Identification and stability evaluation method and system for high and steep slope dangerous rock mass

Abstract

The invention provides a high and steep slope dangerous rock mass recognition and stability evaluation method and system, and the method comprises the steps: building a dangerous rock mass recognition model according to the fall point cloud data of a high and steep slope based on a point cloud density mutation detection algorithm and a genetic neural network, and carrying out the recognition of the three-dimensional boundary of the dangerous rock mass; according to the three-dimensional boundary of the dangerous rock body, any dangerous rock body contour point cloud set is formed, a dangerous rock body geometric feature parameter extraction model is established, and dangerous rock body geometric feature parameters are obtained through extraction; and establishing a dangerous rock mass stability evaluation model comprising a rock mass parameter set, an environment data set and a stability algorithm method set, coupling the dangerous rock mass geometric characteristic parameters with the rock mass parameter set and the environment data set as input conditions, inputting the input conditions into the stability algorithm method set, and evaluating the stability of the dangerous rock mass. According to the method, the data precision, the recognition efficiency, the analysis accuracy and the response real-time performance are greatly improved, and a theoretical basis is provided for early recognition and stability evaluation of the slope dangerous rock mass in the high and steep environment of water conservancy and hydropower engineering.

Description

Technical Field

[0001] The invention belongs to the technical field of water conservancy and hydropower engineering, and relates to a method and system for identifying and evaluating the stability of dangerous rock masses. Background Art

[0002] Early identification and stability assessment of dangerous rock masses on steep slopes in water conservancy and hydropower projects are key means to prevent and control high-altitude collapse disasters. Affected by the topography and landform combination, the current identification and stability assessment methods have the following problems: First, the terrain of steep slopes is complex, and traditional manual measurement or ordinary aerial survey is difficult to obtain high-precision three-dimensional models. Point cloud models with kilometer-level drop heights are prone to data distortion problems; second, relying on manual experience to judge the boundaries of dangerous rock masses is time-consuming and prone to omissions, and cannot adapt to the needs of rapid screening of dangerous rock masses on large-scale slopes; third, the geometric parameters of the structural surface area, inclination, volume, etc. of dangerous rock masses are mostly estimated through simplified two-dimensional models, which are difficult to reflect the three-dimensional spatial characteristics, resulting in large errors in stability analysis; fourth, stability assessment relies on offline calculations and cannot dynamically respond to changes in rock mechanical parameters or the influence of environmental factors such as rainfall and vibration. In summary, in the current identification and stability assessment of dangerous rock masses on steep slopes, the point cloud model data accuracy is low under the condition of kilometer-level drop, the dangerous rock mass identification efficiency is low, the identification accuracy of dangerous rock masses is low, the calculation of dangerous rock mass geometric parameters is rough, and the real-time stability assessment is poor. Summary of the Invention

[0003] In order to solve the problems described in the background technology of low accuracy of point cloud model data, low efficiency of dangerous rock mass identification, low accuracy of dangerous rock mass identification, rough calculation of dangerous rock mass geometric parameters, and poor real-time stability assessment on high and steep slopes with a drop of a kilometer, the present invention provides a method and system for identifying and assessing the stability of dangerous rock masses on high and steep slopes.

[0004] The method of the present invention comprises: Plan the flight path of the UAV based on the steep slope gradient, lighting conditions, topography, ground feature combination, and obstacle distribution, and use the UAV to collect point cloud data of the steep slope drop according to the planned flight path; Based on the point cloud data of high and steep slope drop, a dangerous rock mass identification model was established based on the point cloud density mutation detection algorithm and genetic neural network to identify the three-dimensional boundaries of dangerous rock masses; According to the three-dimensional boundary of the dangerous rock mass, a point cloud set of the contour of any dangerous rock mass is formed, and a geometric characteristic parameter extraction model of the dangerous rock mass is established to extract the geometric characteristic parameters of the dangerous rock mass; A dangerous rock mass stability assessment model is established, which includes a rock mass parameter set, an environmental data set, and a stability algorithm method set. The geometric characteristic parameters of the dangerous rock mass are coupled with the rock mass parameter set and the environmental data set as input conditions and input into the stability algorithm method set to evaluate the stability of the dangerous rock mass.

[0005] Furthermore, in the flight path planning of the UAV, based on the target point cloud density r target With real-time point cloud density r target Difference, target point cloud density r target , real-time point cloud density r crurrent , slope inclination i , adjust the drone's flying height in real time H， As shown in the following formula (1): (1), Where, H The real-time ground height; H 0 is the reference altitude; i is the slope inclination; r target is the target point cloud density; r crurrent is the real-time point cloud density.

[0006] Furthermore, in the dangerous rock mass identification model, based on the point cloud data of the high and steep slope drop, the local point cloud density difference coefficient K is obtained by the point cloud density mutation detection algorithm. As shown in formula (2), the closer the point cloud density difference coefficient K of adjacent areas is, the greater the possibility that the point clouds are located on the same structural surface, and vice versa. Then, according to the spatial topological relationship of different structural surfaces, the potential boundary contour of the dangerous rock mass is preliminarily identified; Based on the point cloud data of high and steep slope drop, the genetic algorithm continuously optimizes the neural network weights, establishes a genetic neural network algorithm based on the point cloud density difference coefficient K and the contour size of the dangerous rock mass, takes the initially identified potential boundary contour of the dangerous rock mass as the input condition, and realizes the final identification of the three-dimensional boundary of the dangerous rock mass through iterative calculation of the genetic neural network. (2), Where, s local is the local density standard deviation; s global is the global density standard deviation; r max 、 r min 、 r avg are the maximum, minimum and average densities, respectively.

[0007] Furthermore, in the geometric characteristic parameter extraction model of the dangerous rock mass, a point cloud set of the contour of any dangerous rock mass is formed based on the identified three-dimensional boundary of the dangerous rock mass, and the point cloud is formed into a number of triangular facets. Through the established intelligent geometric characteristic parameter extraction model of the dangerous rock mass, the inclination angle, area and total volume of the rear edge structural surface of the dangerous rock mass are automatically extracted based on the triangular facets, as shown in formula (3): (3), Where, α is the inclination angle of the structural surface at the rear edge of the dangerous rock mass; α i The rear edge structural surface of the dangerous rock mass i The angle between the normal vector of each triangle and the vertical direction; A is the structural surface area of the rear edge of the dangerous rock mass; S i The structural surface at the rear edge of the dangerous rock mass i The area of the triangle; V is the volume of dangerous rock mass; A (Z) is the horizontal projection area of the dangerous rock mass at point z; Z min and Z max are the minimum and maximum elevations of dangerous rock masses, respectively.

[0008] Furthermore, the dangerous rock mass stability assessment model also includes a set of reinforcement stabilization measures, which couples the geometric characteristic parameters of the dangerous rock mass with the rock mass parameter set and the environmental data set as input conditions and inputs them into the stability algorithm method set. First, the stability safety factor of the dangerous rock mass in the non-reinforced state is evaluated. If it does not meet the engineering requirements, the reinforcement stabilization measure set is called in. Through continuous iteration until the stability safety factor of the dangerous rock mass meets the engineering requirements, the corresponding stability reinforcement plan is obtained.

[0009] Furthermore, in the dangerous rock mass stability assessment model, the rock mass parameter set includes rock mass elastic modulus, internal friction angle, and cohesion parameter; the environmental data set includes rainfall, groundwater level, and earthquake conditions; the stability algorithm method set includes the rigid body limit equilibrium algorithm; and the reinforcement stabilization measures set includes anchor cables, anchor piles, and drainage hole reinforcement measures. The expression of the dangerous rock mass stability assessment model is shown in formula (4): (4), Where, M data are the rock mass parameter set and the environmental data set, and M method is a set of stability algorithm methods, M reinforcement To strengthen the set of stability measures; Based on the geometric characteristic parameter extraction model of dangerous rock mass, the inclination angle of the rear edge structural surface, the area of the rear edge structural surface and the total volume geometric parameters of the dangerous rock mass are obtained, and the dynamic coupling rock mass parameter set and the environmental data set are input into the stability algorithm method set as input conditions. First, the stability safety factor of the dangerous rock mass in the non-reinforced state is evaluated. If it does not meet the engineering requirements, the reinforcement stability measure set is called in. Through continuous iteration until the stability safety factor of the dangerous rock mass meets the engineering requirements, the corresponding stability reinforcement plan is obtained.

[0010] Based on the above method, the present invention proposes a system for identifying and evaluating the stability of dangerous rock masses on steep slopes, including a steep slope drop point cloud data acquisition module, a dangerous rock mass identification module, a dangerous rock mass geometric feature parameter extraction module, and a dangerous rock mass stability evaluation module.

[0011] The high and steep slope drop point cloud data acquisition module is used to plan the UAV flight path based on the high and steep slope gradient, lighting conditions, topography, ground object combination and obstacle distribution, and to collect the high and steep slope drop point cloud data by the UAV according to the planned flight path.

[0012] The dangerous rock mass identification module is used to establish a dangerous rock mass identification model based on the point cloud data of the high and steep slope drop, based on the point cloud density mutation detection algorithm and genetic neural network, and identify the three-dimensional boundary of the dangerous rock mass.

[0013] The dangerous rock body geometric characteristic parameter extraction module is used to form an arbitrary dangerous rock body contour point cloud set based on the dangerous rock body's three-dimensional boundary, establish a dangerous rock body geometric characteristic parameter extraction model, and extract the dangerous rock body geometric characteristic parameters.

[0014] The dangerous rock mass stability assessment module is used to establish a dangerous rock mass stability assessment model including a rock mass parameter set, an environmental data set, and a stability algorithm method set. The geometric characteristic parameters of the dangerous rock mass are coupled with the rock mass parameter set and the environmental data set as input conditions, and input into the stability algorithm method set to evaluate the stability of the dangerous rock mass.

[0015] The present invention also proposes a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-mentioned method for identifying dangerous rock masses on steep slopes and for assessing their stability.

[0016] Compared with the prior art, the present invention has the following beneficial effects: (1) High data acquisition accuracy: By combining UAVs with adaptive flight path planning, the data distortion problem of the point cloud model of steep slopes with a kilometer-level drop was solved, significantly improving the accuracy and integrity of the three-dimensional model of steep slopes, providing a reliable data basis for subsequent analysis; (2) Intelligent and efficient identification of dangerous rock masses: The dangerous rock mass identification model, which couples the point cloud density mutation detection algorithm with the genetic neural network, realizes the intelligent, automated, and rapid screening of dangerous rock mass boundaries, overcoming the defects of low efficiency and high missed detection rate of traditional manual experience judgment, and is extremely suitable for the engineering needs of high and steep slopes and large-scale slopes; (3) Accurate extraction of geometric characteristic parameters: Based on the three-dimensional boundary of the dangerous rock mass, a point cloud set of the contour of any dangerous rock mass is formed, and a model for extracting the geometric characteristic parameters of the dangerous rock mass is established. This breaks through the limitations of traditional two-dimensional simplified estimation and can accurately calculate the geometric characteristic parameters of the dangerous rock mass, significantly reducing the roughness and error of the geometric analysis; (4) Dynamic real-time assessment of stability: By integrating the dangerous rock mass stability assessment model with rock mass parameters, environmental data and stability algorithms, online dynamic real-time assessment of dangerous rock masses can be realized, which solves the lag problem of traditional offline calculations and the problem of poor real-time stability assessment, thereby taking corresponding reinforcement plans and improving the timeliness of disaster warnings.

[0017] In summary, the present invention realizes an intelligent closed-loop design for the entire process from data acquisition, dangerous rock mass identification, geometric feature parameter extraction to stability assessment. It breaks through the limitations of the traditional segmented processing method and realizes the integration of "acquisition-analysis-decision-making" for dangerous rock mass prevention and control. It greatly improves data accuracy, identification efficiency, analysis accuracy and real-time response. It provides a theoretical basis for the early identification and stability assessment of dangerous rock masses on high and steep slopes in water conservancy and hydropower projects, and provides reliable technical support for the prevention and control of high-altitude collapse disasters. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 Flow chart of the method of the present invention.

[0019] Figure 2 This is a system architecture diagram of the present invention. DETAILED DESCRIPTION

[0020] In order to make the technical problems, technical solutions and beneficial effects to be solved by this application more clearly understood, this application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0021] In order to make the technical problems, technical solutions and beneficial effects to be solved by this application more clearly understood, this application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0022] Example 1

[0023] Identification and stability assessment method of dangerous rock mass on steep slopes, the flow chart is as follows Figure 1 The specific steps are as follows.

[0024] The flight path of the UAV is planned based on the slope of the steep slope, lighting conditions, topography, ground object combination and obstacle distribution, and the UAV is used to collect point cloud data of the steep slope drop according to the planned flight path.

[0025] Specifically, in the flight path planning of the UAV, based on the target point cloud density r target With real-time point cloud density r target Difference, target point cloud density r target , real-time point cloud density r crurrent , slope inclination i , adjust the drone's flying height in real time H , solves the problem of point cloud model distortion caused by terrain undulation in traditional aerial survey, and optimizes the accuracy of point cloud model under the slope height of kilometer level, as shown in the following formula (1): (1), Where, H is the real-time ground height, m; H 0 is the reference altitude, m; i is the slope inclination, °; r target is the target point cloud density, points / m 3 ; r crurrent is the real-time point cloud density, points / m 3 .

[0026] According to the point cloud data of high and steep slope drop, a dangerous rock mass identification model is established based on the point cloud density mutation detection algorithm and genetic neural network to identify the three-dimensional boundaries of dangerous rock masses.

[0027] Specifically, based on the point cloud data of the high and steep slope drop, the local point cloud density difference coefficient K is obtained through the point cloud density mutation detection algorithm. As shown in formula (2), the closer the point cloud density difference coefficient K of adjacent areas is, the greater the possibility that the point cloud is located on the same structural surface, and vice versa. Then, according to the spatial topological relationship of different structural surfaces, the potential boundary contour of the dangerous rock mass is preliminarily identified; Based on the point cloud data of high and steep slope drop, the genetic algorithm continuously optimizes the neural network weights, establishes a genetic neural network algorithm based on the point cloud density difference coefficient K and the contour size of the dangerous rock mass, takes the initially identified potential boundary contour of the dangerous rock mass as the input condition, and realizes the final identification of the three-dimensional boundary of the dangerous rock mass through iterative calculation of the genetic neural network. (2), Where, s local is the local density standard deviation; s global is the global density standard deviation; r max 、 r min 、 r avg are the maximum, minimum and average density, pieces / m 3 .

[0028] According to the three-dimensional boundary of the dangerous rock mass, a point cloud set of the contour of any dangerous rock mass is formed, and a geometric characteristic parameter extraction model of the dangerous rock mass is established to extract the geometric characteristic parameters of the dangerous rock mass.

[0029] Specifically, based on the identified three-dimensional boundary of the dangerous rock mass, a point cloud set of the contour of any dangerous rock mass is formed, and the point cloud is formed into several triangular facets. Through the established intelligent extraction model of the geometric characteristic parameters of the dangerous rock mass, the inclination angle, area and total volume of the rear edge structural surface of the dangerous rock mass are automatically extracted based on the triangular facets, as shown in formula (3): (3), Where, α is the inclination angle of the structural surface at the rear edge of the dangerous rock mass, °; α i The rear edge structural surface of the dangerous rock mass i The angle between the normal vector of each triangle and the vertical direction, °; A is the structural surface area of the rear edge of the dangerous rock mass, m 2 ; S i The structural surface at the rear edge of the dangerous rock mass i The area of the triangle, m 2 ; V is the volume of dangerous rock mass, m 3 ; A (Z) is the horizontal projection area of the dangerous rock mass at position z, m 2 ; Z min and Z max are the minimum and maximum elevations of dangerous rock masses, respectively.

[0030] A dangerous rock mass stability assessment model is established, which includes a rock mass parameter set, an environmental data set, and a stability algorithm method set. The geometric characteristic parameters of the dangerous rock mass are coupled with the rock mass parameter set and the environmental data set as input conditions and input into the stability algorithm method set to evaluate the stability of the dangerous rock mass.

[0031] Specifically, the dangerous rock mass stability assessment model also includes a set of reinforcement stabilization measures. The geometric characteristic parameters of the dangerous rock mass are coupled with the rock mass parameter set and the environmental data set as input conditions and input into the stability algorithm method set. First, the stability safety factor of the dangerous rock mass in the non-reinforced state is evaluated. If it does not meet the engineering requirements, the reinforcement stabilization measure set is called in. Through continuous iteration until the stability safety factor of the dangerous rock mass meets the engineering requirements, the corresponding stability reinforcement plan is obtained.

[0032] More specifically, in the rock mass stability assessment model, the rock mass parameter set includes rock mass elastic modulus, internal friction angle, and cohesion parameters, which can be determined by geological engineers. The environmental data set includes rainfall, groundwater level, and earthquake conditions. The above environmental data are regularly updated dynamically based on actual conditions. The stability algorithm method set includes the rigid body limit equilibrium algorithm. The reinforcement stabilization measures set includes anchor cables, anchor piles, and drainage hole reinforcement measures. The expression of the dangerous rock mass stability assessment model is shown in Equation (4): (4), Where, M data are the rock mass parameter set and the environmental data set, and M method is a set of stability algorithm methods, M reinforcement To strengthen the set of stability measures; Based on the geometric characteristic parameter extraction model of dangerous rock mass, the inclination angle of the rear edge structural surface, the area of the rear edge structural surface and the total volume geometric parameters of the dangerous rock mass are obtained, and the dynamic coupling rock mass parameter set and the environmental data set are input into the stability algorithm method set as input conditions. First, the stability safety factor of the dangerous rock mass in the non-reinforced state is evaluated. If it does not meet the engineering requirements, the reinforcement stability measure set is called in. Through continuous iteration until the stability safety factor of the dangerous rock mass meets the engineering requirements, the corresponding stability reinforcement plan is obtained.

[0033] Example 2

[0034] The identification and stability assessment system for dangerous rock masses on steep slopes is shown in the following diagram: Figure 2 As shown in FIG, it consists of a high-steep slope drop point cloud data acquisition module, a dangerous rock mass identification module, a dangerous rock mass geometric feature parameter extraction module, and a dangerous rock mass stability assessment module.

[0035] The high and steep slope drop point cloud data acquisition module is used to plan the UAV flight path based on the high and steep slope gradient, lighting conditions, topography, ground object combination and obstacle distribution, and collect the high and steep slope drop point cloud data through the UAV according to the planned flight path.

[0036] The dangerous rock mass identification module is used to establish a dangerous rock mass identification model based on the point cloud data of the high and steep slope drop, based on the point cloud density mutation detection algorithm and genetic neural network, and to identify the three-dimensional boundaries of the dangerous rock mass.

[0037] The dangerous rock mass geometric characteristic parameter extraction module is used to form an arbitrary dangerous rock mass contour point cloud set based on the dangerous rock mass's three-dimensional boundary, establish a dangerous rock mass geometric characteristic parameter extraction model, and extract the dangerous rock mass geometric characteristic parameters.

[0038] The dangerous rock mass stability assessment module is used to establish a dangerous rock mass stability assessment model including a rock mass parameter set, an environmental data set, and a stability algorithm method set. The geometric characteristic parameters of the dangerous rock mass are coupled with the rock mass parameter set and the environmental data set as input conditions, and input into the stability algorithm method set to evaluate the stability of the dangerous rock mass.

[0039] The specific implementation of each module in this system is consistent with that described in Example 1 and will not be repeated here.

[0040] Example 3

[0041] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the method for identifying and assessing the stability of dangerous rock masses on high and steep slopes as described in Example 1, and the system for identifying and assessing the stability of dangerous rock masses on high and steep slopes as described in Example 2.

[0042] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present application may be implemented in various computer languages, such as object-oriented programming languages Java, C++, Python, and interpreted scripting languages like JavaScript.

[0043] The present application is described with reference to the flowcharts and / or block diagrams of the methods, electronic devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing electronic device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing electronic device generate instructions for implementing the steps in the process. Figure one a process or multiple processes and / or boxes Figure one A device that provides the functions specified in a block or multiple blocks.

[0044] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing electronic device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure one a process or multiple processes and / or boxes Figure one The function specified in one or more boxes.

[0045] These computer program instructions can also be loaded onto a computer or other programmable data processing electronic device so that a series of operating steps are executed on the computer or other programmable electronic device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable electronic device to implement the process. Figure one a process or multiple processes and / or boxes Figure one A step that specifies a function in one or more boxes.

[0046] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application.

[0047] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. The method for identifying and assessing the stability of dangerous rock masses on steep slopes is characterized by: include: Plan the flight path of the UAV based on the steep slope gradient, lighting conditions, topography, ground feature combination, and obstacle distribution, and use the UAV to collect point cloud data of the steep slope drop according to the planned flight path; Based on the point cloud data of high and steep slope drop, a dangerous rock mass identification model was established based on the point cloud density mutation detection algorithm and genetic neural network to identify the three-dimensional boundaries of dangerous rock masses; According to the three-dimensional boundary of the dangerous rock mass, a point cloud set of the contour of any dangerous rock mass is formed, and a geometric characteristic parameter extraction model of the dangerous rock mass is established to extract the geometric characteristic parameters of the dangerous rock mass; A dangerous rock mass stability assessment model is established, which includes a rock mass parameter set, an environmental data set, and a stability algorithm method set. The geometric characteristic parameters of the dangerous rock mass are coupled with the rock mass parameter set and the environmental data set as input conditions and input into the stability algorithm method set to evaluate the stability of the dangerous rock mass.

2. The method for identifying and assessing the stability of dangerous rock masses on high and steep slopes according to claim 1 is characterized by: In the flight path planning of the UAV, based on the target point cloud density ρ target With real-time point cloud density ρ target Difference, target point cloud density ρ target , real-time point cloud density ρ crurrent , slope inclination θ , adjust the drone's flying height in real time H， As shown in the following formula (1): （1）， Where, H The real-time ground height; H 0 is the reference altitude; θ is the slope inclination; ρ target is the target point cloud density; ρ crurrent is the real-time point cloud density.

3. The method for identifying and assessing the stability of dangerous rock masses on high and steep slopes according to claim 2, characterized in that: In the dangerous rock mass identification model, based on the point cloud data of the high and steep slope drop, the local point cloud density difference coefficient K is obtained by the point cloud density mutation detection algorithm. As shown in formula (2), the closer the point cloud density difference coefficient K of adjacent areas is, the greater the possibility that the point cloud is located on the same structural surface, and vice versa. Then, according to the spatial topological relationship of different structural surfaces, the potential boundary contour of the dangerous rock mass is preliminarily identified; Based on the point cloud data of high and steep slope drop, the genetic algorithm continuously optimizes the neural network weights, establishes a genetic neural network algorithm based on the point cloud density difference coefficient K and the contour size of the dangerous rock mass, takes the initially identified potential boundary contour of the dangerous rock mass as the input condition, and realizes the final identification of the three-dimensional boundary of the dangerous rock mass through iterative calculation of the genetic neural network. （2）， Where, σ local is the local density standard deviation; σ global is the global density standard deviation; ρ max 、 ρ min 、 ρ avg are the maximum, minimum and average densities, respectively.

4. The method for identifying and assessing the stability of dangerous rock masses on high and steep slopes according to claim 3 is characterized by: In the geometric characteristic parameter extraction model of dangerous rock mass, an arbitrary dangerous rock mass contour point cloud set is formed based on the identified three-dimensional boundary of the dangerous rock mass, and the point cloud is formed into a number of triangular facets. Through the established intelligent geometric characteristic parameter extraction model of dangerous rock mass, the inclination angle, area and total volume of the trailing edge structural surface of the dangerous rock mass are automatically extracted based on the triangular facets, as shown in formula (3): （3）， Where, α is the inclination angle of the structural surface at the rear edge of the dangerous rock mass; α i The rear edge structural surface of the dangerous rock mass i The angle between the normal vector of each triangle and the vertical direction; A is the structural surface area of the rear edge of the dangerous rock mass; S i The structural surface at the rear edge of the dangerous rock mass i The area of the triangle; V is the volume of dangerous rock mass; A (Z) is the horizontal projection area of the dangerous rock mass at point z; Z min and Z max are the minimum and maximum elevations of dangerous rock masses, respectively.

5. The method for identifying and assessing the stability of dangerous rock masses on high and steep slopes according to claim 4 is characterized by: The dangerous rock mass stability assessment model also includes a set of reinforcement stabilization measures. The geometric characteristic parameters of the dangerous rock mass are coupled with a rock mass parameter set and an environmental data set as input conditions and input into a set of stability algorithm methods. First, the stability safety factor of the dangerous rock mass in the non-reinforced state is evaluated. If it does not meet the engineering requirements, the reinforcement stabilization measure set is introduced. Through continuous iteration until the stability safety factor of the dangerous rock mass meets the engineering requirements, the corresponding stability reinforcement plan is obtained.

6. The method for identifying and assessing the stability of dangerous rock masses on high and steep slopes according to claim 5, characterized in that: In the dangerous rock mass stability assessment model, the rock mass parameter set includes rock mass elastic modulus, internal friction angle, and cohesion parameter; the environmental data set includes rainfall, groundwater level, and earthquake conditions; the stability algorithm method set includes the rigid body limit equilibrium algorithm; and the reinforcement stabilization measures set includes anchor cables, anchor piles, and drainage hole reinforcement measures. The expression of the dangerous rock mass stability assessment model is shown in formula (4): （4）， Where, M data are the rock mass parameter set and the environmental data set, and M method is a set of stability algorithm methods, M reinforcement To strengthen the set of stability measures; Based on the geometric characteristic parameter extraction model of dangerous rock mass, the inclination angle of the rear edge structural surface, the area of the rear edge structural surface and the total volume geometric parameters of the dangerous rock mass are obtained, and the dynamic coupling rock mass parameter set and the environmental data set are input into the stability algorithm method set as input conditions. First, the stability safety factor of the dangerous rock mass in the non-reinforced state is evaluated. If it does not meet the engineering requirements, the reinforcement stability measure set is called in. Through continuous iteration until the stability safety factor of the dangerous rock mass meets the engineering requirements, the corresponding stability reinforcement plan is obtained.

7. A system for identifying and assessing the stability of dangerous rock masses on steep slopes, implementing the method according to any one of claims 1 to 6, characterized in that: It includes high and steep slope drop point cloud data acquisition module, dangerous rock mass identification module, dangerous rock mass geometric characteristic parameter extraction module, and dangerous rock mass stability assessment module; The steep slope drop point cloud data acquisition module is used to plan the UAV flight path based on the steep slope gradient, lighting conditions, topography, ground object combination and obstacle distribution, and collect steep slope drop point cloud data by the UAV according to the planned flight path; The dangerous rock mass identification module is used to establish a dangerous rock mass identification model based on the point cloud data of the high and steep slope drop, based on the point cloud density mutation detection algorithm and genetic neural network, and identify the three-dimensional boundary of the dangerous rock mass; The dangerous rock mass geometric characteristic parameter extraction module is used to form an arbitrary dangerous rock mass contour point cloud set based on the dangerous rock mass's three-dimensional boundary, establish a dangerous rock mass geometric characteristic parameter extraction model, and extract the dangerous rock mass geometric characteristic parameters; The dangerous rock mass stability assessment module is used to establish a dangerous rock mass stability assessment model including a rock mass parameter set, an environmental data set, and a stability algorithm method set. The geometric characteristic parameters of the dangerous rock mass are coupled with the rock mass parameter set and the environmental data set as input conditions, and input into the stability algorithm method set to evaluate the stability of the dangerous rock mass.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for identifying and evaluating the stability of dangerous rock masses on steep slopes as described in any one of claims 1 to 6 is implemented.

Images