A substation intelligent simulation model construction method and device

Abstract

The application provides a substation intelligent simulation model construction method and device, and belongs to the technical field of simulation modeling. The method comprises the following steps: modeling a to-be-modeled substation based on first point cloud data to obtain a first model, wherein the first model is composed of multiple facets; the first point cloud data is point cloud data of the to-be-modeled substation after preprocessing; for each facet in the first model, a simplification strategy of the facet is determined based on the characteristics of the facet and the characteristics of the facets adjacent to the facet; the corresponding facet in the first model is simplified based on the simplification strategy of each facet to obtain a second model; the first model is taken as a root node of a tree structure, and the second model is taken as a child node of the tree structure to obtain a simulation model of the to-be-modeled substation; and the first model and the second model are simulation models of the to-be-modeled substation with different resolutions. The application can reduce the rendering difficulty of a computer when a user observes a model by simplifying facets.

Description

Technical Field

[0001] This application belongs to the field of simulation modeling technology, and more specifically, relates to a method and device for constructing an intelligent simulation model of a substation. Background Technology

[0002] With the advancement of digital transformation in power systems, substation simulation models are increasingly being used in power planning, operation and maintenance, and personnel training. Traditional substation simulation model construction methods are usually based on automatic modeling with fixed rules, resulting in monotonous modeling outcomes. Therefore, when users observe the simulation model, the computer needs to process massive amounts of surface information and calculate the color, texture, lighting, and other attributes of each surface, which puts enormous computational pressure on the computer's graphics processing unit and central processing unit.

[0003] Therefore, a method for constructing intelligent simulation models of substations is needed. Summary of the Invention

[0004] The purpose of this application is to provide a method and device for constructing an intelligent simulation model of a substation, which reduces the rendering difficulty and processing time of the computer when the user observes the model by simplifying the surface patches.

[0005] A first aspect of this application provides a method for constructing an intelligent simulation model of a substation, comprising: modeling the substation to be modeled based on first point cloud data to obtain a first model, the first model being composed of multiple facets; the first point cloud data being the preprocessed point cloud data of the substation to be modeled.

[0006] For each patch in the first model, a simplification strategy for the patch is determined based on the features of the patch and the features of the patches adjacent to it.

[0007] The second model is obtained by simplifying the corresponding facets in the first model based on the simplification strategy for each facet.

[0008] The first model is used as the root node of the tree structure, and the second model is used as the child node of the tree structure to obtain the simulation model of the substation to be modeled. The first model and the second model are simulation models of the substation to be modeled at different resolutions, and the resolution of the first model is greater than or equal to the resolution of the second model.

[0009] A second aspect of this application provides a substation intelligent simulation model construction device, comprising:

[0010] The modeling module is used to model the substation to be modeled based on the first point cloud data to obtain the first model, which consists of multiple facets; the first point cloud data is the preprocessed point cloud data of the substation to be modeled.

[0011] The decision module is used to determine a simplification strategy for each facet in the first model based on the features of the facet and the features of the faces adjacent to the facet.

[0012] The simplification module is used to simplify the corresponding facets in the first model based on the simplification strategy for each facet to obtain the second model;

[0013] The model linking module is used to use the first model as the root node of the tree structure and the second model as the child node of the tree structure to obtain the simulation model of the substation to be modeled; the first model and the second model are simulation models of the substation to be modeled at different resolutions, and the resolution of the first model is greater than or equal to the resolution of the second model.

[0014] A third aspect of this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of the above-described method for constructing an intelligent simulation model of a substation.

[0015] In a fourth aspect of this application, a computer-readable storage medium is provided, which stores a computer program that, when executed by a processor, implements the steps of the above-described method for constructing an intelligent simulation model of a substation.

[0016] The beneficial effects of the intelligent simulation model construction method and device for substations provided in this application are as follows:

[0017] This application first constructs a first model composed of multiple facets based on first point cloud data. Then, it determines a simplification strategy for each facet based on its own and adjacent facet features, reducing the number of facets in the model. This reduces the number of facet attributes that the computer needs to calculate when processing the simulation model, thereby reducing rendering difficulty, alleviating the computational pressure on the computer's graphics processing unit and central processing unit, and improving the system's operating efficiency and response speed. This application uses the first model as the root node of a tree structure and the second model as the child nodes of the tree structure to construct a multi-resolution simulation model of the substation to be modeled, avoiding the resource waste caused by using a high-resolution model in all cases. When a high-precision model is not needed, using a low-resolution model can effectively reduce the computer's computational load, reduce energy consumption, and improve the system's resource utilization efficiency. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A flowchart illustrating a method for constructing an intelligent simulation model of a substation, provided as an embodiment of this application;

[0020] Figure 2 A structural block diagram of a substation intelligent simulation model construction device provided in one embodiment of this application;

[0021] Figure 3 This is a schematic block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0022] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0023] To make the objectives, technical solutions, and advantages of this application clearer, the following description will be provided in conjunction with the accompanying drawings and specific embodiments.

[0024] Please refer to Figure 1 , Figure 1 A flowchart illustrating a method for constructing an intelligent simulation model of a substation, as provided in an embodiment of this application, includes:

[0025] S101: Model the substation to be modeled based on the first point cloud data to obtain the first model, which consists of multiple facets; the first point cloud data is the preprocessed point cloud data of the substation to be modeled.

[0026] In this embodiment, the first point cloud data refers to the set of points that, after preprocessing, reflect the spatial information of the equipment and structure of the substation to be modeled. This data may include the three-dimensional coordinates and reflection intensity of the substation equipment, and serves as the foundational data for constructing the substation model. Preprocessing operations may include denoising, filtering, or registration. The point cloud data prior to preprocessing can be obtained by scanning the substation using instruments such as laser scanners or radar.

[0027] In this embodiment, the substation to be modeled is the substation for which a simulation model needs to be built. It is a collection of actual substation equipment or buildings, and is the object of modeling. 3D modeling software (such as 3ds Max, Maya, etc.) can be used to import the first point cloud data. Based on the spatial relationships of the point cloud, the points are connected into lines and surfaces, ultimately constructing a 3D model of the substation.

[0028] In this embodiment, the first model is a 3D model of a substation constructed based on the first point cloud data, which consists of multiple facets. These facets are the basic elements constituting the surface of the model. Through the combination of facets and operations such as texture mapping, the model has a realistic appearance.

[0029] For example, after modeling, the resulting substation model consists of buildings and equipment composed of multiple facets. For instance, the walls of a substation are composed of multiple quadrilateral facets, and the outer shell of equipment is composed of multiple triangular facets. These facets are combined to form a complete first model. For example, a transformer model consists of multiple facets forming its outer shell and internal structure.

[0030] S102: For each facet in the first model, determine a simplification strategy for that facet based on its features and the features of the faces adjacent to it.

[0031] In this embodiment, a facet is the basic unit that constitutes the surface of a 3D model. It consists of multiple vertices and edges, and multiple faces are pieced together to form a complete 3D object surface. For example, in a substation simulation model, the outer shell of a transformer, the surface of a switchgear, etc., are all constructed by combining individual faces.

[0032] In this embodiment, the features of a patch refer to relevant information that describes the patch's own attributes and characteristics, including but not limited to its geometric features, semantic features, importance, and texture features. Geometric features include, for example, area, shape, curvature, and number of vertices; semantic features include, for example, the category of equipment component it belongs to, such as transformer windings or busbar joints; importance includes, for example, a numerical value or level assessed based on its importance in substation function, modeling process, or visual display; and texture features include, for example, the complexity and color of the surface texture. The features of a patch can be obtained based on a neural network model, etc. It should be noted that this neural network model should be a pre-trained model.

[0033] In this embodiment, adjacent faces refer to other faces in the 3D model structure that are directly connected to the current face and share edges or vertices. For example, when constructing a substation building model, the faces of the walls, floors, or ceilings connected to a wall face are adjacent faces. The above description is for ease of understanding only. In actual modeling, a wall usually contains more than one face, but is composed of multiple faces. A face and its adjacent faces do not necessarily belong to different structures in reality.

[0034] In this embodiment, the simplification strategy is a processing method designed to reduce the amount of model data and computational complexity, while preserving the key features and functions of the model as much as possible, based on different features of the face. Common simplification strategies include face deletion, face merging, vertex merging, and texture simplification. Therefore, the simplification strategy for a face can be determined based on its features and the features of its adjacent faces. For example, if the features of a face and the importance of its adjacent faces are both relatively low, they can be merged into a larger face.

[0035] S103: Based on the simplification strategy for each facet, the corresponding facets in the first model are simplified to obtain the second model.

[0036] In this embodiment, the simplification method for each facet is determined by comprehensively considering the characteristics of the facet itself and the characteristics of adjacent faces. Different facests can have different simplification strategies; for example, some facests may be deleted, some may be merged, and some may only have their details simplified.

[0037] For example, in a substation simulation model, some decorative panels are simplified by directly deleting them because they are of low importance and do not affect the overall function and appearance. For larger panels connected to critical equipment, the strategy is to merge adjacent similar panels to reduce the number of panels, while retaining their basic shape and position information.

[0038] In this embodiment, the corresponding patch in the first model refers to the patch in the first model that corresponds to those patches for which a simplification strategy has been determined. That is, based on the formulation of the simplification strategy, the patch that needs to be operated on is found in the first model. For example, the transformer model in the first model is composed of many patches. When a simplification strategy is determined for a certain patch (such as a small patch on the transformer casing), this patch is found in the first model, i.e., "the corresponding patch in the first model".

[0039] In this embodiment, simplification refers to performing specific operations on the corresponding faces in the first model according to a determined simplification strategy, such as deleting faces, merging adjacent faces, reducing the number of vertices on faces, or simplifying textures, to reduce the complexity and data volume of the model. The second model is a new 3D model of a substation generated after processing each face in the first model according to the simplification strategy.

[0040] S104: Using the first model as the root node of the tree structure and the second model as the child node of the tree structure, a simulation model of the substation to be modeled is obtained; the first model and the second model are simulation models of the substation to be modeled at different resolutions, and the resolution of the first model is greater than or equal to the resolution of the second model.

[0041] In this embodiment, a tree structure is a data structure composed of nodes and edges. Nodes represent data elements, and edges represent the relationships between nodes. In the construction of substation simulation models, tree structures are used to organize models of different resolutions for convenient management and retrieval. A tree structure is similar to a directory structure in a file system, where a root directory contains multiple subdirectories, and each subdirectory can contain further subdirectories and files. In the tree structure of the substation simulation model, nodes represent models of different resolutions, and edges represent the hierarchical relationships between models.

[0042] The root node is the top-level node in a tree structure, serving as the starting point of the entire tree structure, and has no parent node. In the tree structure of the substation simulation model, the first model acts as the root node, forming the foundation of the entire simulation model and containing the most detailed substation information.

[0043] Child nodes are nodes in a tree structure other than the root node; these nodes are called child nodes. The second model, as a child node, is a simplified version of the first model and has a hierarchical relationship with it. For example, in the tree structure of a substation simulation model, the second model, as a child node, is like a subdirectory under the root directory in a file system, belonging to the root node (the first model) and having a different resolution and data volume.

[0044] In this embodiment, the simulation model of the substation to be modeled is a tree structure obtained by constructing the first model as the root node and the second model as the child nodes.

[0045] In this embodiment, models with different resolutions can be selected for rendering and simulation according to different needs (such as observation distance, computing resources, etc.), which can optimize computing performance and improve simulation efficiency while ensuring model accuracy.

[0046] For example, when a user observes the substation simulation model from a distance, the second model can be invoked because it has a smaller data volume and faster rendering speed; when the user observes it up close, the first model can be invoked to obtain more detailed information. In this way, the simulation model of the substation to be modeled can better meet the usage needs in different scenarios. It should be noted that the "user" referred to in this application is a virtual user, not a natural person. It should be understood that during and after the modeling process, the user can switch and move between different scenes in the constructed substation simulation model. In this embodiment, the switching condition between the first and second models is the user's observation distance.

[0047] In 3D models, resolution indicates the level of detail. High-resolution models contain more faces, vertices, and texture information, enabling them to more accurately represent the shape and features of objects; low-resolution models are relatively simplified, with fewer faces and lower levels of detail. Since the second model is obtained by simplifying the faces in the first model, its resolution is less than or equal to that of the first model.

[0048] As can be seen from the above, this application first constructs a first model composed of multiple facets based on the first point cloud data, and then determines a simplification strategy for each facet based on its own and adjacent facet features, reducing the number of facets in the model. This reduces the number of facet attributes that the computer needs to calculate when processing the simulation model, thereby reducing the rendering difficulty, alleviating the computational pressure on the computer's graphics processing unit and central processing unit, and improving the system's operating efficiency and response speed. This application uses the first model as the root node of a tree structure and the second model as the child nodes of the tree structure to construct a multi-resolution simulation model of the substation to be modeled, avoiding the waste of resources caused by using a high-resolution model in all cases. When a high-precision model is not required, using a low-resolution model can effectively reduce the computational load on the computer, reduce energy consumption, and improve the system's resource utilization efficiency.

[0049] In one embodiment of this application, the process of preprocessing the point cloud data of the substation to be modeled to obtain the first point cloud data includes:

[0050] Multiple second point cloud data are acquired, and for each second point cloud data, the target convolutional neural network is used to identify the second point cloud data, determine the substation equipment corresponding to the second point cloud data, and the importance of each point in the second point cloud data;

[0051] Among them, the second point cloud data is the point cloud data of the substation equipment in the substation to be modeled;

[0052] The first point cloud data is determined based on the importance of each point in each second point cloud data.

[0053] In this embodiment, the second point cloud data refers to the point cloud data about various substation equipment collected from the substation to be modeled. Since a substation contains various types of equipment, each with its corresponding point cloud data, multiple second point cloud data sets will be obtained. These data sets record information such as the three-dimensional shape and location of the equipment. For example, for equipment such as transformers and switchgear in a substation, their respective point cloud data are obtained using technologies such as laser scanning; these data constitute multiple second point cloud data sets. One second point cloud data set can correspond to one device or multiple devices; this application does not impose any limitation.

[0054] In this embodiment, the target convolutional neural network is a deep learning model capable of feature extraction and analysis of the input second point cloud data. Through a trained convolutional neural network, the type of substation equipment corresponding to the second point cloud data can be identified, and the importance of each point in the second point cloud data can be determined. By learning from a large amount of labeled point cloud data, the convolutional neural network masters the characteristic patterns of different equipment, thereby achieving accurate identification and importance assessment.

[0055] In this embodiment, the target convolutional neural network is trained based on a first dataset, which includes point cloud data of multiple substation devices and feature annotation information corresponding to the point cloud data of each substation device; the feature annotation information includes the type of substation device and the importance of each point in the point cloud data.

[0056] For example, the second point cloud data of a transformer is input into a trained target convolutional neural network. The network analyzes the geometric and texture features in the data to determine that the device corresponding to the point cloud data is a transformer. Simultaneously, the importance of each point is determined based on factors such as its location within the device and its impact on the device's shape. For instance, points on the transformer windings are considered more important than points on the outer casing.

[0057] In this embodiment, the importance of each point in each second point cloud data is considered, important points are selected, and unimportant points are removed, thereby determining the first point cloud data. The first point cloud data is processed to retain key information about the substation equipment, which is more conducive to subsequent modeling operations.

[0058] For example, among the acquired second point cloud data, points of higher importance are retained and points of lower importance are removed based on their importance. The retained points are then combined to form the first point cloud data. For instance, in the point cloud data of substation equipment, points of important parts such as transformer windings and key operating components of switchgear are retained, while points of some less important parts are removed, resulting in more refined first point cloud data.

[0059] Specifically, determining the first point cloud data based on the importance of each point in each second point cloud data can include:

[0060] For each second point cloud data: determine the starting point of the second point cloud data, traverse all points in the second point cloud data from the starting point, and determine whether to retain the point based on the comparison result of the importance of each point in the second point cloud data with the first importance threshold; until the importance of each point in the second point cloud data is greater than the first importance threshold.

[0061] Merge the data from each second point cloud to obtain the first point cloud data.

[0062] In this embodiment, when processing each piece of second point cloud data, a starting point can be randomly specified. The starting point is the starting point for processing and analyzing the second point cloud data. Based on the determined starting point, each point in the second point cloud data is visited sequentially in a certain order (such as spreading outward from the starting point, following a preset path, etc.). Through traversal operations, each point can be analyzed and processed so that it can be decided whether to retain the point based on its importance.

[0063] In this embodiment, the first importance threshold can be determined based on experience. If the importance of a point is greater than the threshold, the point is retained because it is of great significance to representing the shape, structure, or function of the substation equipment. If the importance of a point is less than the threshold, the point is deleted because it is relatively minor in the overall data.

[0064] For example, in this scenario, if a point is located at a critical position on the transformer winding and its importance is higher than a threshold, then the point is retained; while for points corresponding to some tiny protrusions on the transformer casing, whose importance is lower than a threshold, they are deleted from the data.

[0065] In this embodiment, the importance of points is continuously compared with a threshold, and points are retained or deleted, until the importance of all points in the second point cloud data meets the condition of being greater than the first importance threshold. This process ensures that the retained data points are of high importance, removes relatively unimportant points, and thus optimizes the quality and accuracy of the point cloud data. The retained point cloud data from the multiple second point cloud data sets processed above are then merged. The merged first point cloud data integrates the key information of each device and removes unimportant points, making it more suitable for subsequent operations such as substation modeling.

[0066] In this embodiment, the application employs a point importance-based filtering process, ensuring that the final first point cloud data retains key information about the substation equipment while removing redundant and secondary information. Subsequent modeling based on this first point cloud data allows for a more accurate reconstruction of the substation equipment's true shape and structure, improving the modeling accuracy of the substation simulation model and making it more closely reflect the actual substation equipment conditions.

[0067] In one embodiment of this application, the features of the sheet include: the importance of the sheet;

[0068] The simplification strategy for the facet is determined based on its features and the features of the faces adjacent to it, including:

[0069] The simplification strategy for a surface is determined based on the importance of the surface and the importance of the surfaces adjacent to it; where the importance of a surface is the average of the importance of each point in its corresponding point cloud data.

[0070] In this embodiment, the importance of a surface patch is a key feature. It is determined by calculating the average importance of each point in the point cloud data corresponding to that surface patch. Each point in the point cloud data may have different levels of importance due to factors such as its location within the equipment and its impact on the equipment's function. The average of these point importance values ​​represents the overall importance of the surface patch. For example, in a substation simulation model, the point cloud data for a surface patch on a transformer casing contains multiple points. Some of these points may be located in critical connection areas, while others may be located in ordinary surface areas, and their importance varies. By statistically analyzing and averaging the importance of these points, the importance value of the surface patch is obtained, reflecting its relative importance within the entire model.

[0071] In this embodiment, a simplification strategy can be determined based on the importance of a face and the importance of its adjacent faces. For example, for a face of a switchgear in a substation, if the face itself has low importance and its adjacent faces also have low importance, then the face may be merged with its adjacent faces, or the face may be deleted directly to reduce the complexity of the model. Conversely, if a face located at a critical electrical connection has high importance and its adjacent faces also have high importance, then only slight simplification of the face's details may be performed, such as reducing some unnecessary vertices while retaining its basic shape and connection relationships.

[0072] As can be seen from the above, this application determines the importance of a surface by calculating the average importance of each point in the point cloud data corresponding to the surface, which can more accurately assess the relative importance of each surface in the substation simulation model.

[0073] In one embodiment of this application, the features of the sheet include: the area of ​​the sheet and the importance of the sheet;

[0074] The simplification strategy for the facet is determined based on its features and the features of the faces adjacent to it, including:

[0075] In response to the fact that the area of ​​the given patch and the areas of its adjacent patches are both smaller than a first area, and the importance of the given patch and the importance of its adjacent patches are both smaller than a second importance threshold, a simplification strategy is adopted to merge patches into the given patch. The first importance threshold is smaller than the second importance threshold.

[0076] In this embodiment, patch merging combines two or more adjacent patches into one patch. For example, in a 3D model composed of multiple triangular patches, merging two adjacent triangular patches into a quadrilateral patch aims to reduce the number of patches in the model, simplify the model's topology, thereby reducing the model's complexity and improving rendering efficiency.

[0077] In this embodiment, in addition to the aforementioned importance level, the patch feature also includes the area of ​​the patch. The area of ​​a patch refers to the size of the space occupied by the patch in three-dimensional space. When the area of ​​the patch and the area of ​​its adjacent patches are both less than the first area, and the importance level of the patch and the importance level of its adjacent patches are both less than the second importance level threshold, it indicates that the patch and its adjacent patches are relatively unimportant in the model, and they can be merged into patches.

[0078] As can be seen from the above, when the area of ​​a face and its adjacent faces are all smaller than the first area and their importance is all less than the second importance threshold, merging these faces can effectively reduce the number of faces in the model, thereby significantly reducing the complexity of the model. This embodiment reduces the number of faces in the model by merging unimportant faces, thereby greatly improving the rendering efficiency of the model.

[0079] In one embodiment of this application, the features of a patch include: the position of the vertices in the patch and the importance of the patch;

[0080] If the sum of the number of vertices of each facet in the first model is greater than a preset number, then a simplification strategy for the facet is determined based on the features of the facet and the features of the facest adjacent to it, including:

[0081] In response to the fact that the importance of the face and the importance of the face adjacent to the face are both less than the third importance threshold, and the straight-line distance between the positions of the two target vertices is less than the merging threshold, merging vertices is determined as the simplification strategy for the face; wherein, the target vertex is a vertex in the face or a vertex in the face adjacent to the face.

[0082] In this embodiment, vertices are the basic elements constituting a facet. The position of the vertex determines the shape and orientation of the facet in three-dimensional space. In this embodiment, the position of the vertex can be represented in coordinate form. Vertex merging refers to combining vertices that are close to each other in the model into one vertex. For example, in a complex mesh model, merging two vertices with very close coordinate positions into one vertex aims to reduce the number of vertices in the model, thereby reducing the amount of data and rendering computation; and also to eliminate some unnecessary details in the model, making the model smoother. The third importance threshold can be equal to the second importance threshold.

[0083] In this embodiment, when the sum of the number of vertices of each facet in the first model exceeds a preset number, it indicates that the number of faces in the model is too large, and the model needs to be simplified to reduce its complexity and data volume, thereby improving its processing efficiency. The preset number is an empirically based value. It should be noted that the preset number should be based on factors such as the scale of the substation to be modeled and the amount of point cloud data.

[0084] The merging threshold is a parameter used to measure the distance between vertices. Target vertices include vertices in the current face and vertices in adjacent faces. When the straight-line distance between two target vertices is less than this merging threshold, it means that these vertices are spatially close. In this case, merging these vertices can simplify the face structure, reduce the number of vertices, and thus reduce the complexity of the model. For example, on some relatively smooth faces, adjacent and closely spaced vertices can be merged into one vertex, making the face representation more concise.

[0085] Based on the above criteria, when a face and its adjacent faces have low importance and their vertices are close together, vertex merging is used to simplify the face. After vertex merging, the shape and structure of the face will change to some extent, but while maintaining the overall characteristics of the model, it can effectively reduce the amount of data in the model and improve the model's running efficiency. For example, in the wall face of a substation model, after merging some close and unimportant vertices, the basic shape of the wall is still preserved, but the number of vertices is reduced, and the model becomes simpler.

[0086] As can be seen from the above, this application simplifies faces by vertex merging. Vertices are merged when the importance of a face and its adjacent faces is less than the third importance threshold, and the straight-line distance between two target vertices (vertices within the face itself or adjacent faces) is less than the merging threshold. Vertex merging reduces the number of vertices in the model. In subsequent model processing, such as geometric transformations, collision detection, and lighting calculations, the amount of data that needs to be processed is significantly reduced, enabling the computer to complete these tasks faster and improving the model's processing efficiency. This application comprehensively considers both the importance of faces and the distance between vertices when merging vertices. Vertex merging is only considered when the importance of a face and its adjacent faces is less than the third importance threshold. This means that faces containing critical devices and structures will not be easily merged, thus ensuring the integrity of key features in the model.

[0087] In one embodiment of this application, the process of determining the third importance level and the merging threshold includes:

[0088] The third importance threshold and merging threshold are determined based on the difference between the number of vertices of each facet in the first model and the preset number.

[0089] In the first model, the difference between the number of vertices of each facet and the preset number is positively correlated with both the third importance threshold and the merging threshold.

[0090] In this embodiment, the larger the difference, the greater the degree of simplification required by the model, meaning more unimportant faces need to be identified and simplified. To achieve this, the third importance threshold needs to be increased so that more faces can meet the condition of "importance less than the third importance threshold" and thus be included in the simplification range.

[0091] Similarly, the larger the difference, the more urgent the need to reduce the number of vertices by merging them. Increasing the merging threshold at this point will allow more closely spaced vertices to meet the condition of "straight-line distance less than the merging threshold," thus enabling them to be merged.

[0092] For example, the initial merging threshold may be set to 0.5 cm. When the difference between the number of vertices and the preset number increases, the merging threshold can be increased to 1 cm. At this time, more vertices that were originally slightly far apart but are still within the new threshold range will be merged, achieving a more effective reduction in the number of vertices and simplifying the model.

[0093] In this embodiment, the positive correlation between the third importance threshold and the difference between the number of vertices of each facet in the first model and the preset number can be linear, for example, it can be based on a preset slope or correspondence.

[0094] The merging threshold can be determined based on the first formula, which can be:

[0095] , It is the merging threshold. To merge the base values, Let be the number of vertices in each facet of the first model. For the preset quantity, This is an adjustment coefficient used to adjust the effect of importance distribution factors on the threshold. The total number of dough pieces For the first The importance of each piece of dough.

[0096] In this embodiment, the larger the difference in the number of vertices, the larger the merging threshold. This allows more distant vertices to meet the merging condition, thus more effectively reducing the number of vertices and achieving model simplification. Conversely, a larger sum of the importance of all faces will decrease the merging threshold, preventing excessive merging. It should be noted that the third importance and the merging threshold should have a preset upper limit, also to prevent excessive merging.

[0097] As can be seen from the above, this application determines the third importance threshold and merging threshold based on the difference between the number of vertices in each facet of the first model and a preset number, enabling precise adjustment of the simplification strategy according to the actual complexity of the model. A larger difference indicates that the current number of vertices in the model far exceeds the preset number, and the simplification requirement is higher. In this case, increasing the third importance threshold and merging threshold allows more unimportant faces and closely spaced vertices to be included in the simplification scope, effectively meeting the model's simplification needs. The method of determining the threshold based on the positive correlation of the difference allows the third importance threshold and merging threshold to be flexibly adjusted according to different models and requirements.

[0098] A method for constructing a substation intelligent simulation model, corresponding to the above embodiment, Figure 2 This is a structural block diagram of a substation intelligent simulation model building device according to an embodiment of this application. For ease of explanation, only the parts relevant to the embodiment of this application are shown. References Figure 2 The substation intelligent simulation model construction device 20 includes: a modeling module 21, a decision module 22, a simplification module 23, and a model linking module 24.

[0099] Among them, the modeling module 21 is used to model the substation to be modeled based on the first point cloud data to obtain the first model, which is composed of multiple facets; the first point cloud data is the point cloud data of the substation to be modeled after preprocessing.

[0100] Decision module 22 is used to determine a simplification strategy for each facet in the first model based on the features of the facet and the features of the faces adjacent to the facet.

[0101] The simplification module 23 is used to simplify the corresponding facets in the first model based on the simplification strategy of each facet to obtain the second model;

[0102] The model linking module 24 is used to use the first model as the root node of the tree structure and the second model as the child node of the tree structure to obtain the simulation model of the substation to be modeled; the first model and the second model are simulation models of the substation to be modeled at different resolutions, and the resolution of the first model is greater than or equal to the resolution of the second model.

[0103] In one embodiment of this application, a substation intelligent simulation model construction device 20 further includes:

[0104] The first point cloud data determination module is used to acquire multiple second point cloud data, and for each second point cloud data, it identifies the second point cloud data based on the target convolutional neural network to determine the substation equipment corresponding to the second point cloud data and the importance of each point in the second point cloud data;

[0105] Among them, the second point cloud data is the point cloud data of the substation equipment in the substation to be modeled;

[0106] The first point cloud data is determined based on the importance of each point in each second point cloud data.

[0107] In one embodiment of this application, the first point cloud data determination module is specifically used for each second point cloud data: determining the starting point of the second point cloud data, traversing all points in the second point cloud data from the starting point, and determining whether to retain the point based on the comparison result of the importance of each point in the second point cloud data with a first importance threshold; until the importance of each point in the second point cloud data is greater than the first importance threshold.

[0108] Merge the data from each second point cloud to obtain the first point cloud data.

[0109] In one embodiment of this application, the features of the sheet include: the importance of the sheet;

[0110] The decision module 22 is specifically used to determine the simplification strategy for the surface based on the importance of the surface and the importance of the surfaces adjacent to it; wherein, the importance of the surface is the average of the importance of each point in its corresponding point cloud data.

[0111] In one embodiment of this application, the features of the sheet include: the area of ​​the sheet and the importance of the sheet;

[0112] The decision module 22 is further configured to respond to the fact that the area of ​​the patch and the area of ​​its adjacent patches are both less than a first area, and the importance of the patch and the importance of its adjacent patches are both less than a second importance threshold, and to merge the patches into a simplified patch.

[0113] In one embodiment of this application, the features of a patch include: the position of the vertices in the patch and the importance of the patch;

[0114] If the sum of the number of vertices of each facet in the first model is greater than a preset number, the decision module 22 is further used to determine the vertices as the simplification strategy for the facet in response to the importance of the facet, the importance of the facets adjacent to the facet being less than the third importance threshold, and the straight-line distance between the positions of two target vertices being less than the merging threshold; wherein, the target vertex is a vertex in the facet or a vertex in a facet adjacent to the facet.

[0115] In one embodiment of this application, a substation intelligent simulation model construction device 20 further includes:

[0116] The threshold determination module is used to determine the third importance threshold and the merging threshold based on the difference between the number of vertices of each facet in the first model and the preset number;

[0117] In the first model, the difference between the number of vertices of each facet and the preset number is positively correlated with both the third importance threshold and the merging threshold.

[0118] See Figure 3 , Figure 3 This is a schematic block diagram of an electronic device provided according to an embodiment of this application. Figure 3 The electronic device 300 in this embodiment may include one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memories 304 store computer programs, including program instructions. The processors 301 execute the program instructions stored in the memories 304. Specifically, the processors 301 are configured to invoke the program instructions to perform the functions of the modules in the aforementioned device embodiments, for example... Figure 2 The functions of the modeling module 21, decision module 22, simplification module 23, and model linking module 24 are shown.

[0119] It should be understood that, in the embodiments of this application, the processor 301 may be a central processing unit (CPU), but it may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0120] Input device 302 may include a touchpad, a fingerprint sensor (for collecting the user's fingerprint information and fingerprint orientation information), a microphone, etc., and output device 303 may include a display (LCD, etc.), a speaker, etc.

[0121] The memory 304 may include read-only memory and random access memory, and provides instructions and data to the processor 301. A portion of the memory 304 may also include non-volatile random access memory. For example, the memory 304 may also store a preset amount of data.

[0122] In specific implementations, the processor 301, input device 302, and output device 303 described in the embodiments of this application can execute the implementation methods described in the embodiments of the substation intelligent simulation model construction method provided in this application, or they can execute the implementation methods of the electronic devices described in the embodiments of this application, which will not be repeated here.

[0123] In another embodiment of this application, a computer-readable storage medium is provided. This computer-readable storage medium stores a computer program, which includes program instructions. When executed by a processor, the program instructions implement all or part of the processes in the methods described above. Alternatively, the computer program can instruct related hardware to complete the process. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include any entity or device capable of carrying computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0124] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the foregoing embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device. Furthermore, the computer-readable storage medium can include both internal and external storage units of the electronic device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0125] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0126] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the electronic devices and units described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0127] In the several embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces or units, or it may be an electrical, mechanical, or other form of connection.

[0128] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of this application, depending on actual needs.

[0129] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0130] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for constructing an intelligent simulation model of a substation, characterized in that, include: The substation to be modeled is modeled based on the first point cloud data to obtain a first model, which is composed of multiple facets; the first point cloud data is the preprocessed point cloud data of the substation to be modeled. For each facet in the first model, a simplification strategy for that facet is determined based on its features and the features of the facets adjacent to it. The second model is obtained by simplifying the corresponding facets in the first model based on the simplification strategy for each facet. Using the first model as the root node of the tree structure and the second model as the child node of the tree structure, a simulation model of the substation to be modeled is obtained; the first model and the second model are simulation models of the substation to be modeled at different resolutions, and the resolution of the first model is greater than or equal to the resolution of the second model. The process of preprocessing the point cloud data of the substation to be modeled to obtain the first point cloud data includes: Multiple second point cloud data are acquired, and for each second point cloud data, the target convolutional neural network is used to identify the second point cloud data, determine the substation equipment corresponding to the second point cloud data, and the importance of each point in the second point cloud data; The second point cloud data is the point cloud data of the substation equipment in the substation to be modeled; The first point cloud data is determined based on the importance of each point in each second point cloud data.

2. The method for constructing an intelligent simulation model of a substation as described in claim 1, characterized in that, The determination of the first point cloud data based on the importance of each point in each second point cloud data includes: For each of the second point cloud data: determine the starting point of the second point cloud data, traverse all points in the second point cloud data starting from the starting point, and determine whether to retain the point based on the comparison result of the importance of each point in the second point cloud data with the first importance threshold; until the importance of each point in the second point cloud data is greater than the first importance threshold. The first point cloud data is obtained by merging the data from each second point cloud.

3. The method for constructing an intelligent simulation model of a substation as described in claim 1, characterized in that, The characteristics of the patch include: the importance of the patch; The simplified strategy for determining the face based on the features of the face and the features of the faces adjacent to the face includes: The simplification strategy for a surface is determined based on the importance of the surface and the importance of the surfaces adjacent to it; where the importance of a surface is the average of the importance of each point in its corresponding point cloud data.

4. The method for constructing an intelligent simulation model of a substation as described in claim 1, characterized in that, The characteristics of the sheet include: the area of ​​the sheet and the importance of the sheet; The simplified strategy for determining the face based on the features of the face and the features of the faces adjacent to the face includes: In response to the fact that the area of ​​the patch and the area of ​​its adjacent patches are both smaller than the first area, and the importance of the patch and the importance of its adjacent patches are both smaller than the second importance threshold, a simplification strategy is adopted to merge patches into the patch.

5. The method for constructing an intelligent simulation model of a substation as described in claim 1, characterized in that, The features of the patch include: the position of the vertices in the patch and the importance of the patch; If the sum of the number of vertices of each facet in the first model is greater than a preset number, then the simplification strategy for determining the facet based on its features and the features of the facest adjacent to it includes: In response to the fact that the importance of the face and the importance of the face adjacent to the face are both less than the third importance threshold, and the straight-line distance between the positions of the two target vertices is less than the merging threshold, the vertex merging is determined as the simplification strategy for the face; wherein, the target vertex is a vertex in the face or a vertex in the face adjacent to the face.

6. The method for constructing an intelligent simulation model of a substation as described in claim 5, characterized in that, The process of determining the third importance level and the merging threshold includes: The third importance threshold and the merging threshold are determined based on the difference between the number of vertices of each facet in the first model and the preset number; In the first model, the difference between the number of vertices of each facet and the preset number is positively correlated with both the third importance threshold and the merging threshold.

7. A device for constructing an intelligent simulation model of a substation, characterized in that, include: The modeling module is used to model the substation to be modeled based on the first point cloud data to obtain a first model, which is composed of multiple facets; the first point cloud data is the preprocessed point cloud data of the substation to be modeled. The decision module is used to determine a simplification strategy for each facet in the first model based on the features of the facet and the features of the facest adjacent to the facet. The simplification module is used to simplify the corresponding facets in the first model based on the simplification strategy for each facet to obtain the second model; The model linking module is used to use the first model as the root node of the tree structure and the second model as the child node of the tree structure to obtain a simulation model of the substation to be modeled; the first model and the second model are simulation models of the substation to be modeled at different resolutions, and the resolution of the first model is greater than or equal to the resolution of the second model. The first point cloud data determination module is used to acquire multiple second point cloud data, and for each second point cloud data, it identifies the second point cloud data based on the target convolutional neural network to determine the substation equipment corresponding to the second point cloud data and the importance of each point in the second point cloud data; The second point cloud data is the point cloud data of the substation equipment in the substation to be modeled; The first point cloud data is determined based on the importance of each point in each second point cloud data.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 6.

Images