SIFT algorithm-based power distribution network intelligent mapping method and system, and medium

Abstract

The invention discloses a power distribution network intelligent mapping method and system based on an SIFT algorithm, and a medium. Relates to the technical field of power distribution network three-dimensional modeling. According to the scheme, the method is improved on the basis of the prior art, the two-dimensional feature data are extracted from the two-dimensional design drawing, the three-dimensional design drawing of the power distribution network is mapped by combining the two-dimensional feature data and the mapping rule, the problem of grade crossing of the power distribution lines is fundamentally solved, and the power distribution network design drawing is more accurate. Two-dimensional feature data (such as equipment height and line stacking relation) in a two-dimensional diagram are extracted through an SIFT algorithm, a real three-dimensional topological model is generated through mapping and rendering, artificial experience dependence is converted into algorithm execution, and double rise of design efficiency and quality is achieved; the core technical advantage of the method is that three-dimensional space resources are used for replacing the wiring freedom degree, and a brand new solution path is opened up for the field of intelligent drawing output.

Description

Technical Field

[0001] The present invention relates to the technical field of three-dimensional modeling of distribution networks, and in particular to a method, system and medium for intelligently generating a distribution network map based on a SIFT algorithm. Background Art

[0002] With the advancement of smart grid construction, the need for digital and intelligent distribution network planning, design, and operation and maintenance is becoming increasingly urgent. As the core foundational data for planning, design, construction, and operation and maintenance, the efficiency and accuracy of distribution network electrical wiring diagrams (hereinafter referred to as "drawings") directly impact the progress and quality of grid construction.

[0003] Currently, various intelligent drawing software or systems are widely used within the industry, aiming to leverage computer technology to automate or semi-automatically generate distribution network drawings. These methods typically utilize spatial coordinate information, topological connectivity, and pre-defined drawing rules to automatically layout device symbols and draw line connections.

[0004] However, existing intelligent mapping methods still face significant technical bottlenecks in practical applications, mainly in the wiring of distribution lines: Line crossing and overlapping are prominent issues: During the automatic drawing generation process, especially in areas with densely distributed equipment and complex network structures (such as urban core areas and industrial parks), the automatically drawn distribution lines (such as feeders and tie lines) are prone to numerous unnecessary crossings and overlaps. This crossing and overlapping not only leads to a confusing layout and significantly reduces readability, but more importantly, it obscures the actual route and connection relationships of the lines, making it highly likely that the viewer will misinterpret the drawings.

[0005] Manual verification and adjustment are labor-intensive: To address the aforementioned overlapping and crossing line issues, ensure that the drawings are clear, accurately reflect the actual network structure, and comply with industry drafting standards, the generated drawings typically require a large number of professional designers to manually visually verify, identify conflicting areas, and manually adjust the wiring paths. This process is often tedious and time-consuming, requiring designers to have extensive experience, identify conflicting points one by one, and repeatedly try different wiring solutions to avoid overlapping and crossing lines. This not only greatly reduces the overall efficiency of drawing production and prolongs project cycles, but also significantly increases labor costs, becoming a key obstacle to the maximum effectiveness of intelligent drawing technology.

[0006] Therefore, while existing technologies have achieved a certain degree of automation in diagram generation, they are significantly deficient in optimizing line layouts and avoiding overlaps in complex scenarios. This leads to high costs for subsequent manual intervention and fails to achieve truly efficient, high-quality, one-click intelligent diagram generation. A new intelligent distribution network diagram generation method is urgently needed that can more intelligently optimize distribution line routing, effectively reduce or even eliminate unnecessary overlaps, and thus significantly reduce the workload of manual verification and adjustment. Summary of the Invention

[0007] The technical problem to be solved by the present invention is that although the existing technology has achieved automation in drawing to a certain extent, it has obvious deficiencies in optimizing line layouts and avoiding intersections and overlaps in complex scenarios, resulting in high costs for subsequent manual intervention and failure to truly achieve efficient and high-quality "one-click" intelligent drawing. The purpose of the present invention is to provide a distribution network intelligent drawing method, system and medium based on the SIFT algorithm, and to improve the method on the basis of the existing technology. This solution extracts two-dimensional feature data from the two-dimensional design drawing, combines the two-dimensional feature data and the drawing rules to map out a three-dimensional design drawing of the distribution network, and fundamentally solves the problem of intersection and overlap of distribution lines. The SIFT algorithm (based on the scale-invariant feature transformation algorithm) is used to extract two-dimensional feature data (such as equipment height and line stacking relationship) in the two-dimensional drawing, and maps and renders a real three-dimensional topology model, which converts manual experience dependence into algorithm execution, and achieves a double leap in design efficiency and quality. Its core technical advantage lies in using three-dimensional space resources in exchange for wiring freedom, opening up a new solution path for the field of intelligent drawing.

[0008] The present invention is achieved through the following technical solutions: This solution provides a distribution network intelligent mapping method based on the SIFT algorithm, including: Constructing drawing rules and 2D design drawings for distribution network design projects; Extracting two-dimensional feature data from the two-dimensional design drawing based on the SIFT algorithm, and mapping the three-dimensional design drawing of the distribution network by combining the two-dimensional feature data and the mapping rules; The three-dimensional design drawing of the distribution network is rendered and standardized to generate a three-dimensional design drawing of the distribution network.

[0009] A further optimization solution is that the drawing rules include: drawing element drawing rules, drawing frame drawing rules, drawing description drawing rules and legend drawing rules; The graphic element is the graphic expression information of each distribution network device in the three-dimensional design diagram of the distribution network; the graphic element drawing rule includes constructing graphic elements composed of different surfaces, points and lines based on a digital differential analyzer; The drawing frame is the basic file information in the distribution network three-dimensional design drawing; the drawing rule of the drawing frame includes: loading the drawing frame when generating the distribution network three-dimensional design drawing, and arranging the drawing frame in the free position in the distribution network three-dimensional design drawing; The drawing description is textual description information in the three-dimensional design drawing of the distribution network; the drawing description drawing drawing rule includes: constructing the drawing description based on the first common information; the first common information includes repeated information in the textual description information; The legend is the graphic expression information of electrical equipment and ancillary facilities; the legend drawing rules include: constructing an ancillary facilities legend based on the second common information, and obtaining three-dimensional information of the electrical equipment legend and the ancillary facilities legend based on the orthogonal projection method; the second common information includes repeated information in the graphic expression information.

[0010] A further optimization solution is to use a digital differential analyzer to construct the vertical coordinates of the graph element: ; Where: k F Indicates the number of intervals of the digital differential analyzer; x P represents the horizontal coordinate of the digital differential analyzer; c P Represents the slope of the digital differential analyzer of the graph element.

[0011] A further optimization scheme is that the three-dimensional information of the electrical equipment legend and the auxiliary facility legend is obtained based on the orthogonal projection method; including the following method: Project point A in the three-dimensional space of the electrical equipment legend or auxiliary facilities legend orthogonally onto plane B in any direction, and express point A with the three-dimensional vector of plane B: ; in, b Represents the three-dimensional vector value of point A; e Represents the plane normal vector of the electrical equipment legend or auxiliary facility legend; represents the dot product of the vectors; r S Represents point A represented by a three-dimensional vector in plane B.

[0012] A further optimization scheme is that the two-dimensional feature data is extracted from the two-dimensional design drawing based on the SIFT algorithm, including the following method: Construct a Gaussian pyramid to perform repeated Gaussian blurring on the two-dimensional design image. The Gaussian function G u for: ; Among them, x o and y o Respectively represent the horizontal and vertical coordinates of the original point of the element, frame, drawing description or legend in the two-dimensional design drawing; i and yi They represent the horizontal and vertical coordinates of the edge points of the primitives, frames, drawing descriptions or legends in the two-dimensional design drawings respectively; δ is the kernel function, and all edge points use the same kernel function; π is pi; exp() represents the natural exponential function; Extract the two-dimensional feature data F according to the Gaussian blur result u : Among them, H u Represents the original information of the two-dimensional design of the distribution network; Statistical analysis of the image difference DOG after Gaussian blurring of the two-dimensional design image, and search for the local extreme value of the two-dimensional design image Q u : ; in, E ( x,y ) represents the scale-variable Gaussian function of the two-dimensional design drawing; x, y represent the abscissa and ordinate of the two-dimensional feature data; λ represents the image difference DOG function of the two-dimensional design drawing.

[0013] A further optimization scheme is to map out a three-dimensional design diagram of the distribution network by combining the two-dimensional feature data and the drawing rules; including the following method: Local extreme value of two-dimensional design graph Q u As the boundary, the three-dimensional mapping of two-dimensional feature data is carried out by combining the mapping rules: ; Where: Represents three-dimensional mapping result data; x and y represents two-dimensional feature data; k represents the data for the formulation of three-dimensional design drawing rules; cosa Represents the cosine function of converting two-dimensional feature data into three-dimensional data; sina Represents the sine function of converting two-dimensional feature data into three-dimensional data; a Indicates the projection angle when mapping a 2D design drawing.

[0014] A further optimization solution is that the method for obtaining the three-dimensional design drawing of the distribution network includes: Grid the three-dimensional design diagram of the distribution network and determine the number of renderings N and the number of color curves M; the color curve is composed of grid vertices; Calculate the coloring selection probability of each color curve, and determine the grid vertex color based on the coloring selection probability of the color curve; Renders each mesh according to its vertex colors.

[0015] A further optimization solution is that the method for determining the mesh vertex color includes: Mesh vertex color z C Determined according to the following formula: ; ; in, It represents the probability that the color curve j in the three-dimensional design diagram of the distribution network jumps to the adjacent grid; C j represents the actual color of color curve j; w i Indicates the similarity between the previous grid vertex and the next grid vertex in the three-dimensional design diagram of the distribution network; w i Determines the direction in which the mesh rendering moves forward; l i represents the jump probability of grid i vertex in the three-dimensional design diagram of the distribution network; w j It represents the acceptance similarity between different grid vertices in the three-dimensional design diagram of the distribution network; n represents the total number of grids; p represents the total number of grid vertices.

[0016] This solution also provides a distribution network intelligent mapping system based on the SIFT algorithm, which is used to implement the above-mentioned distribution network intelligent mapping method based on the SIFT algorithm; the system includes: Construction module, used to construct drawing rules and two-dimensional design drawings for distribution network design projects; A mapping module is used to extract two-dimensional feature data from the two-dimensional design drawing based on the SIFT algorithm, and map the three-dimensional design drawing of the distribution network by combining the two-dimensional feature data and the mapping rules; The rendering module is used to render and standardize the three-dimensional design drawing of the distribution network to generate a three-dimensional design drawing of the distribution network.

[0017] This solution also provides a computer-readable medium on which a computer program is stored. The computer program is executed by a processor to implement the above-mentioned distribution network intelligent mapping method based on the SIFT algorithm.

[0018] Compared with the prior art, the present invention has the following advantages and beneficial effects: 1. The present invention provides a method, system and medium for intelligent distribution network mapping based on the SIFT algorithm. This solution improves on the existing technology in terms of method. By extracting two-dimensional feature data from the two-dimensional design drawing, and combining the two-dimensional feature data with the mapping rules to map the three-dimensional design drawing of the distribution network, it fundamentally solves the problem of plane intersection of distribution lines. The SIFT algorithm (based on the scale-invariant feature transformation algorithm) is used to extract two-dimensional feature data (such as equipment height and line stacking relationship) in the two-dimensional drawing, and then maps and renders it to generate a real three-dimensional topology model, transforming the reliance on manual experience into algorithm execution, thereby achieving a double leap in design efficiency and quality. Its core technical advantage lies in exchanging three-dimensional space resources for wiring freedom, opening up a new solution path for the field of intelligent mapping.

[0019] 2. The present invention provides a method, system and medium for intelligent distribution network mapping based on the SIFT algorithm; the SIFT algorithm (based on the scale-invariant feature transformation algorithm) is used to perform intelligent distribution network mapping, effectively analyzing local information in the distribution network design image, thereby avoiding the wiring cross-overlap problem in the conversion of two-dimensional drawings to three-dimensional images, realizing standardized management of distribution network engineering elements, and realizing intelligent conversion of two-dimensional distribution network design to three-dimensional images. The automatically formed distribution network graphics have the characteristics of small errors and high mapping accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required for use in the examples. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be considered as limiting the scope. A person of ordinary skill in the art can also derive other relevant drawings based on these drawings without inventive effort. In the drawings: Figure 1 This is a flow chart of the intelligent mapping method for distribution networks based on the SIFT algorithm; Figure 2 This is a schematic diagram of the intelligent mapping principle of the distribution network based on the SIFT algorithm; Figure 3 This is a structural diagram of the distribution network intelligent mapping system based on the SIFT algorithm. DETAILED DESCRIPTION

[0021] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with examples and drawings. The exemplary embodiments of the present invention and their descriptions are only used to explain the present invention and are not intended to limit the present invention.

[0022] Although the existing technology has achieved the automation of distribution network mapping to a certain extent, it has obvious shortcomings in optimizing line layouts and avoiding overlaps in complex scenarios, resulting in high costs for subsequent manual intervention and failing to truly achieve efficient and high-quality "one-click" intelligent mapping. In view of this, this solution provides the following embodiments to solve the above technical problems.

[0023] Example 1 This embodiment provides a method for intelligently generating a distribution network map based on the SIFT algorithm. Figure 1 and Figure 2 Shown, including: Step 1: Construct the drawing rules and 2D design drawings for the distribution network design project. Different distribution network design units have different habits for intelligent 3D drawing. To improve the quality of distribution network intelligent drawing, it is necessary to customize the 3D design drawing rules. The drawing rules include: element drawing rules, frame drawing rules, drawing description drawing rules, and legend drawing rules. The graphic elements are the graphical expression information of each distribution network equipment in the three-dimensional distribution network design diagram; the distribution network graphic element drawing rules include constructing graphic elements composed of different surface, point and line graphics based on the digital differential analyzer; the graphic elements in the distribution network design include vacuum circuit breakers, voltage transformers, current transformers, grounding switches, disconnectors, lightning arresters and other types.

[0024] Specifically, the vertical coordinate of the graph element constructed by the digital differential analyzer is: ; Where: k F Indicates the number of intervals of the digital differential analyzer; x P represents the horizontal coordinate of the digital differential analyzer; c P Represents the slope of the digital differential analyzer. The digital differential analyzer samples the line segments in the coordinate system of the distribution network design diagram at unit intervals and obtains the corresponding value of the coordinate axis closest to the distribution network design line path.

[0025] The drawing frame is the basic file information in the distribution network three-dimensional design drawing; the drawing rule of the drawing frame includes: loading the drawing frame when generating the distribution network three-dimensional design drawing, and arranging the drawing frame in the free position in the distribution network three-dimensional design drawing; The drawing frame includes the name of the distribution network project, the name of the distribution network design drawing, the file version number, the compilation date and other information; The drawing description is textual description information in the three-dimensional design drawing of the distribution network; the drawing description drawing generation rule includes: constructing the drawing description based on the first common information; the first common information includes repeated information in the textual description information; In distribution network design projects, the repetition rate of text description information is relatively high. Therefore, customizing the common information in the distribution network design will help improve the speed of intelligent distribution network drawing.

[0026] The legend is the graphic expression information of electrical equipment and ancillary facilities; the legend drawing rules include: constructing an ancillary facilities legend based on the second common information, and obtaining three-dimensional information of the electrical equipment legend and the ancillary facilities legend based on the orthogonal projection method; the second common information includes repeated information in the graphic expression information.

[0027] Ancillary facilities include information such as roads and buildings in the distribution network design and civil engineering. During intelligent distribution network mapping, there are typically two types of legends: electrical equipment legends and ancillary facilities legends. The electrical equipment legend is related to the equipment manufacturer and changes frequently. The ancillary facilities legend, which includes information such as roads and buildings in the distribution network design and civil engineering, changes less frequently. For both types of legends, orthogonal projection is used to obtain 3D information.

[0028] Obtaining three-dimensional information of electrical equipment legends and auxiliary facilities legends based on orthogonal projection; including methods: Project point A in the three-dimensional space of the electrical equipment legend or auxiliary facilities legend orthogonally onto plane B in any direction, and express point A with the three-dimensional vector of plane B: ; in, b Represents the three-dimensional vector value of point A; e Represents the plane normal vector of the electrical equipment legend or auxiliary facility legend; represents the dot product of the vectors; r S Represents point A represented by a three-dimensional vector in plane B.

[0029] The orthogonal projection method projects a point in the three-dimensional space of the distribution network legend onto a plane along one direction, and uses the three-dimensional vector of the plane to represent a point in the three-dimensional distribution network diagram.

[0030] Step 2: extracting two-dimensional feature data from the two-dimensional design drawing based on the SIFT algorithm, and mapping the three-dimensional design drawing of the distribution network by combining the two-dimensional feature data and the drawing rules; this step specifically includes the following method: Construct a Gaussian pyramid to perform repeated Gaussian blurring on the two-dimensional design image. The Gaussian function G u for: ; Among them, x o and y o Respectively represent the horizontal and vertical coordinates of the original point of the element, frame, drawing description or legend in the two-dimensional design drawing; i and y iThey represent the horizontal and vertical coordinates of the edge points of the primitives, frames, drawing descriptions or legends in the two-dimensional design drawings respectively; δ is the kernel function, and all edge points use the same kernel function; π is pi; exp() represents the natural exponential function; Extract the two-dimensional feature data F according to the Gaussian blur result u : Among them, H u Represents the original information of the two-dimensional design of the distribution network; Statistical analysis of the image difference DOG after Gaussian blurring of the two-dimensional design image, and search for the local extreme value of the two-dimensional design image Q u : ; in, E ( x,y ) represents the scale-variable Gaussian function of the two-dimensional design drawing; x, y represent the abscissa and ordinate of the two-dimensional feature data; λ represents the image difference DOG function of the two-dimensional design drawing.

[0031] The method of mapping a three-dimensional design diagram of a distribution network by combining two-dimensional feature data and drawing rules includes: Local extreme value of two-dimensional design graph Q u As the boundary, the three-dimensional mapping of two-dimensional feature data is carried out by combining the mapping rules: ; Where: Represents three-dimensional mapping result data; x and y represents two-dimensional feature data; k represents the data for the formulation of three-dimensional design drawing rules; cosa Represents the cosine function of converting two-dimensional feature data into three-dimensional data; sina Represents the sine function of converting two-dimensional feature data into three-dimensional data; a Indicates the projection angle when mapping a 2D design drawing.

[0032] After the two-dimensional design of the distribution network is completed, the graphics elements, legends, frames and drawing description information need to be effectively read to avoid data information loss when converting two-dimensional drawings into three-dimensional images; the SIFT algorithm is a machine vision image feature information extraction method that can effectively analyze local information in the distribution network design image, thereby avoiding the problem of wiring cross-overlap when converting two-dimensional drawings into three-dimensional images.

[0033] Step three: Rendering and standardizing the three-dimensional design drawing of the distribution network to generate a three-dimensional design drawing of the distribution network.

[0034] The data after mapping the 3D image of the distribution network design project is a frame line diagram. To make the 3D image of the distribution network design project more intuitive, color rendering is performed after conversion to a 3D image. Grid rendering is a 3D image coloring method for the distribution network design project. Simply by guiding the surface of the 3D image of the distribution network design project, the colors of various graphic elements and legends can be colored. Therefore, this solution uses the grid coloring method to color the distribution network design image. Specifically, the method for obtaining the 3D design drawing of the distribution network includes: S31, meshing the three-dimensional design drawing of the distribution network, determining the number of renderings N and the number of color curves M; wherein the color curve is composed of mesh vertices; specifically, determining the number of renderings based on the edge lines of the primitives; and confirming the number of color curves based on the number of shapes composed of the edge lines of the primitives.

[0035] S32, calculate the coloring selection probability of each color curve, and determine the grid vertex color according to the coloring selection probability of the color curve; the grid vertex color z C Determined according to the following formula: ; ; in, It represents the probability that the color curve j in the three-dimensional design diagram of the distribution network jumps to the adjacent grid; C j represents the actual color of color curve j; w i Indicates the similarity between the previous grid vertex and the next grid vertex in the three-dimensional design diagram of the distribution network; w i Determines the direction in which the mesh rendering moves forward; l i represents the jump probability of grid vertex i in the three-dimensional design diagram of the distribution network; w k It represents the acceptance similarity between different grid vertices in the three-dimensional design diagram of the distribution network; n represents the total number of grids; p represents the total number of grid vertices.

[0036] S33, performing color rendering on each mesh according to the mesh vertex color.

[0037] After color rendering, the model selects the blank area in the distribution network design 3D image, automatically loads the drawing frame and drawing description information, and outputs the complete distribution network design 3D image through the application programming interface.

[0038] Example 2 This embodiment provides a distribution network intelligent mapping system based on the SIFT algorithm, characterized in that it is used to implement the distribution network intelligent mapping method based on the SIFT algorithm described in Example 1; the system includes: Construction module, used to construct drawing rules and two-dimensional design drawings for distribution network design projects; A mapping module is used to extract two-dimensional feature data from the two-dimensional design drawing based on the SIFT algorithm, and map the three-dimensional design drawing of the distribution network by combining the two-dimensional feature data and the mapping rules; The rendering module is used to render and standardize the three-dimensional design drawing of the distribution network to generate a three-dimensional design drawing of the distribution network.

[0039] Example 3 This embodiment provides a computer-readable medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the method for intelligently generating a distribution network map based on the SIFT algorithm as described in Example 1; Figure 1 and Figure 2 As shown, perform the following steps: Step 1: Construct the drawing rules and two-dimensional design drawings of the distribution network design project; the distribution network intelligent drawing process first customizes the drawing standards according to the element type of the distribution network design project to meet the requirements of three-dimensional design drawing; secondly, customize the drawing frames and drawing descriptions in the design drawings to display the drawing frames and description information in the three-dimensional engineering design drawings; finally, customize the legend of the distribution network design project according to the projection method.

[0040] Step 2: Extract two-dimensional feature data from the two-dimensional design drawing based on the SIFT algorithm, and map the three-dimensional design drawing of the distribution network by combining the two-dimensional feature data and the drawing rules; read the feature information of the two-dimensional design drawing through the SIFT algorithm, and map the two-dimensional design drawing into a three-dimensional design drawing of the distribution network through the three-dimensional graphic mapping technology in combination with the three-dimensional design drawing rules.

[0041] Step three: Render and standardize the distribution network three-dimensional design drawing to generate a distribution network three-dimensional design drawing; obtain a colored three-dimensional image by color rendering and labeling the distribution network three-dimensional design image, standardize it, and output the distribution network three-dimensional design drawing.

[0042] The above-mentioned embodiments 1-3 make methodological improvements based on the existing technology. By extracting two-dimensional feature data from the two-dimensional design drawing, combining the two-dimensional feature data and the drawing rules to map out the three-dimensional design drawing of the distribution network, the problem of plane intersection of distribution lines is fundamentally solved. The two-dimensional feature data (such as equipment height and line stacking relationship) in the two-dimensional drawing is extracted through the SIFT algorithm, and the real three-dimensional topology model is mapped and rendered. The reliance on manual experience is converted into algorithm execution, achieving a double leap in design efficiency and quality. Its core technical advantage lies in using three-dimensional space resources in exchange for wiring freedom, opening up a new solution path for the field of intelligent drawing.

[0043] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. The intelligent distribution network mapping method based on SIFT algorithm is characterized by: include: Constructing drawing rules and 2D design drawings for distribution network design projects; Extracting two-dimensional feature data from the two-dimensional design drawing based on the SIFT algorithm, and mapping the three-dimensional design drawing of the distribution network by combining the two-dimensional feature data and the mapping rules; The three-dimensional design drawing of the distribution network is rendered and standardized to generate a three-dimensional design drawing of the distribution network.

2. The method for intelligently generating a distribution network map based on the SIFT algorithm according to claim 1, characterized in that: The drawing rules include: drawing element drawing rules, drawing frame drawing rules, drawing description drawing rules and legend drawing rules; The graphic element is the graphic expression information of each distribution network device in the three-dimensional design diagram of the distribution network; the graphic element drawing rule includes constructing graphic elements composed of different surfaces, points and lines based on a digital differential analyzer; The drawing frame is the basic file information in the distribution network three-dimensional design drawing; the drawing rule of the drawing frame includes: loading the drawing frame when generating the distribution network three-dimensional design drawing, and arranging the drawing frame in the free position in the distribution network three-dimensional design drawing; The drawing description is textual description information in the three-dimensional design drawing of the distribution network; the drawing description drawing drawing rule includes: constructing the drawing description based on the first common information; the first common information includes repeated information in the textual description information; The legend is the graphic expression information of electrical equipment and ancillary facilities; the legend drawing rules include: constructing an ancillary facilities legend based on the second common information, and obtaining three-dimensional information of the electrical equipment legend and the ancillary facilities legend based on the orthogonal projection method; the second common information includes repeated information in the graphic expression information.

3. The method for intelligently generating a distribution network map based on the SIFT algorithm according to claim 2, characterized in that: The vertical coordinates of the graph element constructed by the digital differential analyzer are: ； Where: k F Indicates the number of intervals of the digital differential analyzer; x P represents the horizontal coordinate of the digital differential analyzer; c P represents the slope of the digital differential analyzer of the graph element; Indicates the vertical coordinate of the primitive.

4. The method for intelligently generating a distribution network map based on the SIFT algorithm according to claim 2, characterized in that: The three-dimensional information of the electrical equipment legend and the auxiliary facilities legend is obtained based on the orthogonal projection method; Includes methods: Project point A in the three-dimensional space of the electrical equipment legend or auxiliary facilities legend orthogonally onto plane B in any direction, and express point A with the three-dimensional vector of plane B: ； in, b Represents the three-dimensional vector value of point A; e Represents the plane normal vector of the electrical equipment legend or auxiliary facility legend; represents the dot product of the vectors; r S Represents point A represented by a three-dimensional vector in plane B.

5. The method for intelligently generating a distribution network map based on the SIFT algorithm according to claim 1, characterized in that: The method of extracting two-dimensional feature data from the two-dimensional design drawing based on the SIFT algorithm includes: Construct a Gaussian pyramid to perform repeated Gaussian blurring on the two-dimensional design image. The Gaussian function G u for: ； Among them, x o and y o Respectively represent the horizontal and vertical coordinates of the original point of the element, frame, drawing description or legend in the two-dimensional design drawing; i and y i They represent the horizontal and vertical coordinates of the edge points of the primitives, frames, drawing descriptions or legends in the two-dimensional design drawings respectively; δ is the kernel function, and all edge points use the same kernel function; π is pi; exp() represents the natural exponential function; Extract the two-dimensional feature data F according to the Gaussian blur result u : Among them, H u Represents the original information of the two-dimensional design of the distribution network; Statistical analysis of the image difference DOG after Gaussian blurring of the two-dimensional design image, and search for the local extreme value of the two-dimensional design image Q u : ； in, E ( x,y ) represents the scale-variable Gaussian function of the two-dimensional design drawing; x, y represent the abscissa and ordinate of the two-dimensional feature data; λ represents the image difference DOG function of the two-dimensional design drawing.

6. The method for intelligently generating a distribution network map based on the SIFT algorithm according to claim 5, characterized in that: The three-dimensional design diagram of the distribution network is mapped out by combining the two-dimensional feature data and the drawing rules; method: Local extreme value of two-dimensional design graph Q u As the boundary, the three-dimensional mapping of two-dimensional feature data is carried out by combining the mapping rules: ； Where: Represents three-dimensional mapping result data; x and y Represents two-dimensional feature data; k represents the data for formulating the rules for 3D design drawing; cosa Represents the cosine function of converting two-dimensional feature data into three-dimensional data; sina Represents the sine function of converting two-dimensional feature data into three-dimensional data; a Indicates the projection angle when mapping a 2D design drawing.

7. The method for intelligently generating a distribution network map based on the SIFT algorithm according to claim 1, characterized in that: The method for obtaining the three-dimensional design drawing of the distribution network includes: Grid the three-dimensional design diagram of the distribution network and determine the number of renderings N and the number of color curves M; the color curve is composed of grid vertices; Calculate the coloring selection probability of each color curve, and determine the grid vertex color based on the coloring selection probability of the color curve; Renders each mesh according to its vertex colors.

8. The method for intelligently generating a distribution network map based on the SIFT algorithm according to claim 7, characterized in that: The method for determining the mesh vertex color includes: Mesh vertex color z C Determined according to the following formula: ； ； in, It represents the probability that the color curve j in the three-dimensional design diagram of the distribution network jumps to the adjacent grid; C j represents the actual color of color curve j; w i Indicates the similarity between the previous grid vertex and the next grid vertex in the three-dimensional design diagram of the distribution network; w i Determines the direction in which the mesh rendering moves forward; l i represents the jump probability of grid vertex i in the three-dimensional design diagram of the distribution network; w j It represents the acceptance similarity between different grid vertices in the three-dimensional design diagram of the distribution network; n represents the total number of grids; p represents the total number of grid vertices.

9. The intelligent distribution network mapping system based on SIFT algorithm is characterized by: A method for intelligently generating a distribution network map based on a SIFT algorithm according to any one of claims 1 to 8; the system comprises: Construction module, used to construct drawing rules and two-dimensional design drawings for distribution network design projects; A mapping module is used to extract two-dimensional feature data from the two-dimensional design drawing based on the SIFT algorithm, and map the three-dimensional design drawing of the distribution network by combining the two-dimensional feature data and the mapping rules; The rendering module is used to render and standardize the three-dimensional design drawing of the distribution network to generate a three-dimensional design drawing of the distribution network.

10. A computer-readable medium having a computer program stored thereon, characterized in that: The computer program is executed by a processor to implement the distribution network intelligent mapping method based on the SIFT algorithm as described in any one of claims 1 to 8.

Images