Substation twin model construction method based on VR virtual reality technology
By performing meshing and deep learning analysis on the dense point cloud of substation equipment, the problems of time-consuming and labor-intensive traditional modeling and failure to consider degradation are solved, thereby improving the modeling accuracy and visualization effect of the substation twin model.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- UHV CO OF STATE GRID HEILONGJIANG ELECTRIC POWER CO LTD
- Filing Date
- 2025-04-30
- Publication Date
- 2026-05-15
AI Technical Summary
Traditional substation modeling methods are time-consuming and labor-intensive, and fail to effectively consider the deterioration of equipment caused by long-term operation, resulting in discrepancies between the twin model and the actual situation, affecting modeling accuracy and visualization effects.
By meshing the dense point cloud of transformer equipment in a substation scenario, calculating the steepness coefficient, coplanarity, and local complexity of each triangular mesh, and combining deep learning algorithms to analyze the distortion evaluation value of the heat sink, the reconstruction weight of the triangular point cloud is determined, and three-dimensional reconstruction is performed to build a twin model.
It improves the accuracy of transformer equipment modeling, reduces the impact of distortion and degradation on the model, and enhances the visualization and realism of twin models.
Smart Images
Figure CN120495574B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of twin model construction technology, specifically to a method for constructing a substation twin model based on VR virtual reality technology. Background Technology
[0002] Switching operations are a crucial part of the daily operation and maintenance of substations, involving complex procedures and stringent requirements. Traditional training for substation switching operations primarily relies on 2D drawings and videos. On-site training is constrained by factors such as space, equipment, and safety, preventing trainees from fully engaging in practical exercises. Furthermore, 2D drawings and video tutorials lack realism and interactivity, hindering trainees' in-depth understanding of equipment structure and operational procedures. Virtual reality (VR) technology, by digitally recreating a 500kV substation in a virtual space, allows for standardized 500kV ultra-high voltage switching operations to be performed within a digital twin environment, providing a new solution for substation switching operation training.
[0003] Traditional substation modeling relies on LiDAR for 3D reconstruction. However, data acquisition for the massive 500kV substation space is time-consuming and labor-intensive. The reconstruction speed in the virtual environment is slow, and the degradation of equipment due to long-term operation in the substation scenario is not taken into account. This results in discrepancies between the constructed substation twin model and the initial condition of the substation, leading to low accuracy in modeling small equipment in the substation scenario, which in turn affects the effectiveness of the substation twin model construction. Summary of the Invention
[0004] To address the aforementioned technical issues, a method for constructing a substation twin model based on VR virtual reality technology is provided to resolve existing problems.
[0005] The solution to the technical problem in this application is to provide a method for constructing a substation twin model based on VR virtual reality technology, including the following steps:
[0006] Obtain the dense point cloud of transformer equipment in the substation scene, mesh all dense point clouds, obtain each triangular mesh, and record the vertices of each triangular mesh as the triangular point cloud;
[0007] Analyze the distribution and dispersion of triangular point clouds in each triangular mesh, and calculate the steepness coefficient of each triangular mesh based on the area of the triangular mesh; calculate the coplanarity characteristic value of each triangular mesh based on the angle between each triangular mesh and the other triangular meshes connected to it.
[0008] By analyzing the distribution of triangular point clouds on each triangular mesh within its neighborhood and the disorder of the triangular point clouds in each dimension of three-dimensional space, the local complexity of each triangular mesh is calculated. Combined with the steepness coefficient and coplanar characterization value, the degradation evaluation value of each triangular mesh is determined. Using the degradation evaluation value of the triangular meshes connected to each triangular point cloud, the degradation contribution of each triangular point cloud is determined.
[0009] The deep learning algorithm is used to extract all triangular point clouds corresponding to each heat sink in the transformer equipment and divide them into blocks. The convex hull algorithm is used to analyze the geometric distribution of triangular point clouds in each block on each heat sink and determine the distortion evaluation value of each block.
[0010] Based on the distribution location of each triangular point cloud on the transformer equipment, the reconstruction weight of each triangular point cloud is determined according to the degradation contribution and distortion evaluation value. The transformer equipment in the substation scene is reconstructed in three dimensions to build a substation twin model.
[0011] Preferably, the calculation of the steepness coefficient of each triangular mesh includes:
[0012] Calculate the degree of dispersion of the position coordinates of all triangular point clouds in each triangular grid along the X-axis, Y-axis, and Z-axis, respectively.
[0013] The sum of the dispersion of each triangular grid along the X, Y, and Z axes is denoted as the dispersion factor.
[0014] The steepness coefficient is the ratio between the dispersion coefficient and the area of each triangular grid.
[0015] Preferably, the calculation of the coplanar characterization value of each triangular mesh includes:
[0016] The remaining triangular meshes that share a common edge with each triangular mesh are denoted as adjacent meshes; the cosine value of the angle between the normal vector of each triangular mesh and each of its adjacent meshes is calculated, and the cosine value is negatively mapped;
[0017] The coplanar representation value is the sum of the results of the negative mapping of each triangular mesh to all its adjacent meshes.
[0018] Preferably, the calculation of the local complexity of each triangular mesh includes:
[0019] Cluster all triangular point clouds on all triangular meshes to obtain the local density of each triangular point cloud. The cutoff distance of the clustering algorithm is the mean of the side lengths of all triangular meshes.
[0020] Calculate the mean of the local density of all triangular point clouds on each triangular mesh, and use it as the local density of each triangular mesh;
[0021] Analyze the clutter of the position coordinates of different triangular point clouds in the neighborhood of all triangular point clouds in each triangular mesh on the X, Y and Z axes, and calculate the distribution clutter of each triangular mesh;
[0022] The local complexity is the product of the distribution disorder and the local density.
[0023] Preferably, the calculation of the distribution disorder of each triangular mesh includes:
[0024] Centered on each triangular point cloud, all triangular point clouds within a spherical neighborhood with the truncation distance as the radius are formed into a first point cloud set; the union of the first point cloud sets of all triangular point clouds on each triangular grid is denoted as the second point cloud set.
[0025] For each triangular mesh, calculate the variance of the position coordinates of all triangular point clouds within the second point cloud set on the X-axis, Y-axis, and Z-axis, respectively;
[0026] The distribution disorder is the sum of the variances on the X, Y, and Z axes.
[0027] Preferably, determining the degradation assessment value of each triangular mesh includes:
[0028] The ratio of the local complexity to the coplanar characterization value is denoted as the degradation coefficient.
[0029] The degradation assessment value is the product of the steepness coefficient and the degradation coefficient.
[0030] Preferably, the degradation contribution V of the k-th triangular point cloud k The calculation method is as follows: Among them, P q Let n be the degradation evaluation value of the q-th triangular mesh. q Let Q be the number of all triangular point clouds in the q-th triangular mesh. k This represents the number of all triangular meshes with the k-th triangular point cloud as the vertex.
[0031] Preferably, the step of extracting all triangular point clouds corresponding to each heat sink in the transformer equipment and dividing them into blocks includes:
[0032] All triangular point clouds on the transformer equipment are used as input to a 3D semantic segmentation deep learning algorithm to extract all triangular point clouds corresponding to each heat sink.
[0033] The triangular point cloud corresponding to each heat sink is divided into multiple blocks according to the Z-axis coordinate of its position coordinate.
[0034] Preferably, determining the distortion assessment value for each block includes:
[0035] Based on all the triangular point clouds within each block of each heat sink, the convex hull of each block is obtained through the convex hull algorithm, and the convex hull volume is calculated.
[0036] Calculate the average degradation contribution of all triangular point clouds corresponding to each heat sink; denote the heat sink with the smallest average value as the standard heat sink; take the average convex hull volume of all blocks on the standard heat sink as the standard volume;
[0037] The difference between the convex hull volume of each segment on each heat sink and the standard volume is recorded as the relative deviation;
[0038] The distortion assessment value is the ratio of the relative deviation to the standard volume.
[0039] Preferably, determining the reconstruction weights of each triangular point cloud includes:
[0040] For all triangular point clouds distributed on the heat sink, calculate the normalized result of the product of the degradation contribution of each triangular point cloud and the distortion evaluation value of its corresponding block; perform negative mapping on the normalized result to obtain the reconstruction weight of each triangular point cloud.
[0041] For the remaining triangular point clouds not distributed on the heat sink, the degradation contribution is normalized, and the normalization result is negatively mapped to obtain the reconstruction weight of each triangular point cloud.
[0042] This application has at least the following beneficial effects:
[0043] This application triangulates the dense point cloud on the transformer equipment, analyzes the distribution of the triangular point cloud on each triangular grid, and calculates the steepness coefficient of each triangular grid by analyzing the grid volume. Its beneficial effects include: considering the flatness of the transformer equipment in the corresponding regions of different triangular meshes to initially reflect the degree of degradation in that region; analyzing the angles between each triangular mesh and its connected triangular meshes, and calculating the coplanar characterization value of each triangular mesh, which further reflects the flatness of the corresponding adjacent regions by considering the coplanar characteristics between adjacent triangular meshes; calculating the local complexity of each triangular mesh, which assesses the structural complexity of the local space of the triangular mesh by observing the distribution of triangular point clouds in the neighborhood, thus indicating the degradation of the transformer equipment surface in the corresponding region; determining the degradation assessment value of each triangular mesh, which analyzes the local features of the triangular mesh at multiple scales to reflect the local structural complexity caused by transformer surface degradation, avoiding misjudging the transformer's sharp corners as degradation conditions, and improving the accuracy of identifying the degradation conditions of the transformer equipment surface; and further determining the degradation contribution of each triangular point cloud, which distributes the degree of degradation of the triangular mesh equally among each triangular point cloud to reflect the influence of each triangular point cloud on the degradation of the triangular mesh, so that different triangular point clouds can be assigned a degradation value based on their degradation conditions in subsequent analysis. Three-dimensional reconstruction is performed with different weights; the distortion evaluation value of each block is determined. The beneficial effect is that it considers the distortion phenomenon of triangular point clouds on the heat sink of transformer equipment, which causes the shape of the area to be stretched or compressed. By quantifying the distortion degree of different triangular point clouds on the heat sink, different weights can be assigned to different triangular point clouds for subsequent three-dimensional reconstruction based on their distortion, thereby weakening the impact of distortion on the three-dimensional reconstruction. The reconstruction weight of triangular point clouds at different locations is determined by judging whether each triangular point cloud is distributed on the heat sink of the transformer equipment. The beneficial effect is... By employing a stereo camera to photograph the vast 500kV substation, data acquisition is rapid. Secondly, the triangular point cloud on the heat sink is used to reduce distortion and degradation levels, minimizing their impact on 3D reconstruction. For triangular point clouds in other locations, the degradation levels are further reduced to minimize their influence on 3D reconstruction. This approach aims to eliminate transformer equipment degradation as much as possible, preventing distortions such as bending and stretching of the heat sink in the constructed twin model. This makes the transformer equipment twin model closer to its original condition, enhancing the precision of modeling small and medium-sized equipment in the substation scene and improving the visualization effect of the twin model. Attached Figure Description
[0044] The following section provides a more detailed explanation of the method for constructing a substation twin model based on VR virtual reality technology, in conjunction with the accompanying drawings.
[0045] Figure 1A flowchart illustrating the steps of a method for constructing a substation twin model based on VR virtual reality technology, as provided in this application embodiment;
[0046] Figure 2 A flowchart illustrating the steps of the method for obtaining the degradation evaluation value of each triangular mesh provided in the embodiments of this application;
[0047] Figure 3 A flowchart illustrating the steps of the method for obtaining reconstruction weights provided in this application embodiment. Detailed Implementation
[0048] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description of the substation twin model construction method based on VR virtual reality technology, in conjunction with the accompanying drawings and implementation examples, is provided. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.
[0049] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.
[0050] Please see Figure 1 The diagram illustrates a flowchart of a method for constructing a substation twin model based on VR virtual reality technology according to an embodiment of this application. The method includes the following steps:
[0051] Step 1: Obtain the dense point cloud of transformer equipment in the substation scene, mesh all dense point clouds, obtain each triangular mesh, and record the vertices of each triangular mesh as the triangular point cloud.
[0052] The core of building a substation twin model is to digitally map the physical entities and operating environment of the real substation to create a virtual model that is highly similar to the real substation. Substation equipment may undergo deformation or modification during long-term operation, resulting in differences between the actual equipment and the original state. By using reverse engineering to build a three-dimensional model of the original substation scene, standardized operation scenarios can be built and supported.
[0053] A multi-view depth camera was used to take multi-angle photos of all equipment in a 500kV substation. Sparse point clouds of the equipment in the 500kV substation were constructed using offline Structure from Motion (SfM) technology, and the trajectory and pose of the camera were obtained. Dense depth maps of the equipment in the substation were estimated from multiple perspectives using Multi-View Stereo (MVS) technology. By fusing the multi-view dense depth maps, dense point clouds of all equipment in the substation were constructed.
[0054] In this embodiment, a binocular depth camera is used to take multi-angle photos of all equipment in the 500kV substation. As for other implementation methods, the implementer can set them according to the actual situation. Secondly, SfM technology and MVS technology are well-known technologies and will not be described in detail here.
[0055] At this point, the dense point clouds of all equipment in the substation are obtained.
[0056] Step 2: Analyze the distribution and dispersion of triangular point clouds in each triangular mesh, and calculate the steepness coefficient of each triangular mesh based on the area of the triangular mesh; calculate the coplanarity characteristic value of each triangular mesh based on the angle between each triangular mesh and the other triangular meshes connected to it.
[0057] As an electrical device that changes the voltage of alternating current, the power transformer is a key piece of equipment in a substation. It has vertical heat sinks, the main function of which is to dissipate heat during operation to maintain the normal operating temperature of the equipment. However, after long-term use, the heat sinks on the transformer will inevitably deteriorate. For example, with long-term use, dust, dirt, oil and other impurities can easily accumulate on the heat sinks, and in some cases, the coating may even peel off and corrosion may occur.
[0058] Secondly, to ensure uniform heat distribution and efficient heat dissipation, transformer equipment requires a smooth and flat surface. The dense point cloud on the heat sink surface should exhibit high flatness. However, heat sinks with deterioration exhibit rough surfaces and highly complex dense point cloud structures. Therefore, analyzing the distribution of dense point clouds in transformer equipment and calculating the steepness coefficient are crucial.
[0059] Triangulate all dense point clouds on transformer equipment in the substation, obtain each triangular mesh, and denote the vertices of each triangular mesh as the triangular point cloud;
[0060] In this embodiment, the Delaunay triangulation algorithm is used for processing. The Delaunay triangulation algorithm is a well-known technology and will not be described in detail here.
[0061] Calculate the degree of dispersion of the position coordinates of all triangular point clouds in each triangular grid along the X-axis, Y-axis, and Z-axis, respectively.
[0062] In this embodiment, the degree of dispersion is measured by calculating the standard deviation of the position coordinates of all triangular point clouds in each triangular grid on the X-axis, Y-axis and Z-axis respectively. As other implementation methods, implementers can use other methods of the prior art, such as variance, etc. This embodiment does not impose any special restrictions on this.
[0063] The sum of the dispersion of each triangular mesh along the X, Y, and Z axes is used as the dispersion coefficient of each triangular mesh.
[0064] The ratio between the dispersion coefficient and the area of each triangular grid is used as the steepness coefficient of each triangular grid.
[0065] It should be noted that the more significant the deterioration of the transformer equipment, the more complex the structure of the dense point cloud in the deteriorated area, and the easier it is to form small-area triangular grids. That is, the smaller the area of the triangular grid and the greater the difference between each triangular point cloud in the same dimension, i.e., the greater the dispersion coefficient, the worse the flatness of the triangular grid and the greater the steepness coefficient, reflecting the more significant the deterioration of the transformer equipment.
[0066] Secondly, in the triangular mesh of transformer equipment, due to the high flatness of the transformer surface and the uniform and sparse distribution of the point cloud, large-area triangles are easily formed. Within the local neighborhood of these triangles, the areas between the triangular meshes are relatively large, the spatial distribution is highly flattened, the local spatial structure is relatively simple, and the coplanarity is strong. Conversely, in the deteriorated areas of the transformer surface, small-area dense triangles are easily formed. Within the local neighborhood of these triangles, the areas between the triangular meshes are relatively small, the spatial distribution is highly discrete, the local spatial structure is relatively complex, and the coplanarity is weak. Based on the above analysis, the coplanarity characteristic value is calculated by considering the included angles between the triangular meshes, specifically:
[0067] The remaining triangular grids that share a common edge with each of the triangular grids are denoted as adjacent grids;
[0068] Calculate the cosine of the angle between each triangular mesh and the normal vector of each adjacent mesh, and perform a negative mapping on the cosine value;
[0069] The sum of the results of calculating the negative mapping of each triangular mesh with all its neighboring meshes is used as the coplanar characterization value of each triangular mesh;
[0070] In this embodiment, the negative mapping process is as follows: the difference between the value 1 and the cosine value is calculated as the result of the negative mapping; therefore, the formula for calculating the coplanar representation value of each triangular mesh is:
[0071]
[0072] Where, λ r M represents the coplanarity of the r-th triangular mesh. r Let be the number of all adjacent grids corresponding to the r-th triangular grid. Let r be the normal vector of the r-th triangular mesh. Let be the normal vector of the i-th adjacent grid corresponding to the r-th triangular grid, and cos() is used to calculate the cosine value.
[0073] It should be noted that the closer the angle between the normal vectors of two triangular meshes is to 180°, the more coplanar they are. The smaller the cosine value, the greater the coplanarity characteristic, the stronger the coplanarity between the two triangular meshes, and the higher the flatness of the triangular mesh in the local neighborhood.
[0074] Thus, the steepness coefficient and coplanarity characterization value of each triangular mesh are obtained.
[0075] Step 3: Calculate the local complexity of each triangular mesh by considering the distribution of triangular point clouds in the neighborhood and the disorder of triangular point clouds in each dimension of three-dimensional space. Combine the steepness coefficient and coplanarity characteristic value to determine the degradation evaluation value of each triangular mesh. Use the degradation evaluation value of the triangular meshes connected to each triangular point cloud to determine the degradation contribution of each triangular point cloud.
[0076] Furthermore, the flowchart of the method for obtaining the degradation evaluation value of each triangular mesh provided in the embodiments of this application is as follows: Figure 2 As shown.
[0077] First, the coplanar eigenvalues of the triangular meshes at the corners of the transformer equipment are relatively weak, but the structural complexity is lower than that of the deteriorated parts. Therefore, cluster analysis is performed on the triangular point cloud to quantify the complexity of the deteriorated parts, specifically:
[0078] Using the mean of all side lengths on all triangular meshes as the cutoff distance of the clustering algorithm, cluster all triangular point clouds on all triangular meshes to obtain the local density of each triangular point cloud;
[0079] In this embodiment, the Density Peak Clustering (DPC) algorithm is used for clustering. The distance metric of the DPC clustering algorithm is the Euclidean distance between any two triangular point clouds. The DPC clustering algorithm is a well-known technique and will not be described in detail here.
[0080] Calculate the mean of the local density of all triangular point clouds on each triangular mesh, and use it as the local density of each triangular mesh;
[0081] It should be noted that the greater the local density, the more triangular point clouds there are in the local neighborhood of the triangular mesh, and the higher the density.
[0082] The first point cloud set is formed by all the triangular point clouds within a spherical neighborhood centered on each triangular point cloud and with the cutoff distance as the radius;
[0083] Find the union of the first point cloud sets of all triangular point clouds on each triangular grid, and denote it as the second point cloud set;
[0084] Calculate the variances of the position coordinates of all triangulation points within the second point set on the X, Y, and Z axes, respectively.
[0085] Calculate the sum of the variances of each triangular mesh along the X, Y, and Z axes, and use this sum as the distribution disorder of each triangular mesh;
[0086] The product of the distribution disorder and the local density is used as the local complexity of each triangular mesh.
[0087] It should be noted that the more triangular meshes there are in a local neighborhood, the greater the local density. At the same time, the more chaotic and irregular the triangular point cloud is in the local neighborhood of the triangular mesh, the greater the local complexity. This indicates that the local spatial structure of the triangular mesh in the local neighborhood is highly complex.
[0088] Secondly, based on the coplanar characterization value, the local complexity, and the steepness coefficient, the degradation evaluation value is determined, specifically as follows:
[0089] The ratio of the local complexity to the coplanar characterization value is used as the degradation coefficient of each triangular mesh.
[0090] The product of the steepness coefficient and the degradation coefficient is used as the degradation evaluation value for each triangular mesh.
[0091] It should be noted that when the coplanar characterization value is 0, the degradation coefficient is equal to the local complexity. Furthermore, the larger the local complexity, the more complex the distribution of the triangular point cloud within the local neighborhood. The smaller the coplanar characterization value, the lower the surface smoothness of the transformer corresponding to the triangular mesh, which is more likely to be due to dust and dirt accumulated on the transformer surface, resulting in more obvious layering of the triangular point cloud on the triangular mesh. The larger the degradation coefficient, the larger the obtained degradation assessment value, indicating that the degradation status of the local area corresponding to the triangular mesh is more significant. By analyzing the local features of the triangular mesh at multiple scales, the misjudgment of the corner parts as a degradation status can be avoided, thereby improving the accuracy of identifying the degradation status of the transformer equipment surface.
[0092] Furthermore, the different triangular meshes of the transformer equipment are interconnected. Therefore, each triangular point cloud connects to multiple triangular meshes. By analyzing the degradation assessment values of the triangular meshes connected to each triangular point cloud, the degradation contribution is calculated, specifically as follows:
[0093] The mesh set is formed by combining all the triangular meshes with each triangular point cloud as its vertex;
[0094] The formula for calculating the degradation contribution of each triangular point cloud is as follows:
[0095]
[0096] Among them, V k P is the contribution of the k-th triangular point cloud to the degradation. q Let n be the degradation evaluation value of the q-th triangular mesh. q Let Q be the number of all triangular point clouds in the q-th triangular mesh. k This represents the number of all triangular meshes within the mesh set corresponding to the k-th triangular point cloud.
[0097] It should be noted that n q The value of is 3. The purpose of dividing the degradation evaluation value by 3 is to distribute the degradation degree of the entire triangular mesh equally to each triangular point cloud, so as to measure the influence of each triangular point cloud on the degradation of the triangular mesh. Therefore, the greater the degradation contribution, the more severe the degradation of the transformer equipment at the kth triangular point cloud. Therefore, when performing three-dimensional reconstruction of the transformer equipment in the future, the triangular point cloud should be given a smaller weight for reconstruction to eliminate the degradation of the transformer equipment as much as possible and make the twin model of the transformer equipment closer to the original condition.
[0098] Thus, the degradation contribution of each triangular point cloud is obtained.
[0099] Step 4: Extract all triangular point clouds corresponding to each heat sink in the transformer equipment using deep learning algorithms and divide them into blocks. Utilize the convex hull algorithm to analyze the geometric distribution of triangular point clouds within each block on each heat sink and determine the distortion evaluation value of each block. Based on the degradation contribution and distortion evaluation value, determine the reconstruction weight of each triangular point cloud according to its distribution position on the transformer equipment. Perform three-dimensional reconstruction of the transformer equipment in the substation scenario to construct a substation twin model.
[0100] When taking multi-angle photographs of transformer equipment using a camera, the point cloud data corresponding to the heat sinks on the transformer equipment is prone to distortion due to complex issues such as reflections, weak textures, and lighting variations in the power industry environment. Distortion of the triangular point cloud corresponding to the heat sink causes its shape to deviate from the actual geometry of the heat sink, resulting in stretching or compression in some areas, making the originally vertical heat sink appear curved. For triangular point clouds with more severe distortion, they should be given less weight during reconstruction to avoid bending or stretching of the heat sink in the twin model. Therefore, identifying the triangular point cloud on the heat sink and calculating the distortion evaluation value by analyzing its deformation is crucial.
[0101] All triangular point clouds on the transformer equipment are used as input to the 3D semantic segmentation deep learning algorithm (Point-VoxelCNN, PVCNN) to extract all triangular point clouds corresponding to each heat sink.
[0102] It should be noted that the PVCNN algorithm is a well-known technology and will not be elaborated upon here.
[0103] Calculate the average degradation contribution of all triangular point clouds corresponding to each heat sink;
[0104] The heat sink with the lowest average value is designated as the standard heat sink.
[0105] Divide all the triangular point clouds corresponding to each heat sink into multiple blocks according to the corresponding Z-axis coordinate in its position coordinates;
[0106] In this embodiment, the height of each block is 1cm. In other implementation methods, the implementer can set the height according to the actual situation.
[0107] Based on all triangular point clouds within each block, the convex hull of each block is obtained through the convex hull algorithm, and the volume of the convex hull is calculated.
[0108] In this embodiment, the Quick Hull algorithm is used to obtain the convex hull of each block. The Quick Hull algorithm is a well-known technology and will not be described in detail here. As other implementation methods, implementers can use other methods of the prior art, such as the Graham Scan algorithm, etc. This embodiment does not impose any special restrictions on this.
[0109] The average of the convex hull volumes corresponding to all blocks on the standard heatsink is taken as the standard volume.
[0110] The difference between the convex hull volume of each segment on each heat sink and the standard volume is recorded as the relative deviation;
[0111] In this embodiment, the absolute value of the difference between the convex hull volume of each block on each heat sink and the standard volume is calculated and denoted as the relative deviation.
[0112] The ratio of the relative deviation to the standard volume is used as the distortion assessment value for each segment on each heat sink.
[0113] It should be noted that the greater the relative deviation, the more likely the triangular point cloud on the heat sink is to be distorted, causing the shape of the corresponding block position on the heat sink to be stretched or compressed. The larger the distortion evaluation value, the greater the weight of the severely distorted triangular point cloud should be reduced when performing 3D reconstruction in order to improve the visual effect of the twin model.
[0114] Furthermore, based on the degradation contribution and the distortion assessment value, the reconstruction weight is determined, specifically as follows:
[0115] For all triangular point clouds distributed on the heat sink, calculate the normalized result of the product of the degradation contribution of each triangular point cloud and the distortion evaluation value of its corresponding block; perform negative mapping on the normalized result to obtain the reconstruction weight of each triangular point cloud.
[0116] For the remaining triangular point clouds not distributed on the heat sink, the degradation contribution is normalized, and the normalization result is negatively mapped to obtain the reconstruction weight of each triangular point cloud.
[0117] In this embodiment, the sigmoid function is used for normalization. The sigmoid function is a well-known technology and will not be described in detail here. As other implementation methods, implementers can use other methods of the prior art, such as the tanh function, etc. This embodiment does not impose any special restrictions on this. Secondly, the negative mapping process is as follows: calculate the difference between the value 1 and the normalization result, and use it as the reconstruction weight of the triangular point cloud.
[0118] It should be noted that the higher the degree of degradation or the more severe the distortion of each triangular point cloud, the smaller the corresponding reconstruction weight. This is to minimize the degradation of the transformer equipment, making the twin model of the transformer equipment closer to its original condition, and avoiding distortions such as bending or stretching of the heat sink in the twin model, thereby improving the visualization effect of the twin model. The flowchart of the method for obtaining reconstruction weights provided in this embodiment is shown below. Figure 3 As shown.
[0119] Based on the reconstruction weights, the transformer equipment is reconstructed in three dimensions using all triangular point clouds to obtain a three-dimensional model;
[0120] In this embodiment, the Screened Poisson Surface Reconstruction algorithm is used for 3D reconstruction. The Screened Poisson Surface Reconstruction algorithm is a well-known technology and will not be described in detail here.
[0121] Texture mapping is performed on the 3D model, and the 3D model of the transformer equipment in the substation scene is loaded into the 3D rendering engine for model rendering to obtain a panoramic view of the substation. Content is created using visual editing tools, including placing virtual nameplates on the transformer equipment. A unified sensing network is built through IoT technology to collect the operating parameters of the transformer equipment in the substation. Logical models of the transformer equipment in each substation are obtained through the equipment instruction manual. Data mapping technology is used to synchronize the logical models and operating parameters to the corresponding 3D models to build a twin model of the substation.
[0122] It should be noted that texture mapping is a well-known technology and will not be elaborated on here; texture mapping is used to enhance the visual experience.
[0123] The substation twin model is uploaded to a cloud server and integrated with physics engines such as Havok and PhysX to simulate physical effects such as gravity and collisions, enhancing the realism of the virtual world. Using gesture recognition software on VR devices or through controller operation, interactive training control and accident simulation of the substation can be realized.
[0124] It should be understood that, although Figure 1 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.
[0125] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0126] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application. Therefore, any simple modifications, equivalent changes, and alterations made to the above embodiments based on the technical essence of this application, without departing from the content of the technical solution of this application, shall fall within the protection scope of the technical solution of this application.
Claims
1. A method for constructing a substation twin model based on VR virtual reality technology, characterized in that, The method includes the following steps: Obtain the dense point cloud of transformer equipment in the substation scene, mesh all dense point clouds, obtain each triangular mesh, and record the vertices of each triangular mesh as the triangular point cloud; Analyze the distribution and dispersion of triangular point clouds in each triangular mesh, and calculate the steepness coefficient of each triangular mesh based on the area of the triangular mesh; calculate the coplanarity characteristic value of each triangular mesh based on the angle between each triangular mesh and the other triangular meshes connected to it. By analyzing the distribution of triangular point clouds on each triangular mesh within its neighborhood and the disorder of the triangular point clouds in each dimension of three-dimensional space, the local complexity of each triangular mesh is calculated. Combined with the steepness coefficient and coplanar characterization value, the degradation evaluation value of each triangular mesh is determined. Using the degradation evaluation value of the triangular meshes connected to each triangular point cloud, the degradation contribution of each triangular point cloud is determined. The deep learning algorithm is used to extract all triangular point clouds corresponding to each heat sink in the transformer equipment and divide them into blocks. The convex hull algorithm is used to analyze the geometric distribution of triangular point clouds in each block on each heat sink and determine the distortion evaluation value of each block. Based on the distribution of each triangular point cloud on the transformer equipment, the reconstruction weight of each triangular point cloud is determined according to the degradation contribution and distortion evaluation value. The transformer equipment in the substation scene is reconstructed in three dimensions to build a substation twin model. Determining the distortion assessment value for each block includes: Based on all the triangular point clouds within each block of each heat sink, the convex hull of each block is obtained through the convex hull algorithm, and the convex hull volume is calculated. Calculate the average degradation contribution of all triangular point clouds corresponding to each heat sink; denote the heat sink with the smallest average value as the standard heat sink; take the average convex hull volume of all blocks on the standard heat sink as the standard volume; The difference between the convex hull volume of each segment on each heat sink and the standard volume is recorded as the relative deviation; The distortion assessment value is the ratio of the relative deviation to the standard volume; The determination of the reconstruction weights for each triangular point cloud includes: For all triangular point clouds distributed on the heat sink, calculate the normalized result of the product of the degradation contribution of each triangular point cloud and the distortion evaluation value of its corresponding block; perform negative mapping on the normalized result to obtain the reconstruction weight of each triangular point cloud. For the remaining triangular point clouds not distributed on the heat sink, the degradation contribution is normalized, and the normalization result is negatively mapped to obtain the reconstruction weight of each triangular point cloud.
2. The method for constructing a substation twin model based on VR virtual reality technology as described in claim 1, characterized in that, The calculation of the steepness coefficient of each triangular mesh includes: Calculate the degree of dispersion of the position coordinates of all triangular point clouds in each triangular grid along the X-axis, Y-axis, and Z-axis, respectively. The sum of the dispersion of each triangular grid along the X, Y, and Z axes is denoted as the dispersion factor. The steepness coefficient is the ratio between the dispersion coefficient and the area of each triangular grid.
3. The method for constructing a substation twin model based on VR virtual reality technology as described in claim 1, characterized in that, The calculation of the coplanar representation value of each triangular mesh includes: The remaining triangular meshes that share a common edge with each triangular mesh are denoted as adjacent meshes; the cosine value of the angle between the normal vector of each triangular mesh and each of its adjacent meshes is calculated, and the cosine value is negatively mapped; The coplanar representation value is the sum of the results of the negative mapping of each triangular mesh to all its adjacent meshes.
4. The method for constructing a substation twin model based on VR virtual reality technology as described in claim 1, characterized in that, The calculation of the local complexity of each triangular mesh includes: Cluster all triangular point clouds on all triangular meshes to obtain the local density of each triangular point cloud. The cutoff distance of the clustering algorithm is the mean of the side lengths of all triangular meshes. Calculate the mean of the local density of all triangular point clouds on each triangular mesh, and use it as the local density of each triangular mesh; Analyze the clutter of the position coordinates of different triangular point clouds in the neighborhood of all triangular point clouds in each triangular mesh on the X, Y and Z axes, and calculate the distribution clutter of each triangular mesh; The local complexity is the product of the distribution disorder and the local density.
5. The method for constructing a substation twin model based on VR virtual reality technology as described in claim 4, characterized in that, The calculation of the distribution disorder of each triangular mesh includes: Centered on each triangular point cloud, all triangular point clouds within a spherical neighborhood with the truncation distance as the radius are formed into a first point cloud set; the union of the first point cloud sets of all triangular point clouds on each triangular grid is denoted as the second point cloud set. For each triangular mesh, calculate the variance of the position coordinates of all triangular point clouds within the second point cloud set on the X-axis, Y-axis, and Z-axis, respectively; The distribution disorder is the sum of the variances on the X, Y, and Z axes.
6. The method for constructing a substation twin model based on VR virtual reality technology as described in claim 1, characterized in that, The determination of the degradation assessment value for each triangular mesh includes: The ratio of the local complexity to the coplanar characterization value is denoted as the degradation coefficient. The degradation assessment value is the product of the steepness coefficient and the degradation coefficient.
7. The method for constructing a substation twin model based on VR virtual reality technology as described in claim 1, characterized in that, No. Degradation contribution of each triangular point cloud The calculation method is as follows: ,in , for the first Degradation assessment value of a triangular mesh, For the first The number of all triangular point clouds in a triangular grid. For the first The number of all triangular meshes with a triangular point cloud as vertices.
8. The method for constructing a substation twin model based on VR virtual reality technology as described in claim 1, characterized in that, The extraction of all triangular point clouds corresponding to each heat sink in the transformer equipment and its segmentation into blocks includes: All triangular point clouds on the transformer equipment are used as input to a 3D semantic segmentation deep learning algorithm to extract all triangular point clouds corresponding to each heat sink. The triangular point cloud corresponding to each heat sink is divided into multiple blocks according to the Z-axis coordinate of its position coordinate.