Method and device for monitoring slope stability of wind power plant
By sub-dividing and data fusion of wind farm slopes, using remote sensing and aerial photography data to generate slope stability data, the problems of low monitoring efficiency and insufficient accuracy in the existing technology are solved, and efficient and panoramic slopes are achieved Stability monitoring.
Patent Information
- Application Number
- CN202410972417.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-19
- Publication Date
- 2024-11-08
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing wind farm slope stability monitoring methods are costly and inefficient, and it is difficult to obtain panoramic disaster hazard information. Manual inspections are dangerous. Monitoring instruments can only cover known hidden danger points, making it difficult to fully monitor the slope of wind farms. stability.
By dividing the test area into several sub-regions, remote sensing images and aerial images are acquired, deformation rate matrix and similarity are constructed, remote sensing data and aerial photography data are fused, slope stability data are generated, and monitoring efficiency and accuracy are improved.
It achieves the improvement of monitoring efficiency while ensuring monitoring accuracy, and can monitor deformation information on the slope of wind power farms with high accuracy and panoramicity, improving the accuracy and flexibility of monitoring, and reducing monitoring costs.
Smart Images

Figure CN118913202A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of slope monitoring, and in particular to a method and device for monitoring the stability of a wind farm slope. Background Art
[0002] Wind power plants are generally built in areas with abundant wind energy resources, such as mountainous areas and plateaus. However, these areas are often prone to geological disasters. The slope stability in the wind farm construction area has a great impact on its construction, operation and maintenance.
[0003] In related technologies, wind farms mainly monitor slope stability by manually checking for geological hazards and deploying instruments to monitor the dynamic changes in known hazard areas. Among them, the manual inspection method is costly, inefficient, and has certain risks. The deployment of monitoring instruments can only take into account the known hazard points, making it difficult to obtain panoramic disaster hazard information in the wind farm construction area.
[0004] In view of this, a high-precision slope stability monitoring method that can improve monitoring efficiency is needed. Summary of the invention
[0005] In view of this, the present invention provides a method for monitoring the slope stability of a wind farm to improve the monitoring efficiency.
[0006] In a first aspect, the present invention provides a method for monitoring the slope stability of a wind farm, the method comprising: dividing the boundary of a test area to obtain a plurality of sub-areas, wherein the sub-areas include at least one wind turbine; based on the boundary range of each sub-area, obtaining a remote sensing image set corresponding to each sub-area within a monitoring period, wherein the remote sensing image set includes at least two remote sensing images of the sub-area taken at different times; for the remote sensing image set corresponding to each sub-area, determining a deformation rate matrix of each sub-area within the monitoring period, wherein the deformation rate matrix is a motion speed matrix of slope deformation within the sub-area; based on the deformation rate matrix of each sub-area within the monitoring period, determining a target sub-area in each sub-area; obtaining at least two aerial images of the target sub-area taken at different times to determine the similarity of the target sub-area; and generating slope stability data of the target sub-area based on the similarity.
[0007] In this embodiment, by fusing remote sensing data and aerial photography data, deformation information of different spatial scales is obtained, which can improve monitoring efficiency while ensuring monitoring accuracy.
[0008] In an optional embodiment, dividing the area to be tested into boundaries and obtaining a plurality of sub-areas includes: obtaining the spatial position of the wind turbine in the area to be tested; constructing a plurality of Thiessen polygons based on the spatial position, wherein the Thiessen polygon includes only one wind turbine; and dividing the sub-areas using the Thiessen polygons as sub-area boundaries.
[0009] In this implementation, the area to be tested is divided into a plurality of sub-areas whose boundaries are Thiessen polygons according to the locations of the wind turbines, which can improve the flexibility of the monitoring method.
[0010] In an optional embodiment, based on the boundary range of each sub-region, obtaining a remote sensing image set corresponding to each sub-region within the monitoring period includes: determining the sampling time of the remote sensing image within the monitoring period; according to the sampling time, obtaining the remote sensing image corresponding to each sub-region to construct a remote sensing image set, wherein the remote sensing image set corresponds to each sub-region.
[0011] In this embodiment, by acquiring remote sensing images within the monitoring period, the area to be tested can be observed in a short time, thereby improving the monitoring efficiency.
[0012] In an optional embodiment, for the remote sensing image sets corresponding to each sub-region, determining the deformation rate matrix of each sub-region during the monitoring period includes: based on the remote sensing image set, obtaining the deformation information of each sub-region during the monitoring period to construct a deformation distance matrix corresponding to each sub-region; based on the deformation distance matrix and the monitoring period, determining the deformation rate matrix of each sub-region.
[0013] In this embodiment, by analyzing remote sensing images and constructing a deformation distance matrix of the sub-regions to determine the deformation rate matrix of each sub-region, the minute deformation of the sub-regions can be accurately measured, thereby improving monitoring accuracy.
[0014] In an optional embodiment, the deformation information of each sub-region within the monitoring period is obtained to construct a deformation distance matrix corresponding to each sub-region, including: for each remote sensing image set corresponding to each sub-region, a phase interference map of each sub-region is generated, wherein the phase difference of the phase interference map represents the deformation information of the sub-region within the monitoring period; for the phase interference map, data preprocessing is performed, wherein the data preprocessing includes at least one of atmospheric correction, noise filtering and terrain correction; based on the phase interference map after data preprocessing, a deformation distance matrix of each sub-region is obtained, wherein the deformation distance matrix represents the deformation distance of the slope deformation within the sub-region.
[0015] In this embodiment, by acquiring a phase interference map of a sub-region and preprocessing the phase interference map to obtain a deformation distance matrix of the sub-region, the accuracy of topographic measurement can be improved, thereby improving the accuracy of monitoring.
[0016] In an optional implementation, before determining the deformation rate matrix of each sub-area based on the deformation distance matrix and the monitoring period, it also includes: acquiring slope aspect data of each sub-area; comparing the line of sight and slope aspect of the remote sensing image, and correcting the deformation distance matrix based on the comparison result.
[0017] In this embodiment, the accuracy and reliability of the data can be ensured by correcting the deformation distance matrix.
[0018] In an optional embodiment, obtaining at least two aerial images of the target sub-area at different times to determine the similarity of the target sub-area includes: obtaining a set of aerial images of the target sub-area; constructing a three-dimensional model based on the set of aerial images; and obtaining the similarity of the target sub-area within the monitoring period based on the three-dimensional model.
[0019] In this embodiment, by acquiring aerial images of the target sub-region at different times and constructing a three-dimensional model, the similarity of the target sub-region can be quickly and accurately obtained, thereby improving the accuracy of the monitoring method.
[0020] In an optional embodiment, constructing a three-dimensional model based on an aerial image set includes: extracting feature points of continuous aerial images in the aerial image set; matching the feature points and generating a feature matrix; and constructing a three-dimensional model based on the feature matrix, wherein the three-dimensional model corresponds to the aerial image.
[0021] In this embodiment, by extracting feature points of the aerial image and constructing a three-dimensional model, detailed deformation data of the monitoring area can be obtained, thereby improving the accuracy of monitoring.
[0022] In an optional embodiment, based on the three-dimensional model, obtaining the similarity of the target sub-region within the monitoring period includes: obtaining a first model and a second model of the target sub-region, wherein the first model and the second model are three-dimensional models with different time phases; extracting feature information of the first model and the second model, wherein the feature information includes structural information of the model; based on the feature information, aligning the first model and the second model, and based on the alignment result, determining the similarity of the target sub-region.
[0023] In this embodiment, by comparing the terrain data of the target sub-region at different time points, the similarity of the target sub-region at different times can be obtained, thereby realizing the monitoring of the target sub-region.
[0024] In a second aspect, the present invention provides a wind farm slope stability monitoring device, the device comprising: a division module, used to divide the boundary of the test area and obtain a plurality of sub-areas, wherein the sub-areas include at least one wind turbine; a remote sensing image acquisition module, used to obtain a remote sensing image set corresponding to each sub-area within a monitoring period based on the boundary range of each sub-area, wherein the remote sensing image set includes at least two sub-area remote sensing images taken at different times; a deformation rate determination module, used to determine the deformation rate matrix of each sub-area within the monitoring period for the remote sensing image set corresponding to each sub-area, wherein the deformation rate matrix is a motion speed matrix of the slope deformation within the sub-area; a target sub-area determination module, used to determine the target sub-area in each sub-area based on the deformation rate matrix of each sub-area within the monitoring period; an acquisition module, used to obtain at least two aerial images of the target sub-area taken at different times to determine the similarity of the target sub-area; and a generation module, used to generate slope stability data of the target sub-area based on the similarity. BRIEF DESCRIPTION OF THE DRAWINGS
[0025] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0026] Figure 1 is a schematic flow chart of a method for monitoring slope stability of a wind farm according to an embodiment of the present invention;
[0027] Figure 2 is a schematic flow chart of another method for monitoring slope stability of a wind farm according to an embodiment of the present invention;
[0028] Figure 3 is a schematic flow chart of another method for monitoring slope stability of a wind farm according to an embodiment of the present invention;
[0029] Figure 4 is a structural block diagram of a wind farm slope stability monitoring device according to an embodiment of the present invention;
[0030] Figure 5 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION
[0031] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.
[0032] An embodiment of the present invention provides a method for monitoring the slope stability of a wind farm. By integrating remote sensing images and drone aerial images, the slope deformation information of the area to be tested is obtained, thereby ensuring monitoring accuracy and significantly improving monitoring efficiency.
[0033] According to an embodiment of the present invention, an embodiment of a method for monitoring slope stability of a wind farm is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.
[0034] In this embodiment, a method for monitoring the slope stability of a wind farm is provided. Figure 1 is a flow chart of a method for monitoring slope stability of a wind farm according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:
[0035] Step S101 : dividing the area to be tested into boundaries to obtain a plurality of sub-areas, wherein each sub-area includes at least one wind turbine.
[0036] In a possible implementation of the embodiment of the present application, the division criteria of the sub-region boundaries can be determined based on multiple factors such as the distribution, power, and terrain conditions of wind turbines. For example, after the computer device obtains the location information of the area to be tested and the distribution of wind turbines in the area to be tested, the area to be tested can be divided into regular grids at fixed intervals to determine whether the grid includes at least one wind turbine. If a grid does not include a wind turbine, it is merged into the nearest grid containing a wind turbine to form a new grid, and each grid is then used as a sub-region. It is also possible to divide the area to be tested into regular grids, take each grid as an initial sub-region, and then merge the sub-regions without wind turbines into the sub-regions with wind turbines with the wind turbines as the core to form a new sub-region.
[0037] In another possible implementation, after obtaining the location information of the area to be tested and the distribution of wind turbines in the area to be tested, each wind turbine can be used as a core point and the perpendicular bisector of the line segment between each two adjacent core points can be used as the boundary of the Thiessen polygon to construct the Thiessen polygon. Each Thiessen polygon is regarded as a sub-area.
[0038] Specifically, the area division tool in GIS (Geographic Information System) software can be used to divide the boundaries of the area to be tested. After the boundaries are divided, the boundaries can be appropriately adjusted according to actual conditions to finally obtain a number of sub-areas.
[0039] Step S102: based on the boundary range of each sub-region, a remote sensing image set corresponding to each sub-region within the monitoring period is obtained, wherein the remote sensing image set includes at least two remote sensing images of the sub-region at different times.
[0040] The acquisition of remote sensing images is not restricted and can be obtained directly through relevant platforms or websites. Remote sensing images can be cropped and adjusted according to the boundary range of the sub-area. The number of remote sensing images in the remote sensing image set is not restricted, and as many remote sensing images as possible within the monitoring period can be obtained to improve the accuracy of subsequent monitoring.
[0041] Step S103, for each remote sensing image set corresponding to each sub-region, determine the deformation rate matrix of each sub-region within the monitoring period, wherein the deformation rate matrix is a movement speed matrix of the slope deformation in the sub-region.
[0042] According to the actual situation, different deformation monitoring methods can be selected to obtain the deformation rate matrix of the sub-area during the monitoring period. The deformation monitoring method can be InSAR (Interferometric Synthetic Aperture Radar) technology, image comparison method, differential deformation method, etc.
[0043] In a practical application, InSAR technology is used to obtain the deformation rate matrix of the sub-area during the monitoring period. By obtaining the InSAR data of each sub-area, the data is processed by phase unwrapping, filtering, and de-noising. Then, the surface deformation rate of the sub-area is analyzed using differential interferometry or time series method, and the deformation rate matrix of the sub-area during the monitoring period is obtained.
[0044] Step S104: determining a target sub-region in each sub-region based on the deformation rate matrix of each sub-region within the monitoring period.
[0045] Among them, the method of determining the target sub-region is not restricted. The dangerousness of the sub-region is determined according to the deformation rate matrix. A dangerousness threshold can be set. If the dangerousness reaches the dangerousness threshold, the sub-region is the target sub-region. The sub-regions can also be sorted according to their dangerousness, and one or more sub-regions with higher dangerousness are selected as target sub-regions.
[0046] Step S105 , obtaining at least two aerial images of the target sub-region taken at different times to determine the similarity of the target sub-region.
[0047] There is no restriction on the way of acquiring aerial images, and they can be taken by a camera mounted on a drone. There is no restriction on the number of aerial images, and as many as possible can be taken. After acquiring aerial images at different times, the aerial images can be preprocessed, and the preprocessing method is not restricted, and can be denoising, adjusting contrast, brightness, etc. Then, the aerial images at different time points are registered to ensure their spatial consistency, and then a suitable similarity measurement method is selected to obtain the similarity of the target sub-areas at different times. There is no restriction on the selection of similarity measurement methods, and they can be selected according to actual conditions.
[0048] Step S106: Generate slope stability data of the target sub-area based on the similarity.
[0049] A similarity threshold may be set, and whether the slope of the target sub-region is stable may be determined by judging whether the similarity reaches the similarity threshold. The representation of the slope stability result data is not limited and may be a specific value.
[0050] After obtaining the slope stability data of the target sub-area, the operating status of the wind turbine can be controlled in combination with factors such as the meteorological conditions and slope deformation in the area to guide the emergency management of geological disasters in the wind farm.
[0051] The wind farm slope stability monitoring method provided in this embodiment obtains deformation information of different spatial scales by fusing remote sensing data and aerial photography data, thereby improving monitoring efficiency while ensuring monitoring accuracy.
[0052] In this embodiment, a method for monitoring the slope stability of a wind farm is provided. Figure 2 is a flow chart of a method for monitoring slope stability of a wind farm according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:
[0053] Step S201 : dividing the area to be tested into boundaries to obtain a plurality of sub-areas, wherein each sub-area includes at least one wind turbine.
[0054] Specifically, the above step S201 includes:
[0055] Step S2011, obtaining the spatial position of the wind turbine in the area to be tested.
[0056] There is no restriction on the method of acquiring the spatial position of the wind turbine. It can be acquired through relevant software and platforms, or by performing image recognition on remote sensing images of the test area to acquire the spatial position of the wind turbine in the test area.
[0057] Step S2012: construct a plurality of Thiessen polygons based on the spatial position, wherein the Thiessen polygon includes only one wind turbine.
[0058] Among them, the method of constructing Thiessen polygons is not restricted, and the automatic construction of Thiessen polygons can be achieved through relevant software.
[0059] Step S2013, using Thiessen polygons as sub-region boundaries to divide sub-regions.
[0060] In a practical application, the locations of all wind turbines in the area to be tested are extracted as discrete spatial location points. Then, using GIS spatial analysis technology, the spatial location point of each wind turbine is used as a generation point. The Thiessen polygon algorithm is used to generate several Thiessen polygons. The boundaries of the Thiessen polygons are used as the boundaries of the sub-areas to achieve boundary division of the area to be tested.
[0061] Dividing the area to be tested into multiple sub-areas whose boundaries are Thiessen polygons according to the locations of wind turbines can improve the flexibility of the monitoring method.
[0062] Step S202: based on the boundary range of each sub-region, a remote sensing image set corresponding to each sub-region within the monitoring period is obtained, wherein the remote sensing image set includes at least two remote sensing images of the sub-region at different times.
[0063] Specifically, the above step S202 includes:
[0064] Step S2021, determining the sampling time of the remote sensing image within the monitoring period.
[0065] Among them, the sampling time of remote sensing images is not restricted and can be selected according to actual conditions.
[0066] Step S2022, acquiring remote sensing images corresponding to each sub-region respectively according to the sampling time to construct a remote sensing image set, wherein the remote sensing image set corresponds to each sub-region.
[0067] There is no restriction on the method of acquiring remote sensing images, and remote sensing images corresponding to each sub-area can be acquired through relevant platforms or websites.
[0068] After acquiring the remote sensing image, the remote sensing image can be preprocessed according to the actual situation to ensure the quality of the remote sensing image and improve the accuracy of subsequent data. The preprocessing method is not limited and can be atmospheric correction, radiation correction, geometric correction, and image enhancement.
[0069] By acquiring remote sensing images during the monitoring period, the area to be tested can be observed in a short time, thus improving monitoring efficiency.
[0070] Step S203, for each remote sensing image set corresponding to each sub-region, determine the deformation rate matrix of each sub-region within the monitoring period, wherein the deformation rate matrix is a movement speed matrix of the slope deformation in the sub-region.
[0071] Specifically, the above step S203 includes:
[0072] Step S2031, based on the remote sensing image set, the deformation information of each sub-region within the monitoring period is obtained to construct a deformation distance matrix corresponding to each sub-region.
[0073] There is no restriction on the method of obtaining the deformation information of the sub-region, and the information can be obtained by using InSAR technology, digital image correlation method, etc.
[0074] In some optional implementations, the above step S2031 includes:
[0075] Step a1, for the remote sensing image sets corresponding to the sub-regions, generate a phase interference map of each sub-region, wherein the phase difference of the phase interference map represents the deformation information of the sub-region during the monitoring period.
[0076] There is no restriction on the generation method of the phase interference diagram. The phase difference between two images can be obtained by performing Fourier transform on the remote sensing image, and then the phase interference diagram can be obtained.
[0077] In a practical application, a phase map is obtained by performing differential interferometry analysis on remote sensing images of a sub-region at different phases.
[0078] Step a2, performing data preprocessing on the phase interferogram, wherein the data preprocessing includes at least one of atmospheric correction, noise filtering and terrain correction.
[0079] The choice of data preprocessing is not limited. In addition to atmospheric correction, noise filtering and terrain correction, it can also include radiation correction, phase consistency processing, etc.
[0080] Step a3: based on the phase interference image after data preprocessing, obtain the deformation distance matrix of each sub-region, wherein the deformation distance matrix represents the deformation distance of the slope deformation in the sub-region.
[0081] By performing phase unwrapping on the phase interference pattern, the deformation distance matrix of the sub-region corresponding to the phase interference pattern can be obtained.
[0082] In a practical application, the spatial resolution of the remote sensing image is m*n, and each remote sensing image contains l pixels, where is the product of m and n. The size of the deformation distance matrix is the same as the spatial resolution of the remote sensing image, which is also m rows and n columns. Each value in the matrix represents the deformation distance of the pixel.
[0083] By obtaining the phase interference map of the sub-area and preprocessing the phase interference map to obtain the deformation distance matrix of the sub-area, the accuracy of topographic measurement can be improved, thereby improving the accuracy of monitoring.
[0084] In some optional implementations, the above step S2031 includes:
[0085] Step b1, obtaining the slope aspect data of each sub-area.
[0086] There is no restriction on the way of obtaining aspect data. It can be obtained by using remote sensing images through stereo measurement or by using relevant terrain analysis software.
[0087] Step b2, comparing the sight line direction and slope direction of the remote sensing image, and correcting the deformation distance matrix based on the comparison result.
[0088] The sight direction of the remote sensing image can be obtained through relevant remote sensing image processing software. The comparison between the sight direction and the slope direction can be achieved by calculating the angle between the sight direction and the slope direction.
[0089] In a practical application, the slope data is calculated using the terrain data of the sub-region, and a matching error threshold is set to perform consistency matching on each pixel in the line of sight and the slope of the remote sensing image. If the line of sight and the slope of the pixel are consistent, the data corresponding to the pixel in the deformation distance matrix is retained. If the line of sight and the slope of the pixel are inconsistent, the data corresponding to the pixel in the deformation distance matrix is set to 0. Among them, the setting of the matching error threshold is not restricted and can be selected according to actual conditions. In a practical application, the matching error threshold is ±90 degrees. If the angle between the line of sight and the slope of the image is within the range of the matching error threshold, it can be determined to be consistent.
[0090] By correcting the deformation distance matrix, the accuracy and reliability of the data can be ensured.
[0091] Step S2032: Determine the deformation rate matrix of each sub-region based on the deformation distance matrix and the monitoring period.
[0092] The deformation rate matrix can be obtained by calculating the quotient of the deformation distance matrix and the detection period.
[0093] In an actual application, step S2031 is repeated several times to obtain deformation distance matrices of the sub-regions at different phases, and these deformation distance matrices are combined into deformation distance information. In an actual application, the deformation distance information is expressed as follows:
[0094] D=[D1,...,D i , ..., D t ]
[0095] Among them, D1 is the deformation distance matrix of the first phase within the monitoring time, D i is the deformation distance matrix of the i-th phase within the monitoring time, D t is the deformation distance matrix of the tth phase within the monitoring time.
[0096] By analyzing each deformation distance matrix in the deformation distance information, the deformation rate matrix within the sub-region monitoring period can be obtained, where the size of the deformation rate matrix is the same as the size of the deformation distance matrix, and each data in the deformation rate matrix represents the surface deformation rate value within the monitoring period.
[0097] By analyzing remote sensing images and constructing the deformation distance matrix of the sub-regions to determine the deformation rate matrix of each sub-region, the tiny deformation of the sub-regions can be accurately measured to improve the monitoring accuracy.
[0098] Step S204: determining a target sub-region in each sub-region based on the deformation rate matrix of each sub-region within the monitoring period.
[0099] For details, please see Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.
[0100] In a practical application, the elements contained in the deformation rate matrix of each sub-region during the monitoring period are divided into dangerous levels. According to the division results, the number of first elements in the deformation rate matrix of each sub-region during the monitoring period is determined, wherein the first element is the dangerous level of the first dangerous level, and the selection of the first dangerous level is not restricted and can be medium, high and extremely high; by calculating the ratio of the number of first elements in each deformation rate matrix to the total number of elements, the dangerousness degree of the sub-region is obtained. According to the dangerousness degree of each sub-region, the target sub-region is selected.
[0101] Among them, the elements contained in the deformation rate matrix of each sub-area during the monitoring period can be divided into dangerous levels according to Table 1.
[0102] grade Rate characteristics Low <0.016 m / year medium 0.016m / year~1.6m / year high 1.6m / year~13m / month Very high >13m / month
[0103] Table 1
[0104] Step S205 , obtaining at least two aerial images of the target sub-region taken at different times to determine the similarity of the target sub-region.
[0105] For details, please see Figure 1 Step S105 of the illustrated embodiment will not be described in detail here.
[0106] Step S206: Generate slope stability data of the target sub-area based on the similarity.
[0107] For details, please see Figure 1 Step S106 of the illustrated embodiment will not be described in detail here.
[0108] The wind farm slope stability monitoring method provided in this embodiment can monitor the area to be tested over a large range and with high precision by analyzing the remote sensing image of the area to be tested, thereby improving the monitoring efficiency.
[0109] In this embodiment, a method for monitoring the slope stability of a wind farm is provided. Figure 3 is a flow chart of a method for monitoring slope stability of a wind farm according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:
[0110] Step S301 : dividing the area to be tested into boundaries to obtain a plurality of sub-areas, wherein each sub-area includes at least one wind turbine.
[0111] For details, please see Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.
[0112] Step S302: based on the boundary range of each sub-region, obtain a remote sensing image set corresponding to each sub-region within the monitoring period, wherein the remote sensing image set includes at least two remote sensing images of the sub-region at different times.
[0113] For details, please see Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.
[0114] Step S303, for the remote sensing image sets corresponding to the sub-regions, respectively, a deformation rate matrix of each sub-region within the monitoring period is determined, wherein the deformation rate matrix is a movement speed matrix of the slope deformation within the sub-region.
[0115] For details, please see Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.
[0116] Step S304: determining a target sub-region in each sub-region based on the deformation rate matrix of each sub-region within the monitoring period.
[0117] For details, please see Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.
[0118] Step S305 , obtaining at least two aerial images of the target sub-region taken at different times to determine the similarity of the target sub-region.
[0119] Specifically, the above step S305 includes:
[0120] Step S3051, obtaining a set of aerial images of the target sub-area.
[0121] There is no restriction on the way of obtaining aerial images, and aerial photography can be performed by using a drone equipped with a camera. There is no restriction on the number of aerial images included in the aerial image collection, and as many images as possible can be taken according to the actual situation.
[0122] In a practical application, if there are at least two target sub-regions, the flight path of the drone can be planned according to the positions of the target sub-regions, and images of the target sub-regions can be collected.
[0123] Step S3052: construct a three-dimensional model based on the aerial image set.
[0124] Among them, the three-dimensional model construction method is not restricted, and a deep learning model can be used based on the aerial images to obtain a three-dimensional model corresponding to the aerial images.
[0125] In some optional implementations, the above step S3052 includes:
[0126] Step c1, extracting feature points of continuous aerial images in the aerial image set.
[0127] There is no restriction on the selection of feature points, which may be edge points, corner points, etc. There is no restriction on the feature point extraction algorithm, which may be SIFT (Scale-Invariant Feature Transform) and SURF (Speeded Up Robust Features), etc.
[0128] Step c2: Match the feature points and generate a feature matrix.
[0129] Among them, the feature points in the continuous aerial images can be matched by a feature matching algorithm. The feature matrix contains the matching information of the feature points.
[0130] Step c3, constructing a three-dimensional model based on the feature matrix, wherein the three-dimensional model corresponds to the aerial image.
[0131] Among them, the construction method of the three-dimensional model is not restricted. In a practical application, sparse point cloud data is generated based on the feature matrix, and then the sparse point cloud data is densely reconstructed in combination with the multi-view dense matching method to generate dense point cloud data, wherein the dense reconstruction algorithm is not restricted. After obtaining the dense point cloud data, the surface of the dense point cloud data can be reconstructed according to the Poisson surface reconstruction algorithm. Among them, the Poisson surface reconstruction algorithm is an algorithm for spatial solution of dense point cloud data. First, the spatial area of the point cloud data is divided into an octree, and then the normal vector of the point cloud data is calculated. Based on this, the gradient space Poisson equation is calculated, and then the isosurface of the spatial area is extracted to construct a three-dimensional space grid.
[0132] By extracting feature points from aerial images and constructing a three-dimensional model, we can obtain detailed deformation data of the monitored area and improve the accuracy of monitoring.
[0133] Step S3053: Based on the three-dimensional model, obtain the similarity of the target sub-areas within the monitoring period.
[0134] There is no restriction on the method of obtaining similarity. The similarity of the target sub-region can be obtained by extracting key set features between multiple three-dimensional models and calculating the distance between feature points. The similarity of the target sub-region can also be obtained by directly using a graph matching algorithm to compare the structural similarities between multiple models.
[0135] In some optional implementations, the above step S3053 includes:
[0136] Step d1, obtaining a first model and a second model of the target sub-region, wherein the first model and the second model are three-dimensional models with different time phases.
[0137] The time phases of the first model and the second model are not limited, and the time phases of the two models can be different. The acquisition method is also not limited, and the aerial images of different time phases can be directly acquired by inputting them into relevant software.
[0138] Step d2, extracting feature information of the first model and the second model, wherein the feature information includes structural information of the model.
[0139] There is no restriction on the method of extracting feature information, and the feature information can be directly extracted using relevant software.
[0140] Step d3, registering the first model and the second model based on the feature information, and determining the similarity of the target sub-region based on the registration result.
[0141] There is no restriction on the registration method. Similarity can be measured using a variety of methods, such as geometric similarity, topological similarity, etc.
[0142] In a practical application, a cloud comparison algorithm is used to obtain the robust distance between the first model and the second model, and the robust distance is used as the similarity of the target sub-region. According to the size of the robust distance value, the changes at each pixel at different time points can be obtained.
[0143] By comparing the terrain data of the target sub-area at different time points, the similarity of the target sub-area at different times can be obtained, thereby realizing the monitoring of the target sub-area.
[0144] Step S306: Generate slope stability data of the target sub-area based on the similarity.
[0145] For details, please see Figure 1 Step S106 of the illustrated embodiment will not be described in detail here.
[0146] The wind farm slope stability monitoring method provided in this embodiment can quickly and accurately obtain the similarity of the target sub-area by acquiring aerial images of the target sub-area at different times and constructing a three-dimensional model, thereby improving the accuracy of the monitoring method.
[0147] In this embodiment, a wind farm slope stability monitoring device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.
[0148] This embodiment provides a wind farm slope stability monitoring device, such as Figure 4 As shown, including:
[0149] A division module 401 is used to divide the boundary of the area to be tested and obtain a plurality of sub-areas, wherein each sub-area includes at least one wind turbine;
[0150] A remote sensing image acquisition module 402 is used to acquire a remote sensing image set corresponding to each sub-region within a monitoring period based on the boundary range of each sub-region, wherein the remote sensing image set includes at least two remote sensing images of the sub-region at different times;
[0151] The deformation rate determination module 403 is used to determine the deformation rate matrix of each sub-region within the monitoring period for the remote sensing image set corresponding to each sub-region, wherein the deformation rate matrix is the movement speed matrix of the slope deformation in the sub-region;
[0152] A target sub-region determining module 404 is used to determine a target sub-region in each sub-region based on a deformation rate matrix of each sub-region within a monitoring period;
[0153] An acquisition module 405 is used to acquire at least two aerial images of the target sub-region at different times to determine the similarity of the target sub-region;
[0154] The generating module 406 is used to generate the slope stability data of the target sub-area based on the similarity.
[0155] In some optional implementations, the division module 401 includes:
[0156] The spatial position acquisition unit is used to acquire the spatial position of the wind turbine in the area to be tested.
[0157] The Thiessen polygon construction unit is used to construct a plurality of Thiessen polygons based on spatial positions, wherein the Thiessen polygon includes only one wind turbine.
[0158] The sub-region division unit is used to divide the sub-region by using Thiessen polygons as sub-region boundaries.
[0159] In some optional implementations, the remote sensing image acquisition module 402 includes:
[0160] The sampling time determination unit is used to determine the sampling time of the remote sensing image within the monitoring period.
[0161] The remote sensing image acquisition unit is used to acquire the remote sensing images corresponding to each sub-region according to the sampling time to construct a remote sensing image set, wherein the remote sensing image set corresponds to each sub-region.
[0162] In some optional implementations, the deformation rate matrix determination module 403 includes:
[0163] The deformation distance matrix construction unit is used to obtain the deformation information of each sub-region within the monitoring period based on the remote sensing image set to construct a deformation distance matrix corresponding to each sub-region.
[0164] The aspect data acquisition unit is used to acquire the aspect data of each sub-area.
[0165] The correction unit is used to compare the sight direction and slope direction of the remote sensing image, and correct the deformation distance matrix based on the comparison result.
[0166] The deformation rate matrix determining unit is used to determine the deformation rate matrix of each sub-area based on the deformation distance matrix and the monitoring period.
[0167] In some optional implementations, the deformation distance matrix construction unit includes:
[0168] The phase interference map generation subunit is used to generate a phase interference map of each sub-region for the remote sensing image set corresponding to each sub-region, wherein the phase difference of the phase interference map represents the deformation information of the sub-region during the monitoring period.
[0169] The data preprocessing subunit is used to perform data preprocessing on the phase interference pattern, wherein the data preprocessing includes at least one of atmospheric correction, noise filtering and terrain correction.
[0170] The matrix acquisition subunit is used to acquire the deformation distance matrix of each sub-region based on the phase interference diagram after data preprocessing, wherein the deformation distance matrix represents the deformation distance of the slope deformation in the sub-region.
[0171] In some optional implementations, the acquisition module 405 includes:
[0172] The aerial image set acquisition unit is used to acquire an aerial image set of a target sub-area.
[0173] The three-dimensional model building unit is used to build a three-dimensional model based on a set of aerial images.
[0174] The similarity acquisition unit is used to acquire the similarity of the target sub-area within the monitoring period based on the three-dimensional model.
[0175] In some optional embodiments, the three-dimensional model building unit includes:
[0176] The feature point extraction subunit is used to extract feature points of continuous aerial images in the aerial image set.
[0177] The feature matrix acquisition subunit is used to match the feature points and generate a feature matrix.
[0178] The model building subunit is used to build a three-dimensional model based on the feature matrix, wherein the three-dimensional model corresponds to the aerial image.
[0179] In some optional implementations, the similarity acquisition unit includes:
[0180] The model acquisition subunit is used to acquire a first model and a second model of the target sub-region, wherein the first model and the second model are three-dimensional models with different phases.
[0181] The feature information extraction subunit is used to extract feature information of the first model and the second model, wherein the feature information includes structural information of the model.
[0182] The similarity determination subunit is used to register the first model and the second model based on the feature information, and determine the similarity of the target sub-region based on the registration result.
[0183] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.
[0184] The wind farm slope stability monitoring device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.
[0185] The embodiment of the present invention also provides a computer device having the above Figure 4 The wind farm slope stability monitoring device shown.
[0186] See also Figure 5 , Figure 5 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 5 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 5 A processor 10 is taken as an example.
[0187] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.
[0188] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.
[0189] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0190] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.
[0191] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 5 The example of connecting through bus is taken in the following.
[0192] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.
[0193] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.
[0194] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.
[0195] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.
Claims
1. A method for monitoring slope stability of a wind farm, characterized in that: The method comprises: Divide the area to be tested into boundaries to obtain a plurality of sub-areas, wherein the sub-areas include at least one wind turbine; Based on the boundary range of each of the sub-areas, a remote sensing image set corresponding to each of the sub-areas within the monitoring period is obtained, wherein the remote sensing image set includes at least two remote sensing images of the sub-areas at different times; For the remote sensing image sets corresponding to the sub-regions, respectively, determining the deformation rate matrix of each sub-region within the monitoring period, wherein the deformation rate matrix is a movement speed matrix of the slope deformation within the sub-region; Determine a target sub-region in each of the sub-regions based on a deformation rate matrix of each of the sub-regions within the monitoring period; Acquire at least two aerial images of the target sub-region at different times to determine the similarity of the target sub-region; Based on the similarity, slope stability data of the target sub-area is generated.
2. The method according to claim 1, characterized in that The step of dividing the boundary of the area to be tested and obtaining a plurality of sub-areas comprises: Acquiring the spatial position of the wind turbine in the area to be tested; Based on the spatial position, construct a plurality of Thiessen polygons, wherein the Thiessen polygons include only one wind turbine; The sub-regions are divided by using the Thiessen polygons as sub-region boundaries.
3. The method according to claim 1, characterized in that The acquiring of remote sensing image sets corresponding to each sub-region within the monitoring period based on the boundary range of each sub-region includes: Determine the sampling time of remote sensing images within the monitoring period; According to the sampling time, remote sensing images corresponding to the sub-regions are acquired to construct a remote sensing image set, wherein the remote sensing image set corresponds to the sub-regions.
4. The method according to claim 1, characterized in that: The step of determining the deformation rate matrix of each sub-region within the monitoring period for each remote sensing image set corresponding to each sub-region comprises: Based on the remote sensing image set, deformation information of each of the sub-regions within a monitoring period is obtained to construct a deformation distance matrix corresponding to each of the sub-regions; Based on the deformation distance matrix and the monitoring period, a deformation rate matrix of each of the sub-areas is determined.
5. The method according to claim 4, characterized in that The acquiring deformation information of each of the sub-regions within the monitoring period to construct a deformation distance matrix corresponding to each of the sub-regions includes: For the remote sensing image sets corresponding to the sub-regions, respectively, a phase interference map of each sub-region is generated, wherein the phase difference of the phase interference map represents the deformation information of the sub-region during the monitoring period; Performing data preprocessing on the phase interferogram, wherein the data preprocessing includes at least one of atmospheric correction, noise filtering and terrain correction; Based on the phase interference diagram after the data preprocessing, a deformation distance matrix of each sub-region is obtained, wherein the deformation distance matrix represents the deformation distance of the slope deformation in the sub-region.
6. The method according to claim 4, characterized in that Before determining the deformation rate matrix of each sub-area based on the deformation distance matrix and the monitoring period, the method further includes: Obtaining the aspect data of each of the sub-areas; The sight direction and the slope direction of the remote sensing image are compared, and based on the comparison result, the deformation distance matrix is corrected.
7. The method according to claim 1, characterized in that Acquiring at least two aerial images of the target sub-region at different times to determine the similarity of the target sub-region includes: Acquire a set of aerial images of the target sub-area; constructing a three-dimensional model based on the aerial image set; Based on the three-dimensional model, the similarity of the target sub-areas within the monitoring period is obtained.
8. The method according to claim 7, characterized in that The constructing of a three-dimensional model based on the aerial image set comprises: Extracting feature points of continuous aerial images in the aerial image set; Matching the feature points and generating a feature matrix; Based on the feature matrix, a three-dimensional model is constructed, wherein the three-dimensional model corresponds to the aerial image.
9. The method according to claim 7, characterized in that: The obtaining, based on the three-dimensional model, the similarity of the target sub-area within the monitoring period comprises: Acquire a first model and a second model of the target sub-region, wherein the first model and the second model are three-dimensional models of different phases; Extracting feature information of the first model and the second model, wherein the feature information includes structural information of the model; Based on the feature information, the first model and the second model are registered, and based on the registration result, the similarity of the target sub-region is determined.
10. A wind farm slope stability monitoring device, characterized in that: The device comprises: A division module, used for dividing the boundary of the area to be tested to obtain a plurality of sub-areas, wherein the sub-areas include at least one wind turbine; A remote sensing image acquisition module, used to acquire a remote sensing image set corresponding to each sub-region within a monitoring period based on the boundary range of each sub-region, wherein the remote sensing image set includes at least two remote sensing images of the sub-region at different times; A deformation rate determination module, for determining a deformation rate matrix of each sub-region within the monitoring period for a remote sensing image set corresponding to each sub-region, wherein the deformation rate matrix is a movement speed matrix of the slope deformation within the sub-region; A target sub-region determining module, configured to determine a target sub-region in each sub-region based on a deformation rate matrix of each sub-region within the monitoring period; An acquisition module, used to acquire at least two aerial images of the target sub-region at different times to determine the similarity of the target sub-region; A generating module is used to generate slope stability data of a target sub-area based on the similarity.
Citation Information
Patent Citations
Method for demarcating large-deformation landslide displacement field based on high-resolution remote sensing image
CN104700399A
Geological disaster monitoring method and device, and computer equipment
CN112598881A
Real-time data processing method and system for dam and landslide GB-SAR monitoring
CN112669334A
Radar time sequence differential interference measurement method for monitoring current lifting speed of mountain
CN113096005A
Slope deformation area division method based on dynamic time warping and k-means clustering
CN113177575A
Cited By
Deformation monitoring system and method
CN119354025A
Slope deformation monitoring method based on image recognition
CN119600298A
