Landslide monitoring method and system based on multiple source parameters

Abstract

The application provides a landslide monitoring method and system based on multi-source parameters, wherein the method comprises: periodically acquiring ground surface information of a landfill by a drone, and generating a dynamic three-dimensional cloud model according to the ground surface information; acquiring monitoring data of a heap body and a dam body in the landfill; performing multi-source parameter analysis on the landfill according to the three-dimensional cloud model and the monitoring data to obtain risk assessment parameters; and performing landslide monitoring on the landfill according to the risk assessment parameters. The application can improve the accuracy of landfill monitoring.

Description

Technical Field

[0001] This application relates to the field of data monitoring technology, specifically to a landslide monitoring method and system based on multi-source parameters. Background Technology

[0002] Landfills are the final disposal sites for municipal solid waste and industrial waste. The waste piles in landfills store large amounts of waste materials, and long-term settling, decomposition, and leaching can lead to ground instability. Landslides can cause secondary pollution and threaten the surrounding environment. Therefore, monitoring the stability of landfills is essential.

[0003] Municipal solid waste landfills have unique characteristics: the waste is highly corrosive, chemical reactions are ongoing, the landfill itself is loose and easily deformable, displacement and settlement changes are significant, stability is poor, the landfill area is large, and the landfill volume is substantial. Traditional landfill landslide monitoring mainly relies on on-site sensors, such as displacement gauges, strain gauges, and water level gauges. These sensors need to be deployed at key locations within the landfill to monitor the deformation of the waste pile and retaining dam in real time.

[0004] However, traditional methods can only monitor key areas of landfills, while landfills are constantly changing, making it difficult for traditional monitoring methods to accurately monitor the entire landfill area. Summary of the Invention

[0005] This application provides a landslide monitoring method and system based on multi-source parameters, which can improve the accuracy of landfill monitoring.

[0006] In a first aspect, this application provides a landslide monitoring method based on multi-source parameters, comprising: The surface information of the landfill is periodically acquired by drones, and a dynamic three-dimensional cloud model is generated based on the surface information. Acquire monitoring data of the landfill's stockpile and dam structures; Based on the three-dimensional cloud model and the monitoring data, multi-source parameter analysis was performed on the landfill to obtain risk assessment parameters; Landslide monitoring was conducted on the landfill based on the aforementioned risk assessment parameters.

[0007] By employing the aforementioned technical solution and combining two data sources—a UAV 3D cloud model and sensor monitoring data—comprehensive, three-dimensional monitoring of the landfill was achieved. The 3D cloud model, acquired periodically by the UAV, dynamically reflects changes in the overall surface morphology of the landfill, enabling the detection of anomalies such as surface subsidence and collapse. Simultaneously, various sensors embedded in key areas of the landfill can detect minute deformations within the landfill structure and dam. The 3D cloud model and sensor monitoring data complement each other, jointly depicting the overall stability of the landfill.

[0008] Based on the acquisition of internal and external monitoring data from the landfill, the aforementioned technical solution further utilizes multi-source parameter analysis algorithms to fuse various data types. Compared to a single data source, multi-source parameter analysis can fully uncover the inherent connections and dependencies between different data, resulting in more accurate and reliable assessment results. The risk assessment parameters obtained from data fusion more comprehensively reflect the key factors affecting the stability of the landfill.

[0009] Finally, the aforementioned technical solution establishes a landslide monitoring model capable of real-time monitoring and early warning of landslide risks at landfills based on risk assessment parameters. Compared to traditional manual periodic inspections, this model achieves dynamic real-time monitoring of landslide conditions at landfills. Timely early warnings facilitate immediate response measures, minimizing losses caused by landslides.

[0010] In summary, the above technical solutions, by integrating multi-source data, parameter correlation analysis, and modeling and early warning technologies, have achieved accurate assessment and effective monitoring of landslide risks at landfills.

[0011] Optionally, the surface information includes multiple surface photographs, and the step of periodically acquiring the surface information of the landfill via drones and generating a dynamic three-dimensional cloud model based on the surface information includes: The drone is controlled according to a preset flight path to acquire multiple surface photos of the landfill, and the marker points in each surface photo are determined. Based on each marker point, an initial three-dimensional cloud model is constructed. According to a preset cycle, photos of each of the marked points are acquired, and the photos of each of the marked points are substituted into the initial three-dimensional cloud model to obtain the dynamic three-dimensional cloud model.

[0012] By employing the aforementioned technical solution, the flight path and aerial perspective of the drone are pre-planned to acquire comprehensive surface photographs of the landfill. These surface photographs contain multiple pre-selected marker points, whose positions are fixed and can be repeated in each aerial photograph. Based on the multi-view surface photographs containing the marker points, an initial 3D cloud model of the landfill is constructed, and the coordinates of each marker point are marked within the model.

[0013] In subsequent monitoring, every time a preset period is reached, drones are used to take new aerial photos of the marker points. The marker points in the new photos are then registered and compared with the corresponding marker points in the 3D cloud model. By calculating the differences in marker point coordinates, it can be determined whether the landfill surface has deformed or shifted, thereby updating the 3D cloud model.

[0014] Optionally, after generating a dynamic three-dimensional cloud model based on the surface information, the method further includes: Determine at least one risk factor among the marked points, calculate the information entropy of each risk factor, and obtain the risk weight of each risk factor. Generate probability clouds and severity clouds for each of the aforementioned risk factors; An inverse cloud model is generated based on the surface information, and an evaluation cloud map is obtained through the inverse cloud model. Calculate the similarity between the evaluation cloud and the preset standard cloud; The assessment results of each risk factor in the landfill are determined based on the similarity, the probability cloud, and the severity cloud.

[0015] By employing the above technical solution, the weights of each risk factor are first quantitatively calculated using information entropy theory, enabling accurate assessment of the impact of different risk factors on landfill stability. Then, by generating probability clouds and severity clouds for each risk factor, the likelihood and severity of each risk factor's occurrence are visually displayed. Based on a 3D cloud model of the landfill, an inverse cloud model algorithm is used to obtain an evaluation cloud map, allowing for quantitative analysis of the parameter distribution of each risk factor under the current landfill condition. Furthermore, the similarity between the evaluation cloud and the standard cloud is calculated to determine the gap between the overall stability of the landfill and the ideal state. Finally, considering all the above results, the assessment result of each risk factor is determined, i.e., the degree of impact on the current landfill stability.

[0016] Optionally, the step of performing multi-source parameter analysis on the landfill based on the three-dimensional cloud model and the monitoring data to obtain risk assessment parameters includes: According to the fuzzy algorithm, the dam body data and pile body data in the three-dimensional cloud model, as well as the deep horizontal displacement, surface horizontal displacement and main water level data in the monitoring data are fused to obtain the risk assessment parameters.

[0017] By employing the above technical solution, this approach uses fuzzy algorithms to analyze and process multi-source monitoring data from landfills. The 3D cloud model provides macroscopic information on the site's morphology; while deep displacement, surface displacement, and water level changes reflect local details. Both types of data serve as criteria for assessing landfill stability, but their focuses differ. Directly merging the data may introduce more uncertainty.

[0018] Fuzzy algorithms can construct fuzzy rules that simulate expert reasoning, comprehensively judging different data like human thinking, effectively solving the uncertainty and contradictions of multi-source data. This scheme uses preset fuzzy rules to perform fuzzy calculations on 3D cloud models and displacement / water level monitoring data, empirically obtaining more reliable risk assessment parameters.

[0019] Optionally, the step of monitoring landslides at the landfill based on the risk assessment parameters includes: Calculate the stability safety factor of the landfill based on the risk assessment parameters. Determine the waste intensity parameter in the risk assessment parameters; Based on the stability safety factor and the waste intensity parameter, the stability of the landfill is assessed as any one of safe, warning, dangerous, and emergency.

[0020] By adopting the above technical solution and utilizing risk assessment parameters, the safety factor of the landfill is quantitatively calculated. The safety factor directly reflects the adequacy of its anti-sliding force and is a key indicator for judging overall stability. Simultaneously, the components related to the strength of the waste itself are identified, namely, the waste strength parameter.

[0021] After obtaining the safety factor and waste intensity parameters, the scheme further classifies the stability status of landfills into four levels: safe, warning, dangerous, and emergency. Based on the comparison of the two indicator values ​​with preset judgment criteria, the specific stability level of the landfill location can be clearly determined.

[0022] Compared to simple threshold-based early warning systems, this multi-level stability assessment method enables precise qualitative judgment of the stability state of landfills. Quantitative parameter calculations and multiple stability levels allow for the full utilization of monitoring information for scientific and systematic risk assessment, making the monitoring results more operationally relevant. This technology enhances the intelligence level of landfill landslide monitoring.

[0023] Optionally, calculating the stability safety factor of the landfill based on the risk assessment parameters includes: Substituting the effective cohesion, effective stress on the sliding surface, total stress on the sliding surface, effective friction angle, and pore water pressure from the risk assessment parameters into the first preset formula, the shear strength is obtained. Substituting the shear strength into the second preset formula, the stability safety factor is obtained; The first preset formula is: t f = c¢ +s ¢ tanj¢ = c¢ + (s - u)tanj¢; In the formula, tf c¢ represents the shear strength, c¢ represents the effective cohesion, s¢ represents the effective stress on the sliding surface, s represents the total stress on the sliding surface, j¢ represents the effective friction angle, and u represents the pore water pressure. The second preset formula is: Fs = t f / t; In the formula, Fs represents the stability safety factor, and t f The shear strength is represented by t, and the shear stress reached at equilibrium is represented by t.

[0024] By employing the aforementioned technical solution, and based on classical mechanics formulas combined with risk assessment parameters, the shear strength of the landfill was calculated. The formula comprehensively considers multiple factors affecting shear strength, resulting in accurate and reliable calculations. Building upon the accurate shear strength, the definition formula for the safety factor was further applied to ultimately obtain the precise safety factor for the landfill.

[0025] Compared to directly using empirical safety factors, this two-step calculation method makes full use of various monitoring parameters and risk assessment results, making the calculation process of safety factors more scientific and reasonable. An accurate safety factor can truly reflect the stable state of a landfill and is the basis for quantitative stability analysis.

[0026] Optionally, determining the waste intensity parameter in the risk assessment parameters includes: The frictional force between particles, the bonding force and electrostatic attraction between components, and the reinforcing force caused by the fiber phase in the risk assessment parameters are determined as the waste strength parameters, and the standard safety range corresponding to each waste strength parameter is determined.

[0027] By adopting the above technical solution, when determining the waste strength parameter in the risk assessment parameters, not only the frictional force between particles is considered, but also the bonding force, electrostatic force, and fiber reinforcement effect are taken into account. These factors together determine the shear strength and overall strength level of the waste pile in the landfill.

[0028] Compared to relying on a single strength index, this scheme uses strength parameters with multiple components, which can more comprehensively reflect the strength level of waste in landfills. Considering the interaction of various sub-intensities makes the determination of strength parameters more accurate and scientific.

[0029] A second aspect of this application provides a landslide monitoring system based on multi-source parameters. The multi-source parameter-based landslide monitoring system includes: The 3D cloud model construction module is used to periodically acquire surface information of landfills via drones and generate dynamic 3D cloud models based on the surface information. The monitoring data acquisition module is used to acquire monitoring data of the landfill's stockpile and dam. The risk assessment parameter calculation module is used to perform multi-source parameter analysis on the landfill based on the three-dimensional cloud model and the monitoring data to obtain risk assessment parameters. The landslide monitoring module is used to monitor landslides at the landfill based on the risk assessment parameters.

[0030] A third aspect of this application provides a computer storage medium storing a plurality of instructions adapted for loading by a processor and executing the method steps described above.

[0031] A fourth aspect of this application provides an electronic device, comprising: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to execute the above-described method steps.

[0032] In summary, one or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages: By adopting the technical solution of this application, and combining two data sources—a UAV 3D cloud model and sensor monitoring data—comprehensive three-dimensional monitoring of landfills is achieved. The 3D cloud model, acquired periodically by the UAV, dynamically reflects changes in the surface morphology of the landfill and can detect anomalies such as surface subsidence and collapse. Simultaneously, various sensors embedded in key areas of the landfill can detect minute deformations within the landfill structure and dam. The 3D cloud model and sensor monitoring data complement each other, jointly depicting the overall stability of the landfill.

[0033] Based on the acquisition of internal and external monitoring data from the landfill, the aforementioned technical solution further utilizes multi-source parameter analysis algorithms to fuse various data types. Compared to a single data source, multi-source parameter analysis can fully uncover the inherent connections and dependencies between different data, resulting in more accurate and reliable assessment results. The risk assessment parameters obtained from data fusion more comprehensively reflect the key factors affecting the stability of the landfill.

[0034] Finally, the aforementioned technical solution establishes a landslide monitoring model capable of real-time monitoring and early warning of landslide risks at landfills based on risk assessment parameters. Compared to traditional timed inspections, this model achieves dynamic real-time monitoring of landslide conditions at landfills. Timely early warnings facilitate immediate response measures, minimizing losses caused by landslides.

[0035] In summary, the above technical solutions, by integrating multi-source data, parameter correlation analysis, and modeling and early warning technologies, have achieved accurate assessment and effective monitoring of landslide risks at landfills. Attached Figure Description

[0036] Figure 1 This is a flowchart illustrating the landslide monitoring method based on multi-source parameters provided in the embodiments of this application; Figure 2 The diagram shown is a schematic representation of a three-dimensional cloud model provided in an embodiment of this application. Figure 3 This is a planar layout diagram of marker points provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of a landslide monitoring system based on multi-source parameters provided in an embodiment of this application; Figure 5 This is a schematic diagram of the structure of an electronic device disclosed in an embodiment of this application.

[0037] Explanation of reference numerals in the attached figures: 500, electronic device; 501, processor; 502, communication bus; 503, user interface; 504, network interface; 505, memory. Detailed Implementation

[0038] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0039] In the description of the embodiments of this application, the words "for example" or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design that is described as "for example" or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design options. Rather, the use of the words "for example" or "for instance" is intended to present the relevant concepts in a specific manner.

[0040] In the description of the embodiments of this application, the term "multiple" means two or more. For example, multiple systems means two or more systems, and multiple screen terminals means two or more screen terminals. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature. The terms "comprising," "including," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0041] This application provides a landslide monitoring method based on multi-source parameters. In one embodiment, please refer to... Figure 1 , Figure 1 This is a flowchart illustrating a landslide monitoring method based on multi-source parameters provided in this application. This method can be implemented using a computer program, which can be integrated into an application or run as a standalone utility application. The method can also be implemented using a microcontroller and can run in a landslide monitoring system based on a von Neumann architecture and multi-source parameters. Specifically, the method may include the following steps: Step 101: Periodically acquire surface information of the landfill using drones, and generate a dynamic 3D cloud model based on the surface information.

[0042] Surface information refers to image information of the surface morphology and condition of landfills obtained through drone aerial photography. Specifically, it can be understood as high-resolution photos including topography, landforms, vegetation, etc. These photos can reflect the detailed situation of the landfill surface morphology.

[0043] In this embodiment, the surface information is used to generate a 3D point cloud model of the landfill surface topography using a 3D reconstruction algorithm. The 3D model can display the landfill surface morphology from multiple angles, reflecting changes in the landfill's morphology, and is used for subsequent stability assessments. By periodically acquiring surface information and generating a 3D model, dynamic changes in the landfill surface morphology can be monitored, providing fundamental data for landfill stability monitoring.

[0044] A 3D cloud model refers to a 3D digital scene model generated using 3D reconstruction algorithms based on landfill surface information obtained from drone aerial photography. Specifically, it can be understood as a 3D point cloud data model reflecting the surface morphology of a landfill. A 3D cloud model can represent 3D views of the landfill surface and landfill structure at different time periods. By comparing 3D cloud models from different times, changes in landfill morphology, such as settlement and displacement, can be measured and calculated. By providing 3D digital information about the landfill surface and landfill structure, the 3D cloud model provides fundamental data for subsequent multi-source parameter analysis, used to assess the overall stability of the landfill.

[0045] Specifically, to dynamically monitor the elevation changes of the landfill, a 3D cloud model of the landfill needs to be established. Due to the complex terrain of the landfill, traditional manual surveying methods cannot quickly obtain 3D data of the entire landfill. This step utilizes unmanned aerial vehicles (UAVs) to periodically acquire orthophoto images of the landfill, obtaining surface information in a low-cost and high-efficiency manner.

[0046] For example, the flight path of the drone can be planned first, based on the scope and terrain of the landfill, to ensure comprehensive imaging of every part of the landfill. During the initial flight, the drone takes comprehensive images of the landfill along the preset route, obtaining surface images. Then, 3D reconstruction is performed on the surface images to generate 3D point cloud data of the landfill. Based on the point cloud data, a 3D mesh model of the landfill is further constructed. Multiple fixed ground markers are marked in the model as reference points for subsequent monitoring. At regular intervals, the drone is repeatedly used to take aerial photographs of the landfill, obtaining updated surface images. The markers in the new images are then registered with the digital elevation model to obtain the updated landfill model.

[0047] This method of acquiring landfill images through periodic flight provides an effective and rapid way to obtain information on changes in the morphology of landfills, avoiding the limitations of manual measurement. The 3D cloud model can intuitively reflect the overall and local elevation changes of the landfill, playing a crucial role in subsequent stability analysis.

[0048] Based on the above embodiments, as a feasible implementation method, the surface information may include multiple surface photos. Step 101, which involves periodically acquiring surface information of the landfill using a drone and generating a dynamic 3D cloud model based on the surface information, may further include the following steps: Step 201: Control the drone to acquire multiple surface photos of the landfill according to the preset flight path, determine the marker points in each surface photo, and construct an initial three-dimensional cloud model based on each marker point.

[0049] Marker points refer to fixed points selected from acquired surface photographs that reflect the surface morphology of landfills. In this embodiment, they can be understood as static, unchanging ground feature points such as the intersection of piles or dams within the landfill. These points are used to set fixed coordinates in the constructed three-dimensional digital elevation model, serving as a reference for comparing subsequent drone aerial photographs with the model. By comparing the coordinate changes of marker points in the model and actual photographs, dynamic monitoring of landfill elevation changes can be achieved.

[0050] Setting up marker points is crucial for enabling dynamic monitoring of landfills using a 3D cloud model. The marker points themselves remain in their fixed positions, serving as known coordinates within the model. Newly acquired surface photographs contain updated information about the marker points, which are compared with the coordinates of the marker points in the model. Based on the discrepancies in position and elevation, it can be determined whether the landfill surface has deformed or shifted, and the 3D cloud model can be updated accordingly.

[0051] Specifically, please refer to Figure 2 , Figure 2This illustration shows a schematic diagram of a 3D cloud model provided in an embodiment of this application. To achieve 3D dynamic monitoring of a landfill, it is necessary to acquire representative multi-angle surface photographs and construct an initial 3D model. Therefore, the flight path of the UAV can be planned and designed based on the extent and terrain of the landfill. Reasonable setting of waypoint positions and angles ensures that multiple surface photographs with comprehensive coverage can be acquired in each flight. During actual flight, the UAV is strictly controlled to take aerial photographs along the preset flight path, acquiring landfill photographs from each observation angle. Then, representative marker points are selected from the acquired large number of surface photographs. These marker points have fixed positions and can reappear in subsequent rounds of aerial photography. Finally, the coordinates of the selected marker points are input into a 3D reconstruction algorithm to generate a 3D point cloud model of the landfill based on the multi-angle surface photographs containing each marker point. The coordinate position of each marker point in the 3D scene is calibrated, completing the construction of the initial 3D cloud model.

[0052] In this way, each aerial survey can acquire multiple surface photographs with good perspectives, and a 3D model can be built based on the marker points, which is beneficial for subsequent 3D data acquisition and dynamic monitoring of the landfill. After each round of aerial surveys, the newly acquired photographs containing marker points are compared with the existing model. By observing the changes in the coordinates of the marker points, the deformation of the landfill can be judged, enabling dynamic updates to the 3D model and continuous monitoring of the stability of the landfill.

[0053] Step 202: According to the preset cycle, acquire photos of each marker point, substitute the photos of each marker point into the initial 3D cloud model, and obtain a dynamic 3D cloud model.

[0054] For details, please refer to Figure 3 , Figure 3 This illustration shows a planar layout of marker points provided in an embodiment of this application. To achieve dynamic monitoring of changes in the surface morphology of a landfill, it is necessary to periodically acquire the latest surface information of the landfill and update the 3D digital elevation model. A pre-set periodic aerial photography cycle for the drone can be configured, such as weekly or monthly. When the aerial photography cycle arrives, the drone is operated to conduct aerial photography of the landfill using the same flight path and control parameters as when the 3D cloud model was initially generated, obtaining the latest surface photographs. Similar to the first round of aerial photography, the newly acquired photographs still contain multiple pre-selected marker points. The coordinates of these marker points remain fixed within the landfill.

[0055] Next, the newly acquired photos containing the markers need to be input into the existing 3D cloud model of the landfill for registration and feature matching with the markers in the model. Using computer vision algorithms, the pixel coordinates of each marker in the new photo are detected and compared with their coordinates in the 3D cloud model. If the two coordinate values ​​are completely identical, it indicates that the landfill surface has not undergone displacement or profile change at that marker point. If there is a discrepancy, the difference in coordinates between the marker in the new photo and the original 3D cloud model is calculated. Based on the difference, the displacement or settlement of the landfill surface at that location is determined, and the mesh structure and surface features of the original 3D cloud model are adjusted accordingly to update the 3D cloud model.

[0056] In one feasible implementation, for calculating the settlement at the same monitoring point: ΔH = H n -H n+1 , where H n H represents the elevation information of the monitoring point during the nth drone patrol. n+1 This represents the elevation information of the monitoring point during the (n+1)th UAV patrol. By centering the marker points and calibrating the point cloud data, the elevation of the marker points for each patrol can be obtained, thus allowing the calculation of settlement changes.

[0057] Based on the above embodiments, as an optional embodiment, after step 101: generating a dynamic three-dimensional cloud model based on surface information, the following steps can also be performed: Step 501: Identify at least one risk factor among each marker point, calculate the information entropy of each risk factor, and obtain the risk weight of each risk factor.

[0058] After obtaining a 3D cloud model of the landfill, risk factors and risk weights can be determined based on the marker point information in the model. Specifically, firstly, factors related to landfill stability are selected from the marker points in the model as risk factors, such as marker point displacement, landfill height, and slope. Then, information entropy theory is used to quantitatively calculate each risk factor, reflecting the degree of influence of different risk factors on system stability.

[0059] The formula for calculating information entropy is H(X) = -∑p(x)logp(x). Here, X represents a risk factor, and p(x) represents the probability of state x occurring for a certain risk factor. The information entropy value of each risk factor is calculated sequentially. A larger information entropy value indicates a greater impact of the risk factor on system stability, and therefore can be used as the weight of the risk factor. The risk factors are then ranked according to their information entropy values, with the risk factor having the highest information entropy value having the highest risk weight.

[0060] Step 502: Generate the probability cloud and severity cloud for each risk factor.

[0061] To intuitively assess the impact of different risk factors on landfill stability, cloud modeling can be used to generate probability clouds and severity clouds for each risk factor.

[0062] First, the probability cloud reflects the likelihood of a risk factor occurring. This can be achieved by statistically analyzing the frequency of the risk factor's occurrence in historical monitoring data; a higher frequency corresponds to a higher probability value. Then, this probability value is mapped to the height of the cloud model, forming the probability cloud. A higher probability cloud indicates a greater likelihood of the corresponding risk factor occurring.

[0063] Secondly, the severity cloud reflects the degree of impact on landfill stability when a risk factor occurs. The severity score for each risk factor can be determined using expert scoring methods, and then mapped to the color depth of the cloud model to form the severity cloud. Darker colors indicate greater severity.

[0064] Finally, the probability clouds and severity clouds generated for each risk factor are visualized, and the severity of different risk factors can be compared by using the height and color of the cloud models. The cloud models represent the impact of risk factors in an intuitive graphical way, making it easier for risk analysts to interpret them.

[0065] Step 503: Generate an inverse cloud model based on the surface information, and obtain an evaluation cloud map through the inverse cloud model.

[0066] The basic principle of reverse cloud modeling is to use cloud modeling algorithms to reverse-calculate the possible distribution of input values ​​that could lead to the current 3D cloud model, thereby obtaining an evaluation cloud map. In practice, it is first necessary to collect parameter data from the 3D cloud model of the landfill, such as land subsidence values, slope, and other risk factor data. Then, based on the cloud modeling algorithm, assuming these parameters follow a certain possible probability distribution, the input values ​​of the model are deduced, i.e., the evaluation cloud map. The evaluation cloud map reflects the distribution of evaluation values ​​for each risk factor under the current state of the landfill.

[0067] The inverse cloud model can quantitatively determine the gap between the current stable state and the ideal state of a landfill. Compared to qualitative judgments, the inverse cloud model provides a quantitative analytical method for assessing landfill stability. The evaluation cloud map, by analyzing the distribution of parameters across the value range, identifies the main risks and problem factors, which helps in developing targeted stabilization measures.

[0068] Step 504: Calculate the similarity between the evaluation cloud and the preset standard cloud.

[0069] To assess the overall stability of a landfill using quantitative indicators, it is necessary to calculate the similarity between the evaluation cloud and the standard cloud. The standard cloud is a cloud model representing the ideal values ​​of various risk factors under safe conditions. The standard cloud can be determined through statistical analysis of monitoring data from historical stable periods, or it can be provided by experts based on experience.

[0070] The similarity between the evaluation cloud and the standard cloud can be calculated using matching algorithms in cloud models, such as calculating the similarity of cloud models based on Euclidean distance. Specifically, the feature values ​​of each risk factor corresponding to the evaluation cloud and the standard cloud are used to construct a vector, and the Euclidean distance between the two vectors is calculated. The smaller the distance, the greater the similarity.

[0071] Once the similarity values ​​between the evaluation cloud and the standard cloud are obtained, the overall stability of the landfill can be assessed based on this similarity. A higher similarity indicates that the evaluation cloud is closer to the standard cloud in a safe state, and the landfill is more stable. A lower similarity means that there are significant differences between the evaluation cloud and the standard cloud, and the landfill's stability is at risk.

[0072] Similarity provides an intuitive and quantitative indicator to measure the safety status of landfills. Compared to directly analyzing monitoring data, this technique, by comparing differences with standard safety conditions, better reflects the overall stability of landfills. The magnitude of the similarity score can be used to prioritize subsequent preventative measures for landfills.

[0073] Step 505: Determine the assessment results of each risk factor in the landfill based on similarity, probability cloud, and severity cloud.

[0074] Specifically, the degree of deviation between the overall stability and the standard safety state can be determined based on the previously obtained similarity scores. Then, a probability cloud is used to reflect the probability of each risk factor occurring. Finally, the severity of each risk factor in the severity cloud is considered. By comprehensively evaluating these three aspects, the assessment result for each risk factor can be determined, i.e., the degree of impact of that risk factor on the current stability of the landfill.

[0075] The above assessment results comprehensively consider three dimensions: the gap between the current landfill and the standard safety status, the probability of occurrence of each risk factor, and its severity. This results in a more comprehensive evaluation. Similarity reflects the overall impact, probability reflects the likelihood, and severity reflects the hazard outcome; combining these three factors allows for a quantitative stability assessment of individual risk factors. The assessment results clearly identify the main problems and threats, which is helpful for developing targeted risk prevention and control strategies in the future.

[0076] Step 102: Obtain monitoring data of the landfill's stockpile and dam.

[0077] Specifically, sensing devices such as fiber optic sensors, strain gauges, and displacement meters can be pre-embedded in key parts of the landfill, such as the landfill structure and retaining dams. These sensors monitor the temperature field, stress state, displacement, and deformation inside the landfill in real time using the principles of fiber optic temperature measurement and strain measurement, and transmit the monitoring data to a central data platform via wired or wireless means.

[0078] Compared to external monitoring that primarily relies on 3D models from drones, internal sensors can directly capture minute changes in the internal structure of landfills. High-precision sensors can detect minute displacements or deformations. Furthermore, internal monitoring enables 24 / 7, real-time monitoring of landfills, unaffected by external environmental factors.

[0079] Real-time monitoring data of the landfill and dam structures acquired through an internal sensor network can be fused with external information from a 3D cloud model to achieve a comprehensive assessment of landfill stability. This combination of internal and external monitoring methods makes the assessment of landfill conditions more accurate and reliable.

[0080] Step 103: Based on the 3D cloud model and monitoring data, conduct multi-source parameter analysis on the landfill to obtain risk assessment parameters.

[0081] Specifically, the system first collects 3D cloud model data of the landfill obtained periodically by drones, which includes parameters such as site area, pile volume, and elevation. Simultaneously, real-time internal monitoring data of the landfill and retaining dam are collected from a sensor network, including parameters such as displacement, stress, and temperature.

[0082] Then, a multi-source parameter joint analysis model for landfills is established using a multi-source data fusion algorithm. This model can employ a method similar to association rule learning to learn the association rules between 3D model parameters and real-time monitoring data from a large amount of historical data. Based on this complex association knowledge between parameters, multi-source comprehensive analysis is performed on new real-time monitoring data to assess the stability risks of the landfill.

[0083] Compared to a single data source, multi-source parameter fusion can fully utilize different types of data to make a more comprehensive stability assessment. The inherent relationships between monitoring data can also be mined and utilized through data fusion models, making risk prediction more accurate. This technique can obtain relatively objective landfill risk assessment parameters, providing a basis for subsequent prevention and control decisions.

[0084] In one feasible implementation, risk assessment parameters can be obtained by fusing dam body data and pile body data from the three-dimensional cloud model, as well as deep horizontal displacement, surface horizontal displacement and main water level data from the monitoring data, based on a fuzzy algorithm.

[0085] To accurately assess landfill stability, the uncertainties and ambiguities among various monitoring data can be considered. Fuzzy algorithms can effectively handle this ambiguity, thus allowing the fusion of data from different sources to obtain more reliable risk assessment parameters.

[0086] Specifically, the 3D cloud model obtained by the drone contains state data of the dam and landfill structures, reflecting the overall condition of the site. Meanwhile, the deep displacement, surface displacement, and water level data monitored by internal sensors reflect minute deformations. Both types of data are used to determine the stability of a landfill, but each has its own emphasis. Directly merging these two types of data may introduce more uncertainty.

[0087] To this end, fuzzy rules can be constructed to simulate the thought process of experts evaluating site information, such as "if the dam deformation is small but the internal displacement is large, then the risk is considered high." During comprehensive analysis, these rules play a leading role, and fuzzy calculations are performed on the two types of data to obtain empirical risk parameters, thus achieving fuzzy fusion of multi-source data.

[0088] Compared to simple linear weighting, fuzzy algorithms can simulate human thinking patterns, yielding more interpretable assessment results while preserving relevant information between data. Fuzzy fusion improves the comprehensiveness and fuzziness of landfill stability assessments, making risk prediction more accurate.

[0089] Step 104: Conduct landslide monitoring at the landfill based on the risk assessment parameters.

[0090] After obtaining multi-source monitoring data of the landfill and calculating risk assessment parameters, it is necessary to monitor the overall landslide risk of the landfill based on these parameter results in order to prevent and warn of landslides in a timely manner.

[0091] Specifically, a landslide monitoring model can be established using risk assessment parameters as input. This model can employ methods such as probability theory and mathematical statistics to analyze the relationships between parameters and determine the weight of each parameter as a landslide influencing factor. Then, by comprehensively calculating the risk assessment parameter inputs for each time period, the model can obtain a landslide risk index for that period. The risk index typically uses quantitative indicators to intuitively reflect the probability and severity of a landslide occurring at the current landslide site.

[0092] Next, the calculated risk index will be compared with a preset threshold. If the risk index exceeds the threshold, it indicates a high risk of landslide at the landfill, requiring preventative measures or a risk warning to be issued to relevant departments. If the risk index remains below the threshold, the landfill is considered relatively safe.

[0093] This landslide monitoring method, based on risk assessment parameters, enables real-time, dynamic monitoring of the stability of landfills. Compared to periodic manual assessments, this technology significantly improves monitoring efficiency. Targeted early warnings also facilitate timely risk management.

[0094] Based on the above embodiments, as an optional embodiment, step 104: the step of monitoring landslides at the landfill according to risk assessment parameters may further include the following steps: Step 401: Calculate the stability safety factor of the landfill based on the risk assessment parameters.

[0095] The safety factor is a parameter reflecting structural stability. By comparing it with a standard value, the safety status of a landfill can be intuitively judged. Its calculation method typically employs the limit equilibrium method, considering the landfill's anti-sliding force and driving force to establish a force balance relationship and obtain the corresponding safety factor.

[0096] Specifically, the risk assessment parameters provide data such as the shape and size of the landfill, soil strength, and displacement. This data can be substituted into the formula for calculating the safety factor to determine the corresponding resistance, driving force, and other variable values ​​in the calculation. Then, the final safety factor is calculated using the formula. By using different calculation models, safety factors can be obtained for different directions or on different slip surfaces.

[0097] Once the safety factor is obtained, if its value is greater than the preset safety threshold, it indicates that the landfill is currently in good stability; otherwise, there is a certain risk of landslide. Compared with directly analyzing monitoring parameters, calculating the safety factor can more intuitively and quantitatively assess the overall stability of the landfill. A quantitative safety factor also facilitates dynamic monitoring or comparison with historical statistical values.

[0098] Step 402: Determine the waste intensity parameter in the risk assessment parameters.

[0099] When calculating the safety factor of a landfill, it is necessary to determine the parameters related to the strength of the waste itself in the risk assessment parameters, namely the waste strength parameters. The waste strength parameters directly affect the overall stability of the landfill slope. Factors considered include interparticle friction, the bonding force and electrostatic attraction between components, and the reinforcing effect of fibrous materials. These factors together determine the shear strength of the waste pile.

[0100] Specifically, the shear strength of waste samples with different compositions and compaction degrees can be determined through methods such as indoor direct shear tests. By combining the test data with data such as the proportion of waste components and compaction coefficients obtained from risk assessment parameters, the average shear strength of the waste in the landfill can be calculated, i.e., the waste strength parameter.

[0101] Obtaining accurate waste strength parameters helps improve the accuracy of safety factor calculations. Compared to using empirical values, experimentally determined shear strength can quantify the mechanical properties of specific waste materials in landfills, resulting in more scientific and reasonable safety factors that better guide the operation and maintenance of landfills.

[0102] Step 403: Based on the stability safety factor and waste strength parameters, assess the stability of the landfill as any one of the following: safe, warning, dangerous, or emergency.

[0103] To intuitively and quantitatively determine the stability of a landfill, it is necessary to assess the overall stability level of the landfill based on the calculated safety factor and waste strength parameters.

[0104] Specifically, quantitative standards for safety factors and waste intensity parameters can be pre-set, dividing them into four levels: safe, warning, dangerous, and emergency. For example, a safety factor greater than 1.5 and a waste intensity greater than 500 kPa constitute the safe level; a safety factor of 1.2-1.5 and an intensity of 200-500 kPa constitute the warning level; a safety factor of 1.0-1.2 and an intensity of 100-200 kPa constitute the dangerous level; and a safety factor less than 1.0 and an intensity less than 100 kPa constitute the emergency level.

[0105] In actual monitoring, by substituting the calculated safety factor and waste intensity parameters into the above-mentioned judgment criteria, the current stability level of the landfill can be determined. The lower the safety level, the greater the stability risk of the landfill.

[0106] This quantitative stability grading method can clearly define the severity of risks posed by landfills, enabling targeted emergency measures of varying degrees and avoiding operational errors caused by poorly understood monitoring parameters. Compared to simple threshold-based early warning systems, multi-level stability assessments are more comprehensive and reliable. The classification results are also more actionable, providing support for landfill risk management.

[0107] Based on the above embodiments, as an optional embodiment, step 401, which involves calculating the stability safety factor of the landfill according to the risk assessment parameters, may further include the following steps: Step 501: Substitute the effective cohesion, effective stress on the sliding surface, total stress on the sliding surface, effective friction angle, and pore water pressure from the risk assessment parameters into the first preset formula to obtain the shear strength; The first preset formula is: t f = c¢ +s ¢ tanj¢ = c¢ + (s - u)tanj¢; In the formula, t fdenoted by c¢, representing shear strength; c¢ representing effective cohesion; s¢ representing effective stress on the sliding surface; s representing total stress on the sliding surface; j¢ representing effective friction angle; and u representing pore water pressure.

[0108] The first pre-defined formula considers the contributions of cohesion and friction to shear strength. Risk assessment parameters can provide definite values ​​for each variable in the formula. Substituting these values ​​into the formula, the shear strength τ corresponding to the landfill on the analyzed sliding surface can be obtained. f .

[0109] This shear strength calculation based on classical mechanics formulas makes full use of the detailed data provided by risk assessment parameters, resulting in more accurate and reliable calculations. Compared to using empirical shear strength values, this method can take into account the specific conditions of the landfill and various influencing factors, improving the specificity of the calculation.

[0110] Step 502: Substitute the shear strength into the second preset formula to obtain the stability safety factor; The second preset formula is: Fs = t f / t; In the formula, Fs represents the stability safety factor, and t f denoted by , where t represents the shear strength and t represents the shear stress reached at equilibrium.

[0111] This formula represents the ratio of shear strength to shear stress. By substituting the previously calculated shear strength tf into the formula, and determining the shear stress τ based on the equilibrium analysis of the landfill, the safety factor Fs of the landfill on the slip surface can be calculated.

[0112] The safety factor Fs reflects the adequacy of shear strength and is a key indicator for judging the overall stability of a landfill. Using a two-step, step-by-step calculation method ensures the accuracy and reliability of the final Fs result. Compared to using empirical safety factors, rigorous mechanical calculations are more scientific and reasonable, and also more conducive to parameter sensitivity analysis.

[0113] Based on the above embodiments, as an optional embodiment, step 402: determining the waste intensity parameter in the risk assessment parameters may specifically include: The frictional force between particles, the bonding force and electrostatic attraction between components, and the reinforcing force caused by the fiber phase in the risk assessment parameters were determined as waste strength parameters, and the standard safety range corresponding to each waste strength parameter was determined.

[0114] To more accurately determine the inherent strength of waste in landfills, various components of waste strength can be considered, including interparticle friction, cohesion, electrostatic force, and fiber reinforcement, and standard safe ranges for these parameters can be determined.

[0115] Specifically, these strength indicators of waste samples with different composition ratios can be quantitatively tested through indoor experiments. Then, combined with the composition data of waste in the site, the numerical range of each strength parameter can be calculated proportionally.

[0116] Next, the standard safety range for each strength parameter is determined based on historical statistical analysis. For example, the standard range for particle friction is 50-80 kPa, and for bonding force it is 15-25 kPa. By comparing the specific strength parameters obtained from the test with the standard range, it can be determined whether each strength is within the safe range.

[0117] Reference Figure 4 This application also provides a landslide monitoring system based on multi-source parameters, the landslide monitoring system based on multi-source parameters comprising: The 3D cloud model construction module is used to periodically acquire surface information of landfills via drones and generate dynamic 3D cloud models based on the surface information. The monitoring data acquisition module is used to acquire monitoring data of the landfill's stockpile and dam. The risk assessment parameter calculation module is used to perform multi-source parameter analysis on the landfill based on the three-dimensional cloud model and the monitoring data to obtain risk assessment parameters. The landslide monitoring module is used to monitor landslides at the landfill based on the risk assessment parameters.

[0118] Based on the above embodiments, as an optional embodiment, the three-dimensional cloud model construction module is further configured to control the UAV to acquire multiple surface photos of the landfill according to a preset flight path, determine the marker points in each surface photo, construct an initial three-dimensional cloud model based on each marker point, acquire photos of each marker point according to a preset period, and substitute the photos of each marker point into the initial three-dimensional cloud model to obtain the dynamic three-dimensional cloud model.

[0119] Based on the above embodiments, as an optional embodiment, the three-dimensional cloud model construction module is further configured to determine at least one risk factor among the marked points, calculate the information entropy of each risk factor, obtain the risk weight of each risk factor; generate a probability cloud and a severity cloud for each risk factor; generate an inverse cloud model based on the surface information, and obtain an evaluation cloud map through the inverse cloud model; calculate the similarity between the evaluation cloud and a preset standard cloud; and determine the assessment result of each risk factor in the landfill based on the similarity, the probability cloud, and the severity cloud.

[0120] Based on the above embodiments, as an optional embodiment, the risk assessment parameter calculation module is further used to fuse the dam body data and pile body data in the three-dimensional cloud model, as well as the deep horizontal displacement, surface horizontal displacement and main water level data in the monitoring data, according to a fuzzy algorithm, to obtain the risk assessment parameters.

[0121] Based on the above embodiments, as an optional embodiment, the landslide monitoring module is further configured to calculate the stability safety factor of the landfill according to the risk assessment parameters; determine the waste intensity parameter in the risk assessment parameters; and assess the stability of the landfill as any one of safe, warning, dangerous, and emergency based on the stability safety factor and the waste intensity parameter.

[0122] Based on the above embodiments, as an optional embodiment, the landslide monitoring module is further used to substitute the effective cohesion, effective stress on the sliding surface, total stress on the sliding surface, effective friction angle, and pore water pressure in the risk assessment parameters into a first preset formula to obtain the shear strength; and to substitute the shear strength into a second preset formula to obtain the stability safety factor. The first preset formula is: t f = c¢ +s ¢ tanj¢ = c¢ + (s - u)tanj¢; In the formula, t f c¢ represents the shear strength, c¢ represents the effective cohesion, s¢ represents the effective stress on the sliding surface, s represents the total stress on the sliding surface, j¢ represents the effective friction angle, and u represents the pore water pressure. The second preset formula is: Fs = t f / t; In the formula, Fs represents the stability safety factor, and t f The shear strength is represented by t, and the shear stress reached at equilibrium is represented by t.

[0123] Based on the above embodiments, as an optional embodiment, the landslide monitoring module is also used to determine the frictional force between particles, the bonding force and electrostatic attraction between components, and the reinforcing force caused by the fiber phase in the risk assessment parameters as the waste strength parameters, and to determine the standard safety range corresponding to each of the waste strength parameters.

[0124] It should be noted that the above embodiments of the apparatus are only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0125] This application also provides a computer storage medium that can store multiple instructions. The instructions are adapted to be loaded by a processor and executed as described in the above embodiments for the landslide monitoring method with multiple source parameters. The specific execution process can be referred to the detailed description of the embodiments shown, which will not be repeated here.

[0126] This application also discloses an electronic device. (See reference...) Figure 5 , Figure 5 This is a schematic diagram of the structure of an electronic device disclosed in an embodiment of this application. The electronic device 500 may include: at least one processor 501, at least one network interface 504, a user interface 503, a memory 505, and at least one communication bus 502.

[0127] The communication bus 502 is used to enable communication between these components.

[0128] The user interface 503 may include a display interface and a camera interface. Optionally, the user interface 503 may also include a standard wired interface and a wireless interface.

[0129] The network interface 504 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0130] The processor 501 may include one or more processing cores. The processor 501 connects to various parts of the server using various interfaces and lines, and performs various server functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in memory 505, and by calling data stored in memory 505. Optionally, the processor 501 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 501 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface graphics, and applications; the GPU is responsible for rendering and drawing the content required for display; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 501 and may be implemented as a separate chip.

[0131] The memory 505 may include random access memory (RAM) or read-only memory. Optionally, the memory 505 may include a non-transitory computer-readable storage medium. The memory 505 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 505 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 505 may also be at least one storage device located remotely from the aforementioned processor 501. (Refer to...) Figure 5 The memory 505, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for a multi-source parameter landslide monitoring method.

[0132] exist Figure 5In the illustrated electronic device 500, the user interface 503 is mainly used to provide an input interface for the user and acquire user input data; while the processor 501 can be used to call an application program storing a landslide monitoring method with multi-source parameters in the memory 505. When executed by one or more processors 501, the electronic device 500 performs one or more of the methods described in the above embodiments. It should be noted that, for the foregoing method embodiments, for the sake of simplicity, they are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, because according to this application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0133] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0134] In the various embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some service interface; the indirect coupling or communication connection between apparatuses or units may be electrical or other forms.

[0135] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0136] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0137] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0138] The above description is merely an exemplary embodiment of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Other embodiments of this disclosure will be readily apparent to those skilled in the art upon consideration of the specification and the disclosure of practical truths.

[0139] This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described in this disclosure. The specification and embodiments are to be considered exemplary only, and the scope and spirit of this disclosure are defined by the claims.

Claims

1. A landslide monitoring method based on multi-source parameters, characterized in that, include: The surface information of the landfill is periodically acquired by drones, and a dynamic three-dimensional cloud model is generated based on the surface information. Acquire monitoring data of the landfill's stockpile and dam structures; Based on the three-dimensional cloud model and the monitoring data, multi-source parameter analysis was performed on the landfill to obtain risk assessment parameters; Landslide monitoring was conducted on the landfill based on the aforementioned risk assessment parameters.

2. The landslide monitoring method based on multi-source parameters according to claim 1, characterized in that, The surface information includes multiple surface photographs. The process of periodically acquiring surface information of the landfill using drones and generating a dynamic 3D cloud model based on this surface information includes: The drone is controlled according to a preset flight path to acquire multiple surface photos of the landfill, and the marker points in each surface photo are determined. Based on each marker point, an initial three-dimensional cloud model is constructed. According to a preset cycle, photos of each of the marked points are acquired, and the photos of each of the marked points are substituted into the initial three-dimensional cloud model to obtain the dynamic three-dimensional cloud model.

3. The landslide monitoring method based on multi-source parameters according to claim 2, characterized in that, After generating the dynamic three-dimensional cloud model based on the surface information, the method further includes: Determine at least one risk factor among the marked points, calculate the information entropy of each risk factor, and obtain the risk weight of each risk factor. Generate probability clouds and severity clouds for each of the aforementioned risk factors; An inverse cloud model is generated based on the surface information, and an evaluation cloud map is obtained through the inverse cloud model. Calculate the similarity between the evaluation cloud and the preset standard cloud; The assessment results of each risk factor in the landfill are determined based on the similarity, the probability cloud, and the severity cloud.

4. The landslide monitoring method based on multi-source parameters according to claim 1, characterized in that, The risk assessment parameters are obtained by performing multi-source parameter analysis on the landfill based on the three-dimensional cloud model and the monitoring data, including: According to the fuzzy algorithm, the dam body data and pile body data in the three-dimensional cloud model, as well as the deep horizontal displacement, surface horizontal displacement and main water level data in the monitoring data are fused to obtain the risk assessment parameters.

5. The landslide monitoring method with multiple parameters according to claim 1, characterized in that, The landslide monitoring of the landfill based on the risk assessment parameters includes: Calculate the stability safety factor of the landfill based on the risk assessment parameters. Determine the waste intensity parameter in the risk assessment parameters; Based on the stability safety factor and the waste intensity parameter, the stability of the landfill is assessed as any one of safe, warning, dangerous, and emergency.

6. The landslide monitoring method with multiple parameters according to claim 5, characterized in that, The step of calculating the stability safety factor of the landfill based on the risk assessment parameters includes: Substituting the effective cohesion, effective stress on the sliding surface, total stress on the sliding surface, effective friction angle, and pore water pressure from the risk assessment parameters into the first preset formula, the shear strength is obtained. Substituting the shear strength into the second preset formula, the stability safety factor is obtained; The first preset formula is: t f = c¢ +s ¢ tanj¢ = c¢ + (s - u)tanj¢ ; In the formula, t f c¢ represents the shear strength, c¢ represents the effective cohesion, s¢ represents the effective stress on the sliding surface, s represents the total stress on the sliding surface, j¢ represents the effective friction angle, and u represents the pore water pressure. The second preset formula is: Fs= t f / t ; In the formula, Fs represents the stability safety factor, and t f The shear strength is represented by t, and the shear stress reached at equilibrium is represented by t.

7. The landslide monitoring method with multiple parameters according to claim 5, characterized in that, The determination of the waste intensity parameter in the risk assessment parameters includes: The frictional force between particles, the bonding force and electrostatic attraction between components, and the reinforcing force caused by the fiber phase in the risk assessment parameters are determined as the waste strength parameters, and the standard safety range corresponding to each waste strength parameter is determined.

8. A landslide monitoring system based on multi-source parameters, characterized in that, The landslide monitoring system based on multi-source parameters includes: The 3D cloud model construction module is used to periodically acquire surface information of landfills via drones and generate dynamic 3D cloud models based on the surface information. The monitoring data acquisition module is used to acquire monitoring data of the landfill's stockpile and dam. The risk assessment parameter calculation module is used to perform multi-source parameter analysis on the landfill based on the three-dimensional cloud model and the monitoring data to obtain risk assessment parameters. The landslide monitoring module is used to monitor landslides at the landfill based on the risk assessment parameters.

9. An electronic device, characterized in that, The device includes a processor, a memory, a user interface, and a network interface. The memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory to cause the electronic device to perform the method as described in any one of claims 1-7.

10. A computer storage medium, characterized in that, The computer storage medium stores instructions that, when executed, perform the method as described in any one of claims 1-7.

Images