An intelligent monitoring system and monitoring method for the stability of high-steep slope rock mass

Abstract

The present invention discloses an intelligent monitoring system and a monitoring method for the stability of rock masses on high-steep slopes, which relates to the technical field of intelligent monitoring. It includes Step 1: Collecting image, vibration and inclinometer tube data in real time, and comprehensively analyzing to generate a landslide coefficient; Step 2: If the coefficient exceeds the threshold, triggering a first-level alarm, otherwise entering trend analysis; Step 3: Judging the trend speed through the ratio of the low-frequency to high-frequency of the vibration signal and the time slope. If it exceeds the threshold, triggering a second-level early warning, otherwise conducting cyclic monitoring. The present invention uses vector transformation and cosine of the included angle to match the landslide direction threshold, combines the bending radius and stress analysis to quantify the effective deformation, eliminates the multi-directional bending interference of the inclinometer tube, improves the measurement accuracy of the displacement direction, reduces the early warning error, and constructs a trend variable using the ratio of the low-frequency to high-frequency amplitudes. Combining the time series slope to analyze the trend speed, comprehensively predicting the signs of rock mass loosening, realizing early warning, and reducing the risk of sudden landslides.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent monitoring, and specifically to an intelligent monitoring system and method for the stability of rock masses on high-steep slopes. Background Technique

[0002] Monitoring the stability of rock masses on high-steep slopes is the core means to prevent geological disasters and ensure the safety of life and property. Due to the steep terrain and complex geological conditions of high-steep slopes, they are vulnerable to factors such as rainfall and earthquakes, which can easily induce disasters such as landslides and collapses, directly threatening the safety of residential areas, transportation arteries, and water conservancy facilities below. By using Beidou satellites to monitor the surface displacement of slopes in real time, and using inclinometers to monitor the deep deformation of rock masses in real time and other monitoring environmental parameter data, these data are used to identify the signs of the initiation of the rock mass slip zone in advance, such as sudden changes in the displacement rate of the rock mass and sudden increases in the seepage pressure within the rock mass, to achieve millimeter-level early warning.

[0003] Among them, before the inclinometer is buried, workers need to first drill holes in the rock mass and insert an inclinometer tube perpendicular to the rock mass. There are grooves inside the inclinometer tube, and the inclinometer slides freely along the grooves. If the rock mass inside undergoes displacement, it will squeeze the inclinometer tube and cause it to bend. The inclinometer measures the bending angle of the inclinometer tube and calculates the displacement of the rock mass using the bending angle.

[0004] When the rock mass undergoes displacement, the inclinometer tube undergoes multi-directional bending due to the uneven extrusion of the surrounding rock mass, resulting in the inclinometer being unable to accurately measure the displacement direction of the rock mass, ultimately increasing the error of the rock mass landslide early warning. Summary of the Invention

[0005] Aiming at the deficiencies of the prior art, the present invention provides an intelligent monitoring system and method for the stability of rock masses on high-steep slopes, which solves the problem that the multi-directional bending of the inclinometer tube caused by the displacement of the rock mass leads to deviation in the measurement direction and increases the landslide early warning error.

[0006] To achieve the above objectives, the present invention is realized through the following technical solutions: An intelligent monitoring system and method for the stability of rock masses on high-steep slopes, including the following specific steps and modules: Step 1: Obtain image data, vibration data, and inclinometer tube state data sets in real time and conduct comprehensive analysis to obtain the rock mass landslide coefficient. Among them, by converting the inclinometer tube state data set into a bending vector and using the cosine formula of the included angle to match the preset landslide direction threshold, only the bending vectors consistent with the landslide direction are counted, and the multi-directional bending of the inclinometer tube caused by the displacement of the rock mass is solved by combining the bending radius and force analysis; Step 2: Judge whether the rock mass landslides according to the rock mass landslide coefficient. If it is judged that the rock mass landslides, a first early warning is carried out. If it is judged that the rock mass is stable, Step 3 is executed; Step 3: Judge whether the rock mass has a tendency to landslide. If it is judged that the rock mass has a tendency to slide, a second early warning is carried out. If it is judged that the rock mass has no tendency to slide, return to Step 1 and continue to repeat the above step process.

[0007] Further, in step one, the image data is subjected to filtering and noise reduction processing, and the image data is processed through an image contour segmentation algorithm and an image contour tracking algorithm to obtain a rock mass image. The rock mass image includes the number of pixel points of the rock mass image and the pixel coordinates of the rock mass image. The pixel coordinates of the rock mass image are summed and averaged according to the number of pixel points of the rock mass image to obtain the center point coordinates of the rock mass image, obtaining the initial coordinates, and the center point coordinates of the rock mass image are recalculated according to time to obtain the current coordinates. The Euclidean distance formula is used to calculate the current coordinates and the initial coordinates to obtain the displacement coefficient of the rock mass image.

[0008] Further, the specific method for obtaining the displacement coefficient of the rock mass image is as follows: ; where represents the displacement coefficient of the rock mass image, reflecting whether the rock mass is displaced, represents the abscissa of the initial coordinates, represents the abscissa of the current coordinates, represents the ordinate of the initial coordinates, represents the ordinate of the current coordinates.

[0009] Further, in step one, the vibration data is subjected to data cleaning processing, and an average calculation is performed on the vibration data to obtain a vibration influence coefficient.

[0010] Further, the specific steps of converting the inclinometer tube state dataset into a bending vector, using the cosine of the angle formula to match the preset landslide direction threshold, only counting the bending vectors consistent with the landslide direction, and combining the bending radius and force analysis to solve the multi-directional bending of the inclinometer tube caused by rock mass displacement are as follows: Three-dimensional modeling is performed on the rock mass image to obtain a rock mass model. Taking the center point of this model as the origin, a three-dimensional coordinate system is established, and the inclinometer tube state dataset is evenly divided into Copies are obtained to get the inclinometer tube status data of different depth layers. The inclinometer tube status data includes the pipe bending angle and the pipe bending radius. The inclinometer tube status data is subjected to data cleaning, and the pipe bending angle is vector-transformed to obtain the pipe bending vector. A bending vector database and a bending radius database are established. The pipe bending vector data is stored in the bending vector database, and the pipe bending radius data is stored in the bending radius database. The pipe bending vector and the pipe bending radius correspond one by one. A landslide direction threshold is set, and the pipe bending vector and the vectors within the landslide direction threshold are successively calculated through the cosine formula of the included angle of vectors to obtain the landslide direction matching value. By comparing the landslide direction matching value with one, if the landslide direction matching value is equal to one, the number of pipe bending vectors with the landslide direction matching value equal to one is counted to obtain the number of times of pushing the landslide. And according to the force analysis and the friction formula, a pipe bending direction influence factor is set. The pipe bending radius corresponding to the pipe bending vector with the landslide direction matching value equal to one and the pipe bending direction influence factor are successively normalized and multiplied to obtain the rock mass anomaly value. The rock mass anomaly values are summed up according to the number of times of pushing the landslide to obtain the rock mass distortion coefficient. If the landslide direction matching value is not equal to one, the inclinometer continues to detect.

[0011] Further, normalization processing and comprehensive analysis are performed according to the rock mass image displacement coefficient, the vibration influence coefficient, and the rock mass distortion coefficient to obtain the rock mass landslide coefficient; ; where represents the rock mass landslide coefficient, reflecting whether the rock mass landslides, represents the rock mass image displacement coefficient, reflecting whether the rock mass image is displaced, represents the vibration influence coefficient, reflecting whether there is vibration inside the rock mass, represents the rock mass distortion coefficient, reflecting the influence on the rock mass sliding, represents the quantity of the inclinometer tube status data of different depth layers.

[0012] Further, in step two, the rock mass landslide threshold is obtained through historical experiments and compared with the rock mass landslide coefficient. If the rock mass landslide coefficient is greater than or equal to the rock mass landslide threshold, it is judged that the rock mass landslides. If the rock mass landslide coefficient is less than the rock mass landslide threshold, it is judged that the rock mass is stable.

[0013] Further, in step three, through the rock mass stability prediction algorithm, the rock mass sliding trend coefficient is calculated, and a rock mass sliding trend threshold is set. The rock mass sliding trend threshold is assigned a value of 2M. By comparing the rock mass sliding trend threshold with the rock mass sliding trend coefficient, if the rock mass sliding trend coefficient is equal to the rock mass sliding trend threshold, it is judged that the rock mass has a sliding trend. If the rock mass sliding trend coefficient is not equal to the rock mass sliding trend threshold, it is judged that the rock mass has no sliding trend.

[0014] Further, the specific method for obtaining the rock mass sliding trend coefficient is as follows: Filter the vibration data through a software filtering algorithm to obtain the low-frequency amplitude and high-frequency amplitude. Divide the low-frequency amplitude by the high-frequency amplitude to obtain the sliding trend variable. When the sliding trend variable increases, assign the value M to the sliding trend variable. When the sliding trend variable decreases, assign the value N to the sliding trend variable. Set the initial variable coordinates according to the sliding trend variable and time. And the current variable coordinates , represents the initial time, represents the current time, represents the initial sliding trend variable, represents the current sliding trend variable. Calculate the initial variable coordinates and the current variable coordinates through the slope formula to obtain the sliding trend velocity. When the sliding trend velocity increases, assign the value M to the sliding trend velocity. When the sliding trend velocity decreases, assign the value N to the sliding trend velocity. Set the rock mass sliding trend coefficient. When the sliding trend variable and the sliding trend velocity increase simultaneously, assign the value 2M to the rock mass sliding trend coefficient. When the sliding trend variable and the sliding trend velocity do not increase simultaneously, assign the value M + N or 2N to the rock mass sliding trend coefficient.

[0015] Further, there are a rock mass sliding monitoring module, a rock mass sliding analysis module, and a rock mass sliding trend prediction module; the rock mass sliding monitoring module is used to obtain image data, vibration data, and the inclinometer tube status data set in real time and conduct comprehensive analysis to obtain the rock mass landslide coefficient; the rock mass sliding analysis module is used to judge whether the rock mass landslides according to the rock mass landslide coefficient. If it is judged that the rock mass landslides, a first warning is given. If it is judged that the rock mass is stable, the judgment result that the rock mass is stable is sent to the rock mass sliding trend prediction module; the rock mass sliding trend prediction module is used to receive the judgment result that the rock mass is stable and judge whether the rock mass has a landslide trend. If it is judged that the rock mass has a sliding trend, a second warning is given. If it is judged that the rock mass has no sliding trend, it returns to the rock mass sliding monitoring module and continues to repeat the execution of the rock mass sliding monitoring module, the rock mass sliding analysis module, and the rock mass sliding trend prediction module.

[0016] Compared with the prior art, the embodiments of the present invention at least have the following advantages or beneficial effects:

[0017] 1. By converting the deflection angle of the inclinometer tube into a vector and using the cosine formula of the included angle to match the preset landslide direction threshold, only the bending vectors consistent with the landslide direction are counted. Combining the bending radius and force analysis, the effects of forces in different directions are quantified, avoiding multi-directional bending of the inclinometer tube caused by uneven extrusion of the surrounding rock mass, which may lead to inaccurate measurement of the displacement direction of the rock mass by the inclinometer, and improving the accuracy of rock mass landslide warning.

[0018] 2. By calculating the ratio of the low-frequency amplitude to the high-frequency amplitude as the sliding trend variable, and combining with the slope analysis of the time series, the sliding trend velocity is obtained. The sliding trend variable and the sliding trend velocity are comprehensively used to predict the rock mass sliding, reducing the risk of rock mass sliding.

[0019] Of course, it is not necessary for any product implementing the present invention to achieve all the above-mentioned advantages simultaneously. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a flowchart of an intelligent monitoring method for the stability of rock mass on a high-steep slope according to the present invention.

[0021] Figure 2 It is a structural diagram of an intelligent monitoring system for the stability of rock mass on a high-steep slope according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0023] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprises", "comprising" or any other variation thereof is intended to cover a non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device.

[0024] As Figure 1 shown, the embodiments of the present invention provide an intelligent monitoring method for the stability of rock mass on a high-steep slope, including the following specific steps:

[0025] Step 1: Real-time obtain image data through a camera. The image data includes the number of pixel points, pixel point coordinates, and pixel point brightness values. Filter and denoise the image data, which helps improve the quality of the image data. Process the image data using an image contour segmentation algorithm and an image contour tracking algorithm. For the image contour segmentation algorithm, such as the sobel algorithm, first convert the image data into a grayscale image to simplify the calculation. Then, use 3×3 convolution kernels in the horizontal and vertical directions (the horizontal convolution kernel focuses on detecting vertical edges, and the vertical convolution kernel focuses on detecting horizontal edges) to perform convolution operations on the grayscale image, obtaining a horizontal gradient matrix and a vertical gradient matrix. Next, perform a square sum and square root calculation on the horizontal gradient matrix and the vertical gradient matrix to obtain the gradient magnitude, which is used to determine the edges. Calculate using the arctangent function to obtain the gradient direction, which is used to determine the direction in which the edges extend. Finally, perform binary processing on the gradient magnitude by setting a threshold, marking the pixel point coordinates with a gradient magnitude higher than the threshold as the contour, obtaining a rock mass image, which is used to reflect the external condition of the rock mass. For the image contour tracking algorithm, such as the Lucas - Kanade optical flow method, first assume that the pixel point brightness value is constant, obtaining an assumption formula, that is, the pixel point brightness values of the same object in two adjacent frames of images are unchanged. Then, perform a first-order Taylor expansion on the assumption formula to obtain an optical flow constraint equation. Next, use the sobel algorithm and the difference between adjacent frames to calculate the spatial gradient and the temporal gradient, which are used to reflect the influence of the changes in the spatial gradient and the temporal gradient on the pixel point brightness value in the optical flow constraint equation. Since the optical flow constraint equation has two unknowns, assume that the pixel points in the neighborhood move the same. Therefore, combine the optical flow constraint equations of the pixel points in the neighborhood into an overdetermined system of equations, and then use the least squares method to solve this system of equations to avoid errors, obtaining an estimated value of the optical flow velocity. Finally, in practical applications, select feature points (such as corner points), perform optical flow calculation and tracking on them, and then update the positions of the feature points in each frame to achieve target tracking. If the rock mass is displaced, track the rock mass image to improve the accuracy of analyzing whether the rock mass is displaced;

[0026] The rock mass image includes the number of pixel points of the rock mass image and the pixel point coordinates of the rock mass image. Sum and average the pixel point coordinates of the rock mass image according to the number of pixel points of the rock mass image to obtain the center point coordinates of the rock mass image, obtaining the initial coordinates. As time goes by, recalculate the center point coordinates of the rock mass image according to the time to obtain the current coordinates. Calculate the current coordinates and the initial coordinates using the Euclidean distance formula to obtain the rock mass image displacement coefficient, , where represents the rock mass image displacement coefficient, reflecting whether the rock mass is displaced, represents the abscissa of the initial coordinates, represents the abscissa of the current coordinates, represents the ordinate of the initial coordinates, Represents the ordinate of the current coordinate.

[0027] Vibration data is obtained in real time through a vibration sensor to reflect the internal condition of the rock mass. The vibration data is subjected to data cleaning to remove redundant values, which helps improve the quality of the data. The vibration data is averaged to obtain a vibration influence coefficient.

[0028] A three-dimensional model of the rock mass image is established to obtain a rock mass model. Taking the center point of this model as the origin, a three-dimensional coordinate system is established. The state data set of the inclinometer tube is obtained in real time through an inclinometer. The state data set of the inclinometer tube is discrete data. Since the inclinometer slides inside the inclinometer tube and stops each time it slides to a limited distance and then measures at this position, the inclinometer needs to measure times from the top to the bottom of the inclinometer tube. The state data set of the inclinometer tube is evenly divided into parts to obtain the state data of the inclinometer tube at different depth layers. The state data of the inclinometer tube includes the pipe bending angle and the pipe bending radius. Since the pipe bending angle and the pipe bending radius are caused by the internal forces in the rock mass, the internal force condition of the rock mass can be analyzed by analyzing the pipe bending angle and the pipe bending radius. The state data of the inclinometer tube is subjected to data cleaning to remove redundant values, which helps improve the quality of the data. The pipe bending angle is vector-transformed to obtain a pipe bending vector. A bending vector database and a bending radius database are established. The pipe bending vector data is stored in the bending vector database, and the pipe bending radius data is stored in the bending radius database, and each pipe bending vector is associated with the corresponding pipe bending radius;

[0029] Set a landslide direction threshold. The rock mass model includes a part located underground and a part exposed in the air. Calculate the vectors obtained by taking any point on the surface of the rock mass model exposed in the air and the origin. The set of vectors is the range of the landslide direction threshold. Calculate the landslide direction matching values in sequence for the pipeline bending vector and the vectors within the landslide direction threshold through the cosine formula of the vector angle. Compare the landslide direction matching value with one. If the landslide direction matching value is equal to one, it reflects that the force corresponding to this pipeline bending vector can push the rock mass to cause a landslide. Count the number of pipeline bending vectors with a landslide direction matching value equal to one to obtain the number of times of pushing the landslide. Set the pipeline bending direction influence factor according to the force analysis and the friction formula. Taking the horizontal plane of the center point of the rock mass model as the reference, divide the pipeline bending vectors into three categories, namely, one category where the arrow of the pipeline bending vector points below the horizontal plane, denoted as A, and the corresponding force is a; one category where the arrow of the pipeline bending vector coincides with the horizontal plane, denoted as B, and the corresponding force is b; one category where the arrow of the pipeline bending vector points above the horizontal plane, denoted as C, and the corresponding force is c. Decompose the force of a to obtain a force tending to B and a force tending to A. Decompose the force of b to obtain a force tending to B as a whole. Decompose the force of c to obtain a force tending to B and a force tending to C. Additionally, according to the friction formula, that is, the friction force is equal to the product of the friction coefficient and the pressure. a has a force tending to A, so the friction force for pushing the rock mass to slide is the largest. c has a force tending to C, so the friction force for pushing the rock mass to slide is the smallest. b is medium. Therefore, the difficulty of a, b, and c in pushing the rock mass to slide from large to small is a, b, and c respectively. Subsequently, the category where the arrow of the pipeline bending vector points above the horizontal plane has the greatest influence on the sliding of the rock mass, and the category where the arrow of the pipeline bending vector points below the horizontal plane has the smallest influence on the sliding of the rock mass. The value range of the pipeline bending direction influence factor is , in degrees. That is, a two-dimensional coordinate system is established based on the origin and a unit vector k passing through the origin. Combining with the physical reality, k is rotated around the origin from an angle infinitely close to and greater than zero degrees to an angle infinitely close to and less than 180 degrees to obtain the value range of the pipeline bending direction influence factor. If the included angle between the arrow of the pipeline bending vector corresponding to the pipeline bending radius and the upper part of the horizontal plane is larger, the pipeline bending direction influence factor is larger. If the included angle between the arrow of the pipeline bending vector corresponding to the pipeline bending radius and the lower part of the horizontal plane is larger, the pipeline bending direction influence factor is smaller. The pipeline bending radius and the pipeline bending direction influence factor corresponding to the pipeline bending vector with a landslide direction matching value equal to 1 are normalized and multiplied in sequence to obtain the rock mass anomaly value. The rock mass anomaly values are summed according to the number of times of pushing the landslide to obtain the rock mass distortion coefficient. Combining the bending radius and force analysis, the action of forces in different directions is quantified to avoid multi-directional bending of the inclinometer tube due to uneven extrusion of the surrounding rock mass, resulting in the inability of the inclinometer to accurately measure the displacement direction of the rock mass and improving the accuracy of rock mass landslide warning. If the landslide direction matching value is not equal to 1, the inclinometer continues to detect.

[0030] The specific method for obtaining the landslide direction matching value is as follows:

[0031] ;

[0032] Among them, represents the landslide direction matching value, with a range from -1 to 1, represents the pipeline bending vector, represents the landslide direction threshold, represents the modulus of the pipeline bending vector, represents the modulus of the landslide direction threshold.

[0033] According to the rock mass image displacement coefficient, vibration influence coefficient, and rock mass distortion coefficient, normalization processing and comprehensive analysis are carried out to obtain the rock mass landslide coefficient, , where represents the rock mass landslide coefficient, reflecting whether the rock mass landslides, represents the rock mass image displacement coefficient, reflecting whether the rock mass image is displaced, represents the vibration influence coefficient, reflecting whether there is vibration inside the rock mass, represents the rock mass distortion coefficient, reflecting the influence on the rock mass sliding, represents the quantity of inclinometer tube state data at different depth layers.

[0034] Step 2: Determine whether the rock mass slides according to the rock mass landslide coefficient. Obtain the rock mass landslide threshold through historical experiments and compare it with the rock mass landslide coefficient. If the rock mass landslide coefficient is greater than or equal to the rock mass landslide threshold, it is determined that the rock mass slides. If it is determined that the rock mass slides, a first warning is issued. If the rock mass landslide coefficient is less than the rock mass landslide threshold, it is determined that the rock mass is stable. If it is determined that the rock mass is stable, proceed to Step 3.

[0035] Step 3: Determine whether the rock mass has a tendency to slide. Calculate through the rock mass stability prediction algorithm to obtain the rock mass sliding tendency coefficient, and set the rock mass sliding tendency threshold. Assign a value of 2M to the rock mass sliding tendency threshold. Compare the rock mass sliding tendency threshold with the rock mass sliding tendency coefficient. If the rock mass sliding tendency coefficient is equal to the rock mass sliding tendency threshold, that is, the rock mass sliding tendency coefficient is equal to 2M, it is determined that the rock mass has a sliding tendency. If it is determined that the rock mass has a sliding tendency, a second warning is issued. If the rock mass sliding tendency coefficient is not equal to the rock mass sliding tendency threshold, that is, the rock mass sliding tendency coefficient is not equal to 2M, it is determined that the rock mass has no sliding tendency. If it is determined that the rock mass has no sliding tendency, return to Step 1 and continue to repeat the above step process.

[0036] The specific method for obtaining the rock mass sliding tendency coefficient is as follows:

[0037] Filter the vibration data through the software filtering algorithm to obtain the low-frequency amplitude and the high-frequency amplitude. Divide the low-frequency amplitude by the high-frequency amplitude to obtain the sliding tendency variable. Since the interior of the rock mass gradually loosens before sliding, resulting in more and larger voids, the low-frequency amplitude can continue to pass through the voids without energy loss, while the high-frequency amplitude scatters energy due to the voids, resulting in a weakened high-frequency amplitude. Therefore, when the voids inside the rock mass become more and larger, the sliding tendency variable increases monotonically. The larger the sliding tendency variable, the more obvious the sliding tendency. Assign a value of M to the sliding tendency variable. The smaller the sliding tendency variable, the less obvious the sliding tendency. Assign a value of N to the sliding tendency variable. As time goes by, set the initial variable coordinates according to the sliding tendency variable and time and the current variable coordinates , represents the initial time, represents the current time, represents the initial sliding tendency variable, represents the current sliding tendency variable. Through the slope formula, for the initial variable coordinates and the current variable coordinates Calculations are performed to obtain the sliding trend velocity. When the sliding trend velocity is greater, that is, the slope is greater, the sliding trend is more obvious. The sliding trend velocity is assigned as M. When the sliding trend velocity is slower, that is, the slope is smaller, the sliding trend is less obvious, and the sliding trend velocity is assigned as N. A rock mass sliding trend coefficient is set. Since it is impossible to accurately judge whether the rock mass has a sliding trend only by the increase of the sliding trend variable or the increase of the sliding trend velocity, when both the sliding trend variable and the sliding trend velocity increase simultaneously, the rock mass sliding trend coefficient is assigned as 2M. When the sliding trend variable and the sliding trend velocity do not increase simultaneously, the rock mass sliding trend coefficient is assigned as M + N or 2N, where M is not equal to N.

[0038] An embodiment of the present invention provides a high-steep slope rock mass stability intelligent monitoring system, including the following specific modules: a rock mass sliding monitoring module, a rock mass sliding analysis module, and a rock mass sliding trend prediction module.

[0039] The rock mass sliding monitoring module is used to obtain real-time image data, vibration data, and inclinometer tube status data sets and perform comprehensive analysis to obtain the rock mass landslide coefficient.

[0040] The rock mass sliding analysis module is used to judge whether the rock mass landslides according to the rock mass landslide coefficient. If it is judged that the rock mass landslides, a first warning is given. If it is judged that the rock mass is stable, the judgment result of the stable rock mass is sent to the rock mass sliding trend prediction module.

[0041] The rock mass sliding trend prediction module is used to receive the judgment result of the stable rock mass and judge whether the rock mass has a sliding trend. If it is judged that the rock mass has a sliding trend, a second warning is given. If it is judged that the rock mass has no sliding trend, it returns to the rock mass sliding monitoring module and continues to repeat the execution of the rock mass sliding monitoring module, the rock mass sliding analysis module, and the rock mass sliding trend prediction module.

[0042] The above-disclosed preferred embodiments of the present invention are only used to help explain the present invention. The preferred embodiments do not describe all details in detail, nor limit the invention to the specific embodiments described. Obviously, many modifications and changes can be made according to the content of this specification. These embodiments are selected and specifically described in this specification to better explain the principle and practical application of the present invention, so that those skilled in the art can understand and utilize the present invention well. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. An intelligent monitoring method for high and steep slope rock mass stability, characterized by: The specific steps include: Step 1: Real-time acquisition of image data, vibration data, and an inclinometer tube status dataset is conducted and comprehensively analyzed to determine the rock mass landslide coefficient. This is achieved by converting the inclinometer tube status dataset into a bending vector and using the angle cosine formula to match a preset landslide direction threshold. Only bending vectors consistent with the landslide direction are counted. This, combined with bending radius and force analysis, addresses the multi-directional bending of the inclinometer tube caused by rock mass displacement. Step 2: Determine whether the rock mass is sliding based on the rock mass landslide coefficient. If the rock mass is determined to be sliding, issue a first warning. If the rock mass is determined to be stable, execute step 3. Step 3: Determine whether the rock mass has a tendency to slide. If it is determined that the rock mass has a tendency to slide, a second warning is issued. If it is determined that the rock mass has no tendency to slide, return to step 1 and continue to repeat the above steps. In step 1, filtering and noise reduction processing is performed on the image data, and the image data is processed by an image contour segmentation algorithm and an image contour tracking algorithm to obtain a rock image, wherein the rock image includes the number of pixels of the rock image and the coordinates of the pixel points of the rock image. The pixel coordinates of the rock image are summed and averaged according to the number of pixels of the rock image to obtain the coordinates of the center point of the rock image, and the initial coordinates are obtained. The coordinates of the center point of the rock image are recalculated according to time to obtain the current coordinates. The current coordinates and the initial coordinates are calculated by the Euclidean distance formula to obtain the displacement coefficient of the rock image; In step 1, the vibration data is cleaned and averaged to obtain the vibration influence coefficient. The step 1 is specifically as follows: perform three-dimensional modeling on the rock mass image to obtain a rock mass model, establish a three-dimensional coordinate system with the center point of the model as the origin, and divide the inclinometer casing state data set into The inclinometer casing status data of different depth layers are obtained, wherein the inclinometer casing status data includes a pipe bending angle and a pipe bending radius, data cleaning is performed on the inclinometer casing status data, and the pipe bending angle is vector-converted to obtain a pipe bending vector; Set a landslide direction threshold, calculate the pipeline bending vector and the vector within the landslide direction threshold in sequence using the vector angle cosine formula to obtain the landslide direction matching value, compare the landslide direction matching value with one, and if the landslide direction matching value is equal to one, count the number of pipeline bending vectors with a landslide direction matching value equal to one to obtain the number of times the landslide is driven, and set the pipeline bending direction influencing factor based on the force analysis and friction formula. Normalize the pipeline bending radius and pipeline bending direction influencing factor corresponding to the pipeline bending vector with a landslide direction matching value equal to one in sequence and perform product calculation to obtain the rock mass anomaly value. Sum the rock mass anomaly values according to the number of times the landslide is driven to obtain the rock mass distortion coefficient. Performing normalization processing and comprehensive analysis based on the rock mass image displacement coefficient, the vibration influence coefficient, and the rock mass distortion coefficient to obtain a rock mass landslide coefficient; ； in, Indicates the rock mass landslide coefficient, reflecting whether the rock mass is sliding. Indicates the displacement coefficient of the rock mass image, reflecting whether the rock mass image is displaced. Indicates the vibration influence coefficient, reflecting whether the rock mass is vibrating inside. It represents the rock mass distortion coefficient, reflecting the impact on rock mass sliding. Indicates the number of inclinometer casing status data at different depth layers.

2. The intelligent monitoring method for high and steep slope rock mass stability according to claim 1 is characterized by: The specific method for obtaining the rock mass image displacement coefficient is: ； in, Indicates the rock mass image displacement coefficient, reflecting whether the rock mass is displaced. represents the horizontal coordinate of the initial coordinate, Indicates the horizontal coordinate of the current coordinate, represents the ordinate of the initial coordinate, Indicates the vertical coordinate of the current coordinate.

3. The intelligent monitoring method for high and steep slope rock mass stability according to claim 1 is characterized by: In step 2, the rock mass landslide threshold is obtained through historical experiments and compared with the rock mass landslide coefficient. If the rock mass landslide coefficient is greater than or equal to the rock mass landslide threshold, the rock mass is judged to be a landslide; if the rock mass landslide coefficient is less than the rock mass landslide threshold, the rock mass is judged to be stable.

4. The intelligent monitoring method for high and steep slope rock mass stability according to claim 1 is characterized by: In step three, the rock mass stability prediction algorithm is used to calculate and obtain the rock mass sliding trend coefficient, and the rock mass sliding trend threshold is set. The rock mass sliding trend threshold is assigned a value of 2M, and the rock mass sliding trend threshold is compared with the rock mass sliding trend coefficient. If the rock mass sliding trend coefficient is equal to the rock mass sliding trend threshold, it is judged that the rock mass has a sliding trend. If the rock mass sliding trend coefficient is not equal to the rock mass sliding trend threshold, it is judged that the rock mass has no sliding trend.

5. The intelligent monitoring method for high and steep slope rock mass stability according to claim 4 is characterized by: The specific method for obtaining the rock mass sliding tendency coefficient is as follows: Vibration data is filtered by software filtering algorithm to obtain low-frequency amplitude and high-frequency amplitude. The low-frequency amplitude and high-frequency amplitude are divided to obtain the sliding trend variable. When the sliding trend variable increases, the sliding trend variable is assigned a value of M. When the sliding trend variable decreases, the sliding trend variable is assigned a value of N. The initial variable coordinates are set according to the sliding trend variable and time. With the current variable coordinates , Indicates the initial time, Indicates the current time, represents the initial sliding trend variable, Indicates the current sliding trend variable, and the initial variable coordinates are calculated using the slope formula With the current variable coordinates Calculation is performed to obtain the sliding trend velocity. When the sliding trend velocity increases, the sliding trend velocity is assigned a value of M. When the sliding trend velocity decreases, the sliding trend velocity is assigned a value of N. The rock mass sliding trend coefficient is set. When the sliding trend variable and the sliding trend velocity increase at the same time, the rock mass sliding trend coefficient is assigned a value of 2M. When the sliding trend variable and the sliding trend velocity increase at different times, the rock mass sliding trend coefficient is assigned a value of M+N or 2N.

6. An intelligent monitoring system for the stability of high and steep slope rock mass, used to implement the intelligent monitoring method for the stability of high and steep slope rock mass according to any one of claims 1 to 5, characterized in that: The system includes: a rock fall monitoring module, a rock fall analysis module and a rock fall trend prediction module; The rock mass landslide monitoring module is used to obtain image data, vibration data and inclinometer status data set in real time and perform comprehensive analysis to obtain the rock mass landslide coefficient; The rock mass landslide analysis module is used to determine whether the rock mass is landslide based on the rock mass landslide coefficient. If the rock mass is determined to be landslide, a first warning is issued. If the rock mass is determined to be stable, the determination result of whether the rock mass is stable is sent to the rock mass landslide trend prediction module. The rock mass sliding trend prediction module is used to receive the judgment result that the rock mass is stable and judge whether the rock mass has a landslide trend. If it is judged that the rock mass has a sliding trend, a second warning is issued. If it is judged that the rock mass has no sliding trend, the module returns to the rock mass sliding monitoring module and continues to repeatedly execute the rock mass sliding monitoring module, the rock mass sliding analysis module and the rock mass sliding trend prediction module.

Images