area, whether the color is abnormal, and the water content of the rock mass at different locations within each water inrush hazard level area; Among them, the total number of cracks per unit area, whether the color is abnormal, and the water content of the rock mass at different locations in each sudden water hazard level area are obtained by interpolating the known data; the specific process is as follows: For a known data point A ( x ki , y ki ) and B ( x kj , y kj ), calculate the distance between data points A and B h , and calculate the square of the numerical difference between data points A and B, that is, ( y ki - y kj ) 2 ; y ki Represents the total number of cracks per unit area, color anomalies after numerical processing, or water content data of rock mass; For all pairs of data points with a distance h, the squares of the differences in the values ​​of the data points are averaged to obtain the semivariance γ ( h ); All the semivariances obtained γ ( h ) are connected into a line in the set order to obtain the variation function curve; According to the shape of the variogram curve, select the appropriate Kriging model and determine the parameters of the model; Based on the Kriging model, the weight coefficient of each data point for the target position is calculated, the value of each known data point is multiplied by its weight coefficient, and then summed to obtain the interpolation result of the target position; then the total number of cracks per unit area, color anomalies or water content data information of the rock mass are obtained at each location point.

8. A terminal device, comprising a processor and a memory, wherein the processor is used to implement instructions; and the memory is used to store multiple instructions, characterized in that: The instructions are suitable for being loaded by a processor and executing the method for assessing water inrush risk based on while-drilling image and spectrum fusion as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a plurality of instructions, characterized in that: The instructions are suitable for being loaded by a processor of a terminal device and executing the method for assessing water inrush risk based on while-drilling image and spectrum fusion as described in any one of claims 1 to 6.

Images