Combined gap calculation method fusing digital twin power grid and visual positioning

Abstract

The invention discloses a combination gap calculation method fusing a digital twin power grid and visual positioning, relates to the technical field of smart power grids, and solves the technical problem of inaccurate calculation result or low calculation efficiency when a combination gap of power grid equipment in a power grid is calculated by using a single technology in the prior art. The method comprises the following steps: preprocessing basic data to obtain structural data; constructing a digital twin power grid according to the structural data and the structural topological graph of the power grid equipment; acquiring a plurality of image data between adjacent power grid equipment; dividing the plurality of image data into a plurality of groups of adjustment images according to the device number of the power grid device; calling a position adjustment model, and sequentially inputting the adjustment images into the position adjustment model to obtain an actual distance between the power grid equipment; adjusting the position of power grid equipment in the digital twin power grid according to the actual distance, and calculating the adjusted combination gap; and the calculation accuracy and efficiency can be improved.

Description

Technical Field

[0001] The present invention belongs to the field of smart grids and relates to a combined gap calculation technology, specifically a combined gap calculation method that integrates digital twin grids and visual positioning. Background Art

[0002] Combined gap calculation mainly involves the process of quantifying the total gap after combining two or more gaps in series under specific circumstances; this calculation usually occurs in fields that require precise control of gap size, such as electrical engineering, mechanical engineering, etc.; the digital twin power grid is the future development form of the power grid in which the physical power grid in the physical dimension and the virtual power grid in the information dimension coexist and the virtual and real are integrated; it is to create a digital power grid in the digital space that matches the physical power grid, and through holographic simulation, dynamic monitoring, real-time diagnosis, accurate prediction and other technical means, reflect the status of the physical power grid in the real environment, and then promote the digitization and virtualization of all elements of the power grid, the real-time and visualization of all states, and the coordination and intelligence of power grid operation and management, so as to realize the coordinated interaction and parallel operation of the physical and digital power grids.

[0003] Existing technology uses digital twin models to build digital twin power grids and calculate the combined gaps of the power grids. When deviations occur in the power grid equipment in the digital twin power grid, the calculation results of the combined gaps will be inaccurate. The combined gaps of the power grid are calculated through visual positioning. There are a large number of power grid devices in the power grid, and the workload of performing a single calculation is large, which affects the efficiency of the calculation.

[0004] The present invention provides a combined gap calculation method that integrates digital twin power grid and visual positioning to solve the above technical problems. Summary of the Invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes a combined gap calculation method that integrates digital twin power grid and visual positioning, which is used to solve the technical problem that when the prior art uses a single technology to calculate the combined gap of power grid equipment in the power grid, the calculation results are inaccurate or the calculation efficiency is low.

[0006] To achieve the above objectives, the first aspect of the present invention provides a combined gap calculation method integrating digital twin power grid and visual positioning, comprising:

[0007] Step S1: Obtain a structural topology diagram of the power grid and basic data of power grid equipment; preprocess the basic data to obtain structural data; and construct a digital twin power grid based on the structural data and structural topology diagram of the power grid equipment. The basic data includes equipment number, appearance data, size data, and electrical parameters.

[0008] Step S2: using an image acquisition device to collect a plurality of image data between adjacent power grid devices; dividing the plurality of image data into a plurality of groups according to device numbers of the power grid devices and adjusting the images; wherein the device numbers of the power grid devices are set according to the locations of the power grid devices;

[0009] Step S3: calling a position adjustment model, inputting the adjustment images into the position adjustment model in sequence, and obtaining the actual distance between the power grid devices; wherein the position adjustment model is constructed based on an artificial intelligence model;

[0010] Step S4: Adjust the position of the grid equipment in the digital twin grid according to the actual distance, and calculate the adjusted combined gap.

[0011] Preferably, the preprocessing of basic data to obtain structural data includes:

[0012] Retrieve basic data and determine whether the basic data includes sub-data of all data types; if yes, retain the corresponding basic data; if not, complete the missing sub-data;

[0013] Determine whether the device numbers in the basic data are consistent. If yes, remove the duplicate or incorrect basic data; if not, retain the corresponding basic data.

[0014] The retained basic data and the completed basic data are marked as structural data.

[0015] The present invention analyzes the integrity of basic data, and when the basic data has missing sub-data of a data type, the missing sub-data is supplemented; the device numbers in the basic data are analyzed, and when repeated device numbers appear, the repeated or erroneous data are eliminated; the integrity and validity of the data can be guaranteed, which is conducive to improving the efficiency of data processing.

[0016] Preferably, the step of constructing a digital twin power grid based on the structural data and structural topology of power grid equipment includes:

[0017] Retrieve the structural data of the power grid equipment and the structural topology of the power grid; build a three-dimensional model of the power grid equipment based on the structural data; determine the connection mode and hierarchical relationship of each node in the power grid based on the structural topology;

[0018] Construct the power grid topology in the digital twin model; place the three-dimensional model of the power grid equipment at the corresponding position in the digital twin model to obtain the digital twin power grid.

[0019] The present invention constructs a three-dimensional model of the power grid equipment based on the structural data of the power grid equipment, and analyzes the connection mode and hierarchical relationship of the power grid according to the structural topology diagram of the power grid to construct a digital twin model; placing the three-dimensional model of the power grid equipment in the digital twin model can construct a digital twin power grid based on actual conditions, so that the constructed digital twin power grid conforms to reality, which is conducive to improving the accuracy of the combined gap calculation.

[0020] Preferably, dividing the plurality of image data into a plurality of groups of adjusted images according to the device numbers of the power grid devices includes:

[0021] Retrieving a plurality of image data, identifying the plurality of image data, and obtaining image data corresponding to adjacent power grid devices; and grouping the plurality of image data having the same adjacent power grid devices into a group;

[0022] The image data in the same group are numbered Sijk; whether the number of image data is greater than the number threshold is determined; if yes, the image data of the corresponding group is marked as an adjusted image; if not, the number of image data at the corresponding position is increased until the number of image data is greater than the number threshold; wherein, i = 1, 2, ..., n-1; j = 1, 2, ..., n; n is a positive integer; i represents the number corresponding to the power grid device on the left, j represents the number corresponding to the power grid device on the right; k = 1, 2, ..., m, m is a positive integer.

[0023] It should be noted that the number threshold is set based on experience before training the model. The larger the number of image data in a group, the more accurate the actual distance analyzed.

[0024] The present invention divides image data according to the adjacent power grid equipment corresponding to the image data, and numbers the image data in the same group. When the number of image data is not greater than the number threshold, the number of image data is increased, and the number of adjusted images can be controlled, which is conducive to ensuring the accuracy of subsequent real-time distance analysis.

[0025] Preferably, the position adjustment model is constructed based on an artificial intelligence model, including:

[0026] Acquire a standard data set; wherein the standard data set includes standard input data consistent with the adjusted image content attributes, and standard output data consistent with the actual distance content attributes;

[0027] Divide the standard data set into a training set, a validation set, and a test set; use the training set to train the artificial intelligence model; use the validation set to adjust the coefficient parameters within the artificial intelligence model; use the test set to test the performance of the artificial intelligence model to obtain performance parameters; determine whether the performance parameters of the artificial intelligence model are greater than the parameter threshold; if yes, mark the artificial intelligence model as a position adjustment model; if not, retrain the artificial intelligence model.

[0028] Preferably, adjusting the position of the grid equipment in the digital twin grid according to the actual distance includes:

[0029] Retrieve the actual distance of the grid equipment and convert it into the model distance of the digital twin grid; obtain the device distance of the grid equipment in the digital twin grid; and compare the device distance with the model distance.

[0030] Determine whether the device distance is consistent with the model distance. If yes, there is no need to adjust the position of the power grid equipment; if not, adjust the device distance of the power grid equipment to be consistent with the model distance.

[0031] It should be noted that when analyzing the device distance of the power grid equipment, adjustments are made in sequence according to the device numbers of the power grid equipment. After the adjustment, the device distance between the power grid equipment needs to be verified until the device distance of the power grid equipment is consistent with the corresponding model distance.

[0032] The present invention adjusts the device distance of the grid devices in the digital twin grid according to the actual distance, which can fine-tune the device distance between the grid devices and is conducive to improving the accuracy of the combined gap calculation.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] 1. The present invention obtains the structural topology of the power grid and the basic data of the power grid equipment; analyzes the integrity of the basic data, and when the basic data has sub-data of missing data types, supplements the missing sub-data; analyzes the equipment numbers in the basic data, and when the equipment numbers are repeated, eliminates the repeated or erroneous data; can ensure the integrity and validity of the data, and is conducive to improving the efficiency of data processing; constructs a three-dimensional model of the power grid equipment according to the structural data of the power grid equipment, and analyzes the connection mode and hierarchical relationship of the power grid according to the structural topology of the power grid, and constructs a digital twin model; places the three-dimensional model of the power grid equipment in the digital twin model, and can construct a digital twin power grid based on actual conditions, so that the constructed digital twin power grid conforms to reality, which is conducive to improving the accuracy of the combined gap calculation.

[0035] 2. The present invention divides the image data according to the adjacent power grid devices corresponding to the image data, and numbers the image data in the same group. When the number of image data is not greater than the number threshold, the number of image data is increased, and the number of adjusted images can be controlled; the position adjustment model is called, and the adjusted images are input into the position adjustment model in sequence to obtain the actual distance between the power grid devices; the device distance of the power grid devices in the digital twin power grid is adjusted according to the actual distance, which can make the device distance between the fine power grid devices, which is conducive to improving the accuracy of the combined gap calculation. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0037] Figure 1 A schematic diagram of the overall steps of the present invention;

[0038] Figure 2 A schematic diagram of the steps for constructing a digital twin power grid according to the present invention;

[0039] Figure 3 Schematic diagram of the steps for adjusting the position of power grid equipment according to the present invention. DETAILED DESCRIPTION

[0040] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0041] See also Figure 1 The first embodiment of the present invention provides a combined gap calculation method integrating digital twin power grid and visual positioning, including:

[0042] Step S1: Obtain a structural topology diagram of the power grid and basic data of power grid equipment; preprocess the basic data to obtain structural data; and construct a digital twin power grid based on the structural data and structural topology diagram of the power grid equipment. The basic data includes equipment number, appearance data, size data, and electrical parameters.

[0043] Step S2: using an image acquisition device to collect a plurality of image data between adjacent power grid devices; dividing the plurality of image data into a plurality of groups according to device numbers of the power grid devices and adjusting the images; wherein the device numbers of the power grid devices are set according to the locations of the power grid devices;

[0044] Step S3: calling a position adjustment model, inputting the adjustment images into the position adjustment model in sequence, and obtaining the actual distance between the power grid devices; wherein the position adjustment model is constructed based on an artificial intelligence model;

[0045] Step S4: Adjust the position of the grid equipment in the digital twin grid according to the actual distance, and calculate the adjusted combined gap.

[0046] See also Figure 2 , obtain the structural topology of the power grid and the basic data of the power grid equipment; determine whether the basic data includes sub-data of all data types; if so, retain the corresponding basic data; if not, complete the missing sub-data; determine whether the equipment numbers in the basic data are consistent, if so, eliminate the duplicate or erroneous basic data; if not, retain the corresponding basic data; mark the retained basic data and the completed basic data as structural data.

[0047] For example: suppose that the basic data of the grid equipment of a certain power grid is obtained, and the integrity of the basic data is analyzed. Among them, one set of data is missing the equipment number, and the grid equipment 13 is missing the electrical parameters; after verification, the equipment number 9 and electrical parameters of the missing grid equipment are supplemented; the equipment number 7 is repeated, and the erroneous data is eliminated after verification; the retained basic data and the supplemented basic data are marked as structural data.

[0048] Retrieve the structural data of the power grid equipment and the structural topology diagram of the power grid; establish a three-dimensional model of the power grid equipment based on the structural data; determine the connection method and hierarchical relationship of each node in the power grid based on the structural topology diagram; construct the power grid topology structure in the digital twin model; place the three-dimensional model of the power grid equipment at the corresponding position in the digital twin model to obtain the digital twin power grid.

[0049] See also Figure 3 The method uses an image acquisition device to collect image data between adjacent power grid devices; identifies the image data to obtain the image data corresponding to the adjacent power grid devices; groups the image data of the same adjacent power grid devices into a group; assigns a number Sijk to the image data within the same group; determines whether the number of image data exceeds a threshold; if so, marks the image data in the corresponding group as an adjustment image; if not, increases the number of image data at the corresponding position until the number of image data exceeds the threshold; calls a position adjustment model, and sequentially inputs the adjustment images into the position adjustment model to obtain the actual distance between the power grid devices. Here, i = 1, 2, ..., n-1; j = 1, 2, ..., n; n is a positive integer; i represents the number corresponding to the left power grid device, and j represents the number corresponding to the right power grid device; k = 1, 2, ..., m, where m is a positive integer.

[0050] For example, assuming that several image data are currently acquired, several image data are identified to obtain several groups of image data. After analysis, it is found that the number of image data between power grid device 3 and power grid device 4 is less than the number threshold 5. Then, the image data of power grid device 3 and power grid device 4 are collected, and finally 6 images of image data between power grid device 3 and power grid device 4 are obtained.

[0051] The image data that meets the standards is marked as an adjustment image, and the image data is sequentially input into the position adjustment model to obtain the actual distance.

[0052] Retrieve the actual distance of the power grid equipment and convert the actual distance into the model distance of the digital twin power grid; obtain the device distance of the power grid equipment in the digital twin power grid; compare the device distance with the model distance; determine whether the device distance is consistent with the model distance. If so, there is no need to adjust the position of the power grid equipment; if not, adjust the device distance of the power grid equipment to be consistent with the model distance; and calculate the adjusted combined gap.

[0053] For example: assume that the actual distance is converted into the model distance of the digital twin power grid; obtain the device distance of the power grid equipment in the digital twin power grid; compare the device distance with the model distance; and find that the device distance between power grid equipment 7 and power grid equipment 8 is inconsistent with the model distance. Then, adjust the device distance and analyze the device distance between power grid equipment 8 and power grid equipment 9.

[0054] It should be noted that the position adjustment model is built based on an artificial intelligence model, including:

[0055] Acquire a standard data set; wherein the standard data set includes standard input data consistent with the adjusted image content attributes, and standard output data consistent with the actual distance content attributes;

[0056] Divide the standard data set into a training set, a validation set, and a test set; use the training set to train the artificial intelligence model; use the validation set to adjust the coefficient parameters within the artificial intelligence model; use the test set to test the performance of the artificial intelligence model to obtain performance parameters; determine whether the performance parameters of the artificial intelligence model are greater than the parameter threshold; if yes, mark the artificial intelligence model as a position adjustment model; if not, retrain the artificial intelligence model; wherein the artificial intelligence model includes a convolutional neural network model or a generative adversarial neural network model; performance parameters include: accuracy, F1 score, recall rate, and stability.

[0057] The working principle of the present invention is as follows: the present invention obtains the structural topology map of the power grid and the basic data of the power grid equipment; pre-processes the basic data to obtain structural data; constructs a digital twin power grid based on the structural data and structural topology map of the power grid equipment; collects a number of image data between adjacent power grid equipment through an image acquisition device; divides the number of image data into a number of groups of adjusted images according to the equipment numbers of the power grid equipment; calls a position adjustment model, and inputs the adjusted images into the position adjustment model in sequence to obtain the actual distance between the power grid equipment; adjusts the position of the power grid equipment in the digital twin power grid according to the actual distance, and calculates the adjusted combined gap.

[0058] The above embodiments are only used to illustrate the technical method of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A combined gap calculation method integrating digital twin power grid and visual positioning, characterized in that: include: Step S1: Obtain the structural topology of the power grid and basic data of power grid equipment; Preprocess the basic data to obtain structural data; construct a digital twin power grid based on the structural data and structural topology diagram of the power grid equipment; wherein the basic data includes equipment number, appearance data, size data and electrical parameters; Step S2: collecting a number of image data between adjacent power grid devices through an image acquisition device; dividing the number of image data into a number of groups and adjusting the images according to the device numbers of the power grid devices; wherein the device numbers of the power grid devices are set according to the positions of the power grid devices; Step S3: calling the position adjustment model, inputting the adjustment images into the position adjustment model in sequence, and obtaining the actual distance between the power grid devices; wherein the position adjustment model is constructed based on the artificial intelligence model; Step S4: Adjust the position of the grid equipment in the digital twin grid according to the actual distance, and calculate the adjusted combined gap.

2. The combined gap calculation method integrating digital twin power grid and visual positioning according to claim 1 is characterized in that: The preprocessing of the basic data to obtain the structural data includes: Retrieve basic data and determine whether the basic data includes sub-data of all data types; if yes, retain the corresponding basic data; if no, complete the missing sub-data; Determine whether the equipment numbers in the basic data are consistent. If yes, remove the duplicate or erroneous basic data; if no, retain the corresponding basic data; The retained basic data and the completed basic data are marked as structural data.

3. The combined gap calculation method integrating digital twin power grid and visual positioning according to claim 1 is characterized in that: The digital twin power grid is constructed according to the structural data and the structural topology diagram of the power grid equipment, including: Retrieve the structural data of the power grid equipment and the structural topology of the power grid; establish a three-dimensional model of the power grid equipment based on the structural data; determine the connection mode and hierarchical relationship of each node in the power grid based on the structural topology; Construct the power grid topology in the digital twin model; place the three-dimensional model of the power grid equipment at the corresponding position in the digital twin model to obtain the digital twin power grid.

4. The combined gap calculation method integrating digital twin power grid and visual positioning according to claim 1 is characterized in that: The step of dividing a plurality of image data into a plurality of groups and adjusting images according to the device numbers of the power grid devices comprises: Retrieving a number of image data, identifying the number of image data, and obtaining image data corresponding to adjacent power grid devices; dividing the number of image data having the same adjacent power grid devices into one group; The image data in the same group are numbered Sijk; whether the number of image data is greater than the number threshold is determined; if yes, the image data of the corresponding group is marked as an adjusted image; if no, the number of image data at the corresponding position is increased until the number of image data is greater than the number threshold; wherein, i=1, 2, ..., n-1; j=1, 2, ..., n; n is a positive integer; i represents the number corresponding to the power grid equipment on the left, and j represents the number corresponding to the power grid equipment on the right; k=1, 2, ..., m, where m is a positive integer.

5. The combined gap calculation method integrating digital twin power grid and visual positioning according to claim 1 is characterized in that: The position adjustment model is constructed based on an artificial intelligence model, including: Acquire a standard data set; wherein the standard data set includes standard input data consistent with the adjusted image content attribute, and standard output data consistent with the actual distance content attribute; Divide the standard data set into a training set, a validation set, and a test set; use the training set to train the artificial intelligence model; use the validation set to adjust the coefficient parameters within the artificial intelligence model; use the test set to test the performance of the artificial intelligence model to obtain performance parameters; determine whether the performance parameters of the artificial intelligence model are greater than the parameter threshold; if yes, mark the artificial intelligence model as a position adjustment model; if not, retrain the artificial intelligence model.

6. The combined gap calculation method integrating digital twin power grid and visual positioning according to claim 1 is characterized in that: The adjusting the position of the power grid equipment in the digital twin power grid according to the actual distance includes: Retrieve the actual distance of power grid equipment and convert it into the model distance of the digital twin power grid; Obtaining the device distance of the power grid devices in the digital twin power grid; comparing the device distance with the model distance; Determine whether the device distance is consistent with the model distance. If yes, there is no need to adjust the position of the power grid equipment; if no, adjust the device distance of the power grid equipment to be consistent with the model distance.

Images