Automatic Modeling Method and System for Low-Voltage Power Grid Data Based on Visual Acquisition

Abstract

This invention provides an automatic modeling method and system for low-voltage power grid data based on visual data acquisition, relating to the field of low-voltage power grid technology. The method includes: dividing the low-voltage power grid area into multiple sub-regions and constructing multiple local coordinate systems; analyzing the power grid equipment to be acquired and determining at least one matching local coordinate system; configuring a visual data acquisition task template, performing data acquisition to obtain at least one set of equipment modeling data; constructing a multi-region coordinate system transformation model, performing coordinate system transformation to obtain at least one set of equipment modeling transformation data corresponding to the equipment modeling data, and generating visual modeling simulation results for the data acquisition task. This invention solves the technical problem in existing technologies where, in the process of low-voltage power grid data modeling, a large, unified global modeling coordinate system is typically established for data acquisition or modeling of all power grid equipment. While this achieves a unified effect, it is not accurate enough, affecting the true reflection of power grid data and its application effectiveness.

Description

Technical Field

[0001] This invention relates to the field of low-voltage power grid technology, and more specifically to an automatic modeling method and system for low-voltage power grid data based on visual acquisition. Background Technology

[0002] Power grid data modeling supports various tasks such as power grid operation monitoring, fault diagnosis, and planning and design. Accurate equipment modeling and data acquisition are particularly crucial during smart grid construction. However, current low-voltage power grid data modeling suffers from significant problems of "fieldwork-office separation" and "inconsistent work standards among personnel." Current technology establishes a large, unified global modeling coordinate system to collect or model data from all power grid equipment. However, due to the large scale of the power grid and the different responsibilities of each technician, data collection often focuses on a single object. While collecting data from a single object within a large, unified coordinate system achieves uniformity, the accuracy of the modeling data collected in this situation may be insufficient, affecting the true reflection and application effectiveness of power grid data. Summary of the Invention

[0003] This application provides an automatic modeling method and system for low-voltage power grid data based on visual acquisition. It aims to solve the technical problem that in the process of low-voltage power grid data modeling, a large unified global modeling coordinate system is usually established to collect or model data from all power grid equipment. Although the established unified global system can achieve a unified effect, it is not accurate enough, which affects the true reflection of power grid data and the application effect.

[0004] The first aspect disclosed in this application provides an automatic modeling method for low-voltage power grid data based on visual data acquisition. The method includes: dividing a low-voltage power grid area into multiple sub-regions and constructing multiple local coordinate systems corresponding to the multiple sub-regions; analyzing the power grid equipment to be acquired in the acquisition task of a first user, and determining at least one matching local coordinate system from the multiple local coordinate systems according to the type of the power grid equipment to be acquired; configuring a visual data acquisition task template, wherein the visual data acquisition task template acquires data from the power grid equipment to be acquired in the acquisition task according to the at least one matching local coordinate system, thereby obtaining at least one set of equipment modeling data; constructing a multi-region coordinate system transformation model based on the multiple local coordinate systems, performing coordinate system transformation on the at least one matching local coordinate system using the multi-region coordinate system transformation model, obtaining equipment modeling transformation data corresponding to at least one set of equipment modeling data, and generating visual modeling simulation results of the acquisition task according to the equipment modeling transformation data.

[0005] The second aspect of this application discloses an automatic modeling system for low-voltage power grid data based on visual acquisition. This system is used in the aforementioned automatic modeling method for low-voltage power grid data based on visual acquisition. The system includes: a sub-region division module for dividing a low-voltage power grid region into multiple sub-regions and constructing multiple local coordinate systems corresponding to the sub-regions; a coordinate system determination module for analyzing the power grid equipment to be acquired in the acquisition task of a first user and determining at least one matching local coordinate system from the multiple local coordinate systems according to the type of the power grid equipment to be acquired; a data acquisition module for configuring a visual acquisition task template, which acquires data from the power grid equipment to be acquired in the acquisition task according to the at least one matching local coordinate system, obtaining at least one set of equipment modeling data; and a simulation result generation module for constructing a multi-region coordinate system transformation model based on the multiple local coordinate systems, performing coordinate system transformation on the at least one matching local coordinate system using the multi-region coordinate system transformation model, obtaining equipment modeling transformation data corresponding to at least one set of equipment modeling data, and generating visual modeling simulation results for the acquisition task according to the equipment modeling transformation data.

[0006] One or more technical solutions provided in this application have at least the following beneficial effects:

[0007] Traditional methods treat the entire power grid as a single global coordinate system, leading to reduced device positioning accuracy over large areas. This is especially problematic in large-scale power grids where spatial characteristics and location differences between devices can cause coordinate deviations. By dividing the grid into multiple sub-regions and establishing a local coordinate system for each, separate modeling for different devices and regions can be performed, improving the positioning accuracy within each sub-region. Furthermore, due to differences in device type, function, and location, using a unified coordinate system is insufficient to accurately meet the specific needs of different devices. Based on device type and regional characteristics, the most suitable local coordinate system is selected from multiple local coordinate systems for each device to be acquired, ensuring a high degree of alignment between the coordinate system and device characteristics during data acquisition. Finally, inconsistent personnel operating standards and different acquisition methods can lead to variations in data quality. Inconsistencies can affect the final modeling results. By configuring visual acquisition task templates, the acquisition path, viewpoint, and acquisition distance of each device are standardized. Templated acquisition ensures that each device follows a unified standard during acquisition, thereby improving the standardization and consistency of data acquisition. Transformations between local coordinate systems are prone to errors. By establishing a multi-region coordinate system transformation model, the transformation relationship between each local coordinate system and the global coordinate system is clearly defined. This ensures that data in each local coordinate system can be seamlessly and accurately transformed into the global coordinate system, eliminating errors between local and global coordinate systems. This not only improves the uniformity and consistency of data in different regions, but also allows device modeling in different regions to be compared and analyzed under the same reference frame, thereby improving the accuracy and reliability of the entire modeling system.

[0008] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0009] Figure 1 A schematic diagram of the process for an automatic modeling method for low-voltage power grid data based on visual acquisition, provided in an embodiment of this application.

[0010] Figure 2 A schematic diagram of the structure of an automatic modeling system for low-voltage power grid data based on visual acquisition provided in this application embodiment.

[0011] Figure labeling: Sub-region division module 10, coordinate system determination module 20, data acquisition module 30, simulation result generation module 40. Detailed Implementation

[0012] This application provides an automatic modeling method and system for low-voltage power grid data based on visual acquisition. It solves the technical problem that in the process of low-voltage power grid data modeling, a large unified global modeling coordinate system is usually established to collect or model all power grid equipment. Although the established unified global system can achieve a unified effect, it is not accurate enough, which affects the true reflection of power grid data and the application effect.

[0013] After introducing the basic principles of this application, various non-limiting embodiments of this application will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0014] Example 1, as Figure 1 As shown in the figure, this application provides an automatic modeling method for low-voltage power grid data based on visual acquisition, the method comprising:

[0015] Divide the low-voltage power grid area into multiple sub-regions and construct multiple local coordinate systems corresponding to the multiple sub-regions.

[0016] Information on all equipment within the low-voltage power grid area is acquired, including transformers, circuit breakers, and distribution boxes. For each device, basic attribute information such as type, size, spatial location, and electrical connections is recorded. This basic attribute information forms the basis for subsequent region division and local coordinate system construction. Feature vectors are constructed based on the basic attribute information of each device. After normalization, methods such as cosine similarity are used to calculate the similarity between devices. Devices with high similarity are clustered together, with each cluster corresponding to a sub-region. Based on the clustering results, the low-voltage power grid area is divided into multiple sub-regions, each with similar device types and distribution characteristics, thus making the construction of the local coordinate system more accurate. Principal component analysis is used to analyze the spatial coordinates of the devices within each sub-region, extracting the principal axis direction. Once the principal axis direction is determined, it is selected as the X-axis, and the Y and Z axes are determined using orthogonality rules to form a three-dimensional coordinate system. The center point of each sub-region is used as the origin of its coordinate system. Ultimately, each sub-region has a corresponding local coordinate system, allowing for precise data collection for each device and improving the accuracy of modeling.

[0017] The system analyzes the power grid equipment to be recorded in the first user's task and determines at least one matching local coordinate system from the plurality of local coordinate systems according to the type of the power grid equipment to be recorded.

[0018] When the first user submits a data collection task, the content of the task is parsed to determine the power grid equipment that needs to be collected. Based on the type, installation location, and adjacent equipment of the equipment, a matching process is performed from multiple established local coordinate systems. For example, if a device is located in a sub-region, it needs to use the local coordinate system of that sub-region. If the device spans multiple sub-regions or is adjacent to multiple sub-regions, a local coordinate system related to that device is selected for matching. Finally, at least one matching local coordinate system is determined.

[0019] Configure a visual data acquisition task template. The visual data acquisition task template performs data acquisition on the power grid equipment to be acquired according to the at least one matching local coordinate system, and obtains at least one set of equipment modeling data.

[0020] The visual acquisition task template is configured based on a matched local coordinate system. It ensures that the device acquires data in the correct coordinate system. The visual acquisition task template contains a series of acquisition parameters that affect the acquisition method and quality, including configuring the acquisition path, viewpoint parameters, image sharpness, acquisition distance range, point cloud density threshold, and coverage angle range. After the visual acquisition task template is configured, it is automatically sent to the acquisition device. The acquisition device executes the task according to the visual acquisition task template, generating at least one set of device modeling data.

[0021] A multi-region coordinate system transformation model is constructed based on the multiple local coordinate systems. The multi-region coordinate system transformation model is used to transform the coordinate system of at least one matching local coordinate system to obtain at least one set of equipment modeling data corresponding to the equipment modeling data. The visualization modeling and simulation results of the task to be recorded are generated according to the equipment modeling and transformation data.

[0022] In low-voltage power grid areas, each sub-region has its own independent local coordinate system. It is necessary to transform different local coordinate systems into a unified global coordinate system. To achieve this goal, a multi-region coordinate system transformation model is first constructed based on multiple local coordinate systems. This multi-region coordinate system transformation model includes the transformation relationship between multiple local coordinate systems.

[0023] Key parameters for each local coordinate system include the three-dimensional coordinates of the origin in the global coordinate system, the direction vectors of the coordinate axes (i.e., the directions of the X, Y, and Z axes), and the unit and angle definition of the local coordinate system. Based on the key parameters of the local coordinate system, a transformation matrix from the local coordinate system to the global coordinate system is constructed using transformation formulas. The transformation matrix converts the coordinates of the local coordinate system to the coordinates of the global coordinate system. The transformation matrices of multiple local coordinate systems are indexed and stored according to the region to which the device belongs, so as to facilitate quick retrieval and application later.

[0024] When at least one set of equipment modeling data is collected in different local coordinate systems, coordinate transformation is performed on at least one set of equipment modeling data according to the coordinate system transformation model to transform the data under different local coordinate systems to the global coordinate system. After the transformation is completed, the equipment modeling transformation data corresponding to at least one set of equipment modeling data is obtained. The equipment modeling transformation data contains information such as the position, attitude, and size of the equipment in the global coordinate system.

[0025] Based on the obtained equipment modeling and transformation data, a modeling engine generates 3D visualization models of power grid equipment. These models can include electrical equipment, lines, transformers, etc., showcasing the actual layout of the power grid. All equipment is placed in a unified virtual space, arranged according to the actual layout, demonstrating the electrical connections, locations, and structures between the equipment. The power grid simulation scene generated in this process reflects the physical relationships and operating status of the power grid equipment. The visualization modeling and simulation results are displayed through an interactive simulation module. This module allows users to interact with the simulation scene, including rotating, panning, zooming the view, and even highlighting specific equipment or areas. Users can adjust the view and perspective as needed to obtain detailed information about the equipment or power grid. This interactive process provides users with an immersive experience, helping them gain a deeper understanding of various aspects of the power grid.

[0026] Furthermore, methods for dividing a low-voltage power grid area into multiple sub-regions include:

[0027] The system acquires the set of equipment in the low-voltage power grid area and the basic attribute information of each equipment, including equipment type, equipment volume calibration range, equipment spatial location, and electrical connection relationship; it extracts the sampling similarity feature vector according to the basic attribute information; it performs cluster analysis on the set of equipment in the low-voltage power grid area based on the sampling similarity feature vector to obtain clustering results, which include multiple equipment clusters, and uses the multiple equipment clusters to obtain multiple sub-regions of the low-voltage power grid area.

[0028] Low-voltage power grid areas contain a wide variety of equipment, including transformers, circuit breakers, and distribution boxes. Collecting and classifying all equipment within the low-voltage power grid area forms an equipment set. For each piece of equipment, key basic attribute information includes: equipment type, indicating the type of each device; equipment volume calibration range, indicating the volume range of each device for subsequent spatial positioning; equipment spatial location, indicating the three-dimensional position coordinates of the device within the power grid area (e.g., X, Y, Z coordinates); and electrical connection relationships, indicating the electrical connection information of each device and describing the electrical connection relationships between devices, such as the connection between transformers and switches, and the connection between distribution boxes and cables.

[0029] Different types of equipment require different data collection methods and requirements when modeling on-site. In order to effectively adapt to the on-site modeling and data collection habits of different equipment types, similarity feature vectors are extracted based on basic attribute information. This helps with subsequent equipment classification and cluster analysis, ensuring the effectiveness of data collection tasks.

[0030] Equipment within the low-voltage power grid area is clustered according to its similarity feature vector, for example, using K-means clustering. By calculating the similarity between equipment, the equipment is divided into a predetermined number of clusters. The equipment in each cluster has similar attribute characteristics and collection requirements. After the clustering analysis is completed, each cluster represents a sub-region. The equipment in each sub-region will be modeled and data collected according to its characteristics. The equipment in each sub-region has similar collection requirements, which can improve the accuracy and efficiency of data collection.

[0031] Furthermore, the method for extracting the similarity feature vector based on the aforementioned basic attribute information includes:

[0032] An initial feature vector dimension space is defined, which includes feature terms and the feature values ​​corresponding to each feature term. The feature terms include device type code, device volume level, average distance to adjacent devices, electrical connection topology depth, and installation direction classification. The feature values ​​corresponding to each feature term are normalized to obtain a normalized feature vector dimension space. The similarity of the feature vectors in the normalized feature vector dimension space is calculated by using cosine similarity to extract the sampling similarity feature vector.

[0033] Define an initial feature vector dimension space where the feature terms can effectively distinguish the differences between devices and reflect the data acquisition requirements of each device. Specifically, the device type code is a unique code representation for each device type, typically using integers or strings to identify different types of devices; the device volume level is the volume range or size level of the device; based on the actual volume of the device, it can be divided into multiple levels, such as small devices, large devices, etc.; the average distance to adjacent devices is the average spatial distance between a device and its adjacent devices; this feature term reflects the layout density of devices in the power grid and affects the complexity of data acquisition; the electrical connection topology depth is the depth of the electrical connection relationship between a device and other devices, for example, device A connects to device B, and device B connects to device C. This connection depth can be represented numerically; the greater the depth, the more complex the connection relationship between devices; and the installation direction classification refers to the installation method of the device, such as vertical, horizontal, or tilted, which affects the viewing angle requirements of the data acquisition task.

[0034] Because the numerical ranges and dimensions of each feature are different—for example, equipment type is a discrete integer while equipment volume is a continuous, large-scale value—the different scales of these feature items can affect the similarity calculation results. To avoid certain feature items having an excessive impact on the similarity calculation, it is necessary to normalize the feature items. For example, the min-max normalization method can be used to convert all feature values ​​to a uniform range, usually [0,1]. For discrete feature items, such as equipment type encoding and installation direction, one-hot encoding or direct mapping to discrete integer values ​​can be used to avoid their impact on the similarity calculation.

[0035] Through normalization, the feature vector of each device is transformed into a standardized vector, resulting in a normalized feature vector dimension space. This ensures that the feature vectors of all devices are consistent and can be compared on the same scale. Cosine similarity is used as a standard to measure the similarity between two devices. The result of cosine similarity ranges from -1 to 1; the closer to 1, the more similar the two devices are, and the closer to -1, the more different they are. By calculating the cosine similarity of the feature vectors of all devices, the similarity feature vector between each device and other devices is obtained.

[0036] Furthermore, the method for constructing multiple local coordinate systems corresponding to the multiple sub-regions includes:

[0037] Calculate the boundary envelope boxes of the multiple sub-regions to obtain the spatial boundary coordinate set and spatial center coordinates; use principal component analysis to fit the device distribution coordinates of each region in the multiple sub-regions to extract the first principal axis direction, use the first principal axis direction as the X-axis and define the Y-axis and Z-axis using three-dimensional orthogonality rules to output the three-dimensional coordinate axes; use the spatial center coordinates as the origin of the local coordinate system and the three-dimensional coordinate axes as the coordinate axes of the local coordinate system to construct multiple local coordinate systems corresponding to the multiple sub-regions.

[0038] For each sub-region, the spatial positions of all devices within that sub-region are first obtained, typically in 3D coordinates. Then, the boundary envelope of the sub-region is calculated using these device coordinates. The boundary envelope is a minimal rectangle that completely encloses the spatial distribution of all devices. In 3D space, the boundary envelope contains the minimum and maximum coordinates of the devices in the x, y, and z directions, forming a cuboid. After obtaining the boundary envelope, the spatial boundary coordinate set and spatial center coordinates of the sub-region are calculated. The spatial boundary coordinate set is the set of coordinate points on the boundary envelope, and the spatial center coordinates are the center point of the boundary envelope, determined by calculating the median values ​​of the minimum and maximum coordinates in the x, y, and z directions.

[0039] Principal component analysis (PCA) is a technique that maps high-dimensional data to a low-dimensional space. It helps to find the most important directions in the data. In the spatial distribution of power grid equipment, PCA is used to find the most representative direction in the equipment layout, namely the first principal axis direction. Specifically, the PCA algorithm analyzes the spatial distribution coordinates of the equipment, maximizes the variance of the equipment coordinates, and extracts the principal components in the direction. That is, for all coordinate points of the equipment distribution, a covariance matrix is ​​constructed and eigenvalue decomposition is performed. The eigenvectors represent the principal directions of the equipment distribution, and the magnitude of the eigenvalues ​​represents the magnitude of the variance in that direction. The eigenvector corresponding to the largest eigenvalue is the first principal axis direction. The first principal axis direction is a three-dimensional vector, representing the maximum distribution of equipment in that direction. This direction is used as the X-axis direction of the local coordinate system. Next, the Y-axis and Z-axis are defined using orthogonalization. The cross product can be used to calculate the other two directions perpendicular to the first principal axis. For example, if the first principal axis is the X-axis, an arbitrary direction can be selected, such as a random point on the device coordinate axis, and then its cross product with the X-axis can be calculated to obtain the Z-axis direction. The Y-axis direction can then be calculated using the cross product. This orthogonalization method ensures that the X, Y, and Z axes are perpendicular to each other.

[0040] The spatial center coordinates are set as the origin of the local coordinate system. This coordinate is calculated from the center point of the envelope box of the equipment distribution. This center point serves as the zero point of the local coordinate system. The obtained three-dimensional coordinate axes are used as the coordinate axes of the local coordinate system, corresponding to the X, Y, and Z directions, respectively. The spatial position of the equipment (i.e., the original equipment coordinates) is converted into coordinates relative to the local coordinate system. This conversion is accomplished by setting the origin (spatial center) and the rotation matrix (coordinate axis directions calculated by principal component analysis). For each sub-region, a corresponding local coordinate system is created and the equipment data in that region is converted to that local coordinate system. This ensures that the equipment data in different sub-regions are modeled under a unified standard and avoids coordinate deviations between different regions.

[0041] Furthermore, a visual acquisition task template is configured, which includes configuring the acquisition path, viewing angle parameters, image clarity, acquisition distance range, point cloud density threshold, and coverage angle range.

[0042] The acquisition path configuration sets the travel path or acquisition sequence of the devices during the acquisition process. The acquisition path ensures that the devices acquire data along the optimal path to cover all necessary devices or areas. This helps avoid duplicate acquisition or missed areas, while reducing unnecessary interference during the acquisition process. Viewpoint parameters set appropriate viewpoints for each device. By adjusting the viewpoint parameters of the camera or sensor, such as pitch angle, horizontal angle, and lens focal length, comprehensive device information can be obtained from different angles and directions, improving the accuracy and completeness of data acquisition. Image clarity is set according to the type of device and environmental requirements, including image pixel quality, contrast, and brightness, ensuring that the acquired image information is clear and unblurred, which is helpful for subsequent modeling and analysis. The acquisition distance range is configured based on the physical size and spatial layout of the devices. The acquisition distance range ensures that the device can effectively acquire clear and accurate data from a predetermined distance. Acquisition distances that are too close or too far can affect data quality. The point cloud density threshold is a density threshold set according to the device's needs during point cloud data acquisition. Point cloud density affects the detail and accuracy of the acquisition; too low a density leads to sparse data, affecting modeling results, while too high a density may overload the processing. The point cloud density can be dynamically adjusted according to the specific device or acquisition environment to achieve a balance between data accuracy and processing efficiency. The coverage angle range is the coverage angle set for the camera or sensor based on the device layout and the required field of view. This ensures that each device can cover all necessary areas during acquisition, especially in complex spatial structures, avoiding blind spots. These configurations make the acquisition process more standardized, avoid errors caused by human differences, improve the accuracy of data modeling, and ensure the clarity, comprehensiveness, and precision of the final visualization results.

[0043] Furthermore, the visualization data acquisition task template acquires data from the power grid equipment to be acquired in the task according to the at least one matching local coordinate system, and the method includes:

[0044] The visualization acquisition task template obtains at least one acquisition task instruction set corresponding to at least one matching local coordinate system; binds the at least one matching local coordinate system with the corresponding at least one acquisition task instruction set and sends it to the acquisition terminal device of the first user, and the acquisition terminal device performs data acquisition on the power grid equipment to be acquired in the acquisition task to obtain at least one set of equipment modeling data.

[0045] For each matching local coordinate system, the matching acquisition task instruction set is extracted from the visualization acquisition task template. The acquisition task instruction set includes the rules and parameters that need to be followed in the visualization acquisition task template, including the configuration acquisition path, viewpoint parameters, image sharpness, acquisition distance range, point cloud density threshold, and coverage angle range. For example, if a certain local coordinate system corresponds to the equipment distribution of a power distribution transformer, then its task instruction set contains specific acquisition requirements for that equipment type.

[0046] For each device to be acquired and its corresponding matching local coordinate system, it is bound to the acquisition task instruction set. This binding process ensures that the acquisition process is carried out according to the specific coordinate system of the area where the device is located, avoiding coordinate system confusion or data deviation. After binding the matching local coordinate system and the acquisition task instruction set, this information is sent to the first user's acquisition terminal device. The acquisition terminal device can be a laser scanner, 3D camera, drone, or other hardware capable of performing data acquisition tasks. When performing data acquisition tasks, the acquisition terminal device strictly follows the acquisition task instruction set. For example, it performs device scanning at a specified viewpoint, ensuring that the requirements for image resolution, acquisition distance, and point cloud density are met during the scanning process. The acquired data is transmitted back to the system in real time to form device modeling data. After post-processing, it will be transformed into model data for further analysis and use.

[0047] Furthermore, a multi-region coordinate system transformation model is constructed based on the aforementioned multiple local coordinate systems, the method of which includes:

[0048] Obtain the key parameters of each local coordinate system, including the three-dimensional coordinates of the origin in the global coordinate system, the coordinate axis direction vectors, the local coordinate units, and the angle definition method; construct a local-global coordinate transformation matrix based on the key parameters of each local coordinate system and the transformation formula of the pre-constructed global coordinate system, and store the local-global coordinate transformation matrix according to the corresponding sub-region index to establish a multi-region coordinate system transformation model.

[0049] The three-dimensional coordinates of the origin in the global coordinate system represent the position of the local coordinate system within the global coordinate system. By determining the position of the origin, the local coordinate system can be aligned with the global coordinate system. The three-dimensional coordinates of the origin are usually obtained through geographic positioning or measurement, representing the reference position of the local coordinate system. The coordinate axis direction vectors define the directions of the three axes (X-axis, Y-axis, and Z-axis) of the local coordinate system. These vectors reflect the spatial orientation of the local coordinate system and are usually determined by the physical location of the equipment, installation angle, or other geometric characteristics. Through these direction vectors, the rotation and spatial orientation of the local coordinate system relative to the global coordinate system can be determined. The local coordinate unit refers to the length of the unit in the coordinate system. For example, if the unit of the local coordinate system is meters, then each coordinate value represents the actual spatial position in that local coordinate system. This unit may differ from that of the global coordinate system, so conversion is required. The angle definition method is used to describe how to represent the angular relationship between the coordinate axes. In different coordinate systems, angles may use different units (degrees or radians) and standards (e.g., clockwise or counterclockwise). A unified definition method for angles needs to be agreed upon to ensure consistency in coordinate transformation.

[0050] Based on the acquired key parameters of the local coordinate system, the first step is to determine how to transform the coordinates from the local coordinate system to the global coordinate system. By analyzing the origin coordinates, direction vectors, and angle definitions, the translation, rotation, and scaling information of the local coordinate system relative to the global coordinate system can be calculated. The transformation formula for the global coordinate system has been pre-constructed, containing the mapping rules from the local coordinate system to the global coordinate system. This formula includes the relationships between all sub-region coordinate systems, including rotation matrices and translation matrices, to ensure seamless integration between each local coordinate system and the global coordinate system. Using the key parameters of the local coordinate system and the transformation formula for the global coordinate system, the coordinate transformation matrix from the local coordinate system to the global coordinate system is calculated. This matrix contains all the information required for the coordinate transformation, ultimately achieving an accurate mapping from the local coordinate system to the global coordinate system. The calculated local-global coordinate transformation matrix is ​​stored according to the sub-region indices, forming a multi-region coordinate system transformation model. This model ensures that all local coordinate systems can be effectively transformed when needed based on the sub-region indices, thereby achieving accurate cross-regional data integration in large-scale power grid modeling.

[0051] Furthermore, the method for performing coordinate system transformation on the at least one matching local coordinate system using the multi-region coordinate system transformation model includes:

[0052] The transformation key parameters of at least one matching local coordinate system are obtained using the multi-region coordinate system transformation model; initial equipment modeling transformation data corresponding to at least one set of equipment modeling data are obtained according to the transformation key parameters; cross-region anchor point equipment is identified, wherein the cross-region anchor point equipment is a common equipment located at the intersection of two or more sub-regions; spatial deviation vectors, including rotation deviation vectors and translation deviation vectors, are calculated for the initial equipment modeling transformation data corresponding to the at least one set of equipment modeling data through the cross-region anchor point equipment; the initial equipment modeling transformation data is re-registered according to the spatial deviation vectors to update the equipment modeling transformation data.

[0053] Based on the identifier or index of at least one matching local coordinate system, the corresponding key transformation parameters are extracted from the multi-region coordinate system transformation model, including the origin, coordinate axis direction, rotation matrix, translation vector, etc. of the local coordinate system. These key transformation parameters are the basis for subsequent coordinate transformations.

[0054] The obtained key transformation parameters are applied to the equipment modeling data to be transformed. Based on the relationship between the local coordinate system and the global coordinate system, coordinate transformation is performed. The transformed data represents the position and characteristics of the equipment in the global coordinate system. In this way, equipment data can be processed and integrated across regions, ensuring that the modeling data of the entire low-voltage power grid is under the same reference coordinate system. Finally, the transformed data becomes the initial equipment modeling transformation data. This data is the equipment information after coordinate system transformation and can be used for subsequent visualization modeling or further analysis.

[0055] Cross-regional anchor points refer to common equipment that spans two or more sub-regions. The location information of these common devices serves as a reference between multiple local coordinate systems. They are typically critical equipment in the power grid, such as transformers, switchgear, or electrical connection equipment at junctions. By analyzing the relationship between local coordinate systems and local equipment, cross-regional anchor points located at the boundaries of different sub-regions can be identified. Cross-regional anchor points often have unique physical locations or electrical connections, which can be identified through the spatial location or electrical connection relationships of the equipment. These cross-regional anchor points provide a common reference point between the coordinate systems of different regions and can play a calibration role during coordinate transformation.

[0056] Spatial deviation vectors refer to the difference between the device's position in the global coordinate system and its expected position during coordinate system transformation. Specifically, rotation deviation vectors represent the rotation error of the device's coordinate system, i.e., the angular difference between the device's local and global coordinate systems; translation deviation vectors represent the translation error of the device's coordinate system, i.e., the positional difference of the device along the coordinate axes. Cross-regional anchor point devices are common devices connecting different regional coordinate systems; therefore, they can be used as positioning references. Specifically, rotation errors are calculated by comparing the directional differences of cross-regional anchor point devices in the local and global coordinate systems. This can be done by comparing the coordinate axis direction vectors or by using a rotation matrix to calculate the angular difference between the two coordinate systems. Translation errors are calculated by comparing the positional differences of cross-regional anchor point devices in the local and global coordinate systems. Generally, this involves calculating the difference in the device's spatial position coordinates (x, y, z).

[0057] Spatial deviation vectors (including rotation and translation deviation vectors) are used to correct the initial equipment modeling transformation data, making it more accurately aligned to the global coordinate system. Specifically, rotation deviation vectors are used to adjust the rotation angle of the equipment. Based on the calculated rotation error, the coordinates of the equipment are rotated using a rotation matrix to align them with the standard of the global coordinate system. For example, if a rotation deviation angle is calculated, it can be applied to adjust the coordinates of the equipment. Translation deviation vectors are used to adjust the position of the equipment. By applying the translation error to the coordinates of the equipment, the equipment can be accurately positioned in the correct location in the global coordinate system. For example, the translation deviation vectors are increased or decreased for the coordinate values ​​of all equipment to ensure that their coordinates are aligned with the global coordinate system. After completing the rotation and translation registration, the initial equipment modeling transformation data is updated with the corrected new coordinates, i.e., the equipment modeling transformation data, reflecting the precise position of the equipment in the global coordinate system. After deviation correction, they will accurately correspond to the correct power grid location.

[0058] Furthermore, the visualization modeling and simulation results of the task to be recorded are generated according to the equipment modeling and conversion data; wherein, the visualization modeling and simulation results are output through an interactive simulation module, and the interactive simulation module provides a visualization display response by receiving interactive operations from the first user.

[0059] The visualized modeling and simulation results are generated from the acquired equipment modeling and conversion data to create a 3D power grid model. This model displays the precise locations of the equipment, their connections, and the overall layout of the power grid. Once generated, the visualized modeling and simulation results are provided to the first user for display and operation via an interactive simulation module. The core of this module is to allow the first user to interact with the power grid model, view detailed information about different areas, equipment, or functions, and perform simulations and adjustments as needed. For example, the first user can use a mouse, touchpad, or other input devices to rotate, pan, and zoom the power grid model, viewing various equipment from different angles. During the interaction, the user's actions trigger real-time system responses. For instance, when the user drags equipment or adjusts its parameters, the system updates the model in real time based on these changes, displaying the changes in the power grid under these operations. Through this interactive simulation, the first user can perform power grid modeling and analysis more flexibly and accurately, improving operational efficiency and reducing human error.

[0060] In summary, the automatic modeling method for low-voltage power grid data based on visual acquisition provided in this application has the following technical effects:

[0061] Traditional methods treat the entire power grid as a single global coordinate system, leading to reduced device positioning accuracy over large areas. This is especially problematic in large-scale power grids where spatial characteristics and location differences between devices can cause coordinate deviations. By dividing the grid into multiple sub-regions and establishing a local coordinate system for each, separate modeling for different devices and regions can be performed, improving the positioning accuracy within each sub-region. Furthermore, due to differences in device type, function, and location, using a unified coordinate system is insufficient to accurately meet the specific needs of different devices. Based on device type and regional characteristics, the most suitable local coordinate system is selected from multiple local coordinate systems for each device to be acquired, ensuring a high degree of alignment between the coordinate system and device characteristics during data acquisition. Finally, inconsistent personnel operating standards and different acquisition methods can lead to variations in data quality. Inconsistencies can affect the final modeling results. By configuring visual acquisition task templates, the acquisition path, viewpoint, and acquisition distance of each device are standardized. Templated acquisition ensures that each device follows a unified standard during acquisition, thereby improving the standardization and consistency of data acquisition. Transformations between local coordinate systems are prone to errors. By establishing a multi-region coordinate system transformation model, the transformation relationship between each local coordinate system and the global coordinate system is clearly defined. This ensures that data in each local coordinate system can be seamlessly and accurately transformed into the global coordinate system, eliminating errors between local and global coordinate systems. This not only improves the uniformity and consistency of data in different regions, but also allows device modeling in different regions to be compared and analyzed under the same reference frame, thereby improving the accuracy and reliability of the entire modeling system.

[0062] Example 2 is based on the same inventive concept as the low-voltage power grid data automatic modeling method based on visual acquisition in the previous examples, such as... Figure 2 As shown in the figure, this application provides an automatic modeling system for low-voltage power grid data based on visual acquisition. The system includes:

[0063] The sub-region division module 10 is used to divide the low-voltage power grid area into multiple sub-regions and construct multiple local coordinate systems corresponding to the multiple sub-regions; the coordinate system determination module 20 is used to analyze the power grid equipment to be collected in the first user's task and determine at least one matching local coordinate system from the multiple local coordinate systems according to the type of the power grid equipment to be collected; the data collection module 30 is used to configure a visual collection task template, which performs data collection on the power grid equipment to be collected in the task according to the at least one matching local coordinate system to obtain at least one set of equipment modeling data; the simulation result generation module 40 is used to construct a multi-region coordinate system transformation model based on the multiple local coordinate systems, perform coordinate system transformation on the at least one matching local coordinate system using the multi-region coordinate system transformation model to obtain at least one set of equipment modeling data corresponding to the equipment modeling data, and generate the visual modeling simulation result of the task to be collected according to the equipment modeling transformation data.

[0064] Furthermore, the sub-region division module 10 is used to perform the following operation steps:

[0065] The system acquires the set of equipment in the low-voltage power grid area and the basic attribute information of each equipment, including equipment type, equipment volume calibration range, equipment spatial location, and electrical connection relationship; it extracts the sampling similarity feature vector according to the basic attribute information; it performs cluster analysis on the set of equipment in the low-voltage power grid area based on the sampling similarity feature vector to obtain clustering results, which include multiple equipment clusters, and uses the multiple equipment clusters to obtain multiple sub-regions of the low-voltage power grid area.

[0066] Furthermore, the sub-region division module 10 is used to perform the following operation steps:

[0067] An initial feature vector dimension space is defined, which includes feature terms and the feature values ​​corresponding to each feature term. The feature terms include device type code, device volume level, average distance to adjacent devices, electrical connection topology depth, and installation direction classification. The feature values ​​corresponding to each feature term are normalized to obtain a normalized feature vector dimension space. The similarity of the feature vectors in the normalized feature vector dimension space is calculated by using cosine similarity to extract the sampling similarity feature vector.

[0068] Furthermore, the sub-region division module 10 is used to perform the following operation steps:

[0069] Calculate the boundary envelope boxes of the multiple sub-regions to obtain the spatial boundary coordinate set and spatial center coordinates; use principal component analysis to fit the device distribution coordinates of each region in the multiple sub-regions to extract the first principal axis direction, use the first principal axis direction as the X-axis and define the Y-axis and Z-axis using three-dimensional orthogonality rules to output the three-dimensional coordinate axes; use the spatial center coordinates as the origin of the local coordinate system and the three-dimensional coordinate axes as the coordinate axes of the local coordinate system to construct multiple local coordinate systems corresponding to the multiple sub-regions.

[0070] Furthermore, a visual acquisition task template is configured, which includes configuring the acquisition path, viewing angle parameters, image clarity, acquisition distance range, point cloud density threshold, and coverage angle range.

[0071] Furthermore, the data acquisition module 30 is used to perform the following operation steps:

[0072] The visualization acquisition task template obtains at least one acquisition task instruction set corresponding to at least one matching local coordinate system; binds the at least one matching local coordinate system with the corresponding at least one acquisition task instruction set and sends it to the acquisition terminal device of the first user, and the acquisition terminal device performs data acquisition on the power grid equipment to be acquired in the acquisition task to obtain at least one set of equipment modeling data.

[0073] Furthermore, the simulation result generation module 40 is used to perform the following operation steps:

[0074] Obtain the key parameters of each local coordinate system, including the three-dimensional coordinates of the origin in the global coordinate system, the coordinate axis direction vectors, the local coordinate units, and the angle definition method; construct a local-global coordinate transformation matrix based on the key parameters of each local coordinate system and the transformation formula of the pre-constructed global coordinate system, and store the local-global coordinate transformation matrix according to the corresponding sub-region index to establish a multi-region coordinate system transformation model.

[0075] Furthermore, the simulation result generation module 40 is used to perform the following operation steps:

[0076] The transformation key parameters of at least one matching local coordinate system are obtained using the multi-region coordinate system transformation model; initial equipment modeling transformation data corresponding to at least one set of equipment modeling data are obtained according to the transformation key parameters; cross-region anchor point equipment is identified, wherein the cross-region anchor point equipment is a common equipment located at the intersection of two or more sub-regions; spatial deviation vectors, including rotation deviation vectors and translation deviation vectors, are calculated for the initial equipment modeling transformation data corresponding to the at least one set of equipment modeling data through the cross-region anchor point equipment; the initial equipment modeling transformation data is re-registered according to the spatial deviation vectors to update the equipment modeling transformation data.

[0077] Furthermore, the visualization modeling and simulation results of the task to be recorded are generated according to the equipment modeling and conversion data; wherein, the visualization modeling and simulation results are output through an interactive simulation module, and the interactive simulation module provides a visualization display response by receiving interactive operations from the first user.

[0078] Through the foregoing detailed description of the automatic modeling method for low-voltage power grid data based on visual acquisition, those skilled in the art can clearly understand the automatic modeling system for low-voltage power grid data based on visual acquisition in this embodiment. Since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and relevant parts can be referred to the method section.

[0079] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An automatic modeling method for low-voltage power grid data based on visual acquisition, characterized in that, The method includes: Divide the low-voltage power grid area into multiple sub-regions and construct multiple local coordinate systems corresponding to the multiple sub-regions; The power grid equipment to be recorded in the task to be recorded by the first user is analyzed, and at least one matching local coordinate system is determined from the plurality of local coordinate systems according to the type of the power grid equipment to be recorded; Configure a visual data acquisition task template. The visual data acquisition task template performs data acquisition on the power grid equipment to be acquired according to the at least one matching local coordinate system, and obtains at least one set of equipment modeling data. A multi-region coordinate system transformation model is constructed based on the multiple local coordinate systems. The multi-region coordinate system transformation model is used to transform the coordinate system of at least one matching local coordinate system to obtain at least one set of equipment modeling data corresponding to the equipment modeling data. The visualization modeling and simulation results of the task to be recorded are generated according to the equipment modeling and transformation data. The method for constructing multiple local coordinate systems corresponding to the multiple sub-regions includes: Calculate the boundary envelope boxes of the multiple sub-regions to obtain the set of spatial boundary coordinates and the spatial center coordinates; Principal component analysis is used to fit the device distribution coordinates of each region in the multiple sub-regions to extract the first principal axis direction. The first principal axis direction is used as the X-axis, and the Y-axis and Z-axis are defined using three-dimensional orthogonality rules to output the three-dimensional coordinate axes. Using the spatial center coordinates as the origin of the local coordinate system and the three-dimensional coordinate axes as the coordinate axes of the local coordinate system, multiple local coordinate systems corresponding to the multiple sub-regions are constructed.

2. The automatic modeling method for low-voltage power grid data based on visual acquisition as described in claim 1, characterized in that, Methods for dividing a low-voltage power grid area into multiple sub-regions include: Obtain the set of equipment in the low-voltage power grid area and the basic attribute information of each equipment. The basic attribute information includes equipment type, equipment volume calibration range, equipment spatial location and electrical connection relationship. Extract the similarity feature vector based on the aforementioned basic attribute information; Clustering analysis is performed on the equipment set in the low-voltage power grid area based on the collected similarity feature vector to obtain clustering results. The clustering results include multiple equipment clusters, and multiple sub-regions of the low-voltage power grid area are obtained using the multiple equipment clusters.

3. The automatic modeling method for low-voltage power grid data based on visual acquisition as described in claim 2, characterized in that, The method for extracting similarity feature vectors based on the aforementioned basic attribute information includes: Define an initial feature vector dimension space, which includes feature terms and the feature values ​​corresponding to each feature term. The feature terms include device type code, device volume level, average distance to adjacent devices, electrical connection topology depth, and installation direction classification. For each feature term, the feature value is normalized to a normalized feature vector dimension space. The similarity of the feature vectors in the normalized feature vector dimension space is calculated by cosine similarity, and the similarity feature vector is extracted.

4. The automatic modeling method for low-voltage power grid data based on visual acquisition as described in claim 1, characterized in that, Configure a visual acquisition task template, which includes configuring the acquisition path, viewpoint parameters, image clarity, acquisition distance range, point cloud density threshold, and coverage angle range.

5. The automatic modeling method for low-voltage power grid data based on visual acquisition as described in claim 4, characterized in that, The visualization data acquisition task template acquires data from the power grid equipment to be acquired in the task according to at least one matching local coordinate system. The method includes: The visual acquisition task template obtains at least one acquisition task instruction set corresponding to at least one matching local coordinate system; The at least one matching local coordinate system is bound to the corresponding at least one set of acquisition task instructions and sent to the acquisition terminal device of the first user. The acquisition terminal device then acquires data from the power grid equipment to be acquired for the acquisition task, thereby obtaining at least one set of equipment modeling data.

6. The automatic modeling method for low-voltage power grid data based on visual acquisition as described in claim 1, characterized in that, A multi-region coordinate system transformation model is constructed based on the aforementioned multiple local coordinate systems. The method includes: Obtain the key parameters of each local coordinate system, including the three-dimensional coordinates of the origin in the global coordinate system, the coordinate axis direction vectors, the local coordinate units, and the angle definition method; Based on the key parameters of each local coordinate system and the transformation formula of the pre-constructed global coordinate system, a local-global coordinate transformation matrix is ​​constructed. The local-global coordinate transformation matrix is ​​stored according to the corresponding sub-region index to establish a multi-region coordinate system transformation model.

7. The automatic modeling method for low-voltage power grid data based on visual acquisition as described in claim 6, characterized in that, The method for performing coordinate system transformation on the at least one matching local coordinate system using the multi-region coordinate system transformation model includes: The transformation key parameters of at least one matching local coordinate system are obtained using the multi-region coordinate system transformation model. According to the aforementioned key conversion parameters, at least one set of initial equipment modeling conversion data corresponding to equipment modeling data is obtained; Identify cross-regional anchor point devices, wherein the cross-regional anchor point devices are common devices located at the boundary of two or more sub-regions; The spatial deviation vectors of the initial equipment modeling conversion data corresponding to the at least one set of equipment modeling data are calculated using the cross-regional anchor point devices, including rotation deviation vectors and translation deviation vectors. The initial equipment modeling conversion data is re-registered according to the spatial deviation vector to update the equipment modeling conversion data.

8. The automatic modeling method for low-voltage power grid data based on visual acquisition as described in claim 1, characterized in that, The visualization modeling and simulation results of the task to be acquired are generated based on the equipment modeling and conversion data. The visualization modeling and simulation results are output through an interactive simulation module, which responds by displaying the results in a visual manner by receiving interactive operations from the first user.

9. An automatic modeling system for low-voltage power grid data based on visual acquisition, characterized in that, The system is used to implement the automatic modeling method for low-voltage power grid data based on visual acquisition as described in any one of claims 1-8, the system comprising: The sub-region division module is used to divide the low-voltage power grid area into multiple sub-regions and construct multiple local coordinate systems corresponding to the multiple sub-regions. The coordinate system determination module is used to analyze the power grid equipment to be recorded in the first user's recording task, and determine at least one matching local coordinate system from the plurality of local coordinate systems according to the type of the power grid equipment to be recorded; The data acquisition module is used to configure a visual acquisition task template. The visual acquisition task template performs data acquisition on the power grid equipment to be acquired according to the at least one matching local coordinate system, and obtains at least one set of equipment modeling data. The simulation result generation module is used to construct a multi-region coordinate system transformation model based on the multiple local coordinate systems, use the multi-region coordinate system transformation model to perform coordinate system transformation on the at least one matching local coordinate system, obtain at least one set of equipment modeling data corresponding to the equipment modeling data, and generate the visualization modeling simulation results of the task to be recorded according to the equipment modeling transformation data.

Images