Method, device and equipment for digital conversion of power distribution network drawings and storage medium thereof

Abstract

The application discloses a power distribution network drawing digital conversion method, device and equipment and a storage medium thereof. It relates to the technical field of image recognition. The method comprises the following steps: after obtaining a power distribution network drawing, analyzing the obtained power distribution network drawing, and extracting all the graphic element information in the power distribution network drawing; based on the graphic element information, classifying and aggregating the graphic elements in the power distribution network drawing to obtain component graphic blocks and line objects; based on a preset feature matching model, identifying the component categories of the component graphic blocks, and synchronously labeling the attribute information of the component graphic blocks and the line objects based on a preset drawing rule; based on the component types and the attribute information, constructing a structured and attribute-complete power distribution network topology structure diagram containing the component graphic blocks and the line objects. Thus, end-to-end automatic conversion from unstructured graphics to structured knowledge is realized, and the automatic conversion efficiency of the power distribution network drawing is improved.

Description

Technical Field

[0001] This application relates to the field of image recognition technology, and in particular to methods, apparatus, equipment and storage media for the digital conversion of power distribution network drawings. Background Technology

[0002] A power distribution network topology diagram is an engineering drawing that records and describes the electrical equipment in the power distribution network and the connections between them, so as to reflect the structure, connection relationships and construction or equipment information of the power grid system.

[0003] With the development of smart grid and digital twin technologies, the management of distribution network topology diagrams has shifted from historical drawings to structured, computable, and analyzable power grid topology models. Currently, image processing technology is commonly used to recognize the drawings, extracting graphics and some text. Then, user-defined rules are used to add type labels and attributes to the extracted graphics. Finally, based on the graphics, text, type labels, and attributes, the distribution network drawings are digitally converted. However, separating attribute recognition, semantic determination, and topology reconstruction into independent steps results in the final product being unusable for engineering applications of power grid computational topology models, leading to low efficiency in the automatic conversion of distribution network drawings.

[0004] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main objective of this application is to provide a digital conversion method, apparatus, device, and storage medium for distribution network drawings, aiming to solve the technical problem that distribution network drawings cannot be directly converted into power grid calculation topology models for engineering applications, resulting in low efficiency of automatic conversion of distribution network drawings.

[0006] To achieve the above objectives, this application proposes a method for digital conversion of power distribution network drawings, the method comprising: After obtaining the power distribution network drawing, the drawing is parsed to extract all graphic element information. Based on the graphic element information, the graphic elements in the power distribution network drawing are classified and aggregated to obtain component graphic blocks and line objects; Based on a preset feature matching model, the component category of the component graphic block is identified, and the attribute information of the component graphic block and the line object is simultaneously labeled based on preset drawing rules. Based on the component type and the attribute information, a structured and attribute-complete power distribution network topology diagram is constructed, which includes the component graphic blocks and the line objects.

[0007] In one embodiment, the step of identifying the component category of the component graphic block based on a preset feature matching model includes: Based on a preset feature matching model, the feature vector of the component graphic block is extracted; The feature vector is matched with the standard features in the power grid standard legend library to identify the component category of the component graphic block.

[0008] In one embodiment, the step of extracting the feature vector of the component graphic block based on a preset feature matching model includes: Render the component graphic block into a standardized image; Based on a preset feature matching model, the standardized image is mapped into a feature vector in the feature space; The feature matching model is trained based on metric learning, which makes the feature vectors corresponding to component graphic blocks belonging to the same device category closer together in the feature space, while the feature vectors of different device categories are further apart.

[0009] In one embodiment, the step of annotating the attribute information of the component graphic block and the line object based on preset drawing rules includes: Traverse each of the component graphic blocks and the line objects to obtain the original line type, original color and original layer information; Query the multidimensional attributes that correspond to the original line type, the original color, and the original layer information from the preset drawing rules; The multidimensional attributes are labeled as attribute information of the component graphic block and the line object.

[0010] In one embodiment, the step of constructing a structured and attribute-complete distribution network topology diagram containing the component graphic blocks and the line objects based on the component type and the attribute information includes: Based on the component type, a geometric analysis is performed on the component graphic block to obtain the outer envelope of the component image block; Based on the attribute information, endpoint and intersection analysis is performed on the line object to determine the connection relationship between each outer envelope; Based on the connection relationship, a structured and attribute-complete power distribution network topology diagram is constructed, which includes the component graphic blocks and the line objects.

[0011] In one embodiment, the step of constructing a structured and attribute-complete distribution network topology diagram containing the component graphic blocks and the line objects based on the connection relationships includes: The component graphic block is instantiated as a graph node, and the graph node contains the corresponding component type and attribute information; The lines between the line objects are instantiated as graph edges, and the graph edges contain corresponding attribute information; Based on the connection relationship, the graph nodes and graph edges are connected to obtain a structured and attribute-complete distribution network topology graph.

[0012] In one embodiment, the step of classifying and aggregating the graphic elements in the power distribution network drawing based on the graphic element information to obtain component graphic blocks and line objects includes: Based on preset layer naming rules, geometric features of graphic elements, line types and graphic element information, the graphic elements in the power distribution network drawings are divided into component graphic elements and line graphic elements; Cluster the component elements belonging to the same equipment, and then aggregate the clustered elements into component graphic blocks; Based on the endpoint coordinates of the line elements, the line elements are clustered and connected to obtain continuous line objects belonging to the same electrical line.

[0013] Furthermore, to achieve the above objectives, this application also proposes a digital conversion device for power distribution network drawings, the digital conversion device for power distribution network drawings comprising: The extraction module is used to parse the obtained power distribution network drawing after obtaining it, and extract all the graphic element information in the power distribution network drawing; The aggregation module is used to classify and aggregate the graphic elements in the power distribution network drawing based on the graphic element information to obtain component graphic blocks and line objects; The annotation module is used to identify the component category of the component graphic block based on a preset feature matching model, and simultaneously annotate the attribute information of the component graphic block and the line object based on preset drawing rules. The construction module is used to construct a structured and attribute-complete power distribution network topology diagram containing the component graphic blocks and the line objects based on the component type and the attribute information.

[0014] In addition, to achieve the above objectives, this application also proposes a digital conversion device for power distribution network drawings, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the digital conversion method for power distribution network drawings as described above.

[0015] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the digital conversion method for power distribution network drawings as described above.

[0016] One or more technical solutions proposed in this application have at least the following technical effects: After acquiring the distribution network drawings, the drawings are parsed to extract all graphic element information, ensuring no geometric or symbolic elements are omitted. Based on this information, the graphic elements are then categorized and aggregated to form semantically meaningful component graphic blocks and line objects. Scattered graphic elements are organized into identifiable equipment-level units. A preset feature matching model is used to identify the component categories of the graphic blocks, and attribute information for the graphic blocks and line objects is simultaneously labeled according to preset drafting rules. This ensures logical consistency between component types and attributes during the generation stage, avoiding attribute mismatches or omissions due to information gaps. Since the structured distribution network topology diagram can be directly used in engineering applications for power grid calculation topology models, and to ensure the power grid calculation topology model contains complete attributes, a structured and attribute-complete distribution network topology diagram is constructed based on component categories and attribute information. In other words, this application achieves end-to-end automated conversion from unstructured graphics to structured knowledge through a process of parsing – classification and aggregation – identification – labeling – diagram construction, thereby improving the efficiency of automatic conversion of distribution network drawings. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

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

[0019] Figure 1 A flowchart illustrating the digital conversion method for power distribution network drawings provided in this application (Example 1); Figure 2 A flowchart illustrating the second embodiment of the digital conversion method for power distribution network drawings in this application; Figure 3 A flowchart illustrating the digital conversion method for power distribution network drawings provided in Embodiment 3 of this application. Figure 4 A simplified flowchart illustrating the digital conversion method for the power distribution network drawings provided in this application; Figure 5 This is a schematic diagram of the module structure of the digital conversion device in the power distribution network drawing of an embodiment of this application; Figure 6 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the digital conversion method of power distribution network drawings in this application embodiment.

[0020] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0022] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device or computer capable of performing the above functions. The following description uses a computer as an example to illustrate this embodiment and the subsequent embodiments.

[0023] Based on this, embodiments of this application provide a method for digital conversion of power distribution network drawings, referring to... Figure 1 , Figure 1 This is a flowchart illustrating an embodiment of the digital conversion method for power distribution network drawings in this application.

[0024] In this embodiment, the digital conversion method of the power distribution network drawings includes steps S10~S40: Step S10: After obtaining the power distribution network drawing, the obtained power distribution network drawing is parsed to extract all graphic element information in the power distribution network drawing; It should be noted that power distribution network drawings are design or construction drawings used to represent the layout of power distribution networks, and typically include information on the arrangement of various electrical equipment and lines. Graphical element information refers to the information on the basic graphic elements that make up the graphics in the power distribution network drawings, such as points, lines, and polygons.

[0025] Understandably, power distribution network drawings are usually in CAD, PDF, or image formats, and contain unstructured graphic elements. By automatically parsing and fully extracting all graphic element information, power distribution network drawings can be transformed into underlying data that can be processed by computer programs, avoiding the inefficiency and error risks associated with manual drawing reading and data entry.

[0026] In the specific implementation, the CAD drawing is read layer by layer by calling the corresponding graphics parsing engine, and all the graphic element information contained therein is extracted, including but not limited to point coordinates, line segment endpoints, arc parameters, text annotations, layer names, line types, colors and fill areas, etc. To be compatible with the drafting habits of different design institutes or historical periods, the parsing process can be configured with fault tolerance mechanisms, such as splicing broken line segments and enhancing the recognition of fuzzy text, to ensure the integrity and robustness of graphic element information extraction.

[0027] Step S20: Based on the graphic element information, classify and aggregate the graphic elements in the power distribution network drawing to obtain component graphic blocks and line objects; It should be noted that component graphic blocks are graphic collections formed by classifying and aggregating graphic element information extracted from power distribution network drawings, each with a specific function or representing a particular device. Line objects are continuous lines formed by merging discrete line segments belonging to the same electrical line, representing paths or conductors connecting different component graphic blocks in power distribution network drawings.

[0028] Understandably, the graphic elements in power distribution network drawings are usually discrete and semantically unrelated basic graphics such as points, lines, and arcs. Direct use of these elements makes it difficult to reflect the logical units of real equipment or lines. By intelligently classifying and aggregating graphic elements based on layers, geometric features, and connection relationships, scattered graphic elements can be reorganized into component graphic blocks and line objects with engineering significance, thereby achieving a semantic leap from geometric graphics to power components.

[0029] Understandably, the aggregation process can also effectively shield against interference from differences in cartographic styles, improve the robustness of subsequent identification and modeling, and reduce the complexity of topology analysis.

[0030] Optionally, step S20 may also include: Based on preset layer naming rules, geometric features of graphic elements, line types and graphic element information, the graphic elements in the power distribution network drawings are divided into component graphic elements and line graphic elements; Cluster the component elements belonging to the same equipment, and then aggregate the clustered elements into component graphic blocks; Based on the endpoint coordinates of the line elements, the line elements are clustered and connected to obtain continuous line objects belonging to the same electrical line.

[0031] It should be noted that layer naming rules are the naming conventions used for each layer in power distribution network drawings. These are usually specified by the design unit or industry standards and are used to identify the type of graphic content carried by the layer. Geometric characteristics of graphic elements are the geometric attributes possessed by the basic graphic elements (graphic elements) that constitute the drawing. Line type and graphic element information refer to the drawing style of line segments within a graphic element, including solid lines, dashed lines, dotted lines, double-dotted lines, etc., often used to express different electrical meanings. Component graphic elements are the collection of graphic elements used to represent electrical equipment in power distribution network drawings. Line graphic elements are the graphic elements used to represent electrical connection paths in power distribution network drawings. Endpoint coordinates are the spatial coordinates of the starting and ending points of a line graphic element in its geometric representation.

[0032] Understandably, by combining layer naming rules, geometric features, and line type information to perform initial classification of graphic elements, it is possible to effectively distinguish between device symbols and connecting lines, avoid misjudgments caused by symbol similarity, and thus improve the accuracy of graphic element semantic parsing.

[0033] It is understandable that clustering and aggregating component primitives belonging to the same device into component graphic blocks achieves semantic reconstruction from fragmented graphics to complete device entities.

[0034] Understandably, the line element clustering and connection mechanism based on endpoint coordinates can automatically restore the electrical lines drawn in segments in the power distribution network drawings, avoiding the inability to identify or misidentify broken lines caused by drawing interruptions, layer segmentation, or scanning distortion, thereby ensuring that the generated line objects are electricalally continuous and complete.

[0035] Step S30: Based on a preset feature matching model, identify the component category of the component graphic block, and simultaneously label the attribute information of the component graphic block and the line object based on preset drawing rules; It should be noted that the feature matching model is a model trained on a deep neural network, used to solve the problem of measuring the similarity of images or graphics.

[0036] Understandably, by using a feature matching model, the image of the component graphic block is mapped to a high-dimensional feature space, so that the feature vectors of similar devices are close in space, while the feature vectors of different devices are far apart. By comparing the features of the graphic block to be identified with the features in the standard legend library, robust device type identification that does not rely on a fixed template can be achieved.

[0037] It should be noted that component categories are standardized business type identifiers for power equipment or facilities represented in distribution network drawings, and are the core basis for constructing node semantic types in the power grid computational topology model. Drafting rules are used to standardize how to label the attribute information of component graphic blocks and line objects to ensure consistency and accuracy. Attribute information is a set of multi-dimensional engineering business parameters attached to component graphic blocks or line objects, used to describe their non-geometric characteristics such as physical properties, operating status, construction stage, and laying method.

[0038] Understandably, since simply recognizing component graphic blocks is not enough to support power grid business applications, it is also necessary to clarify the equipment type and electrical attributes to which the component graphic blocks belong. By introducing a feature matching model trained based on metric learning, component graphic blocks can be classified with high accuracy.

[0039] Understandably, by combining preset drawing rules, the appearance features of component graphic blocks are mapped to standardized multi-dimensional attributes, realizing the automatic alignment of graphic semantics and business semantics. This not only ensures the consistency and compliance of attribute annotation, but also avoids reliance on manual experience judgment, greatly improving the usability and integrability of digital results.

[0040] In practical implementation, a learnable attribute mapping rule base can be predefined or trained, allowing the rule base to store the correspondence between graphical features and power grid engineering semantics. For example, the rule can be defined as: color = red, line type = dashed line → {voltage level: 10kV, construction status: planned}.

[0041] Step S40: Based on the component type and the attribute information, construct a structured and attribute-complete power distribution network topology diagram that includes the component graphic blocks and the line objects.

[0042] Understandably, by analyzing the outer envelope geometry and detecting the intersection of line endpoints, the electrical connectivity between devices can be accurately inferred. This allows the graphical blocks to be instantiated as graph nodes with attributes, and the line objects to be instantiated as graph edges with attributes, ultimately generating a structured topology graph that conforms to graph theory standards.

[0043] This embodiment provides a digital conversion method for distribution network drawings. After acquiring the distribution network drawings, the method parses the drawings to extract all graphic element information, ensuring that no geometric or symbolic elements are omitted. Then, based on the graphic element information, the elements are classified and aggregated to form semantically meaningful component graphic blocks and line objects. Scattered graphic elements are organized into identifiable equipment-level units. The component categories of the component graphic blocks are then identified based on a preset feature matching model, and the attribute information of the component graphic blocks and line objects is simultaneously labeled according to preset drafting rules. This ensures that component types and attributes remain logically consistent during the generation stage, avoiding attribute mismatches or omissions caused by information gaps. Since the structured distribution network topology diagram can be directly used in power grid calculation topology models for engineering applications, and to ensure that the power grid calculation topology model contains complete attributes, a structured and attribute-complete distribution network topology diagram is constructed based on component categories and attribute information. In other words, this application achieves end-to-end automated conversion from unstructured graphics to structured knowledge through a process of parsing – classification and aggregation – identification – labeling – diagram construction, thereby improving the automatic conversion efficiency of distribution network drawings.

[0044] Based on Embodiment 1 of this application, in Embodiment 2 of this application, the content that is the same as or similar to that in Embodiment 1 can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 Step S30 also includes steps S01~S02: Step S01: Extract the feature vector of the component graphic block based on the preset feature matching model; Step S02: Perform similarity matching between the feature vector and the standard features in the power grid standard legend library to identify the component category of the component graphic block.

[0045] It should be noted that the feature vector, obtained through the feature extraction process, is a mathematical representation used to describe the key attributes or characteristics of a component graphic block. The power grid standard legend library is a database collection containing a large number of known electrical devices and their corresponding standard diagrams and feature information. Similarity matching is used to measure the degree of similarity between two entities.

[0046] Understandably, by applying a pre-defined feature matching model to extract feature vectors of component graphic blocks, the annotation workflow is simplified, the possibility of human error is reduced, and the consistency and accuracy of feature extraction for graphic blocks of different styles and complexities are improved.

[0047] Understandably, by leveraging the rich resources in the power grid standard legend library for similarity matching, even with some degree of deformation or blurring, the component category of the component graphic block can be identified relatively accurately. This greatly reduces the reliance on high-quality input images.

[0048] Furthermore, step S01 also includes: Render the component graphic block into a standardized image; Based on a preset feature matching model, the standardized image is mapped into a feature vector in the feature space; The feature matching model is trained based on metric learning, which makes the feature vectors corresponding to component graphic blocks belonging to the same device category closer together in the feature space, while the feature vectors of different device categories are further apart.

[0049] It should be noted that standardized images are image data obtained by redrawing or rendering component graphic blocks according to uniform size, resolution, background color, grayscale, or color channel requirements. A mathematical space composed of feature vectors, where each dimension corresponds to a certain abstract feature, represents the position of different samples within this space, reflecting their semantic or visual similarity. The goal of metric learning is to learn a distance metric function or embedding space that ensures similar samples are close to each other and dissimilar samples are far apart.

[0050] Understandably, rendering component graphic blocks as standardized images can eliminate input differences in power distribution network drawings caused by non-essential factors such as drawing habits, scale, and layer settings.

[0051] Understandably, by using a feature matching model trained based on metric learning, a semantically aware feature representation can be learned, avoiding reliance on fixed template matching or hard-coded rules. This allows for accurate classification even when faced with unseen device legend variants, based on nearest neighbor relationships in the feature space.

[0052] Furthermore, step S30 also includes: Traverse each of the component graphic blocks and the line objects to obtain the original line type, original color and original layer information; Query the multidimensional attributes that correspond to the original line type, the original color, and the original layer information from the preset drawing rules; The multidimensional attributes are labeled as attribute information of the component graphic block and the line object.

[0053] It should be noted that the original linetype is the basic line style used by the component graphic block or line object. The original color is the color value assigned to the component graphic block or line object in its initial state. The original layer is the organizational hierarchy of the component graphic block or line object in CAD or other drawing software. Multidimensional attributes refer to a set of descriptive features defined for component graphic blocks and line objects according to drafting rules.

[0054] Understandably, by extracting detailed information from component graphic blocks and wiring objects, and adding multi-dimensional attributes to these objects based on preset drafting rules, the information density and usability of electrical engineering drawings are enhanced. This also reduces human error in interpretation and improves the professionalism and standardization of design documents.

[0055] Based on Embodiments 1 and 2 of this application, the same or similar content in Embodiment 3 of this application can be referred to the above description, and will not be repeated hereafter. Please refer to [the above description]. Figure 3 Step S40 also includes steps S1 to S3: Step S1: Based on the component type, perform geometric analysis on the component graphic block to obtain the outer envelope of the component image block; Step S2: Based on the attribute information, perform endpoint and intersection analysis on the line object to determine the connection relationship between each outer envelope; Step S3: Based on the connection relationship, construct a structured and attribute-complete power distribution network topology diagram that includes the component graphic blocks and the line objects.

[0056] It should be noted that geometric analysis is the process of calculating and processing the spatial geometric properties of a component graphic block, such as its shape, outline, and position. The outer envelope is the smallest closed geometric region surrounding the component graphic block. Endpoint and intersection analysis involves detecting and extracting the coordinates of the geometric endpoints of a line object and its intersections with other lines or outer envelopes.

[0057] Understandably, by performing geometric analysis on component graphic blocks based on component type and extracting the outer envelope, the effective connection area of ​​the equipment in space can be accurately depicted, avoiding the misjudgment of decorative graphics or irrelevant primitives as connection points, thereby improving the accuracy of topology modeling.

[0058] Understandably, by combining the analysis of the endpoints and intersections of the line objects and introducing attribute information for logical verification, visual intersections and electrical connections can be distinguished, thereby ensuring that the constructed connection relationships conform to the actual situation of power engineering.

[0059] Understandably, the final structured and attribute-complete distribution network topology diagram not only retains the spatial layout of the original drawings, but also incorporates complete equipment semantics and electrical attributes, forming active data that can be directly used for advanced applications such as power flow calculation, fault isolation, network reconfiguration, asset management, and digital twins, thereby achieving end-to-end automated conversion.

[0060] Furthermore, step S3 also includes: The component graphic block is instantiated as a graph node, and the graph node contains the corresponding component type and attribute information; The lines between the line objects are instantiated as graph edges, and the graph edges contain corresponding attribute information; Based on the connection relationship, the graph nodes and graph edges are connected to obtain a structured and attribute-complete distribution network topology graph.

[0061] It should be noted that each node in the graph node table, which identifies power grid equipment (such as substations and switches), has attributes (such as type, name, and ID). The graph edges represent the identified connecting lines, and each edge has attributes (such as voltage level, laying method, and length).

[0062] Understandably, instantiating component graphic blocks and line objects as graph nodes and graph edges respectively achieves a semantic leap from geometric graphics to graph theory models, transforming power distribution network drawings from static images that are visible but not computable into structured data that is indexable, traversable, and reasonable.

[0063] Understandably, by having graph nodes and edges carry complete attribute information, the generated topology graph can not only reflect the connection logic but also contain rich engineering semantics. Therefore, it can be directly used for advanced applications such as power flow analysis, short-circuit calculation, fault location, and load transfer, thereby improving the value of data reuse.

[0064] For example, to help understand the implementation process of the digital conversion method for distribution network drawings obtained by combining the above embodiments, please refer to... Figure 4 , specifically: Specific steps: Step A. CAD Drawing Analysis and Element Extraction (1) Use the CAD parsing library to read the target DWG / DXF file.

[0065] (2) Traverse all primitives, extract their core information, and form a structured record. Each record contains: primitive type (line, circle, polyline, etc.), geometric coordinates, line type name, color index, and layer name.

[0066] Step B. Primitive Intelligent Classification and Geometric Aggregation (1) Based on the layer naming rules (such as layer name containing "device"), geometric characteristics of the elements (such as whether they are closed) and line type, design rules are established to initially divide the elements into "component elements", "line elements" and "legend".

[0067] (2) Cluster the “component primitives” belonging to the same device according to spatial proximity (such as coordinate distance threshold) and merge them into a single “component primitive block” using a geometric algorithm (such as calculating the minimum bounding box), retaining all its internal sub-primitives.

[0068] (3) For “line elements” (mainly straight line segments), cluster and connect them according to the endpoint coordinates, and merge discrete line segments belonging to the same electrical line into continuous “line objects”.

[0069] Step C. Component type identification based on deep learning (1) Render each “component graphic block” generated in step B into a standardized size RGB image to form a “candidate component image sample set”.

[0070] (2) Construct a deep learning model based on metric learning and train it using the labeled "Power Grid Standard Legend Library" (containing standard images of various types of equipment). The model learns to map images to a feature space, making the features of similar equipment similar and the features of dissimilar equipment dissimilar.

[0071] (3) Input the candidate component image into the trained model, extract the feature vector, perform similarity matching with the standard features in the legend library, and assign the standard legend label with the highest similarity (such as "ring network room" or "power distribution room") to the candidate component to complete semantic recognition.

[0072] Step D. Automatic labeling of circuit and component attributes (1) Establish a mapping rule base for “graphic features - power grid attributes”. For example, define the rule: line type = “dashed line” & color = red → {construction status: “planning”}; layer name contains “CABLE” → {laying method: “buried”}.

[0073] (2) Traverse each identified “line object” and “component graphic block”, and query the rule base according to the line type, color and layer information of its original graphic elements to automatically label its voltage level, laying method, construction status and other multi-dimensional attributes.

[0074] Step E. Topology Connectivity Calculation and Structured Model Construction (1) Calculate geometric connections: Analyze the outer envelope of all “component graphic blocks” and the endpoints of “line objects”, as well as the intersections and endpoints between “line objects”. Set a distance tolerance; if a line endpoint falls within or near the outer envelope of a component, the two are considered connected; determine whether it is a “T-connection” or a “crossing” based on the line intersection type and context.

[0075] (2) Constructing an attributed topology graph: Instantiate each identified component as a "graph node", with attributes including its identified type and the attributes marked in step D. Instantiate each line as a "graph edge", with attributes including its electrical attributes. Connect the nodes and edges according to the connection relationship calculated in step E (1) to form a complete attributed graph model.

[0076] Step F. Output Results and Application Integration (1) Serialize the constructed attribute graph topology model into a standard structured data format, such as JSON or GraphML, or convert it into the CIM / XML format commonly used in power systems.

[0077] (2) The output file can be directly imported into power distribution simulation software, digital twin platform or power grid planning and analysis system as an accurate data basis for advanced applications such as power flow calculation, fault analysis and network optimization.

[0078] The core implementation process can be summarized as follows: "Analysis → Classification and Aggregation → Intelligent Recognition (Deep Learning) → Attribute Mapping (Rules) → Geometric Connection → Graph Construction." This process achieves end-to-end automated transformation from unstructured graphs to structured knowledge.

[0079] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the digital conversion method of the power distribution network drawings in this application. Any simple transformations based on this technical concept are within the protection scope of this application.

[0080] This application also provides a digital conversion device for power distribution network drawings; please refer to... Figure 5 The digital conversion device for the power distribution network drawings includes: The extraction module 10 is used to parse the obtained power distribution network drawing after obtaining the drawing and extract all the graphic element information in the drawing. The aggregation module 20 is used to classify and aggregate the graphic elements in the power distribution network drawing based on the graphic element information to obtain component graphic blocks and line objects; The annotation module 30 is used to identify the component category of the component graphic block based on a preset feature matching model, and simultaneously annotate the attribute information of the component graphic block and the line object based on preset drawing rules. The construction module 40 is used to construct a structured and attribute-complete power distribution network topology diagram containing the component graphic blocks and the line objects based on the component type and the attribute information.

[0081] Optionally, the annotation module 30 is further configured to extract the feature vector of the component graphic block based on a preset feature matching model; and to perform similarity matching between the feature vector and the standard features in the power grid standard legend library to identify the component category of the component graphic block.

[0082] Optionally, the annotation module 30 is further configured to render the component graphic block into a standardized image; and based on a preset feature matching model, map the standardized image into a feature vector in the feature space; wherein the feature matching model is obtained based on metric learning training, so that the feature vectors corresponding to component graphic blocks belonging to the same device category are close in the feature space, while the feature vectors of different device categories are far apart.

[0083] Optionally, the annotation module 30 is further configured to traverse each of the component graphic blocks and the line object to obtain the original line type, original color and original layer information; query the multi-dimensional attributes corresponding to the original line type, the original color and the original layer information from the preset drawing rules; and annotate the multi-dimensional attributes as the attribute information of the component graphic block and the line object.

[0084] Optionally, the construction module 40 is further configured to perform geometric analysis on the component graphic block based on the component type to obtain the outer envelope of the component image block; perform endpoint and intersection analysis on the line object based on the attribute information to determine the connection relationship between each outer envelope; and construct a structured and attribute-complete distribution network topology diagram containing the component graphic block and the line object based on the connection relationship.

[0085] Optionally, the construction module 40 is further configured to instantiate the component graphic block into a graph node, the graph node containing the corresponding component type and attribute information; instantiate the lines between the line objects into graph edges, the graph edges containing the corresponding attribute information; and connect the graph nodes and graph edges based on the connection relationship to obtain a structured and attribute-complete distribution network topology diagram.

[0086] Optionally, the aggregation module 20 is used to divide the elements in the power distribution network drawing into component elements and line elements based on preset layer naming rules, element geometric features, line types and element information; cluster the component elements belonging to the same equipment, and aggregate the clustered elements into component graphic blocks; and cluster and connect the line elements based on the endpoint coordinates of the line elements to obtain continuous line objects belonging to the same electrical line.

[0087] The digital conversion device for distribution network drawings provided in this application, employing the digital conversion method for distribution network drawings in the above embodiments, can solve the technical problem of low automatic conversion efficiency of distribution network drawings due to the inability to directly convert them into power grid calculation topology models for engineering applications. Compared with the prior art, the beneficial effects of the digital conversion device for distribution network drawings provided in this application are the same as those of the digital conversion method for distribution network drawings provided in the above embodiments, and other technical features in the digital conversion device for distribution network drawings are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0088] This application provides a digital conversion device for power distribution network drawings. The digital conversion device for power distribution network drawings includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the digital conversion method for power distribution network drawings in the above embodiment 1.

[0089] The following is for reference. Figure 6 The diagram illustrates a structural schematic of a digital conversion device suitable for implementing power distribution network drawings in the embodiments of this application. The digital conversion device for power distribution network drawings in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 6 The digital conversion device shown in the power distribution network drawing is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0090] like Figure 6As shown, the digital conversion device for power distribution network drawings may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the digital conversion device for power distribution network drawings. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the digital conversion device for power distribution network drawings to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows digital conversion devices for power distribution network drawings with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0091] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0092] The digital conversion device for distribution network drawings provided in this application, employing the digital conversion method for distribution network drawings in the above embodiments, can solve the technical problem of low automatic conversion efficiency of distribution network drawings due to the inability to directly convert them into power grid calculation topology models for engineering applications. Compared with the prior art, the beneficial effects of the digital conversion device for distribution network drawings provided in this application are the same as those of the digital conversion method for distribution network drawings provided in the above embodiments, and other technical features in this digital conversion device for distribution network drawings are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0093] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0094] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included 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.

[0095] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the digital conversion method of power distribution network drawings in the above embodiments.

[0096] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0097] The aforementioned computer-readable storage medium may be included in the digital conversion device for power distribution network drawings; or it may exist independently and not be assembled into the digital conversion device for power distribution network drawings.

[0098] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the digital conversion device for power distribution network drawings, enable the digital conversion device for power distribution network drawings to implement the aforementioned digital conversion method for power distribution network drawings.

[0099] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0100] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0101] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0102] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the digital conversion method for distribution network drawings described above. This solves the technical problem that distribution network drawings cannot be directly converted into power grid calculation topology models for engineering applications, resulting in low efficiency in the automatic conversion of distribution network drawings. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the digital conversion method for distribution network drawings provided in the above embodiments, and will not be repeated here.

[0103] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the digital conversion method for power distribution network drawings as described above.

[0104] The computer program product provided in this application can solve the technical problem that distribution network drawings cannot be directly converted into power grid calculation topology models for engineering applications, resulting in low efficiency of automatic conversion of distribution network drawings. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the digital conversion method for distribution network drawings provided in the above embodiments, and will not be repeated here.

[0105] The above description is only a part of the embodiments of this application and does not limit the scope of protection of this application. All equivalent structural transformations made under the technical concept of this application and using the content of this application specification and drawings, or direct / indirect applications in other related technical fields, are included in the scope of protection of this application.

Claims

1. A method for digital conversion of power distribution network drawings, characterized in that, The method includes: After obtaining the power distribution network drawing, the drawing is parsed to extract all graphic element information. Based on the graphic element information, the graphic elements in the power distribution network drawing are classified and aggregated to obtain component graphic blocks and line objects; Based on a preset feature matching model, the component category of the component graphic block is identified, and the attribute information of the component graphic block and the line object is simultaneously labeled based on preset drawing rules. Based on the component type and the attribute information, a structured and attribute-complete power distribution network topology diagram is constructed, which includes the component graphic blocks and the line objects.

2. The method as described in claim 1, characterized in that, The step of identifying the component category of the component graphic block based on a preset feature matching model includes: Based on a preset feature matching model, the feature vector of the component graphic block is extracted; The feature vector is matched with the standard features in the power grid standard legend library to identify the component category of the component graphic block.

3. The method as described in claim 2, characterized in that, The step of extracting the feature vector of the component graphic block based on the preset feature matching model includes: Render the component graphic block into a standardized image; Based on a preset feature matching model, the standardized image is mapped into a feature vector in the feature space; The feature matching model is trained based on metric learning, which makes the feature vectors corresponding to component graphic blocks belonging to the same device category closer together in the feature space, while the feature vectors of different device categories are further apart.

4. The method as described in claim 2, characterized in that, The step of annotating the attribute information of the component graphic blocks and the line objects based on preset drawing rules includes: Traverse each of the component graphic blocks and the line objects to obtain the original line type, original color and original layer information; Query the multidimensional attributes that correspond to the original line type, the original color, and the original layer information from the preset drawing rules; The multidimensional attributes are labeled as attribute information of the component graphic block and the line object.

5. The method as described in claim 1, characterized in that, The step of constructing a structured and attribute-complete distribution network topology diagram containing the component graphic blocks and the line objects based on the component type and the attribute information includes: Based on the component type, a geometric analysis is performed on the component graphic block to obtain the outer envelope of the component image block; Based on the attribute information, endpoint and intersection analysis is performed on the line object to determine the connection relationship between each outer envelope; Based on the connection relationship, a structured and attribute-complete power distribution network topology diagram is constructed, which includes the component graphic blocks and the line objects.

6. The method as described in claim 5, characterized in that, The step of constructing a structured and attribute-complete distribution network topology diagram containing the component graphic blocks and the line objects based on the connection relationships includes: The component graphic block is instantiated as a graph node, and the graph node contains the corresponding component type and attribute information; The lines between the line objects are instantiated as graph edges, and the graph edges contain corresponding attribute information; Based on the connection relationship, the graph nodes and graph edges are connected to obtain a structured and attribute-complete distribution network topology graph.

7. The method as described in claim 1, characterized in that, The step of classifying and aggregating the graphic elements in the power distribution network drawing based on the graphic element information to obtain component graphic blocks and line objects includes: Based on preset layer naming rules, geometric features of graphic elements, line types and graphic element information, the graphic elements in the power distribution network drawings are divided into component graphic elements and line graphic elements; Cluster the component elements belonging to the same equipment, and then aggregate the clustered elements into component graphic blocks; Based on the endpoint coordinates of the line elements, the line elements are clustered and connected to obtain continuous line objects belonging to the same electrical line.

8. A digital conversion device for power distribution network drawings, characterized in that, The device includes: The extraction module is used to parse the obtained power distribution network drawing after obtaining it, and extract all the graphic element information in the power distribution network drawing; The aggregation module is used to classify and aggregate the graphic elements in the power distribution network drawing based on the graphic element information to obtain component graphic blocks and line objects; The annotation module is used to identify the component category of the component graphic block based on a preset feature matching model, and simultaneously annotate the attribute information of the component graphic block and the line object based on preset drawing rules. The construction module is used to construct a structured and attribute-complete power distribution network topology diagram containing the component graphic blocks and the line objects based on the component type and the attribute information.

9. A digital conversion device for power distribution network drawings, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the digital conversion method for power distribution network drawings as claimed in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the digital conversion method for power distribution network drawings as described in any one of claims 1 to 7.

Images