Slope stability intelligent monitoring and supporting optimization method based on digital twinning

Abstract

The invention discloses a side slope stability intelligent monitoring and supporting optimization method based on digital twinning, which comprises the following steps: extracting gradient, curvature and geological layering characteristics from a holographic terrain model, calculating a preliminary change trend of stress distribution of a rock-soil body in combination with a finite element analysis method, and determining spatial position distribution of a potential sliding surface of a side slope; according to the space coordinate set of the real-time monitoring point position, the data acquisition frequency of the sensor is adjusted through a time sequence analysis method, and a high-frequency monitoring data set reflecting dynamic changes of stress and underground water is obtained; extracting stress peak values and underground water level fluctuation characteristics from the high-frequency monitoring data set, and generating a multi-dimensional information matrix containing terrain, stress and water dynamics by combining spatial characteristics of the holographic terrain model and adopting a data fusion algorithm; according to the state parameters of the digital twinborn body, if it is judged that the stress distribution exceeds a preset threshold value, the stress distribution of the supporting structure is recalculated through finite element analysis, and an adjusted slope supporting design scheme is obtained.

Description

Technical Field

[0001] The present invention relates to the technical field of digital twins. Specifically, it relates to an intelligent monitoring and support optimization method for slope stability based on digital twins. Background Art

[0002] The research on slope stability is a core topic in the fields of geotechnical engineering and geological disaster prevention and control. Its importance is directly related to the safety of infrastructure construction and the sustainability of the natural environment. Currently, traditional slope analysis methods mostly rely on manual surveys and two-dimensional image data, with defects such as limited coverage, lagging data updates, and insufficient adaptability to complex terrains. When facing slopes with drastic terrain undulations or variable geological conditions, these methods often cannot accurately reflect the true three-dimensional characteristics, resulting in a lack of sufficient scientific basis for subsequent support design. In addition, there is generally blindness in the optimization of sensor layout and data acquisition frequency in existing monitoring means, making it difficult to comprehensively capture the real-time characteristics of the stress distribution of rock and soil masses and the dynamic changes of groundwater.

[0003] In this field, the core challenges focus on how to achieve image data acquisition with strong adaptability to terrain undulations, improve the texture accuracy of three-dimensional models, and the collaborative optimization of sensor layout and data acquisition. Due to the failure to fully combine terrain features and time parameters in image acquisition, the spatial resolution and dynamics of the obtained data are insufficient, thus affecting the accuracy of three-dimensional modeling. At the same time, the randomness in the design of the burial depth and spacing of sensors makes it difficult for monitoring data to accurately reflect the mechanical state and fluid movement laws inside rock and soil masses. These unresolved technical factors lead to the difficulty in achieving the organic integration of multi-dimensional information in slope support design when facing complex geological conditions, forming a bottleneck in technology application.

[0004] Therefore, how to generate a high-precision holographic terrain model through UAV image acquisition and three-dimensional remote sensing technology, and on this basis, optimize the sensor layout and data acquisition frequency to construct a multi-dimensional digital twin of the slope support construction process has become a key issue in improving the reliability of slope stability analysis and design. Summary of the Invention

[0005] In view of the above technical problems in the related art, the present invention provides an intelligent monitoring and support optimization method for slope stability based on digital twins, which can solve the above problems.

[0006] To achieve the above technical objectives, the technical solution of the present invention is realized as follows: An intelligent monitoring and support optimization method for slope stability based on digital twins, comprising the following steps: S100. For a slope area with severe terrain undulation, use a drone equipped with a high-resolution camera and lidar equipment to collect multi-angle image data, and obtain a terrain image dataset that covers comprehensively and has a resolution of centimeter level; S200. Generate an initial 3D model based on the collected terrain image dataset, perform local interpolation processing on the areas with blurred texture, and obtain a holographic terrain model with enhanced texture details; S300. Extract slope, curvature, and geological stratification features from the holographic terrain model, combine with the finite element analysis method to calculate the preliminary change trend of the stress distribution of the rock and soil mass, and determine the spatial position distribution of potential slip surfaces of the slope; S400. Based on the position distribution of the potential slip surfaces of the slope, combine with the buried depth and spacing of the sensors to obtain the spatial coordinate set of real-time monitoring points; S500. According to the spatial coordinate set of real-time monitoring points, adjust the data acquisition frequency of the sensors through time series analysis method, and obtain a high-frequency monitoring dataset that reflects the dynamic changes of stress and groundwater; S600. Extract stress peak values and groundwater level fluctuation characteristics from the high-frequency monitoring dataset, combine with the spatial characteristics of the holographic terrain model, and use a data fusion algorithm to generate a multi-dimensional information matrix containing terrain, stress, and water dynamics; S700. For the multi-dimensional information matrix, use digital twin modeling technology to generate a dynamic simulation body of the slope support construction process, and update the state parameters of the simulation body combined with real-time monitoring data to obtain a digital twin body that reflects the change of slope stability; S800. According to the state parameters of the digital twin body, judge that if the stress distribution exceeds the preset threshold, then recalculate the force distribution of the support structure through finite element analysis to obtain an adjusted slope support design scheme; S900. Extract key parameters from the adjusted slope support design scheme, combine with the latest image data collected by drone remote sensing technology, and optimize the geometric and mechanical characteristics of the digital twin body through an iterative update algorithm to obtain a final digital twin body that is synchronized with the actual slope state.

[0007] Furthermore, S100 specifically includes the following steps: S110. Use a drone device equipped with a camera and lidar to obtain multi-angle image data of the slope area, adjust the flight path to cover the terrain undulation, and obtain a preliminary image dataset; S120. Analyze the preliminary image dataset using a planning algorithm, determine the optimization parameters of the flight path, adjust the acquisition angle and height, and generate optimized flight path data; S130. Control the drone device through the optimized flight path data to obtain high-resolution image data, judge the coverage integrity of the terrain undulation, and obtain a second image dataset; S140. For the second image dataset, use lidar to process the terrain undulation features, determine the depth information of the slope area, and generate a third image dataset containing the depth information; S150. Analyze the third image dataset through the random forest algorithm, judge the correlation between the image data and the terrain undulation, and obtain the classified terrain feature data; S160. According to the classified terrain feature data, optimize the acquisition perspective using the height adjustment parameter, obtain the final image data, and generate a dataset with a resolution reaching the centimeter level; S170. Through the final image dataset, use the rasterization processing method to determine the full-coverage characteristics of the slope area and obtain the terrain image dataset.

[0008] Further, S200 specifically includes the following steps: S210. Obtain point cloud data through the terrain image and use the structured light algorithm to process and generate three-dimensional structure data; S220. Extract the motion recovery features from the three-dimensional structure data and fuse the point cloud data to generate a preliminary three-dimensional model; S230. Detect the texture-blurred areas for the preliminary three-dimensional model and use the local interpolation technique to repair the blurred parts to obtain an optimized three-dimensional model; S240. Analyze the texture detail features according to the optimized three-dimensional model, judge the integrity of the detail enhancement, and generate holographic three-dimensional data; S250. Extract the image processing parameters through the holographic three-dimensional data, adjust the data fusion method, and obtain a fusion-optimized dataset; S260. Generate a final holographic model using the fusion-optimized dataset, determine the three-dimensional generation consistency, and obtain a full-coverage terrain model; S270. Analyze the terrain feature distribution for the full-coverage terrain model, classify the features through the random forest algorithm, and obtain the classified terrain data.

[0009] Further, S300 specifically includes the following steps: S310. Extract the slope data and curvature data through the holographic terrain model, obtain the terrain feature distribution information, and obtain the initial terrain parameter set; S320. Combine the initial terrain parameter set with the geological stratification data to generate a description of the geotechnical body characteristics and determine the geotechnical body characteristic set; S330. Obtain the parameters required for stress distribution calculation from the geotechnical body characteristic set and use the finite element analysis method to obtain the stress distribution change trend; S340. Analyze the spatial characteristics of the sliding surface position for the stress distribution change trend and determine the preliminary distribution range of the potential sliding surface; S350. Adjust the boundary conditions of the sliding surface position by combining the preliminary distribution range with the curvature data to obtain the optimized sliding surface distribution. S360. If there is a deviation between the optimized sliding surface distribution and the geological stratification data, supplement the geotechnical characteristics information through data acquisition to determine the final spatial position of the sliding surface. S370. Extract the classification basis of the terrain features according to the final spatial position, and use the random forest algorithm for classification to obtain the slope stability zoning data.

[0010] Furthermore, S400 specifically includes the following steps: S410. Generate an initial point grid through the position distribution of the sliding surface position, and use the genetic algorithm to optimize the burial depth and spacing to obtain the adjusted sensor layout parameters. S420. Determine the coverage range of the key area according to the adjusted sensor layout parameters to obtain the optimized sensor layout plan. S430. For the optimized sensor layout plan, extract the point coordinates of real-time monitoring from the spatial set to obtain the monitoring point distribution data. S440. If the monitoring point distribution data is inconsistent with the boundary conditions of the key area, supplement the point coordinates through the position distribution to judge the adjusted point distribution range. S450. Use the adjusted point distribution range to obtain the dynamic monitoring data of the sliding surface position and determine the coverage integrity of real-time monitoring. S460. Through the coverage integrity of real-time monitoring, combined with the genetic algorithm to analyze the stability of the point coordinates, obtain the final sensor layout plan. S470. According to the final sensor layout plan, extract the monitoring point set of the key area from the spatial set to obtain the spatial coordinate result of real-time monitoring.

[0011] Furthermore, S500 specifically includes the following steps: S510. Obtain the initial data distribution of real-time monitoring through the spatial coordinate set, and use time series analysis to process the time interval of data acquisition to obtain the adjusted acquisition frequency parameter. S520. For the adjusted acquisition frequency parameter, extract the fluctuation characteristics of stress changes from real-time monitoring to obtain the time series set of high-frequency data. S530. If the stress change in the time series set of high-frequency data exceeds the preset threshold, update the acquisition frequency through sensor adjustment to obtain the monitoring data set reflecting the dynamic changes. S540. According to the monitoring data set reflecting the dynamic changes, obtain the fluctuation characteristics of the groundwater level and determine the time series correlation corresponding to the stress change. S550. Analyze the trend of dynamic changes through time series correlation analysis, and use a clustering algorithm to divide the distribution area of high-frequency data to obtain the characteristic grouping of point distribution. S560. For the characteristic grouping of point distribution, extract the key monitoring points related to dynamic changes from the spatial coordinates to obtain the spatial coverage range of high-frequency data. S570. According to the spatial coverage range of high-frequency data, adjust the sensor parameters of real-time monitoring to obtain an optimized monitoring data set.

[0012] Furthermore, S600 specifically includes the following steps: S610. Extract the stress peak and the fluctuation characteristics of the groundwater level from high-frequency monitoring data to generate an initial feature set. S620. Use a data fusion algorithm to process the initial feature set and combine it with the spatial distribution of the holographic terrain model to obtain a multi-dimensional information matrix. S630. According to the multi-dimensional information matrix, divide the dynamic change area of the spatial distribution to determine the distribution range of terrain characteristics. S640. If the dynamic change area exceeds the preset threshold, adjust the time interval of high-frequency monitoring through the monitoring data to obtain an updated feature set. S650. For the updated feature set, use a clustering algorithm to divide the distribution pattern of the fluctuation characteristics to generate a classified information matrix. S660. Extract the key terrain characteristics related to the spatial distribution from the classified information matrix to obtain an optimized multi-dimensional information matrix. S670. Analyze the correlation between the fluctuation characteristics and the dynamic changes through the optimized multi-dimensional information matrix to generate a final monitoring distribution set.

[0013] Furthermore, S700 specifically includes the following steps: S710. Obtain the spatial distribution characteristics of slope support through the multi-dimensional information matrix to generate an initial simulation body state. S720. Use digital twin modeling technology to process the initial simulation body state to obtain a dynamic simulation body. S730. Extract the state parameters from the real-time monitoring data and update the operating conditions of the dynamic simulation body to obtain an adjusted simulation body state. S740. For the adjusted simulation body state, analyze the spatial change trend of the construction process to determine the distribution range of stability changes. S750. If the distribution range of stability changes exceeds the preset threshold, adjust the data update frequency through the real-time monitoring data to obtain optimized state parameters. S760. According to the optimized state parameters, use a clustering algorithm to divide the fluctuation pattern of the dynamic simulation body to obtain a classified simulation body state. S770. Analyze the correlation between slope support and stability changes through the classified simulation body state, and generate the final simulation body state.

[0014] Further, S800 specifically includes the following steps: S810. If the stress distribution exceeds the preset threshold, process the force distribution of the support structure through finite element analysis to obtain a preliminary adjustment plan; S820. Extract the change characteristics of the force distribution through the preliminary adjustment plan, and generate the distribution grid of the support structure by using the interpolation method; S830. Analyze the spatial characteristics of slope support for the distribution grid to obtain the optimized force distribution; S840. If the optimized force distribution still exceeds the preset threshold, adjust the boundary conditions of the finite element analysis through state parameters to obtain an updated adjustment plan; S850. Divide the force area of the support structure according to the updated adjustment plan, and use the clustering algorithm to determine the distribution law between regions; S860. Generate the dynamic update parameters of slope support through the distribution law to obtain the final support plan; S870. Analyze the fluctuation trend of stress distribution for the final support plan to determine the dynamic update frequency.

[0015] Further, S900 specifically includes the following steps: S910. Obtain the latest image data through remote sensing technology, and process the image data by using the filtering method to obtain a clear representation of the slope state; S920. Extract key parameters from the slope state representation, combine with the initial data in the design plan, and adjust the geometric characteristics by using the iterative update algorithm to obtain a preliminary updated digital twin; S930. For the preliminary updated digital twin, analyze the mechanical characteristics through the extraction process. If the mechanical characteristics are inconsistent with the slope state, adjust the iteration step of the update algorithm to obtain an optimized digital twin; S940. According to the optimized digital twin, analyze the matching degree between the image data and the geometric characteristics, generate the synchronous adjustment spatial distribution by using the interpolation method, and determine the boundary conditions of the mechanical characteristics; S950. Extract the change characteristics from the synchronous adjustment spatial distribution, update the design plan in combination with the key parameters to obtain a digital twin consistent with the actual slope state; S960. For the consistent digital twin, obtain the dynamic image data through remote sensing technology. If the image data exceeds the preset threshold, adjust the weights of the geometric characteristics and the mechanical characteristics to obtain the final digital twin; S970. Based on the final digital twin, use a clustering algorithm to divide the regional characteristics of the slope state and determine the update frequency for synchronous adjustment.

[0016] Advantages of the present invention: This application realizes the all-round monitoring of slope topography, stress and water dynamics, as well as the real-time optimization of the support plan, significantly improving the safety and efficiency of the slope construction process and providing an intelligent solution for slope engineering under complex terrain conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0018] The present invention will be further described in detail below with reference to the drawings.

[0019] Figure 1 It is a flowchart of an intelligent monitoring and support optimization method for slope stability based on digital twin according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the 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 of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0021] As Figure 1 shown, according to the present invention, an intelligent monitoring and support optimization method for slope stability based on digital twin is disclosed, including the following steps: S100. For the slope area with severe terrain undulation, collect multi-angle image data through an unmanned aerial vehicle equipped with a high-resolution camera and a lidar device to obtain a terrain image dataset that covers the entire area and has a resolution of centimeter level.

[0022] By equipping a drone device with a camera and a lidar, multi-angle image data of the slope area is obtained. The flight path is adjusted to cover the terrain undulations, and a preliminary image dataset is obtained. The preliminary image dataset is analyzed using a planning algorithm to determine the optimization parameters of the flight path, and the acquisition perspective and height are adjusted to generate optimized flight path data. The drone device is controlled by the optimized flight path data to obtain high-resolution image data, and the coverage integrity of the terrain undulations is judged to obtain a second image dataset. For the second image dataset, the lidar is used to process the terrain undulation features to determine the depth information of the slope area, and a third image dataset containing depth information is generated. The third image dataset is analyzed using a random forest algorithm to judge the correlation between the image data and the terrain undulations, and the classified terrain feature data is obtained. According to the classified terrain feature data, the acquisition perspective is optimized using the height adjustment parameters to obtain the final image data, and a dataset with a resolution of up to centimeter level is generated. Through the final image dataset, a rasterization processing method is used to determine the full coverage characteristics of the slope area, and a terrain image dataset is obtained.

[0023] S200. Generate an initial three-dimensional model based on the collected terrain image dataset, and perform local interpolation processing on the texture-blurred areas to obtain a holographic terrain model with enhanced texture details.

[0024] Point cloud data is obtained through the terrain image, and a three-dimensional structure data is generated by processing using the structured light algorithm. The motion recovery features are extracted from the three-dimensional structure data, and the point cloud data is fused to generate a preliminary three-dimensional model. The texture-blurred areas are detected for the preliminary three-dimensional model, and the blurred parts are repaired using local interpolation techniques to obtain an optimized three-dimensional model. The texture detail features are analyzed based on the optimized three-dimensional model to judge the integrity of the detail enhancement, and holographic three-dimensional data is generated. The image processing parameters are extracted from the holographic three-dimensional data, and the data fusion method is adjusted to obtain a fused and optimized dataset. The final holographic model is generated using the fused and optimized dataset to determine the three-dimensional generation consistency, and a full coverage terrain model is obtained. The terrain feature distribution is analyzed for the full coverage terrain model, and the features are classified using a random forest algorithm to obtain the classified terrain data.

[0025] S300. Extract the slope, curvature, and geological stratification features from the holographic terrain model, and combine the finite element analysis method to calculate the preliminary change trend of the stress distribution of the rock and soil mass, and determine the spatial position distribution of the potential slip surface of the slope.

[0026] The slope data and curvature data are extracted through the holographic model to obtain the terrain feature distribution information, and an initial terrain parameter set is obtained. The calculation formula is: , where S represents the terrain feature parameter, z represents the elevation value, x represents the spatial coordinate, represents the slope, represents the curvature, and n represents the number of spatial coordinates.

[0027] Using the initial terrain parameter set combined with geological stratification data, generate a description of the geotechnical body characteristics and determine the geotechnical body characteristic set. Obtain the parameters required for stress distribution calculation from the geotechnical body characteristic set, and use the finite element analysis method to obtain the stress distribution change trend. Its stress distribution function is: , where σ represents the stress distribution function, represents the vertical load, A represents the acting area, represents the bending moment, represents the moment of inertia, and h represents the calculation depth.

[0028] Analyze the spatial characteristics of the sliding surface position based on the stress distribution change trend, and determine the preliminary distribution range of the potential sliding surface. Combine the preliminary distribution range with the curvature data to adjust the boundary conditions of the sliding surface position, and obtain the optimized sliding surface distribution. The calculation formula for its sliding surface distribution index is: , where D represents the sliding surface distribution index, r represents the radius of curvature, d represents the depth parameter, α represents the dip angle coefficient, and P represents the number of sliding surfaces.

[0029] If there is a deviation between the optimized sliding surface distribution and the geological stratification data, supplement the geotechnical body characteristic information through data acquisition to judge the final spatial position of the sliding surface. Extract the classification basis of the terrain characteristics according to the final spatial position, and use the random forest algorithm to process the classification to obtain the slope stability zoning data. Its corresponding slope stability index is: , where F represents the slope stability index, c represents the cohesion, σ represents the normal stress, φ represents the internal friction angle, T represents the shear force, and m represents the number of sliding surfaces.

[0030] S400. Based on the position distribution of the potential sliding surface of the slope, combined with the buried depth and spacing of the sensors, obtain the spatial coordinate set of the real-time monitoring points.

[0031] Generate an initial point grid through the position distribution of the sliding surface position, use the genetic algorithm to process the optimization of the buried depth and spacing, and obtain the adjusted sensor layout parameters. According to the adjusted sensor layout parameters, determine the coverage range of the key area and obtain the optimized sensor layout plan. For the optimized sensor layout plan, extract the point coordinates of the real-time monitoring from the spatial set to obtain the monitoring point distribution data. If the monitoring point distribution data is inconsistent with the boundary conditions of the key area, supplement the point coordinates through the position distribution to judge the adjusted point distribution range. Use the adjusted point distribution range to obtain the dynamic monitoring data of the sliding surface position and determine the coverage integrity of the real-time monitoring. Through the coverage integrity of the real-time monitoring, combined with the genetic algorithm to analyze the stability of the point coordinates, obtain the final sensor layout plan. According to the final sensor layout plan, extract the monitoring point set of the key area from the spatial set to obtain the spatial coordinate result of the real-time monitoring.

[0032] S500. Adjust the data acquisition frequency of the sensors through time series analysis method according to the spatial coordinate set of real-time monitoring points, and obtain a high-frequency monitoring data set reflecting the dynamic changes of stress and groundwater.

[0033] Obtain the initial data distribution of real-time monitoring through the spatial coordinate set, adopt time series analysis to process the time interval of data acquisition, and obtain the adjusted acquisition frequency parameter. For the adjusted acquisition frequency parameter, extract the fluctuation characteristics of stress changes from real-time monitoring to obtain the time series set of high-frequency data. If the stress change in the time series set of high-frequency data exceeds the preset threshold, adjust and update the acquisition frequency through the sensor to obtain a monitoring data set reflecting dynamic changes. According to the monitoring data set reflecting dynamic changes, obtain the fluctuation characteristics of the groundwater level and determine the time series correlation corresponding to the stress change.

[0034] The fluctuation characteristics of the groundwater level are expressed by the groundwater level fluctuation characteristic function F(s) as: , where W represents the water level observation value, m represents the number of observations, α represents the fluctuation coefficient, β represents the spatial influence factor, s represents the spatial distance, represents the difference in the observation time between two adjacent water level observations.

[0035] Analyze the trend of dynamic changes through time series correlation, use the clustering algorithm to divide the distribution area of high-frequency data, and obtain the characteristic grouping of point distribution. For the characteristic grouping of point distribution, extract the key monitoring points related to dynamic changes from the spatial coordinates to obtain the spatial coverage range of high-frequency data. According to the spatial coverage range of high-frequency data, adjust the sensor parameters of real-time monitoring to obtain an optimized monitoring data set.

[0036] The sensor parameter optimization function S(v) is expressed as: , v p represents the current parameter value, k represents the number of parameters, γ represents the optimization coefficient, v max and v min represent the maximum and minimum values of the parameters respectively.

[0037] S600. Extract the stress peak and the fluctuation characteristics of the groundwater level from the high-frequency monitoring data set, combine the spatial characteristics of the holographic terrain model, and use the data fusion algorithm to generate a multi-dimensional information matrix including terrain, stress and water dynamics.

[0038] Extract the peak stress and the fluctuation characteristics of the groundwater level from the high-frequency monitoring data to generate an initial feature set. Use a data fusion algorithm to process the initial feature set and combine it with the spatial distribution of the holographic terrain model to obtain a multi-dimensional information matrix. Divide the dynamically changing areas of the spatial distribution according to the multi-dimensional information matrix to determine the distribution range of the terrain features. If the dynamically changing area exceeds the preset threshold, adjust the time interval of the high-frequency monitoring through the monitoring data to obtain an updated feature set. For the updated feature set, use a clustering algorithm to divide the distribution patterns of the fluctuation features and generate a classified information matrix. Extract the key terrain features related to the spatial distribution from the classified information matrix to obtain an optimized multi-dimensional information matrix. Analyze the correlation between the fluctuation features and the dynamic changes through the optimized multi-dimensional information matrix to generate a final monitoring distribution set.

[0039] S700. For the multi-dimensional information matrix, use digital twin modeling technology to generate a dynamic simulation of the slope support construction process, and update the state parameters of the simulation in combination with real-time monitoring data to obtain a digital twin that reflects the changes in slope stability.

[0040] Obtain the spatial distribution characteristics of the slope support through the multi-dimensional information matrix to generate an initial simulation state. Use digital twin modeling technology to process the initial simulation state to obtain a dynamic simulation. Extract the state parameters from the real-time monitoring data and update the operating conditions of the dynamic simulation to obtain an adjusted simulation state. For the adjusted simulation state, analyze the spatial change trend of the construction process to determine the distribution range of the stability changes. If the distribution range of the stability changes exceeds the preset threshold, adjust the data update frequency through the real-time monitoring data to obtain optimized state parameters. According to the optimized state parameters, use a clustering algorithm to divide the fluctuation patterns of the dynamic simulation to obtain a classified simulation state. Analyze the correlation between the slope support and the stability changes through the classified simulation state to generate a final simulation state.

[0041] S800. According to the state parameters of the digital twin, if it is judged that the stress distribution exceeds the preset threshold, recalculate the force distribution of the support structure through finite element analysis to obtain an adjusted slope support design scheme.

[0042] If the stress distribution exceeds the preset threshold, the force distribution of the support structure is processed through finite element analysis to obtain a preliminary adjustment plan. The change characteristics of the force distribution are extracted from the preliminary adjustment plan, and an interpolation method is used to generate the distribution grid of the support structure. The spatial characteristics of the slope support are analyzed for the distribution grid to obtain the optimized force distribution. If the optimized force distribution still exceeds the preset threshold, the boundary conditions of the finite element analysis are adjusted through state parameters to obtain an updated adjustment plan. The force area of the support structure is divided according to the updated adjustment plan, and a clustering algorithm is used to determine the distribution law between regions. The dynamic update parameters of the slope support are generated through the distribution law to obtain the final support plan. The fluctuation trend of the stress distribution is analyzed for the final support plan to determine the dynamic update frequency.

[0043] S900. Extract key parameters from the adjusted slope support design plan, combine with the latest image data collected by the UAV remote sensing technology, and optimize the geometric and mechanical characteristics of the digital twin through the iterative update algorithm to obtain the final digital twin synchronized with the actual slope state.

[0044] The latest image data is obtained through remote sensing technology, and the image data is processed by a filtering method to obtain a clear representation of the slope state. Key parameters are extracted from the slope state representation, combined with the initial data in the design plan, and the geometric characteristics are adjusted using an iterative update algorithm to obtain a preliminary updated digital twin. For the preliminary updated digital twin, the mechanical characteristics are analyzed through the extraction process. If it is determined that the mechanical characteristics are inconsistent with the slope state, the iteration step of the update algorithm is adjusted to obtain an optimized digital twin. Based on the optimized digital twin, the matching degree between the image data and the geometric characteristics is analyzed, and an interpolation method is used to generate a synchronously adjusted spatial distribution to determine the boundary conditions of the mechanical characteristics. The change characteristics are extracted from the synchronously adjusted spatial distribution, combined with the key parameters to update the design plan, and a digital twin consistent with the actual slope state is obtained. For the consistent digital twin, dynamic image data is obtained through remote sensing technology. If it is determined that the image data exceeds the preset threshold, the weights of the geometric and mechanical characteristics are adjusted to obtain the final digital twin. Based on the final digital twin, a clustering algorithm is used to divide the regional characteristics of the slope state to determine the update frequency of the synchronous adjustment.

[0045] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for intelligent monitoring and support optimization of slope stability based on digital twins, characterized in that: The steps include: S100, for slope areas with dramatic terrain fluctuations, uses drones equipped with high-resolution cameras and lidar equipment to collect multi-angle image data, obtaining a comprehensive terrain image dataset with a centimeter-level resolution; S200, generating an initial three-dimensional model according to the collected terrain image data set, performing local interpolation processing on the texture fuzzy area, and obtaining a holographic terrain model with enhanced texture details; S300, extract the slope, curvature and geological stratification characteristics from the holographic terrain model, calculate the initial change trend of the stress distribution of the rock and soil mass by combining the finite element analysis method, and determine the spatial position distribution of the potential sliding surface of the slope; S400, based on the position distribution of the potential sliding surface of the slope, combined with the buried depth and spacing of the sensors, a spatial coordinate set of real-time monitoring points is obtained; S500, adjusting the data acquisition frequency of the sensor by a time series analysis method according to the spatial coordinate set of the real-time monitoring points, and obtaining a high-frequency monitoring data set reflecting the dynamic changes of stress and groundwater; S600, extracting stress peaks and groundwater level fluctuation characteristics from high-frequency monitoring data sets, combining them with the spatial characteristics of the holographic terrain model, and using data fusion algorithms to generate a multidimensional information matrix containing terrain, stress, and water dynamics; S700. Based on the multi-dimensional information matrix, the digital twin modeling technology is used to generate a dynamic simulation body of the slope support construction process, and the state parameters of the simulation body are updated in combination with the real-time monitoring data to obtain a digital twin body that reflects the changes in slope stability; S800, judging, based on the state parameters of the digital twin, that if the stress distribution exceeds a preset threshold, recalculating the force distribution of the support structure through finite element analysis to obtain an adjusted slope support design scheme; S900 extracts key parameters from the adjusted slope support design scheme, combines the latest image data collected by UAV remote sensing technology, optimizes the geometric and mechanical characteristics of the digital twin through an iterative update algorithm, and obtains the final digital twin that is synchronized with the actual slope status.

2. According to claim 1, a method for intelligent monitoring and support optimization of slope stability based on digital twins is characterized in that: S100 specifically includes the following steps: S110, using a drone equipped with a camera and a laser radar to obtain multi-angle image data of the slope area, adjusting the flight path to cover the terrain undulations, and obtaining a preliminary image data set; S120, using a planning algorithm to analyze the preliminary image data set, determine the optimization parameters of the flight path, adjust the acquisition angle and height, and generate optimized flight path data; S130, controlling the UAV device through the optimized flight path data, acquiring high-resolution image data, determining the coverage completeness of the terrain undulations, and obtaining a second image data set; S140, for the second image data set, using laser radar to process terrain undulation features, determine depth information of the slope area, and generate a third image data set containing depth information; S150, analyzing the third image data set by using a random forest algorithm, determining the correlation between the image data and the terrain undulation, and obtaining classified terrain feature data; S160, according to the classified terrain feature data, using height adjustment parameters to optimize the acquisition viewing angle, obtain final image data, and generate a data set with a resolution of centimeters; S170. Using the final image data set, a rasterization processing method is used to determine the full coverage characteristics of the slope area, thereby obtaining a terrain image data set.

3. The method for intelligent monitoring and support optimization of slope stability based on digital twin according to claim 1 is characterized in that: S200 specifically includes the following steps: S210, acquiring point cloud data through terrain images, and processing with a structured light algorithm to generate three-dimensional structure data; S220, extracting motion recovery features from the three-dimensional structure data, and fusing the point cloud data to generate a preliminary three-dimensional model; S230, detecting the texture fuzzy area of ​​the preliminary three-dimensional model, and repairing the fuzzy part using a local interpolation technique to obtain an optimized three-dimensional model; S240, analyzing texture detail features according to the optimized three-dimensional model, determining detail enhancement integrity, and generating holographic three-dimensional data; S250, extracting image processing parameters through holographic three-dimensional data, adjusting the data fusion method, and obtaining a fusion optimized data set; S260, using the fused optimized data set to generate a final holographic model, determining the consistency of the three-dimensional generation, and obtaining a full coverage terrain model; S270, analyzing the distribution of terrain features for the full coverage terrain model, classifying the features through a random forest algorithm, and obtaining classified terrain data.

4. The method for intelligent monitoring and support optimization of slope stability based on digital twin according to claim 1 is characterized in that: S300 specifically includes the following steps: S310, extracting slope data and curvature data through the holographic terrain model, obtaining terrain feature distribution information, and obtaining an initial terrain parameter set; S320, using the initial terrain parameter set in combination with the geological stratification data to generate a rock and soil mass feature description and determine a rock and soil mass feature set; S330, obtaining parameters required for stress distribution calculation from the rock and soil mass feature set, and using a finite element analysis method to obtain a stress distribution change trend; S340, analyzing the spatial characteristics of the sliding surface according to the stress distribution change trend, and determining the preliminary distribution range of the potential sliding surface; S350, adjusting the boundary conditions of the sliding surface position by combining the preliminary distribution range with the curvature data to obtain an optimized sliding surface distribution; S360, if there is a deviation between the optimized sliding surface distribution and the geological stratification data, supplement the rock and soil body characteristic information through data acquisition to determine the final spatial position of the sliding surface; S370. Extract the classification basis of the terrain features according to the final spatial position, use the random forest algorithm to process the classification, and obtain the slope stability zoning data.

5. The method for intelligent monitoring and support optimization of slope stability based on digital twin according to claim 1 is characterized in that: S400 specifically includes the following steps: S410, generating an initial point grid through the position distribution of the sliding surface, using a genetic algorithm to process the burial depth and spacing optimization, and obtaining adjusted sensor layout parameters; S420, determining the coverage of the key area according to the adjusted sensor layout parameters, and obtaining an optimized sensor layout plan; S430, extracting the coordinates of the points to be monitored in real time from the spatial set for the optimized sensor deployment plan, and obtaining the distribution data of the monitoring points; S440, if the monitoring point distribution data is inconsistent with the boundary conditions of the key area, the point coordinates are supplemented by the position distribution to determine the adjusted point distribution range; S450, using the adjusted point distribution range, obtaining dynamic monitoring data of the sliding surface, and determining the coverage integrity of the real-time monitoring; S460, by real-time monitoring of coverage integrity and combining genetic algorithm to analyze the stability of point coordinates, the final sensor deployment plan is obtained; S470. According to the final sensor deployment plan, a monitoring point set of a key area is extracted from the spatial set to obtain a spatial coordinate result of real-time monitoring.

6. The method for intelligent monitoring and support optimization of slope stability based on digital twin according to claim 1 is characterized in that: S500 specifically includes the following steps: S510, obtaining the initial data distribution of real-time monitoring through the spatial coordinate set, using time series analysis to process the time interval of data collection, and obtaining the adjusted collection frequency parameter; S520, extracting the fluctuation characteristics of stress changes from real-time monitoring for the adjusted acquisition frequency parameters, and obtaining a time series set of high-frequency data; S530, if the stress change in the time series set of high-frequency data exceeds a preset threshold, the acquisition frequency is adjusted and updated through the sensor to obtain a monitoring data set reflecting the dynamic change; S540, obtaining the fluctuation characteristics of the groundwater level based on the monitoring data set reflecting the dynamic changes, and determining the time series correlation corresponding to the stress changes; S550, analyzing the trend of dynamic changes through time series correlation, using clustering algorithm to divide the distribution area of ​​high-frequency data, and obtaining characteristic grouping of point distribution; S560, based on the feature grouping of point distribution, extracting key monitoring points related to dynamic changes from spatial coordinates, and obtaining the spatial coverage of high-frequency data; S570: According to the spatial coverage of the high-frequency data, adjust the sensor parameters of the real-time monitoring to obtain an optimized monitoring data set.

7. The method for intelligent monitoring and support optimization of slope stability based on digital twin according to claim 1 is characterized in that: S600 specifically includes the following steps: S610, extracting stress peak value and groundwater level fluctuation characteristics through high-frequency monitoring data to generate an initial feature set; S620, using a data fusion algorithm to process the initial feature set, combined with the spatial distribution of the holographic terrain model, to obtain a multi-dimensional information matrix; S630, dividing the dynamically changing area of ​​spatial distribution according to the multi-dimensional information matrix, and determining the distribution range of the terrain features; S640: If the dynamically changing area exceeds a preset threshold, the time interval of high-frequency monitoring is adjusted according to the monitoring data to obtain an updated feature set; S650, for the updated feature set, using a clustering algorithm to divide the distribution pattern of the fluctuation features to generate a classified information matrix; S660, extracting key terrain features related to spatial distribution from the classified information matrix to obtain an optimized multi-dimensional information matrix; S670. Analyze the correlation between the fluctuation characteristics and the dynamic changes through the optimized multi-dimensional information matrix to generate the final monitoring distribution set.

8. The method for intelligent monitoring and support optimization of slope stability based on digital twin according to claim 1 is characterized in that: S700 specifically includes the following steps: S710, obtaining spatial distribution characteristics of slope support through a multi-dimensional information matrix, and generating an initial simulation shape; S720, using digital twin modeling technology to process the initial simulation body shape to obtain a dynamic simulation body; S730, extracting state parameters from the real-time monitoring data, updating the operating conditions of the dynamic simulation body, and obtaining an adjusted simulation body state; S740, analyzing the spatial variation trend of the construction process for the adjusted simulation shape, and determining the distribution range of the stability variation; S750, if the distribution range of the stability change exceeds a preset threshold, adjusting the frequency of data update through real-time monitoring data to obtain optimized state parameters; S760, using a clustering algorithm to divide the fluctuation mode of the dynamic simulation body according to the optimized state parameters, and obtaining a classified simulation body shape; S770. Analyze the correlation between slope support and stability change through the classified simulation shape to generate a final simulation shape.

9. The method for intelligent monitoring and support optimization of slope stability based on digital twin according to claim 1 is characterized in that: S800 specifically includes the following steps: S810, if the stress distribution exceeds a preset threshold, the stress distribution of the support structure is processed by finite element analysis to obtain a preliminary adjustment plan; S820, extracting the change characteristics of the force distribution through the preliminary adjustment scheme, and generating the distribution grid of the support structure by using the interpolation method; S830, analyzing the spatial characteristics of the slope support according to the distribution grid to obtain an optimized force distribution; S840, if the optimized force distribution still exceeds the preset threshold, adjusting the boundary conditions of the finite element analysis through the state parameters to obtain an updated adjustment plan; S850, dividing the stress-bearing areas of the branch protection structure according to the updated adjustment plan, and using a clustering algorithm to determine the distribution pattern between the areas; S860, generating dynamic update parameters of slope support through distribution law, and obtaining a final support plan; S870. Analyze the fluctuation trend of stress distribution for the final support scheme and determine the frequency of dynamic update.

10. The method for intelligent monitoring and support optimization of slope stability based on digital twin according to claim 1, characterized in that: S900 specifically includes the following steps: S910, obtain the latest image data through remote sensing technology, use filtering method to process the image data, and obtain a clear representation of the slope status; S920, extract key parameters from the slope state representation, combine with the initial data in the design scheme, use an iterative update algorithm to adjust the geometric characteristics, and obtain a preliminary updated digital twin; S930, for the initially updated digital twin, analyzing the mechanical properties through the extraction process, and if it is determined that the mechanical properties are inconsistent with the slope state, adjusting the iteration step size of the update algorithm to obtain an optimized digital twin; S940, analyzing the matching degree between the image data and the geometric characteristics according to the optimized digital twin, generating the spatial distribution of synchronous adjustment by using the interpolation method, and determining the boundary conditions of the mechanical characteristics; S950, extract the change characteristics from the spatial distribution of synchronous adjustment, update the design scheme in combination with key parameters, and obtain a digital twin consistent with the actual slope state; S960, for the consistent digital twin, obtain dynamic image data through remote sensing technology, and if it is determined that the image data exceeds a preset threshold, adjust the weights of the geometric characteristics and the mechanical characteristics to obtain the final digital twin; S970. Based on the final digital twin, a clustering algorithm is used to divide the regional characteristics of the slope state and determine the update frequency of the synchronous adjustment.

Images