Tower foundation landslide monitoring method, system, equipment and medium
By integrating InSAR and GNSS data, multi-dimensional collaborative monitoring by drones, and an active waveguide acoustic emission system, the problems of limited monitoring range and insufficient accuracy of tower foundation landslides have been resolved, enabling real-time, comprehensive, and accurate landslide monitoring and early warning.
Patent Information
- Application Number
- CN202510574679.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-06
- Publication Date
- 2025-10-03
AI Technical Summary
The existing tower-based landslide monitoring technology has the disadvantages of limited monitoring range, insufficient accuracy, and difficulty in sensing the internal state of the landslide body. In addition, the existing technology cannot achieve real-time, comprehensive and accurate landslide monitoring.
InSAR and GNSS data are integrated for wide-area deformation monitoring. Multi-dimensional collaborative monitoring is carried out by drones. Edge computing devices are used to generate landslide risk heat maps. An active waveguide acoustic emission system is used to capture deep deformation signals of landslides. Early warning is achieved by combining ring counts with acoustic emission rate parameters.
It has achieved real-time, comprehensive and accurate monitoring of tower foundation landslides, improved monitoring accuracy and coverage, and ensured the reliability and accuracy of early warning.
Smart Images

Figure CN120742313A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of tower foundation landslide monitoring, and in particular to a tower foundation landslide monitoring method, system, equipment and medium. Background Art
[0002] In recent years, global climate change and the impact of human activities have led to frequent geological disasters. Landslides at tower foundations, among them, pose a serious threat to the safe and stable operation of power systems. To ensure the safety of transmission lines, tower foundation landslide monitoring technology has garnered widespread attention. Currently, tower foundation landslide monitoring technologies are primarily divided into traditional single-point monitoring methods and wide-area remote sensing monitoring technologies.
[0003] However, existing technologies have many shortcomings. Traditional single-point monitoring methods, such as the use of a single displacement sensor or strain sensor, can only obtain local information, making it difficult to fully reflect the overall stability of the tower foundation and easily miss potential landslide risk areas, which makes it lack a comprehensive and accurate basis when formulating prevention strategies; although wide-area remote sensing monitoring technology can observe the terrain of a large area from a macro perspective, it is greatly affected by weather conditions. In adverse weather conditions such as cloud and fog obstruction, clear and effective image information cannot be obtained, resulting in interrupted monitoring. Although InSAR technology (synthetic aperture radar interferometry) can monitor surface deformation over a wide area, it is easily affected by atmospheric delay, temporal incoherence, and terrain obstruction (such as vegetation cover or steep areas), resulting in data loss or monitoring blind spots. This makes it difficult to capture micro-displacements at the millimeter level, limiting its application in early warning. GNSS technology (global navigation satellite technology) has high positioning accuracy, but it relies on satellite signals, which are easily interfered with in complex terrain or obscured environments. In addition, GNSS technology can only obtain surface displacement data and cannot detect changes in the internal structure of landslides. Drone monitoring, while flexible and efficient, has limited endurance and coverage. The sensors it carries, such as radar and oblique imaging, can only obtain surface and shallow-layer information and lack awareness of internal conditions such as fractures and seepage in underground rock and soil. Existing monitoring technologies are not well integrated, and a single technology cannot coordinate coordinated monitoring of wide-area and local areas, or surface and internal areas. This leads to serious data silos, limiting the timeliness and accuracy of early warnings. Summary of the Invention
[0004] In view of the above existing problems, the present invention is proposed.
[0005] Therefore, the present invention provides a tower foundation landslide monitoring method, system, equipment and medium to solve the technical problems: the existing tower foundation landslide monitoring method has a limited monitoring range, insufficient monitoring accuracy, and difficulty in perceiving the internal state of the landslide body, as well as how to achieve real-time, comprehensive and accurate landslide monitoring.
[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:
[0007] In the first aspect, the present invention provides a method for monitoring landslides at tower foundations, including: fusing InSAR data and GNSS data for wide-area deformation monitoring, establishing a quadratic fitting model to dynamically correct errors in InSAR observations, and identifying areas with potential landslide hazards; using drones equipped with sensors to conduct multi-dimensional collaborative monitoring of areas with potential landslide hazards, and using edge computing devices to fuse multi-source data to generate a landslide risk heat map; using an active waveguide acoustic emission system to capture deep deformation signals of landslides, and achieving early warning through ringing counts and acoustic emission rate parameters.
[0008] As a preferred solution of the tower foundation landslide monitoring method described in the present invention, the wide-area deformation monitoring includes projecting the three-dimensional deformation of the GNSS monitoring point to the InSAR line of sight, calculating the unit projection vector of the InSAR observation value based on the satellite heading angle and the radar incident angle, and calculating the GNSS line of sight deformation.
[0009] As a preferred solution of the tower foundation landslide monitoring method described in the present invention, the dynamic error correction includes using GNSS observations to spatially constrain InSAR data, establish a quadratic fitting model, and calculate differences; and solve the quadratic fitting model parameters to correct the InSAR data.
[0010] As a preferred solution of the tower foundation landslide monitoring method described in the present invention, the multi-dimensional collaborative monitoring includes: the drone flying along a preset route, generating millimeter-level surface point clouds through lidar scanning, and providing high-precision data for three-dimensional modeling of the landslide body; synchronously collecting visible light and near-infrared band effects through a multispectral camera, calculating the normalized vegetation index, and analyzing soil moisture anomalies; detecting the surface temperature field distribution through an infrared thermal imager, identifying local low-temperature areas caused by groundwater seepage; and shooting a video stream of surface crack expansion through a pan-tilt camera.
[0011] As a preferred solution of the tower foundation landslide monitoring method described in the present invention, the method comprises: using edge computing devices to fuse multi-source data to generate a landslide risk heat map, including pre-processing the multi-dimensional collaborative monitoring data of the drone by the edge computing device; identifying risk areas in combination with a deep learning algorithm, and storing and transmitting the data to a ground station in real time; based on the three-dimensional model of the landslide body established by the drone, periodic inspections are performed to compare point cloud differences, and the LSTM model is combined with multi-dimensional parameters to generate a landslide risk heat map.
[0012] As a preferred solution of the tower foundation landslide monitoring method described in the present invention, the active waveguide acoustic emission system includes a steel waveguide tube, backfill granular material and an acoustic emission monitoring device.
[0013] As a preferred solution of the tower foundation landslide monitoring method described in the present invention, the early warning includes fitting the acoustic emission rate and landslide velocity based on historical data to establish an empirical model; and achieving early landslide warning based on the empirical model.
[0014] In the second aspect, the present invention provides a tower foundation landslide monitoring system, including: a wide-area deformation monitoring module, a drone monitoring module, and a capture and warning module; the wide-area deformation monitoring module is used to fuse InSAR data and GNSS data for wide-area deformation monitoring, establish a quadratic fitting model to dynamically correct errors of InSAR observations, and identify potential landslide hazard areas; the drone monitoring module is used to perform multi-dimensional collaborative monitoring of potential landslide hazard areas through drones equipped with sensors, and use edge computing devices to fuse multi-source data to generate a landslide risk heat map; the capture and warning module is used to use an active waveguide acoustic emission system to capture deep deformation signals of landslides, and achieve early warning through ringing counts and acoustic emission rate parameters.
[0015] In a third aspect, the present invention provides an electronic device, comprising:
[0016] memory and processor;
[0017] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the tower foundation landslide monitoring method are implemented.
[0018] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the tower foundation landslide monitoring method.
[0019] Compared with the existing technology, the present invention has the following beneficial effects: by integrating InSAR and GNSS technologies and combining the Kalman filter algorithm, the present invention effectively reduces the InSAR system error and improves the accuracy of surface deformation monitoring; by constraining and correcting InSAR observations through high-precision GNSS observations, the deformation monitoring accuracy is improved, and the subtle changes of tower foundation landslides can be captured more accurately; by using drones equipped with radar, imaging, and infrared equipment, richer surface information is obtained, providing more accurate data support for landslide monitoring; wide-area monitoring is achieved through InSAR technology, and by using drones to focus on regional identification, it is possible to conduct in-depth and detailed detection in complex environments, which not only improves monitoring efficiency but also ensures the comprehensiveness and accuracy of monitoring; by using active waveguide acoustic emission technology, it is possible to sensitively perceive the subtle deformation of tower foundation landslides and continuously monitor larger deformations, providing strong support for early warning of landslide disasters; by the mutual cooperation and complementary advantages of multiple technologies, the accuracy and reliability of tower foundation landslide monitoring are comprehensively improved, and real-time, comprehensive, and accurate landslide monitoring is achieved. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0021] Figure 1 The figure is a schematic diagram of the overall process of a tower foundation landslide monitoring method according to an embodiment of the present invention.
[0022] Figure 2 A diagram showing the composition of a drone for a tower foundation landslide monitoring method according to an embodiment of the present invention.
[0023] Figure 3 Figure 1 is an active waveguide acoustic emission monitoring system diagram of a tower foundation landslide monitoring method according to an embodiment of the present invention.
[0024] Figure 4 This is a schematic diagram of the overall process of a tower foundation landslide monitoring system according to an embodiment of the present invention. DETAILED DESCRIPTION
[0025] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.
[0026] Example 1, reference Figure 1 , as one embodiment of the present invention, provides a tower foundation landslide monitoring method, comprising:
[0027] S1: Fusion of InSAR and GNSS data for wide-area deformation monitoring, establishment of a quadratic fitting model for dynamic error correction of InSAR observations, and identification of potential landslide risk areas;
[0028] S2: Use sensor-equipped drones to conduct multi-dimensional collaborative monitoring of potential landslide risk areas, and use edge computing devices to fuse multi-source data to generate landslide risk heat maps;
[0029] S3: An active waveguide acoustic emission system is used to capture deep deformation signals of landslides and provide early warning through ring counts and acoustic emission rate parameters.
[0030] It should be noted that pole towers are an important part of transmission lines. The stability of the pole tower foundation is directly related to the safe operation of the entire transmission line. Geological disasters such as landslides will cause the pole tower foundation to become unstable, which will in turn cause serious consequences such as power outages and equipment damage in the transmission line, affecting power supply and social production and life. Therefore, monitoring of pole tower foundation landslides is very important.
[0031] Therefore, in response to the above-mentioned problems of tower foundation monitoring, wide-area deformation monitoring is carried out through steps S1-S3, and the monitoring data is error-corrected to identify potential landslide risk areas, thus realizing wide-area identification of tower foundation landslide monitoring, overcoming the defect that existing technologies cannot cover large areas, and timely discovering potential landslide risk points; collaborative monitoring of potential landslide risk areas is carried out through drones, and risk heat maps are generated for multi-source data, thus realizing detailed identification of potential landslide risk areas; and the active waveguide acoustic emission system is used to realize the tiny deformation of tower foundation landslides, providing a key basis for early warning of landslides.
[0032] Example 2, reference Figure 1-Figure 3 , which is an embodiment of the present invention, provides a tower foundation landslide monitoring method based on the above embodiment.
[0033] In the embodiment of the present application, the fusion of InSAR data and GNSS data in step S1 is achieved through Kalman filtering.
[0034] Specifically, the Kalman filter observation equation and state equation are established;
[0035] The observation equation is expressed as:
[0036] L k =A * X k +Δ
[0037] Among them, L k is the observed quantity, X k is the state vector, Δ is the observation noise;
[0038] The observed quantity is expressed as:
[0039]
[0040] in, They represent the east-west, north-south, and vertical observation values of the GNSS monitoring point, respectively. InSAR represents the InSAR shape variable observation value, and T is the time.
[0041] The state vector is expressed as:
[0042] X k =[d e d n d u v e v n v u ] T
[0043] Among them, d e d n d u Respectively represent the deformation of the monitoring point in the east-west, north-south, and vertical directions, v e 、v n 、v u Respectively represent the deformation rates in the east-west, north-south, and vertical directions of the monitoring point;
[0044] The equation of state is expressed as:
[0045] X k =Φ kk-1 *X k-1 +Γ k-1 *W k-1
[0046] Among them, Φ kk-1 is the state transfer matrix, Γ k-1 is the noise distribution matrix of the system dynamic process, W k-1 is the noise vector of the system dynamic process;
[0047] The state transition matrix is expressed as:
[0048]
[0049] Among them, I3 is a 3*3 identity matrix, Δt is the time step;
[0050] The noise distribution matrix of the system dynamic process is expressed as:
[0051]
[0052] System dynamic process noise vector W k-1 =
[111] T ;
[0053] After the state equation and observation equation are established, the initial state of the system is given, the deformation and variance at the initial moment are taken as 0, the state vector X0 at the initial moment and the corresponding variance matrix are the deformation rate and variance after adjustment of GNSS and InSAR data;
[0054] The variance matrix of the observation noise Σ W , expressed as:
[0055]
[0056] In an optional implementation, the system dynamic noise vector may also be the average value of the accelerations in three directions of the monitoring point.
[0057] In the embodiment of the present application, the wide-area deformation monitoring in step S1 includes projecting the three-dimensional deformation of the GNSS monitoring point to the InSAR line of sight, calculating the unit projection vector of the InSAR observation value based on the satellite heading angle and the radar incident angle, and calculating the GNSS line of sight deformation.
[0058] Specifically, the GNSS observations are projected onto the InSAR line of sight, expressed as:
[0059]
[0060] in, is the GNSS line-of-sight deformation of the monitoring point, E, N, and U are the east-west, north-south, and vertical deformations of the monitoring point, respectively, and S x 、S y 、S z are the unit projection vectors of InSAR observations respectively;
[0061] Among them, the unit projection vector S x , expressed as:
[0062]
[0063] Unit projection vector S y , expressed as:
[0064]
[0065] Unit projection vector S z , expressed as:
[0066] Sz =cosθ
[0067] Among them, α is the satellite heading azimuth, θ is the radar incident angle;
[0068] The satellite heading azimuth rotates clockwise starting from due north.
[0069] In the embodiment of the present application, the dynamic error correction in step S1 includes using GNSS observations to spatially constrain the InSAR data, establish a quadratic fitting model, calculate the difference; and solve the quadratic fitting model parameters to correct the InSAR data.
[0070] Specifically, the spatial constraint is expressed as:
[0071]
[0072] in, is the InSAR observation value;
[0073] Calculate the difference, expressed as:
[0074] V=a0+a1*B+a2*L+a3*B 2 +a4*L 2 +a5*B*L+Δ
[0075] Where B is the latitude of the monitoring point, L is the longitude of the monitoring point, V is the difference between the GNSS-calculated value and the InSAR value, a0, a1, a2, a3, a4, and a5 are the quadratic fitting model parameters, and Δ is the observation noise.
[0076] The quadratic fitting model parameters a0, a1, a2, a3, a4, and a5 are solved by the least squares method. The longitude and latitude difference of any point is calculated using the formula to obtain the difference of the point. The InSAR observation value is compensated to obtain the corrected InSAR line-of-sight observation value.
[0077] In an optional embodiment, the quadratic fitting model parameters can also be solved by Kalman filtering, by using the quadratic model parameters as the state vector of the Kalman filter, using the GNSS and InSAR differences as observation values, and dynamically updating the parameter estimates through the Kalman gain.
[0078] In an optional embodiment, the quadratic fitting model parameters can also be solved by robust regression, and the influence of the difference points on the quadratic fitting model can be reduced by iterative weighted least squares. The model can be fitted from the data subset through a random sampling consistency algorithm to eliminate outliers that do not meet the threshold.
[0079] In the embodiment of the present application, the multi-dimensional collaborative monitoring in step S2 includes the drone flying along a preset route, generating a millimeter-level surface point cloud through lidar scanning, and providing high-precision data for three-dimensional modeling of the landslide body; synchronously collecting visible light and near-infrared band effects through a multispectral camera, calculating the normalized vegetation index, and analyzing soil moisture anomalies; detecting the surface temperature field distribution through an infrared thermal imager, identifying local low-temperature areas caused by groundwater seepage; and shooting a video stream of surface crack expansion through a pan-tilt camera.
[0080] Specifically, refer to Figure 2 The UAV is composed of a navigation control system, a mission payload system, a data processing unit, and an auxiliary equipment system. The navigation and control system uses an RTK differential GPS module to work in conjunction with a ground base station to achieve centimeter-level positioning, ensuring the coordinate consistency of the aerial survey data. It also supports flight on preset routes and corrects path deviations in real time through satellite signals. It is suitable for complex environments with frequent signal interference. Combined with the IMU inertial measurement unit, it corrects flight attitude in real time to ensure a stable track in complex environments such as strong winds in mountainous areas.
[0081] LiDAR generates millimeter-level surface point clouds through high-frequency pulse scanning, penetrates vegetation to identify deformation features such as cracks and bulges, and provides high-precision data for 3D modeling of landslides.
[0082] The mission payload system is equipped with a multispectral imager to capture the vegetation reflectance spectrum, combines the NDVI index to analyze soil moisture anomalies, and simultaneously detects temperature changes caused by groundwater seepage or sliding friction through infrared thermal imaging. It cooperates with the pan-tilt camera to transmit real-time dynamic video streams of surface crack expansion, forming a multi-dimensional monitoring network of "spectral-thermal-imaging".
[0083] In the implementation manner of the present application, in step S2, the edge computing device is used to fuse multi-source data to generate a landslide risk heat map, including the edge computing device pre-processing the multi-dimensional collaborative monitoring data of the drone; and combining the deep learning algorithm to identify the risk area, and storing the data and transmitting it to the ground station in real time; based on the three-dimensional model of the landslide body established by the drone, the point cloud differences are compared through periodic inspections, and the multi-dimensional parameters are fused in combination with the LSTM model to generate a landslide risk heat map.
[0084] Specifically, the drone data processing unit uses edge computing devices to denoise the lidar point cloud and perform radiometric correction on the multispectral image;
[0085] A deep learning algorithm is used to automatically identify risk areas where displacement exceeds 5mm / month. Data is stored on dual-backup SSDs and transmitted to the ground station in real time via wireless networks.
[0086] During actual operations, the drone establishes a centimeter-level three-dimensional background model, compares point cloud differences based on periodic inspections, and combines the LSTM model to fuse displacement, humidity, and temperature parameters to generate a heat map of the tower foundation landslide risk.
[0087] In an optional implementation, a landslide risk heat map can also be generated based on a Bayesian network. By constructing Bayesian network nodes, the point cloud displacement, humidity, and temperature are used as observation variables, and the landslide risk level is used as a latent variable. The dependency between parameters is quantified through a conditional probability table. Combined with periodic drone inspection data, the Markov chain Monte Carlo method is used to dynamically update the posterior probability to generate a risk heat map.
[0088] In an optional implementation, the landslide risk heat map can also be generated through dynamic risk prediction using a spatiotemporal graph convolutional network. This discretizes the landslide area into network nodes, where each node contains multidimensional features and edge weights reflect spatial adjacency or deformation correlation. The graph convolution layer is used to extract spatial features, and the temporal convolution layer is combined to capture the temporal dependencies of periodic inspection data to output the risk level of each node.
[0089] It should be noted that the auxiliary equipment system includes an IP68 rainproof casing, solar cells and an emergency parachute; it can ensure the reliability of the equipment under extreme conditions such as heavy rain and low temperature.
[0090] In the embodiment of the present application, the active waveguide acoustic emission system in step S3 includes a steel waveguide tube, backfill granular material and an acoustic emission monitoring device.
[0091] Specifically, refer to Figure 3 The backfill granular material uses rock particles, and the particles interact with each other to produce sound, which can improve the monitoring accuracy of the acoustic emission monitoring device;
[0092] The acoustic emission monitoring device consists of a resonant emission sensor connected to the above-ground part of the waveguide, an amplifier, a filter, and an acoustic emission characteristic parameter extraction and analysis module;
[0093] Among them, the resonant emission sensor is used to convert the acoustic emission elastic wave into a voltage signal, and the amplifier and filter are used to improve the acoustic signal-to-noise ratio;
[0094] Ring count is one of the key parameters in the acoustic emission characteristic parameter extraction and analysis module. It refers to the number of times the acoustic emission waveform exceeds the preset voltage threshold within a certain period of time, reflecting the intensity and frequency of the acoustic emission signal.
[0095] In the embodiment of the present application, achieving early warning in step S3 includes fitting the acoustic emission rate and the landslide velocity based on historical data to establish an empirical model; and achieving early warning of landslide based on the empirical model.
[0096] Specifically, the active waveguide is installed in the drill hole of the landslide body and intersects with the surveyed or inferred sliding surface. There is a causal relationship between the deep deformation of the landslide and the acoustic emission of the active waveguide. The deep deformation exerts mechanical effects such as shear and extrusion on the active waveguide, causing collision and friction between the waveguide tube and the backfill particles, thereby generating acoustic emission signals. The signals propagate upward along the steel pipe to the sensor, thereby monitoring possible signs of landslide and achieving early warning.
[0097] Based on statistical experience, the proportional coefficient C is introduced p The positive correlation between acoustic emission rate and landslide velocity was quantified and an empirical model was established, which is expressed as:
[0098] AE rate ∝v
[0099] AE rate =C p v
[0100] C p =f(V)
[0101] Among them, AE rate represents the acoustic emission rate, v represents the landslide velocity, and f(V) is the inherent variable of acoustic emission monitoring;
[0102] C p It reflects the sensitivity of the monitoring device and characterizes the response intensity between landslide velocity and acoustic emission rate.
[0103] It should be noted that the sensitivity of the device depends on the inherent variables of the acoustic emission monitoring device, such as sensor sensitivity, waveguide length, active waveguide material and structure, etc.
[0104] Example 3, reference Figure 4 The above is a schematic diagram of a method for monitoring tower foundation landslides. It should be noted that the technical solution of the tower foundation landslide monitoring system and the technical solution of the tower foundation landslide monitoring method described above are based on the same concept. For details not described in detail in the technical solution of the tower foundation landslide monitoring system in this embodiment, please refer to the description of the technical solution of the tower foundation landslide monitoring method described above.
[0105] This embodiment also provides a tower foundation landslide monitoring system, which includes: a wide-area deformation monitoring module, a drone monitoring module, and a capture and early warning module.
[0106] Among them, the wide-area deformation monitoring module is used to fuse InSAR data and GNSS data for wide-area deformation monitoring, establish a quadratic fitting model to dynamically correct the errors of InSAR observations, and identify potential landslide hazard areas; the drone monitoring module is used to conduct multi-dimensional collaborative monitoring of potential landslide hazard areas through drones equipped with sensors, and use edge computing devices to fuse multi-source data to generate landslide risk heat maps; the capture and warning module is used to use an active waveguide acoustic emission system to capture deep deformation signals of landslides, and achieve early warning through ringing counts and acoustic emission rate parameters.
[0107] This embodiment also provides an electronic device suitable for monitoring tower foundation landslides, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the tower foundation landslide monitoring method proposed in the above embodiment.
[0108] This embodiment further provides a storage medium storing a computer program, which, when executed by a processor, implements the tower foundation landslide monitoring method proposed in the above embodiment.
[0109] The storage medium proposed in this embodiment and the method for implementing tower foundation landslide monitoring proposed in the above embodiment belong to the same inventive concept. For technical details not described in detail in this embodiment, please refer to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.
[0110] Through the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented with the help of software and necessary general hardware, and of course can also be implemented by hardware. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of various embodiments of the present invention.
[0111] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.
Claims
1. A tower foundation landslide monitoring method, characterized in that: include: InSAR data and GNSS data are integrated for wide-area deformation monitoring. A quadratic fitting model is established to dynamically correct errors in InSAR observations and identify potential landslide risk areas. Sensor-equipped drones conduct multi-dimensional collaborative monitoring of potential landslide risk areas, and edge computing devices fuse multi-source data to generate landslide risk heat maps. An active waveguide acoustic emission system is used to capture deep deformation signals of landslides, and early warning is achieved through ringing counts and acoustic emission rate parameters.
2. The tower foundation landslide monitoring method according to claim 1, characterized in that: The wide-area deformation monitoring includes projecting the three-dimensional deformation of the GNSS monitoring point to the InSAR line of sight, calculating the unit projection vector of the InSAR observation value based on the satellite heading angle and the radar incident angle, and calculating the deformation in the GNSS line of sight.
3. The tower foundation landslide monitoring method according to claim 2, characterized in that: The dynamic error correction includes using GNSS observations to spatially constrain InSAR data, establish a quadratic fitting model, and calculate differences; Solve the quadratic fitting model parameters to correct InSAR data.
4. The tower foundation landslide monitoring method according to claim 3, characterized in that: The multi-dimensional collaborative monitoring involves drones flying along preset routes and using lidar scanning to generate millimeter-level surface point clouds, providing high-precision data for three-dimensional modeling of landslides. Multispectral cameras are used to simultaneously capture visible and near-infrared images, calculate the normalized vegetation index, and analyze soil moisture anomalies. Use infrared thermal imaging cameras to detect the surface temperature distribution and identify local low-temperature areas caused by groundwater seepage; The video stream of surface crack expansion is captured by a pan-tilt camera.
5. The tower foundation landslide monitoring method according to claim 4, characterized in that: The generation of a landslide risk heat map by fusing multi-source data using an edge computing device includes pre-processing the multi-dimensional collaborative monitoring data of the UAV by the edge computing device; It also combines deep learning algorithms to identify risk areas, store data, and transmit it to ground stations in real time; Based on the three-dimensional model of the landslide body established by drones, the point cloud differences are compared through periodic inspections, and the multi-dimensional parameters are integrated with the LSTM model to generate a landslide risk heat map.
6. The tower foundation landslide monitoring method according to claim 5, characterized in that: The active waveguide acoustic emission system includes a steel waveguide tube, backfill granular material and an acoustic emission monitoring device.
7. The tower foundation landslide monitoring method according to claim 6, characterized in that: The early warning includes fitting the acoustic emission rate and landslide velocity based on historical data to establish an empirical model; Realize early warning of landslides based on empirical models.
8. A tower foundation landslide monitoring system, applying the method according to any one of claims 1 to 7, characterized in that: include: Wide-area deformation monitoring module, drone monitoring module, capture and early warning module; The wide-area deformation monitoring module is used to fuse InSAR data and GNSS data for wide-area deformation monitoring, establish a quadratic fitting model to dynamically correct errors in InSAR observations, and identify potential landslide risk areas; The drone monitoring module is used to conduct multi-dimensional collaborative monitoring of potential landslide risk areas through drones equipped with sensors, and to generate landslide risk heat maps by fusing multi-source data using edge computing devices; The capture and early warning module is used to capture the deep deformation signal of the landslide using an active waveguide acoustic emission system, and to achieve early warning through ring count and acoustic emission rate parameters.
9. An electronic device comprising: memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the tower foundation landslide monitoring method according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the steps of the tower foundation landslide monitoring method according to any one of claims 1 to 7.
Citation Information
Cited By
Mountain area power transmission line risk detection method driven by unmanned aerial vehicle oblique photography data, equipment and medium
CN121438158A
An unmanned aerial vehicle tilt photography data-driven mountainous area power transmission line risk detection method, device and medium
CN121438158B
Power transmission line tower landslide multi-source three-dimensional monitoring method and system and storage medium
CN121475315A
Landslide intelligent monitoring and early warning method and precise prevention and ecological collaborative restoration system
CN121884531A
Throwing type landslide mass monitoring system and device based on surface laser ranging
CN122050072A
