A method for processing digital twin data of a grounding power grid

Abstract

The present invention relates to a method for processing digital twin data of a grounding grid, characterized in that the method comprises the following steps: Step S1, obtaining the design and construction CAD drawings of the grounding grid and the coordinate drawings of each grounding wire in the grounding grid; Step S2, extracting the characteristic information of the grounding wires in the design and construction CAD drawings of the grounding grid and converting the characteristic information of the grounding wires into a 3D model; Step S3, determining the positioning data of the positioning points in the coordinate drawings of each grounding wire in the grounding grid through feature extraction algorithms and Hough detection; Step S4, merging the 3D model and the positioning data of the positioning points, and saving and outputting the 3D model corresponding to the complete grounding grid; Step S5, matching the position information of the excavation site with the points in the 3D model, so as to visually display the matched model data at the excavation site of the grounding grid. Compared with the prior art, the present invention has the advantages of greatly improving the modeling efficiency and the like.

Description

Technical Field

[0001] The present invention relates to a data processing method for a grounding power grid, and more particularly to a data processing method for digital twins of a grounding power grid. Background Art

[0002] The grounding grid is buried deep underground and is the only way for short-circuit and lightning current discharge. Local defects can threaten personal safety and cause equipment failures. The safety control of the grounding device in a substation is the basis for safe and reliable operation in the energy Internet and is also the key to ensuring the safety of equipment and personnel.

[0003] The construction and detection of the grounding grid mainly adopt the method of manual excavation. During the manual excavation process, it is usually impossible to accurately determine the actual positions of the respective grounding wires of the grounding grid. Therefore, only fixed-point excavation can be carried out, which leads to problems such as a large excavation area, a blind excavation process, and low grounding grid detection efficiency. Moreover, the grounding grid similar to the grounding of a transmission high-voltage line tower has certain particularities. Multiple grounding wires are interconnected underground through a ring network under the tower to form a grounding grid. In the detection of the grounding grid by conventional underground detection methods, there is a problem of signal interference between the respective grounding wires, resulting in difficulty in detecting the end of the grounding wire. Furthermore, during the detection and excavation process of the already built grounding grid, it is difficult to accurately position the grounding grid.

[0004] Therefore, for newly built or already built grounding devices, during the excavation process, it is impossible to accurately locate the positions of the respective grounding pipelines of the grounding grid, resulting in problems such as a large excavation area, a blind excavation process, low excavation efficiency, and even excavation accidents. Summary of the Invention

[0005] The purpose of the present invention is to overcome the above-mentioned defects existing in the prior art and provide a data processing method for digital twins of a grounding power grid, which greatly improves the modeling efficiency and can be quickly matched with the site in the GIS dimension, so as to achieve the accurate positioning of each grounding wire of the grounding grid at the excavation site through the visually displayed model.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] According to one aspect of the present invention, there is provided a data processing method for digital twins of a grounding power grid, the method comprising the following steps:

[0008] Step S1, obtaining the design and construction CAD drawings of the grounding grid and the coordinate drawings of each grounding wire in the grounding grid;

[0009] Step S2, extracting the characteristic information of the grounding wires in the design and construction CAD drawings of the grounding grid and converting the characteristic information of the grounding wires into a 3D model;

[0010] Step S3: Identify and perform Hough detection through a feature extraction algorithm to determine the positioning data of the positioning points of each grounding wire in the coordinate drawing of the grounding grid.

[0011] Step S4: Merge the 3D model and the positioning data of the positioning points, and save and output the complete 3D model corresponding to the grounding grid.

[0012] Step S5: Match the location information of the excavation site with the points in the 3D model, so as to visually display the matched model data at the excavation site of the grounding grid.

[0013] As a preferred technical solution, step S2 specifically includes:

[0014] Step S21: Extract the layer of the grounding wire and the layers of other key specialties from the design and construction CAD drawings of the grounding grid.

[0015] Step S22: Identify and extract the closed polygon structures in the extracted layers through image recognition, and use the information of the closed polygon structures as the feature information of the grounding wire.

[0016] Step S23: Automatically convert the feature information of the grounding wire extracted from the CAD drawings into a 3D model through a rapid modeling method.

[0017] As a preferred technical solution, the image recognition in step S22 uses a neural network model. The neural network model is trained through the target layer in the historical CAD drawings and the annotation information of the target layer, so that the trained neural network model can identify the closed polygon structures in the target layer, and use the information of the identified closed polygon structures as the feature information of the grounding wire.

[0018] As a preferred technical solution, the feature information in step S22 includes dimension information, shape information, and depth information.

[0019] As a preferred technical solution, the 3D model in step S23 is various types of building models.

[0020] As a preferred technical solution, the feature extraction algorithm ORB in step S3 is used to quickly create feature vectors for the key points in the image, and these feature vectors are used to identify the objects in the image.

[0021] As a preferred technical solution, the Hough detection in step S3 uses the Hough transform to convert the problem of detecting any shape into a problem of statistical peak value.

[0022] As a preferred technical solution, the Hough transform is to use the transformation between two coordinate spaces to map a curve or a straight line in one space to a point in another coordinate space to form a peak.

[0023] As a preferred technical solution, the recognition result in step S3 is saved in a JS object simple score configuration file, and the specific data of each positioning point and the position of each positioning point are saved in each configuration file to constitute the positioning data of the positioning point.

[0024] As a preferred technical solution, the position of the positioning point is represented by the coordinate information of the geographic information system.

[0025] Compared with the prior art, the present invention automates the modeling process and adds positioning information, greatly improving the modeling efficiency, and can quickly match with the site in the dimension of GIS, effectively and efficiently improving the use effect of digital assets, so as to realize the accurate positioning of each grounding wire of the grounding grid at the excavation site through the visually displayed model. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 is a schematic flow chart of the method for processing digital twin data of a grounding power grid in an embodiment of the present invention.

[0027] Figure 2 is a schematic diagram of the data model of the grounding power grid in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0029] Figure 1 is a schematic flow chart of the method for processing digital twin data of a grounding power grid in an embodiment of the present invention. As Figure 1 shown, the Figure 1 is a schematic flow chart of the method for processing digital twin data of a grounding power grid in an embodiment of the present invention, including steps S101-S104:

[0030] S101: Obtain the design and construction CAD drawings of the grounding grid and the coordinate drawings of each grounding wire in the grounding grid.

[0031] In practical applications, in order to facilitate rapid modeling, the layers of CAD drawings and additional interfering content should not be excessive. It is best to directly use the layers of the pipe network and there should be no interference from other specialties during the design process of the pipe network layers. Therefore, after obtaining the CAD drawings for the design and construction of the grounding grid, the number of layers in the CAD drawings for the design and construction of the grounding grid can be detected. If the number of layers is less than the preset number, it can be directly used. If the number of layers is greater than the preset number, additional processing of the CAD drawings for the design and construction of the grounding grid is required to remove the unnecessary layers.

[0032] Correspondingly, the coordinate drawings of each grounding wire in the grounding grid can also be detected to determine whether the coordinate data is missing or significantly abnormal. In addition, each coordinate point can also be detected to determine whether there is a unified and obvious structure for each coordinate point.

[0033] S102: Extract the characteristic information of the grounding wires in the CAD drawings for the design and construction of the grounding grid, and convert the characteristic information of the grounding wires into a 3D model.

[0034] Specifically, the layers of the grounding wires and the layers of the remaining key specialties can be extracted from the CAD drawings for the design and construction of the grounding grid first. Subsequently, through image recognition, the closed polygon structures in the extracted layers are recognized, and the information of the closed polygon structures is used as the characteristic information of the grounding wires. Finally, through rapid modeling, the characteristic information of the grounding wires extracted from the CAD drawings is automatically converted into a 3D model.

[0035] Among them, for image recognition, a common neural network model can be used. Through the target layers in the historical CAD drawings and the annotation information for the target layers, the neural network model is trained, so that the trained neural network model can recognize the closed polygon structures in the target layers, and the information of the recognized closed polygon structures is used as the characteristic information of the grounding wires.

[0036] Among them, the above-mentioned characteristic information can include dimension information, shape information, depth information, etc. Among them, the 3D model can be various types of building models. For example, Building Information Modeling (BIM).

[0037] Exemplarily, Figure 2 is a schematic diagram of the data model of the grounding grid in the embodiment of the present invention. As Figure 2 shown, it shows the routing and layout of each grounding wire in the grounding grid.

[0038] S103: Determine the positioning data of the positioning points in the coordinate drawing of each grounding wire in the grounding grid through the recognition method of the feature extraction algorithm (Oriented Fast and Rotated Brief, ORB) and Hough detection (Hough Transform).

[0039] Specifically, through the recognition method of ORB and Hough detection, determine the specific information and location of the positioning points of each grounding wire in the coordinate drawing of the grounding grid. Subsequently, through the image recognition method, judge the specific position of each positioning point in the coordinate drawing. The above recognition results can be saved in a JavaScript Object Notation (json) configuration file. Each configuration file will save the specific data of each positioning point and the location of each positioning point to form the positioning data of the positioning point.

[0040] Among them, the position of the above positioning points can be represented by the coordinate information of the Geographic Information System (GIS).

[0041] ORB recognition is used to quickly create feature vectors for key points in an image, and these feature vectors can be used to identify objects in the image. Hough detection is to use the Hough transform to convert the problem of detecting any shape into a problem of statistical peaks. The so-called Hough transform is to use the transformation between two coordinate spaces (usually the rectangular coordinate system and the polar coordinate system) to map a curve or a straight line in one space (rectangular coordinate system) to a point in another coordinate space (polar coordinate system) to form a peak.

[0042] Since the coordinate drawings used on site all use engineering coordinates, and in order to preserve digital assets, it is hoped to use longitude and latitude coordinates as a unique value to save the information of each point. Therefore, it is necessary to convert the engineering coordinates into BLH longitude and latitude coordinates by inverse calculation based on the base point for generating the engineering coordinates. The new BLH values obtained based on this conversion relationship will also be updated to the json configuration file obtained through recognition above. After that, through this configuration file, in the same way as in step two, a new BIM file with only the position point models of the positioning points is generated, and each point model has the attached parameter of the corresponding BLH.

[0043] S104: The two types of data in steps S102 and S103 are generated based on a unified coordinate system. Therefore, the two can be merged by simply superimposing them to achieve perfect registration. Thus, the 3D model obtained in step S102 and the positioning data of the positioning points obtained in step S103 can be merged, and the output 3D model corresponding to the complete grounding grid is saved.

[0044] S105: Match the location information of the excavation site with the points in the 3D model, so as to visually display the matched model data at the excavation site of the grounding grid. Among them, the visual display can include displaying the 3D model corresponding to the location of the excavation site through the AR interface of the terminal device.

[0045] As described above, the above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for processing digital twin data of a grounding power grid, characterized in that, The method includes the following steps: Step S1, obtaining the design and construction CAD drawings of the grounding grid and the coordinate drawings of each grounding wire in the grounding grid; Step S2, extracting the characteristic information of the grounding wires in the design and construction CAD drawings of the grounding grid, and converting the characteristic information of the grounding wires into a 3D model; Step S3, determining the positioning data of the positioning points in the coordinate drawings of each grounding wire in the grounding grid through feature extraction algorithms for recognition and Hough detection; Step S4, merging the 3D model and the positioning data of the positioning points, and saving and outputting the 3D model corresponding to the complete grounding grid; Step S5, matching the position information of the excavation site with the points in the 3D model, so as to visually display the matched model data at the excavation site of the grounding grid.

2. The processing method of digital twin data of a grounding power grid according to claim 1, wherein The specific steps of step S2 include: Step S21, extracting the layers of the grounding wires and the layers of the remaining key specialties from the design and construction CAD drawings of the grounding grid; Step S22, identifying and extracting the closed polygon structures in the extracted layers by means of image recognition, and using the information of the closed polygon structures as the characteristic information of the grounding wires; Step S23, automatically converting the characteristic information of the grounding wires extracted from the CAD drawings into a 3D model by means of rapid modeling.

3. The processing method of digital twin data of a grounding power grid according to claim 2, wherein The image recognition in step S22 adopts a neural network model, and the neural network model is trained through the target layers in the historical CAD drawings and the annotation information of the target layers, so that the trained neural network model can recognize the closed polygon structures in the target layers, and use the information of the recognized closed polygon structures as the characteristic information of the grounding wires.

4. A method for processing digital twin data of a grounding power grid according to claim 2, characterized in that The characteristic information in step S22 includes dimension information, shape information and depth information.

5. A method for processing digital twin data of a grounding power grid according to claim 2, characterized in that, The 3D model in step S23 is various types of building models.

6. The processing method of digital twin data of a grounding power grid according to claim 2, characterized in that, The feature extraction algorithm ORB in step S3 is used to quickly create feature vectors for the key points in the image, and these feature vectors are used to identify the objects in the image.

7. A method for processing digital twin data of a grounding power grid according to claim 2, characterized in that, The Hough detection in step S3 uses the Hough transform to convert the problem of detecting any shape into the problem of statistical peaks.

8. A method for processing digital twin data of a grounding power grid according to claim 7, characterized in that, The Hough transform is to use the transformation between two coordinate spaces to map the curves or straight lines in one space to a point in another coordinate space to form peaks.

9. The processing method of digital twin data of a grounding power grid according to claim 2, wherein, The recognition result in step S3 is saved in a JSON configuration file. Each configuration file will save the specific data of each positioning point and the position of each positioning point to form the positioning data of the positioning points.

10. A method for processing digital twin data of a grounding power grid according to claim 9, characterized in that, The position of the positioning point is represented by the coordinate information of the geographic information system.

Images