Transformer substation step voltage detection method and system based on edge calculation

Abstract

The invention discloses a transformer substation step voltage detection method and system based on edge calculation, relates to the field of electric power engineering, and solves the problem of low accuracy of step voltage detection, and the method comprises the steps: setting a plurality of potential detection points at the position of an electric power facility in a transformer substation, and measuring the real-time detection potential of each potential detection point through a voltage sensor; to-be-estimated points corresponding to the transformer substation are set in combination with the top view of the transformer substation, and then to-be-estimated point coordinates of each to-be-estimated point are recorded; the edge calculation platform calculates the estimated calculation potential of each point to be estimated through the real-time detection potential of the potential detection point; constructing a plurality of potential contour lines based on the potential conditions of each to-be-estimated point and the potential detection point, and obtaining a step voltage dangerous area in the transformer substation based on the potential contour lines; according to the method, the pre-estimated calculation potentials of a plurality of points to be estimated in the transformer substation are calculated, and accurate identification of the step voltage dangerous area in the transformer substation is realized.

Description

Technical Field

[0001] This invention belongs to the field of power engineering technology, specifically a method and system for detecting step voltage in substations based on edge computing. Background Technology

[0002] Edge computing is a distributed computing framework that refers to an open platform that integrates core capabilities of networking, computing, storage, and applications at the network edge, close to the source of objects or data, to provide edge intelligent services locally. A substation is a place in a power system that transforms voltage and current, receives electrical energy, and distributes electrical energy. A substation in a power plant is a step-up substation, whose function is to step up the electrical energy generated by the generator and feed it to the high-voltage power grid. Step voltage refers to the voltage between the feet of a person walking in the potential distribution area around the point where the grounding current enters when an electrical equipment grounds fault occurs. A large step voltage can cause an electric shock accident.

[0003] However, at present, when detecting step voltage in substations, manual detection or centralized detection through data centers is commonly used. Manual detection requires a lot of time to measure point by point, while centralized detection through data centers can cause data corruption or delay due to data transmission, which greatly prolongs the detection time of step voltage and makes it impossible to accurately detect step voltage. To address this, the present invention proposes a method and system for detecting step voltage in substations based on edge computing. Summary of the Invention

[0004] The purpose of this invention is to propose a method and system for detecting step voltage in substations based on edge computing, so as to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: A substation step voltage detection method based on edge computing includes: Step S1: Set up multiple potential detection points at the location of the power facilities in the substation, and measure the real-time detection potential of each potential detection point through a voltage sensor; Step S2: Based on the top view of the substation, set the corresponding points to be estimated for the substation, and then record the coordinates of each point to be estimated. Step S3: The edge computing platform calculates the estimated potential of each point to be estimated by real-time detection of the potential at the potential detection points. Step S4: Based on the potential conditions of each point to be estimated and the potential detection point, multiple potential contour lines are constructed, and the dangerous areas of step voltage in the substation are obtained based on the potential contour lines. Step S5: Output and warn of the step voltage danger zone corresponding to the substation, so that users can be aware of the step voltage danger zone and avoid it.

[0006] Furthermore, step S1 includes the following sub-steps: Step S11: Obtain the distribution map of the power facilities in the substation and identify the location of the grounding wire of each power facility; Step S12: Using the location of any grounding wire as the center, draw circles with radii R, 2R, and 3R in sequence; the circular area from the center to R is recorded as the first-level radiation area, the concentric circular area from R to 2R is recorded as the second-level radiation area, and the concentric circular area from 2R to 3R is recorded as the third-level radiation area. Step S13: Set the number of potential detection points in the third-level radiation area to N, the number of potential detection points in the second-level radiation area to 2N, and the number of potential detection points in the first-level radiation area to 3N; Step S14: Based on the number of potential detection points, a corresponding number of potential detection points are randomly set in the corresponding radiation area, and voltage sensors are installed on the corresponding potential detection points. The real-time detection potential corresponding to each potential detection point is collected and transmitted to the edge computing platform.

[0007] Furthermore, step S2 includes the following sub-steps: Step S21: Obtain the top view of the substation, read the topmost point of the top view and record it as the top boundary point, read the bottommost point of the top view and record it as the bottom boundary point, read the leftmost point of the top view and record it as the left boundary point, and read the rightmost point of the top view and record it as the right boundary point. Step S22: Draw a horizontal line at the location of the upper boundary point and the lower boundary point, and a vertical line at the location of the left boundary point and the right boundary point. The rectangle enclosed by the four lines is called the substation area. Step S23: Expand outward synchronously along the four boundaries of the substation area, and record the length of the expansion as the extension length and the area obtained by the expansion as the extension area.

[0008] Furthermore, step S2 also includes the following sub-steps: Step S24: Within the substation area, the substation area is divided into multiple grids of the same size with a first boundary length K, and the area of ​​each grid is K×K. The endpoints of each grid are recorded as points to be estimated. Within the extended area, the extended area is divided into multiple grids of the same size with a second boundary length L, and the endpoints of each grid within the extended area are recorded as points to be estimated. Step S25: Set the origin of the coordinate system at any point outside the extended area, and establish the X-axis and Y-axis with the origin of the coordinate system to obtain the plane rectangular coordinate system corresponding to the substation, and identify the coordinates of each point to be estimated. Step S26: Identify the coordinates of each potential detection point, and compare the coordinates of the point to be estimated with the coordinates of the detection points. If the coordinates of any point to be estimated are the same as the coordinates of the detection points, delete the corresponding point to be estimated; otherwise, do not perform any operation.

[0009] Furthermore, step S3 includes the following sub-steps: Step S31: Obtain the coordinates of the estimated point for each estimated point and the coordinates of the detection point for each potential detection point; Step S32: Calculate the straight-line distance between each point to be estimated and all potential detection points using the distance formula between two points; compare the straight-line distance corresponding to any point to be estimated with the straight-line distance threshold; if the straight-line distance is less than or equal to the straight-line distance threshold, then record the corresponding potential detection point as a valid detection point of the point to be estimated. If the straight-line distance is greater than the straight-line distance threshold, the corresponding potential detection point is recorded as an invalid detection point of the point to be estimated; there is spatial correlation between valid detection points and the point to be estimated, and no spatial correlation between invalid detection points and the point to be estimated.

[0010] Furthermore, step S3 also includes the following sub-steps: Step S33: Read the real-time detection potential of the valid detection points, and calculate the potential half-variation value between each pair of valid detection points based on the real-time detection potential of each valid detection point. The specific formula for calculating the half-variability of potential is as follows: BYnm = (DWn - DWm) 2 / 2; where DWn is the real-time detection potential of an effective detection point, and DWm is the real-time detection potential of another effective detection point; Step S34: Plot a scatter plot of the semivariogram function corresponding to the point to be estimated with the straight-line distance JL as the abscissa and the potential semivariogram value BY as the ordinate. Select the semivariogram function based on the trend of the scatter plot of the semivariogram function. Obtain the actual semivariogram function corresponding to the point to be estimated by fitting the scatter plot of the semivariogram function with the semivariogram function. Step S35: Identify the straight-line distance between the point to be estimated and each effective detection point and substitute it into the actual semivariogram to calculate the potential semivariogram value BYin between each effective detection point and the point to be estimated.

[0011] Furthermore, step S3 also includes the following sub-steps: Step S36: Construct the semi-variation matrix A corresponding to the effective detection point by using the potential semi-variation values ​​between all effective monitoring points; construct the corresponding semi-variation function matrix B by using the potential semi-variation values ​​between the effective detection point and the point to be estimated; calculate the weight vector QX of all effective detection points based on the semi-variation function matrix B and the semi-variation matrix A. Step S37: Calculate the estimated potential of the corresponding point to be estimated based on the weight vector and the real-time detection potential of each effective detection point; Step S38: Calculate the estimated potential corresponding to all points to be estimated.

[0012] Furthermore, the specific formula for calculating the weight vector is as follows: A×QZ=B; In the formula, ; ; In the formula, QZi1 is the weight corresponding to effective detection point 1, QZi2 is the weight corresponding to effective detection point 2, and so on; C is the Lagrange multiplier; QZ is the weight matrix, which is the transpose of the weight vector QX, QX=QZ. T .

[0013] Furthermore, step S4 includes the following sub-steps: Step S41: Obtain the estimated potentials of all points to be estimated; Step S42: Iterate through and compare the estimated potentials corresponding to the four endpoints of each grid. If the absolute value of the estimated potential difference between any two endpoints is greater than or equal to the human body's tolerance voltage, then the corresponding grid is recorded as a dangerous grid; otherwise, no operation is performed. Step S43: Select any non-boundary endpoint within the substation area, identify the four grids corresponding to the endpoint, treat the four grids as a whole as an equivalent large grid, read the estimated potential of the four endpoints corresponding to the equivalent large grid, and judge the danger of the equivalent large grid according to the process of step S42 until all non-boundary endpoints are traversed. Step S44: Summarize all the dangerous grids and record them as step voltage dangerous areas.

[0014] The substation step voltage detection system based on edge computing includes a detection point setting module, a data acquisition module, a region analysis module, an edge computing platform, a step analysis module, and an alert platform. The detection point setting module is used to set multiple potential detection points at the locations of power facilities within the substation and send them to the data acquisition module. The data acquisition module is used to collect the real-time detection potential at the location of each potential detection point and transmit it to the edge computing platform. The region analysis module is used to set multiple points to be estimated corresponding to the substation based on the substation's top view and send the coordinates of the points to be estimated to the edge computing platform. The edge computing platform is used to calculate the estimated potential of each point to be estimated by real-time detection of potential at potential detection points, and send the estimated potential of each point to be estimated to the step analysis module; the step analysis module is used to determine the step danger area corresponding to the substation by combining the estimated potential of the point to be estimated and generate a warning signal; the warning platform is used to receive the step danger area and the warning signal and issue a warning.

[0015] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: 1. This invention first sets up multiple potential detection points at the location of power facilities in the substation, and measures the real-time detection potential of each potential detection point through voltage sensors; then, it sets the corresponding estimated points of the substation based on the top view of the substation, and records the estimated point coordinates of each estimated point. By analyzing the layout of the substation, the setting of potential detection points and estimated points is realized.

[0016] 2. This invention utilizes an edge computing platform to calculate the estimated potential of each point to be estimated through real-time potential detection at potential detection points; then, based on the potential conditions of each point to be estimated and the potential detection points, multiple potential contour lines are constructed, and step voltage hazard areas within the substation are obtained based on these potential contour lines; finally, the corresponding step voltage hazard areas of the substation are output and warned, allowing users to be aware of and avoid step voltage hazard areas. By calculating the estimated potential of multiple points to be estimated within the substation, the invention achieves accurate identification of step voltage hazard areas within the substation. Attached Figure Description

[0017] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings.

[0018] Figure 1 This is a flowchart of the method of the present invention; Figure 2 This is a schematic diagram of the substation area in this invention; Figure 3 This is a scatter plot of the semivariogram function of the present invention; Figure 4 This is a system block diagram of the power plant step voltage detection system in this invention. Detailed Implementation

[0019] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] Example 1: Please refer to Figures 1-3As shown, the technical solution provided by this invention is: a substation step voltage detection method based on edge computing. This method involves setting multiple potential detection points near the corresponding power facilities of the substation and measuring the real-time detection potential of each point. Simultaneously, the substation is divided into multiple grids using a top-down view, and multiple potential estimation points are set. Then, an edge computing platform is used to calculate the estimated potential of each estimation point using the real-time detection potential of the potential detection points. Finally, based on the estimated potential, the corresponding step voltage danger zone of the substation is determined and output as a warning, achieving accurate early warning of substation step voltage. In this invention, the substation step voltage detection method includes the following steps: Step S1: Set up multiple potential detection points at the location of the power facilities in the substation, and measure the real-time detection potential of each potential detection point through a voltage sensor; It needs to be explained that electric potential is the potential energy of a point in an electric field relative to a reference point, and its unit is volt. Its value depends on the positional relationship between the point and the zero-potential reference point. It is a single-point property. Voltage, on the other hand, is the difference in potential between two points, and its unit is also volt. It reflects the ability of the electric field force to move charges and does work. It is a property between two points. In this invention, step S1 includes the following sub-steps: Step S11: Obtain the distribution map of the power facilities in the substation and identify the location of the grounding wire of each power facility; Step S12: Using the location of any grounding wire as the center, draw circles with radii R, 2R, and 3R in sequence; the circular area from the center to R is recorded as the first-level radiation area, the concentric circular area from R to 2R is recorded as the second-level radiation area, and the concentric circular area from 2R to 3R is recorded as the third-level radiation area. Step S13: Set the number of potential detection points in the third-level radiation area to N, the number of potential detection points in the second-level radiation area to 2N, and the number of potential detection points in the first-level radiation area to 3N; where N is a constant. Step S14: Based on the number of potential detection points, a corresponding number of potential detection points are randomly set in the corresponding radiation area, and voltage sensors are installed on the corresponding potential detection points. The real-time detection potential corresponding to each potential detection point is collected and transmitted to the edge computing platform. It should be noted that when the voltage sensor is actually installed, one end needs to be grounded. In order to get rid of the influence of substation faults on the measured value, the voltage sensor is an isolated differential voltage sensor. Step S2: Based on the top view of the substation, set the corresponding points to be estimated for the substation, and then record the coordinates of each point to be estimated. In this invention, step S2 includes the following sub-steps: Step S21: Obtain the top view of the substation, read the topmost point of the top view and record it as the top boundary point, read the bottommost point of the top view and record it as the bottom boundary point, read the leftmost point of the top view and record it as the left boundary point, and read the rightmost point of the top view and record it as the right boundary point. Step S22: Draw a horizontal line at the location of the upper boundary point and the lower boundary point, and a vertical line at the location of the left boundary point and the right boundary point. The rectangle enclosed by the four lines is called the substation area. Step S23, as Figure 2 As shown, the substation area is synchronously expanded outward from its four boundaries. The length of the expansion is denoted as the extension length, and the area obtained by the expansion is denoted as the extension area. Step S24: Within the substation area, the substation area is divided into multiple grids of the same size by a first boundary length K, and the area of ​​each grid is K×K. The endpoints of each grid are recorded as points to be estimated. Within the extended area, the extended area is divided into multiple grids of the same size by a second boundary length L, and the endpoints of each grid within the extended area are recorded as points to be estimated. Wherein, K and L are constants, L=2K, and preferably L is the average step size per person, and K is half of the average step size per person. It should be noted that the intersection line between the substation area and the extension area is regarded as the boundary of the substation area. Therefore, if the endpoint of the grid in the extension area falls on the intersection line, it is not considered as a point to be estimated. Step S25: Set the origin of the coordinate system at any point outside the extended area, and establish the X-axis and Y-axis with the origin of the coordinate system to obtain the plane rectangular coordinate system corresponding to the substation, and identify the coordinates of each point to be estimated. Step S26: Identify the coordinates of each potential detection point, and compare the coordinates of the point to be estimated with the coordinates of the detection points. If the coordinates of any point to be estimated are the same as the coordinates of the detection points, delete the corresponding point to be estimated; otherwise, do not perform any operation.

[0021] Step S3: The edge computing platform calculates the estimated potential of each point to be estimated by real-time detection of the potential at the potential detection points. In this invention, step S3 includes the following sub-steps: Step S31: Obtain the coordinates of each point to be estimated and denot them as ZBi = (Xi, Yi); obtain the coordinates of each potential detection point and denot them as JCj = (Xj, Yj); where i is the number of the point to be estimated, j is the number of the potential detection point, i = 1, 2, ..., z; j = 1, 2, ..., q; z and q are both positive integers; Step S32: Calculate the straight-line distance between each point to be estimated and all potential detection points using the distance formula between two points; compare the straight-line distance corresponding to any point to be estimated with a straight-line distance threshold. If the straight-line distance is less than or equal to the straight-line distance threshold, the corresponding potential detection point is recorded as a valid detection point for the point to be estimated; if the straight-line distance is greater than the straight-line distance threshold, the corresponding potential detection point is recorded as an invalid detection point for the point to be estimated; valid detection points and points to be estimated have spatial correlation, while invalid detection points and points to be estimated do not have spatial correlation. It should be noted that for any point to be estimated, if the number of valid detection points corresponding to the point to be estimated is less than or equal to two, the point to be estimated will be deleted directly, indicating that the point to be estimated is too far away from the substation area and will not have step voltage. Specifically, the formula for calculating the straight-line distance between the point to be estimated i and the potential detection point j is as follows: ; Step S33: Read the real-time detection potential DWn of the valid detection point, and calculate the potential half-variation value BYnm between each pair of valid detection points based on the real-time detection potential of each valid detection point; where n is the number of the valid detection point, m is the number of another valid detection point; n, m = 1, 2, ..., p, p is a positive integer; The specific formula for calculating the half-variability of potential is as follows: BYnm = (DWn - DWm) 2 / 2; where DWm is the real-time detection potential of another effective detection point, and the semi-variable value is a core concept in geostatistics used to quantify spatial autocorrelation. In this invention, it is used to describe the average difference between the real-time detection potentials corresponding to two effective detection points in space. Step S34, as Figure 3 As shown, a scatter plot of the semivariogram function corresponding to the point to be estimated is plotted with the straight-line distance JL as the abscissa and the potential semivariogram value BY as the ordinate. The semivariogram function is selected based on the trend of the semivariogram function scatter plot. The actual semivariogram function corresponding to the point to be estimated is obtained by fitting the semivariogram function scatter plot and the semivariogram function. Specifically, by identifying the nugget value, sill value, and range corresponding to the semivariogram scatter plot, and substituting these values ​​into the corresponding semivariograms, the actual semivariogram of the point to be estimated is obtained. The nugget value represents the variation within a very short distance, obtained by reading the potential semivariogram when the straight-line distance is 0. The sill value represents the value at which the semivariogram tends to stabilize, obtained by adding the variance of the potential semivariograms corresponding to all valid detection points to the nugget value. The range represents the maximum distance of spatial autocorrelation, obtained by selecting the straight-line distance of the maximum potential semivariogram in the semivariogram scatter plot. If the trend of the semivariogram scatter plot is a slow rise followed by a steady rise, then the semivariogram corresponding to the spherical model is selected; if the trend of the semivariogram scatter plot is a steep rise followed by an asymptote, then the semivariogram corresponding to the exponential model is selected; if the trend of the semivariogram scatter plot is a flat rise followed by an accelerated rise, then the semivariogram corresponding to the Gaussian model is selected; in practice, in this invention, the semivariogram corresponding to the spherical model is selected by default. Specifically, the semi-variogram function of the spherical model is: Where BYin is the potential half-variation value between the estimated point i and the effective detection point n; KJi is the nugget value, JTi is the sill value, BCI is the range, and JLin represents the straight-line distance between the estimated point i and the effective detection point n. Step S35: Identify the straight-line distance between the point to be estimated and each effective detection point and substitute it into the actual semivariogram to calculate the potential semivariogram value BYin between each effective detection point and the point to be estimated. Step S36: Construct the semi-variation matrix A corresponding to the effective detection point by using the potential semi-variation values ​​between all effective monitoring points; construct the corresponding semi-variation function matrix B by using the potential semi-variation values ​​between the effective detection point and the point to be estimated; calculate the weight vector QX of all effective detection points based on the semi-variation function matrix B and the semi-variation matrix A. The formula is as follows: A×QZ=B; where, ; ; In the formula, QZi1 is the weight corresponding to effective detection point 1, QZi2 is the weight corresponding to effective detection point 2, and so on; C is the Lagrange multiplier, and the 1 at the end of the semi-mutation function matrix B and the semi-mutation matrix A are terms related to the Lagrange multiplier C, used to constrain all weights to sum to 1; QZ is the weight matrix, which is the transpose of the weight vector QX, QX=QZ. T ; Step S37: Calculate the estimated potential YDi of the corresponding point to be estimated based on the weight vector and the real-time detection potential of each valid detection point; the specific formula is as follows: Where QZin is the weight of the finite number of detection points n when calculating the estimated point i corresponding to the predicted point position; Step S38: Calculate the estimated potential corresponding to all points to be estimated based on the process of steps S31-S37.

[0022] Step S4: Based on the potential conditions of each point to be estimated and the potential detection point, multiple potential contour lines are constructed, and the dangerous areas of step voltage in the substation are obtained based on the potential contour lines. In this invention, step S4 includes the following sub-steps: Step S41: Obtain the estimated potentials of all points to be estimated; Step S42: Iterate through and compare the estimated potentials corresponding to the four endpoints of each grid. If the absolute value of the estimated potential difference between any two endpoints is greater than or equal to the human body's tolerance voltage, then the corresponding grid is recorded as a dangerous grid; otherwise, no operation is performed. Here, the human body's tolerance voltage is the step voltage that the human body is allowed to take. Step S43: Select any non-boundary endpoint within the substation area, identify the four grids corresponding to the endpoint, treat the four grids as a whole as an equivalent large grid, read the estimated potential of the four endpoints corresponding to the equivalent large grid, and judge the danger of the equivalent large grid according to the process of step S42 until all non-boundary endpoints are traversed. Step S44: Summarize all the dangerous grids and record them as step voltage dangerous areas.

[0023] Step S5: Output and warn of the step voltage danger zone corresponding to the substation, so that users can be aware of the step voltage danger zone and avoid it.

[0024] Example 2: Figure 4 As shown, based on another concept of the same invention, a substation step voltage detection system based on edge computing is proposed, including a detection point setting module, a data acquisition module, a region analysis module, an edge computing platform, a step analysis module, and an alarm platform; The detection point setting module is used to set multiple potential detection points at the locations of power facilities within the substation and send them to the data acquisition module; the data acquisition module is used to collect the real-time detection potential at the location of each potential detection point and transmit it to the edge computing platform; the area analysis module is used to set multiple points to be estimated corresponding to the substation based on the substation top view and send the coordinates of the points to be estimated to the edge computing platform. The edge computing platform is used to calculate the estimated potential of each point to be estimated by real-time detection of potential at potential detection points, and send the estimated potential of each point to be estimated to the step analysis module; the step analysis module is used to determine the step danger area corresponding to the substation by combining the estimated potential of the point to be estimated and generate a warning signal; the warning platform is used to receive the step danger area and the warning signal and issue a warning.

[0025] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A method for detecting step voltage in substations based on edge computing, characterized in that, include: Step S1: Set up multiple potential detection points at the location of the power facilities in the substation, and measure the real-time detection potential of each potential detection point through a voltage sensor; Step S2: Based on the top view of the substation, set the corresponding points to be estimated for the substation, and then record the coordinates of each point to be estimated. Step S3: The edge computing platform calculates the estimated potential of each point to be estimated by real-time detection of the potential at the potential detection points. Step S4: Based on the potential conditions of each point to be estimated and the potential detection point, multiple potential contour lines are constructed, and the dangerous areas of step voltage in the substation are obtained based on the potential contour lines. Step S5: Output and warn of the step voltage danger zone corresponding to the substation, so that users can be aware of the step voltage danger zone and avoid it.

2. The substation step voltage detection method based on edge computing according to claim 1, characterized in that, Step S1 includes the following sub-steps: Step S11: Obtain the distribution map of the power facilities in the substation and identify the location of the grounding wire of each power facility; Step S12: Using the location of any grounding wire as the center, draw circles with radii R, 2R, and 3R in sequence; the circular area from the center to R is recorded as the first-level radiation area, the concentric circular area from R to 2R is recorded as the second-level radiation area, and the concentric circular area from 2R to 3R is recorded as the third-level radiation area. Step S13: Set the number of potential detection points in the third-level radiation area to N, the number of potential detection points in the second-level radiation area to 2N, and the number of potential detection points in the first-level radiation area to 3N; Step S14: Based on the number of potential detection points, a corresponding number of potential detection points are randomly set in the corresponding radiation area, and voltage sensors are installed on the corresponding potential detection points. The real-time detection potential corresponding to each potential detection point is collected and transmitted to the edge computing platform.

3. The substation step voltage detection method based on edge computing according to claim 1, characterized in that, Step S2 includes the following sub-steps: Step S21: Obtain the top view of the substation, read the topmost point of the top view and record it as the top boundary point, read the bottommost point of the top view and record it as the bottom boundary point, read the leftmost point of the top view and record it as the left boundary point, and read the rightmost point of the top view and record it as the right boundary point. Step S22: Draw a horizontal line at the location of the upper boundary point and the lower boundary point, and a vertical line at the location of the left boundary point and the right boundary point. The rectangle enclosed by the four lines is called the substation area. Step S23: Expand outward synchronously along the four boundaries of the substation area, and record the length of the expansion as the extension length and the area obtained by the expansion as the extension area.

4. The substation step voltage detection method based on edge computing according to claim 3, characterized in that, Step S2 further includes the following sub-steps: Step S24: Within the substation area, the substation area is divided into multiple grids of the same size with a first boundary length K, and the area of ​​each grid is K×K. The endpoints of each grid are recorded as points to be estimated. Within the extended area, the extended area is divided into multiple grids of the same size with a second boundary length L, and the endpoints of each grid within the extended area are recorded as points to be estimated. Step S25: Set the origin of the coordinate system at any point outside the extended area, and establish the X-axis and Y-axis with the origin of the coordinate system to obtain the plane rectangular coordinate system corresponding to the substation, and identify the coordinates of each point to be estimated. Step S26: Identify the coordinates of each potential detection point, and compare the coordinates of the point to be estimated with the coordinates of the detection points. If the coordinates of any point to be estimated are the same as the coordinates of the detection points, delete the corresponding point to be estimated; otherwise, do not perform any operation.

5. The substation step voltage detection method based on edge computing according to claim 1, characterized in that, Step S3 includes the following sub-steps: Step S31: Obtain the coordinates of the estimated point for each estimated point and the coordinates of the detection point for each potential detection point; Step S32: Calculate the straight-line distance between each point to be estimated and all potential detection points using the distance formula between two points; The straight-line distance corresponding to any point to be estimated is compared with the straight-line distance threshold. If the straight-line distance is less than or equal to the straight-line distance threshold, the corresponding potential detection point is recorded as the valid detection point of the point to be estimated. If the straight-line distance is greater than the straight-line distance threshold, the corresponding potential detection point is recorded as an invalid detection point for the point to be estimated. There is spatial correlation between valid detection points and the points to be estimated, while there is no spatial correlation between invalid detection points and the points to be estimated.

6. The substation step voltage detection method based on edge computing according to claim 5, characterized in that, Step S3 further includes the following sub-steps: Step S33: Read the real-time detection potential of the valid detection points, and calculate the potential half-variation value between each pair of valid detection points based on the real-time detection potential of each valid detection point. The specific formula for calculating the half-variability of potential is as follows: BYnm = (DWn - DWm) 2 / 2; where DWn is the real-time detection potential of effective detection point n, and DWm is the real-time detection potential of another effective detection point m; Step S34: Plot a scatter plot of the semivariogram function corresponding to the point to be estimated with the straight-line distance JL as the abscissa and the potential semivariogram value BY as the ordinate. Select the semivariogram function based on the trend of the scatter plot of the semivariogram function. Obtain the actual semivariogram function corresponding to the point to be estimated by fitting the scatter plot of the semivariogram function with the semivariogram function. Step S35: Identify the straight-line distance between the point to be estimated and each effective detection point and substitute it into the actual semivariogram to calculate the potential semivariogram value BYin between each effective detection point and the point to be estimated.

7. The substation step voltage detection method based on edge computing according to claim 6, characterized in that, Step S3 further includes the following sub-steps: Step S36: Construct the semi-variation matrix A corresponding to the effective detection point by using the potential semi-variation values ​​between all effective monitoring points; construct the corresponding semi-variation function matrix B by using the potential semi-variation values ​​between the effective detection point and the point to be estimated; calculate the weight vector QX of all effective detection points based on the semi-variation function matrix B and the semi-variation matrix A. Step S37: Calculate the estimated potential of the corresponding point to be estimated based on the weight vector and the real-time detection potential of each effective detection point; Step S38: Calculate the estimated potential corresponding to all points to be estimated.

8. The substation step voltage detection method based on edge computing according to claim 7, characterized in that, The specific formula for calculating the weight vector is as follows: A×QZ=B; In the formula, ; ; In the formula, QZi1 is the weight corresponding to effective detection point 1, QZi2 is the weight corresponding to effective detection point 2, and so on; C is the Lagrange multiplier; QZ is the weight matrix, which is the transpose of the weight vector QX, QX=QZ. T .

9. The substation step voltage detection method based on edge computing according to claim 1, characterized in that, Step S4 includes the following sub-steps: Step S41: Obtain the estimated potentials of all points to be estimated; Step S42: Iterate through and compare the estimated potentials corresponding to the four endpoints of each grid. If the absolute value of the estimated potential difference between any two endpoints is greater than or equal to the human body's tolerance voltage, then the corresponding grid is recorded as a dangerous grid. Conversely, no action is taken. Step S43: Select any non-boundary endpoint within the substation area, identify the four grids corresponding to the endpoint, treat the four grids as a whole as an equivalent large grid, read the estimated potential of the four endpoints corresponding to the equivalent large grid, and judge the danger of the equivalent large grid according to the process of step S42 until all non-boundary endpoints are traversed. Step S44: Summarize all the dangerous grids and record them as step voltage dangerous areas.

10. A substation step voltage detection system based on edge computing, characterized in that, The substation step voltage detection method based on edge computing according to any one of claims 1-9 includes a detection point setting module, a data acquisition module, a region analysis module, an edge computing platform, a step analysis module, and an alert platform. The detection point setting module is used to set multiple potential detection points at the locations of power facilities within the substation and send them to the data acquisition module. The data acquisition module is used to acquire the real-time detection potential at the location of each potential detection point and transmit it to the edge computing platform. The region analysis module is used to set multiple points to be estimated corresponding to the substation based on the substation top view and send the coordinates of the points to be estimated to the edge computing platform. The edge computing platform is used to calculate the estimated potential of each point to be estimated by real-time detection of the potential at the potential detection point, and send the estimated potential of each point to be estimated to the step analysis module. The step analysis module is used to determine the step danger zone corresponding to the substation by combining the estimated potential of the point to be estimated and generate a warning signal. The warning platform is used to receive the step danger zone and the warning signal and issue a warning.

Images