A distribution network grid division and full-process control method based on artificial intelligence

Abstract

The application discloses a power distribution network grid division method and a whole-process management and control method based on artificial intelligence, and the method comprises the following steps: acquiring a regional meandering degree index of a first regional cable trench in a target power distribution network grid division area, and then determining a target transformer substation; determining an actual power supply range boundary with the target transformer substation as the center; performing calculation and screening in the actual power supply range boundary to obtain a plurality of intermediate joint installation positions of cables in the actual power supply range; determining evaluation scores of the intermediate joint installation positions and distances from the intermediate joint installation positions to the actual power supply boundary as to-be-optimized positions; establishing a polar coordinate sampling network according to the to-be-optimized positions to determine the final optimized positions; and dividing a power supply area of the power distribution network according to the actual power supply range boundary and the final optimized positions to obtain a final result of the power distribution network grid division. Through the above division method, the reliability of the power distribution network grid division result is improved, and the operation efficiency of the power distribution network is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power distribution network planning, and particularly relates to a power distribution network grid division and whole-process management and control method based on artificial intelligence. BACKGROUND

[0002] In the process of power distribution network grid division in mountainous and hilly areas, the winding degree of the cable trench has a significant impact on the actual power supply distance. Due to the large terrain undulation, the cable laying is difficult to be laid along the straight line path, resulting in that the actual power supply distance is much larger than the straight line distance from the substation to the load center. This difference leads to a more complex mapping relationship between the power supply radius in the grid and the substation layout, which is difficult to obtain directly through geometric calculation. Meanwhile, the cable intermediate joint as a weak link in the cable line, its reasonable arrangement is the key to guarantee the power supply reliability.

[0003] However, in the mountainous and hilly areas, limited by the terrain conditions, the cable intermediate joint arrangement position selection is subject to many restrictions. How to consider the electrical performance of the joint position on the premise of meeting the construction conditions, and evaluate the rationality of its arrangement, is a problem to be further studied. In addition, the rationality evaluation results of the winding degree of the cable trench and the cable intermediate joint arrangement position have important guiding significance for the reasonable demarcation of the power distribution network grid boundary. However, the demarcation of the grid boundary needs to consider many factors such as the actual power supply distance, the cable line direction, the joint arrangement, so as to realize the optimization of grid division and improve the overall operation efficiency of the power distribution network while ensuring the power supply reliability. SUMMARY

[0004] In order to solve the above technical problems, the embodiment of the present application provides a power distribution network grid division and whole-process management and control method based on artificial intelligence, so as to solve the technical problems of low reliability of the power distribution network grid division result in the prior art and reduce the overall operation efficiency of the power distribution network.

[0005] The first aspect of the embodiment of the present application provides a power distribution network grid division method based on artificial intelligence, and the method comprises:

[0006] Obtaining the topographic feature parameters and the power consumption load distribution of a first region in a target power distribution network grid division region, quantitatively analyzing the topographic feature parameters to obtain a region winding degree index of the first region, obtaining the topographic feature according to the region winding degree index, and obtaining the cable trench path according to the minimum curvature principle and the topographic feature;

[0007] The plurality of grid nodes are determined according to the power load distribution, the plurality of grid nodes are optimized, and a plurality of substation positions to be laid out are obtained; a target substation is determined according to the plurality of substation positions; an optimal path of the cable trench path is obtained according to the target substation; the optimal path is corrected according to a path tortuosity index, and an actual power supply range boundary of the target substation is obtained;

[0008] Based on the cable load value in the actual power supply range boundary and the path tortuosity index, a cable segmentation region is obtained, a dynamic programming algorithm is used to calculate the cable segmentation region, a plurality of candidate joint positions of the cable are obtained, and the plurality of candidate joint positions of the cable are screened according to a cable temperature rise curve along the line, to obtain a plurality of intermediate joint installation positions of the cable in the actual power supply range.

[0009] The annual maintenance cost, the terrain restriction data and the construction cost data of each intermediate joint installation position are calculated by using the analytic hierarchy process, to obtain an evaluation score of each intermediate joint installation position; the distance from each intermediate joint installation position to the actual power supply boundary is calculated, to obtain a plurality of distance values; and the intermediate joint installation position with a distance value less than a preset distance value and an evaluation score less than a preset evaluation value is determined as a position to be optimized.

[0010] A polar coordinate sampling network is established according to the position to be optimized, a sampling point position in the polar coordinate sampling network is determined, the power supply distance and the voltage drop amplitude value of each sampling point position are calculated, the sampling point position with a voltage drop amplitude value satisfying a preset condition is selected as an optimized position, and a final optimized position is obtained according to the load density distribution in the actual power supply range boundary.

[0011] The power supply area of the power distribution network is divided according to the actual power supply range boundary and the final optimized position, to obtain an initial grid division result; and the grid boundary is corrected based on the initial grid division result, to obtain a final result of the grid division of the power distribution network.

[0012] In a possible implementation manner of the first aspect, the topographic feature parameters are quantitatively analyzed to obtain the path tortuosity index of the cable trench in the first region, including:

[0013] According to the topographic feature parameters, a height difference ratio between adjacent sampling points in the first region is calculated, and the slope of the sampling point is obtained according to the height difference ratio.

[0014] The contour line density distribution in the first region is calculated, the topography in the first region is sampled at a preset interval based on the contour line density distribution, to obtain section data, and the path tortuosity index is obtained according to the section data and the straight line distance corresponding to the section data.

[0015] In a possible implementation manner of the first aspect, the plurality of grid nodes are determined according to the power load distribution, the plurality of grid nodes are optimized, and the substation positions to be laid out are obtained, including:

[0016] The load density index is calculated according to the power load distribution, and the normalized load density distribution curve is obtained according to the load density index and the load density values greater than the preset density value in the first region;

[0017] The load center coordinate point is determined according to the normalized load density distribution curve, the boundary range is constructed according to the load center coordinate point and the power supply point position in the first region, the grid nodes are set at the preset interval in the boundary range, and the plurality of grid nodes are obtained;

[0018] The plurality of grid nodes are filtered according to the preset power supply radius, the plurality of filtered grid nodes are obtained, and the plurality of substation positions to be laid out are obtained by using the simulated annealing algorithm to optimize the plurality of filtered grid nodes.

[0019] In a possible implementation manner of the first aspect, the best path of the cable trench path is obtained according to the target substation, the actual power supply range boundary of the target substation is obtained by correcting the best path according to the path tortuosity index, including:

[0020] The along-path impedance values of the grid nodes to be searched are calculated according to the terrain slope data and the reference impedance value of the target substation;

[0021] The path traversal is performed on the grid nodes with the along-path impedance values less than the preset impedance value threshold by using the depth-first algorithm, and a traversal path set is obtained;

[0022] The tortuosity index of each path in the traversal path set is obtained by calculating the actual length of each path in the traversal path set and the straight-line distance corresponding to each path, and the plurality of power supply path combinations are obtained by constructing the coordinate point sequence of the path with the tortuosity index less than the preset tortuosity.

[0023] The total impedance value of each power supply path combination is obtained based on the impedance value and the length of each path, and the power supply path combination with the total impedance value less than the preset total impedance value threshold is selected as the actual power supply range boundary.

[0024] In a possible implementation manner of the first aspect, the cable segmentation region is obtained based on the cable load value in the actual power supply range boundary and the path tortuosity index, including:

[0025] The current load value in the actual power supply range boundary is obtained, the voltage drop amplitude is obtained according to the current load value and the path tortuosity index, and if the voltage drop amplitude is greater than the preset drop amplitude threshold, the path in the actual power supply range is segmented, and the cable segmentation region is obtained.

[0026] In a possible implementation manner of the first aspect, the cable segment area is calculated by using a dynamic programming algorithm to obtain a plurality of candidate joint positions, and the candidate joint positions of each cable are screened according to a cable temperature rise curve along the line to obtain a plurality of intermediate joint installation positions of the cable in the actual power supply range, including:

[0027] According to the cable segment area, a plurality of candidate joint positions are determined in a preset interval range by using a dynamic programming algorithm according to a set search depth threshold;

[0028] Conductor temperature data at each candidate joint position is collected;

[0029] Stress analysis is performed according to each candidate joint position to obtain a maximum shear stress distribution value of each candidate joint position, a stress limiting area is determined according to the maximum shear stress distribution value, and the candidate joint position to be arranged is screened through the stress limiting area;

[0030] If the conductor temperature data corresponding to the candidate joint position to be arranged is less than a preset temperature threshold, and the maximum shear stress distribution value corresponding to the candidate joint position to be arranged is less than a preset material strength, the candidate joint position to be arranged is determined as an intermediate joint installation position.

[0031] In a possible implementation manner of the first aspect, the annual maintenance cost, the terrain restriction data and the construction cost data of each intermediate joint installation position are calculated by using an analytic hierarchy process to obtain an evaluation score of each intermediate joint installation position, including:

[0032] A judgment matrix of each intermediate joint installation position is established according to the annual maintenance cost value, the terrain restriction data and the construction cost data of each intermediate joint installation position;

[0033] Based on the judgment matrix of each intermediate joint installation position, a scale value is calculated to obtain an eigenvector of each intermediate joint installation position, the eigenvector is normalized to obtain a weight vector, and if a consistency ratio of the weight vector is less than a preset ratio, a terrain restriction weight value, a maintenance cost weight value and a construction cost weight value are extracted from the weight vector;

[0034] The terrain restriction weight value, the maintenance cost weight value and the construction cost weight value are weighted calculated with the corresponding annual maintenance cost value, terrain restriction data and construction cost data to obtain the evaluation score of each intermediate joint installation position.

[0035] In a possible implementation manner of the first aspect, a final optimized position is obtained according to a load density distribution within the boundary of the actual power supply range, including:

[0036] According to the load density distribution within the actual power supply range boundary, a position with a load density greater than a preset load density threshold is selected as a branch connection point;

[0037] According to the branch connection point and the optimized position, a new position combination is obtained, and if the voltage drop amplitude value of the new position combination meets a preset condition, the new position combination is determined as the final optimized position.

[0038] In a possible implementation manner of the first aspect, the grid boundary correction is performed based on the initial grid division result to obtain a final result of the grid division of the power distribution network, including:

[0039] According to the load center points of each network in the initial grid division result, a coverage area with a preset radius is constructed to obtain a plurality of coverage areas;

[0040] The proportion of the intersection area of each coverage area and an adjacent coverage area is calculated, and it is determined whether the proportion exceeds a preset proportion of the total area of the coverage area, if yes, the voltage distribution of the coverage area is calculated, if the voltage distribution reaches the rated voltage, the boundary of the grid corresponding to the coverage area is adjusted according to a preset offset to obtain an adjusted grid boundary;

[0041] According to the adjusted grid boundary, the final result of the grid division of the power distribution network is obtained.

[0042] To solve the same technical problem, a second aspect of an embodiment of the present application provides a power distribution network whole-process management and control method, the method including:

[0043] Obtaining a final result of grid division of a power distribution network, wherein the final result of grid division of the power distribution network is obtained by the power distribution network grid division method based on artificial intelligence of the first aspect;

[0044] According to the final result of grid division of the power distribution network, equipment operation state data is collected at a sampling interval, and voltage, current and temperature in the operation state data are quantitatively scored to obtain an equipment state mapping matrix;

[0045] A construction constraint control matrix is constructed according to the equipment state mapping matrix, and a construction quality evaluation index is obtained by comparing construction process monitoring data with equipment rated values based on the control matrix; an equipment operation state score is calculated according to the construction quality evaluation index, and when the equipment operation state score is lower than a preset operation state evaluation threshold, the equipment is marked as a warning state, and an equipment maintenance cycle is generated according to the warning state;

[0046] The equipment state change in the equipment maintenance cycle is quantitatively counted to obtain a statistical result, a maintenance quality score is calculated according to the statistical result, a maintenance scheme is corrected according to the maintenance quality score, and an updated equipment inspection and maintenance scheme is obtained.

[0047] The technical scheme of the present application has the following advantages:

[0048] The power distribution network grid division method based on artificial intelligence provided by the embodiment of the present application obtains the topographic feature parameters and the power load distribution of a first region in the target power distribution network grid division region, performs quantitative analysis on the topographic feature parameters, obtains a region meandering degree index of the first region, obtains a topographic feature according to the region meandering degree index, and obtains a cable trench path according to the minimum curvature principle and the topographic feature; determines a plurality of grid nodes according to the power load distribution, optimizes each grid node, and obtains a plurality of substation positions to be laid out, determines a target substation according to each substation position, obtains an optimal path of the cable trench path according to the target substation, corrects the optimal path according to a path meandering degree index, and obtains an actual power supply range boundary of the target substation; obtains a cable segmentation region based on the cable load value in the actual power supply range boundary and the path meandering degree index, calculates the cable segmentation region by using a dynamic programming algorithm, obtains a plurality of candidate joint positions of the cables, screens each candidate joint position of the cables according to a cable temperature rise curve along the line, and obtains a plurality of intermediate joint installation positions of the cables in the actual power supply range; calculates the annual maintenance cost, the topographic restriction data, and the construction cost data of each intermediate joint installation position by using an analytic hierarchy process, obtains an evaluation score of each intermediate joint installation position, calculates the distance from each intermediate joint installation position to the actual power supply boundary, obtains a plurality of distance values, determines an intermediate joint installation position with a distance value less than a preset distance value and an evaluation score less than a preset evaluation value as a position to be optimized, establishes a polar coordinate sampling network according to the position to be optimized, determines a sampling point position in the polar coordinate sampling network, calculates the power supply distance and the voltage drop amplitude value of each sampling point position, selects a sampling point position with a voltage drop amplitude value meeting a preset condition as an optimized position, and obtains a final optimized position according to the load density distribution in the actual power supply range boundary; divides the power supply region of the power distribution network according to the actual power supply range boundary and the final optimized position, obtains an initial grid division result, corrects the grid boundary based on the initial grid division result, and obtains a final result of the power distribution network grid division. Through the above division method, the reliability of the power distribution network grid division result is improved. BRIEF DESCRIPTION OF DRAWINGS

[0049] In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the drawings needed to be used in the specific embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without any creative effort.

[0050] Figure 11 is a flow chart of a grid division method for a distribution network based on artificial intelligence in an embodiment of the present invention;

[0051] Figure 2 This is a flow chart of the control method for the full-process control method of the distribution network in an embodiment of the present invention. DETAILED DESCRIPTION

[0052] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0053] The method for dividing the distribution network grid based on artificial intelligence provided by the embodiment of the present invention is as follows: Figure 1 As shown, Figure 1 The flowchart of the distribution network grid division method based on artificial intelligence includes steps S101 to S106. The details of each step are as follows:

[0054] S101. Obtain terrain characteristic parameters and power load distribution of a first area within the target distribution network grid division area, perform quantitative analysis on the terrain characteristic parameters, obtain a regional winding degree index of the first area, obtain terrain characteristics based on the regional winding degree index, and obtain a cable trench path based on the minimum curvature principle and the terrain characteristics.

[0055] In this embodiment, grid area terrain elevation data is read from a geographic information database. The terrain relief value is derived from the standard deviation of elevation per unit area. A three-dimensional laser scanner is used to collect terrain point cloud data. Slope classification data is derived from the elevation difference ratio between adjacent sampling points. Elevation differences between 0 and 15 degrees are classified as flat land, 15 to 30 degrees as gentle slopes, and above 30 degrees as steep slopes. Cross-sectional data is collected based on the contour line density distribution. The regional sinuosity index is derived by comparing the actual length of the cross-sectional curve to the straight-line distance between the starting and ending points. The slope classification data is overlaid on the surface elevation grid. A support vector machine is used to extract terrain features from the terrain relief value and the sinuosity index. The cable trench path is then determined based on the principle of minimum curvature.

[0056] In one embodiment, the terrain characteristic parameters are quantitatively analyzed to obtain a regional winding degree index of the first region, including:

[0057] Calculating the height difference ratio between adjacent sampling points in the first area according to the terrain characteristic parameters, and obtaining the slope of the sampling points according to the height difference ratio;

[0058] Calculate the contour line density distribution in the first area, sample the terrain in the first area at preset intervals based on the contour line density distribution, obtain cross-sectional data, and obtain a winding degree index based on the cross-sectional data and the straight-line distance corresponding to the cross-sectional data.

[0059] In this embodiment, terrain elevation data for the gridded area is read from a geographic information database. The standard deviation of elevation per unit area is calculated to obtain the terrain relief value. The surface slope value is calculated by dividing the elevation difference between adjacent grid points by the horizontal distance. A 3D laser scanner collects 100 terrain point cloud data per square meter. Based on this point cloud data, the elevation difference ratio between adjacent sampling points is calculated. Slopes are classified as flat land (0 to 15 degrees), gentle slopes (15 to 30 degrees), and steep slopes (over 30 degrees). The contour density distribution is calculated based on the length of the contour lines per unit area. The terrain is sampled at 20-meter intervals to obtain longitudinal section curves. The regional sinuosity index is calculated based on the ratio of the actual length of the section curve to the straight-line distance between the starting and ending points.

[0060] It should be noted that terrain feature parameters refer to terrain point cloud data.

[0061] The slope classification data is then superimposed on the surface elevation grid, and a support vector machine is used to extract terrain features from the terrain undulation value and the winding index. The path direction of the cable trench within each slope interval is calculated based on the principle of minimum curvature. The terrain elevation data in the geographic information database contains the coordinates of the elevation point location and the corresponding elevation value. The grid vertex data is selected from it to form a regular grid. The height difference between two adjacent elevation points is divided by the horizontal distance to obtain the slope of the area. The standard deviation of the elevation point height reflects the degree of terrain undulation. The larger the standard deviation, the greater the terrain elevation undulation. In the mountainous scene, the standard deviation of the 12 elevation points is 52 meters, reflecting that the terrain in this area is relatively undulating. In the hilly area, the standard deviation of the 12 elevation points is 23 meters, which is a moderately undulating terrain. The numerical values ​​show that the differences between mountainous and hilly terrains are obvious.

[0062] When three-dimensional laser scanning is used to collect terrain point cloud data, 100 points are collected per square meter to ensure data density. The point cloud data obtained by scanning contains spatial coordinate information. The local slope is obtained by calculating the elevation difference between adjacent points and dividing it by the horizontal distance. When the slope value is within the range of 0 to 15 degrees, it is judged to be flat land, which is suitable for laying cables in a straight line. A slope of 15 to 30 degrees is a gentle slope, which needs to be laid in a curved manner along the contour line. A slope greater than 30 degrees is a steep slope, which needs to be avoided or special engineering measures must be taken. A cross-sectional curve is sampled every 20 meters along the terrain direction, and the ratio of the actual cross-sectional curve length to the straight-line distance between the starting and ending points is calculated to obtain the winding index.

[0063] The terrain relief value is greater than 1.3, indicating that the terrain is rugged, and the cable laying needs to be detoured to avoid steep slopes. For areas with a tortuosity index less than 1.1, the terrain is flat, and it is suitable for straight cable laying. The more mountainous the terrain, the greater the tortuosity index, and the cable trench needs to avoid steep terrain areas. The support vector machine extracts features from the terrain relief value and the tortuosity index, combines with the slope classification data, and plans the cable trench path according to the minimum curvature principle. In mountainous areas, the large terrain relief value area usually avoids steep slope strike and detours along the gentle slope. In flat areas, the cable trench tries to choose straight laying to save engineering quantity. The path calculated by the minimum curvature principle not only meets the terrain constraint but also reduces the turning as much as possible. At the turning angle, a circular arc transition is used to avoid too small turning radius. According to the actual case, a 500-meter-long mountainous cable trench, after optimization, the actual laying length is 680 meters, increasing the detour distance of 180 meters to avoid steep slopes.

[0064] The tortuosity index reflects the deviation of the actual path from the straight line distance. In the plain area, the path is basically laid along the straight line, and the tortuosity index is close to 1.1. In hilly areas, due to the need to bypass areas with large slope, the tortuosity index increases to about 1.3. When the path turning angle exceeds 45 degrees, it indicates that there is a significant terrain obstacle or impassable area, at this time, the path is multiplied by a correction factor of 1.2, which reflects the increased construction difficulty and line loss at the turning. In the power supply path planning, a substation within a radius of 3 kilometers plans 12 main paths. By calculating the product of the unit length impedance and the actual length of each path, the total impedance value of the path is obtained. The path combination with the smallest total impedance contains 4 main paths, which extend in the southeast, southwest and northwest directions, forming the actual power supply range of the substation. On the east path, due to passing through a mountainous area with a slope of 25 degrees, the actual length of the path reaches 2.4 kilometers, which is 0.6 kilometers more than the straight line distance, but it is still better than other available paths. Therefore, the endpoint of this path is the power supply boundary point in this direction, marking the effective power supply range of the substation in that direction.

[0065] In calculating the tortuosity index of the cable trench path, the elevation point data of the area where the cable trench is located is extracted from the geographic database at a sampling interval of 20 meters, 400 sampling points are obtained within each square kilometer, the difference between adjacent elevation points is calculated, and the slope value is obtained by dividing the horizontal distance. According to the slope value, it is divided into 5 levels within the range of 0 to 45 degrees. The standard deviation value of the elevation point is calculated by the sum of squared deviations formula:

[0066]

[0067] wherein, the standard deviation of the sample elevation is represented by s, the sample size is represented by n, the first elevation of a sample, an average value representing the elevations of the samples.

[0068] The relative height difference is obtained by averaging the elevation of each sampling point minus the average elevation of the region. The terrain roughness is calculated from the maximum height difference between adjacent sampling points. The slope value is multiplied by a weight coefficient of 0.4, and the terrain roughness is multiplied by a weight coefficient of 0.6. The integrated index value is obtained by weighted summation. The quantization result between 0 and 1 is obtained by normalization based on the maximum value of the index. According to the slope classification value and the normalized result of the terrain roughness, the cable trench sinuosity index is calculated. The weighted average of the slope weight and the roughness weight is linearly mapped to the preset sinuosity index range. The sampling of elevation points in the geographic database is crucial for accurately reflecting the terrain features. Under a sampling interval of 20 meters, 400 elevation points are obtained per square kilometer of area, forming a regular grid of 20x20.

[0069] As an example of the present embodiment, in a certain mountainous region, the elevation values of 400 sampling points range from 320 meters to 580 meters, and the maximum height difference between adjacent points reaches 26 meters, reflecting the dramatic changes in the topography of the region. By calculating the ratio of the height difference to the horizontal distance between adjacent elevation points, the slope data range is obtained, which is between 5 degrees and 42 degrees, and is divided into 5 levels according to the slope value: 0-9 degrees for gentle area, 9-18 degrees for gentle slope area, 18-27 degrees for medium slope area, 27-36 degrees for steep slope area, and 36 degrees or more for steep slope area. The standard deviation calculation reflects the degree of dispersion of the terrain. In the same mountainous region, the average elevation of the 400 sampling points is 450 meters, and the standard deviation value of 38 meters is obtained by the sum of squared deviations calculation, indicating that the terrain in this region is relatively large. The relative height difference reflects the local topographic characteristics, and the elevation value of a certain sampling point is 15 meters higher than the average of the surrounding 8 adjacent points, indicating that this is a local topographic protruding part. The maximum height difference between adjacent sampling points in the region reaches 26 meters, corresponding to a higher terrain undulation. In the weight distribution, the terrain undulation accounts for 0.6 of the weight, and the slope value accounts for 0.4 of the weight. This distribution reflects the dominant influence of terrain undulation on the degree of cable trench meandering. Taking a certain region as an example, the terrain undulation is 0.85, the slope classification value is 0.65, and the weighted calculation obtains a comprehensive index value of 0.77. Divide this value by the maximum comprehensive index value in the region, 0.92, to obtain the normalized quantitative result, 0.84. When calculating the cable trench meandering index according to the normalized result, a linear mapping method is used. The normalized value of a certain region is 0.84, and the corresponding meandering index is 1.45, indicating that the actual laying length of the cable trench in this region increases by 45% compared to the straight-line distance. This increase is mainly due to bypassing areas with large height differences. In actual engineering, when a region with a standard deviation exceeding 35 meters is encountered, a bypass scheme is often used. In flat areas with a standard deviation of less than 15 meters, the cable trench is basically laid along a straight line. In this way, not only is the adverse terrain avoided, but the excessive increase in line length is also controlled.

[0070] S102, according to the power load distribution, a plurality of grid nodes are determined, each grid node is optimized, a plurality of substation positions to be laid out are obtained, a target substation is determined according to each substation position, a best path of the cable trench path is obtained according to the target substation, the best path is corrected according to the path meandering degree index, and the actual power supply range boundary of the target substation is obtained.

[0071] In the present embodiment, then the grid area unit area power consumption in the first region is obtained, the load density index is calculated according to the power consumption data and normalized load density distribution curve is obtained by dividing the maximum load density value in the region, and the load center coordinate point is determined through the distribution curve. The layout constraint boundary is constructed according to the load center coordinate point and the power supply point position, the grid nodes are set in the boundary range, and the grid nodes are pre-screened based on the power supply radius to obtain the screened grid nodes.

[0072] Then the simulated annealing algorithm is used to encode the screened grid nodes, and the target fitness value is calculated by multiplying the power supply distance by the weight and adding the load density multiplied by the weight; if the change rate of the target fitness value of adjacent iterations is less than a preset threshold, the substation position to be laid is determined from the corresponding grid node with the minimum fitness value after iteration optimization.

[0073] Then, the target substation is determined in the substation position to be laid, the terrain slope data of the area around the target substation in the geographic information database is obtained, and the impedance distribution of the search grid node is calculated according to the terrain slope data and the reference impedance value. According to the impedance distribution of the search grid node, the deep-first algorithm is used to select the adjacent grid points with the minimum impedance value to perform path traversal, and a set of traversal paths is obtained. For the set of traversal paths, the path tortuosity index is calculated by the ratio of the actual length of the path to the straight-line distance, and the paths with the path tortuosity index within the preset range are screened. According to the screened paths, a power supply path combination is constructed by extracting a coordinate point sequence, the total impedance value of the path is calculated by multiplying the unit length impedance by the path length, and the power supply range boundary point is determined according to the total impedance value of the path.

[0074] In an embodiment, a plurality of grid nodes are determined according to the power load distribution, and each grid node is optimized to obtain the substation position to be laid, including:

[0075] The load density index is calculated according to the power load distribution, and the normalized load density distribution curve is obtained according to the load density index and the load density value greater than the preset density value in the first area;

[0076] The load center coordinate point is determined according to the normalized load density distribution curve, the boundary range is constructed according to the load center coordinate point and the power supply point position in the first area, the grid nodes are set at a preset interval within the boundary range, and a plurality of grid nodes are obtained;

[0077] Each grid node is screened according to the preset power supply radius to obtain a plurality of screened grid nodes, and the simulated annealing algorithm is used to optimize each screened grid node to obtain a plurality of substation positions to be laid.

[0078] In this embodiment, the unit area power consumption in the grid area is collected, the load density index is calculated based on the power consumption data, and the load density index is normalized by dividing the maximum load density value of the region. The load center coordinate points of each region are calculated according to the normalized load density distribution curve. The layout constraint boundary is constructed according to the power supply point position and the load center coordinate, the uniform grid nodes are set at an interval of 200 meters within the boundary range, the grid nodes are pre-screened based on a power supply radius of 1 to 3 kilometers, and the pre-screened grid nodes are obtained.

[0079] The power supply coverage area of each node is calculated from 315 kilovolt-ampere to 1000 kilovolt-ampere capacity specification, the simulated annealing algorithm is used, the initial temperature value is set to 100, the temperature is reduced by 0.95, the pre-screening grid node code is calculated, the power supply distance is multiplied by 0.6 and the load density is multiplied by 0.4 to calculate the target fitness value, and the target fitness value is calculated in the preset iteration number. Compare the target fitness values of adjacent 50 iterations, when the change rate is less than 0.1%, it is judged that the optimization convergence condition is reached, from the grid node corresponding to the minimum fitness value after iteration optimization, the substation layout coordinate point is determined according to the unit area power consumption distribution and the power supply radius constraint.

[0080] As an example of the present embodiment, the power distribution network monitoring device collects power load data in the area every 5 minutes, obtains 288 sampling point data in 24 hours, and statistically obtains the unit area daily maximum load value. When the area of a certain residential area is 1 square kilometer, the daily maximum load density reaches 6000 kilowatts, the daily maximum load density of the commercial area under the same area reaches 8000 kilowatts, and the industrial area reaches 12000 kilowatts. By dividing the maximum load value of the area 12000 kilowatts, the normalized load density is 0.5, 0.67 and 1 respectively. The load density value at the load center position is significantly higher than that of the surrounding area. The layout constraint boundary is determined based on the position characteristics of the power supply point and the load center. The connecting line of the power supply point and the load center is used as the main axis, and the boundary is determined within 3 kilometers on both sides of the axis. Grid nodes are evenly arranged in the boundary according to the interval of 200 meters to form potential substation layout positions. Considering four capacity specifications of 315 kilovolt-ampere, 500 kilovolt-ampere, 800 kilovolt-ampere and 1000 kilovolt-ampere, the power supply radius of the grid node to the power load point changes in the range of 1 to 3 kilometers. The industrial load area selects 1000 kilovolt-ampere substation, the commercial area selects 800 kilovolt-ampere substation, and the residential area selects 500 kilovolt-ampere substation. The simulated annealing algorithm starts from a temperature value of 100, and the temperature is multiplied by a decay factor of 0.95 each time. In the iteration optimization process, power supply distance and load density are two mutually restrictive factors. The shorter the power supply distance, the smaller the line loss but the less the covered load; the more concentrated the load density, the more the covered load but the power supply distance may increase. The two factors are balanced by the weighting coefficients of 0.6 and 0.4 to calculate the target fitness value. Each temperature iteration is calculated 100 times, and the current optimal solution is recorded. When the algorithm converges, the target fitness value change of the last 50 iterations is compared. If the change rate is less than 0.1% continuously, it means that a relatively stable local optimal solution has been found.

[0081] As an example in this embodiment, the initial stage target fitness value is 0.85, and after 2000 iterations, it converges to 0.42, and the final determined substation position is 1.2 kilometers away from the load center, located between the two main power consumption areas. This position not only ensures a reasonable power supply radius, but also effectively covers the high load density area. The distance between 98% of the power consumption load points in the power supply range and the substation is within 2 kilometers, meeting the power supply radius requirement.

[0082] In an embodiment, according to the target substation, the optimal path of the cable trench path is obtained, and the optimal path is corrected according to the path winding degree index to obtain the actual power supply range boundary of the target substation, including:

[0083] According to the terrain slope data of the target substation and the reference impedance value, the impedance value along the path of the grid node to be searched is calculated;

[0084] The path traversal set is obtained by using the depth-first algorithm to traverse the path of the grid node with an impedance value less than the preset impedance value threshold.

[0085] The tortuosity index of each path in the traversal path set is calculated by using the actual length of each path and the corresponding straight-line distance, and the coordinate point sequence of the path with a tortuosity index less than the preset tortuosity is constructed to obtain a plurality of power supply path combinations.

[0086] Based on the impedance value and the length of each path, the total impedance value of each power supply path combination is obtained, and the power supply path combination with a total impedance value less than the preset total impedance value threshold is selected as the actual power supply range boundary.

[0087] In this embodiment, the terrain slope data of the target substation in the geographic information database is obtained, and the impedance distribution along the path of the search grid node is calculated according to the terrain slope data and the reference impedance value. According to the impedance distribution along the path of the search grid node, the depth-first algorithm is used to select the adjacent grid point with the minimum impedance value for path traversal to obtain the traversal path set. For the traversal path set, the path tortuosity index is calculated by the ratio of the actual path length to the straight-line distance, and the paths with a path tortuosity index within a preset range are screened. According to the screened paths, the coordinate point sequence is extracted to construct the power supply path combination, the total impedance value of the path is calculated by multiplying the unit length impedance by the path length, and the power supply range boundary point is determined according to the total impedance value of the path.

[0088] Specifically, after obtaining the terrain slope data of the target substation surrounding area, the line impedance distribution is calculated according to the line reference impedance value of 0.2 ohm per kilometer, the search grid nodes are divided at an interval of 50 meters, and the obstacle weight value of the impassable area is marked as 999. Then, the depth-first algorithm is used to traverse the path in the search grid, the adjacent grid point with the minimum impedance value is selected as the next search node each time, the path cost is calculated by accumulating the impedance value of the path segment and the obstacle weight, and the traversal path is sorted according to the value. The tortuosity index is calculated according to the ratio of the actual length of the path to the straight-line distance, the paths with the tortuosity index in the range of 1.1 to 1.5 are screened, the turning points of the path are judged based on the 45-degree turning threshold, and the path impedance at the turning points is recalculated by multiplying the path by a correction coefficient of 1.2. The coordinate point sequence is extracted from the screened path to construct a power supply path combination, the total impedance of the path is calculated by multiplying the unit length impedance by the path length, the power supply radius is calculated along the path, and the actual power supply range boundary point is determined on the path combination with the minimum total impedance.

[0089] The terrain slope data in the geographic information database reflects the terrain characteristics of different areas. In a mountainous area, the slope value varies from 10 degrees to 35 degrees, resulting in the need for detours for cable laying lines. A 50-meter grid interval is used to divide the search space, and 4000 grid nodes are formed in a 10-square-kilometer area. The line reference impedance is 0.2 ohm per kilometer, and in areas with a slope exceeding 30 degrees, the actual line impedance increases to 0.4 ohm per kilometer. For impassable areas such as buildings and water systems, an obstacle weight value of 999 is set to allow the search algorithm to automatically avoid these areas. Then, a depth-first search is performed from the substation location, and the point with the minimum impedance is selected as the next search location from the adjacent 8 grid points each time. Specifically, from the substation to a power load point within a range of 2 kilometers from the power supply radius, the algorithm searches more than 200 grid nodes, each of which records the cumulative path cost from the starting point to the point, including the superposition of the impedance value along the path and the obstacle weight. In addition, multiple feasible paths are found during the search process, which are sorted in ascending order of the value according to the value, and the path with the smallest value is often the optimal path after detouring around the obstacles.

[0090] S103, based on the cable load value in the actual power supply range boundary and the path tortuosity index, obtain the cable segmented area, use the dynamic programming algorithm to calculate the cable segmented area, obtain multiple candidate joint positions of the cable, and select the candidate joint positions of each cable according to the cable along-line temperature curve to obtain multiple intermediate joint installation positions of the cable in the actual power supply range.

[0091] In the embodiment, the current load value in the actual power supply range is obtained, the voltage drop amplitude is calculated according to the current load value and the path length value, the cable segmentation area is obtained through the voltage drop amplitude, the dynamic programming algorithm is used to process the cable segmentation area, the candidate joint coordinate point is calculated according to the dynamic programming algorithm, and the conductor temperature data is collected from the candidate joint coordinate point; the maximum shear stress distribution value is calculated for the candidate joint coordinate point, the stress limiting area is judged according to the maximum shear stress distribution value, and the candidate joint coordinate point is screened through the stress limiting area; the cable temperature rise curve along the line is generated according to the candidate joint coordinate point, and if the temperature rise curve is lower than the temperature threshold value and the maximum shear stress distribution value is lower than the material strength limit, the candidate joint coordinate point is determined as the intermediate joint installation point.

[0092] In an embodiment, the cable segmentation area is obtained based on the cable load value in the boundary of the actual power supply range and the path winding degree index, including:

[0093] The current load value in the boundary of the actual power supply range is obtained, the voltage drop amplitude is obtained according to the current load value and the path winding degree index, and if the voltage drop amplitude is greater than a preset drop amplitude threshold value, the path in the actual power supply range is segmented to obtain the cable segmentation area.

[0094] In the embodiment, the current load value in the boundary of the actual power supply range is obtained, the voltage drop amplitude is calculated according to the path length value and the path winding degree index, the laying path is segmented when the voltage drop amplitude exceeds 5%, and the appropriate specification is selected in the range of 240 to 400 square millimeter cable cross section.

[0095] In an embodiment, the dynamic programming algorithm is used to calculate the cable segmentation area to obtain a plurality of candidate joint positions, the cable temperature rise curve along the line is used to screen the candidate joint positions of each cable to obtain a plurality of intermediate joint installation positions of the cable in the actual power supply range, including:

[0096] According to the cable segmentation area, a plurality of candidate joint positions are determined in a preset interval range by using the dynamic programming algorithm according to a set search depth threshold value;

[0097] The conductor temperature data at each candidate joint position is collected;

[0098] The stress analysis is performed according to each candidate joint position to obtain the maximum shear stress distribution value of each candidate joint position, the stress limiting area is judged according to the maximum shear stress distribution value, and the candidate joint position to be arranged is screened through the stress limiting area;

[0099] If the conductor temperature data corresponding to the candidate joint position to be arranged is less than a preset temperature threshold value, and the maximum shear stress distribution value corresponding to the candidate joint position to be arranged is less than a preset material strength, the candidate joint position to be arranged is determined as the intermediate joint installation position.

[0100] In this embodiment, dynamic programming algorithm is used to calculate cable section scheme, set the maximum search depth of 100 layers, mark the alternative joint position in the range of 500 to 800 meters, collect conductor temperature data from each alternative position, generate cable temperature distribution curve along the line. At the cable bending, the maximum shear stress criterion is used to calculate the stress distribution value, and the stress concentration area is marked as the joint arrangement restriction point. According to the position of the restriction point, the alternative joint position is screened, and the joint installation area is set where the stress value is less than the material strength limit. Based on the current load distribution, the temperature rise curve along the cable is generated, and the section with temperature lower than 90 degrees is identified from the temperature rise curve. The dynamic programming result is superimposed on the temperature rise limited section, and the intermediate joint coordinate point is determined in the section meeting the stress limit and temperature rise limit.

[0101] The current load value directly determines the voltage drop and temperature rise of the cable. In a certain 10kV distribution line, the load current gradually decreases from 280 amperes at the outlet end of the substation to 120 amperes at the end. When the total length of the cable reaches 1200 meters, and the meandering index is 1.3, the calculated voltage drop amplitude is 5.8%, which exceeds the limit value of 5%. At this time, the line needs to be divided into two sections, and a cable with a cross section of 300 square millimeters is selected, so that the voltage drop of each section is controlled within 3%. Dynamic programming algorithm sets a calculation node every 50 meters along the cable at a search depth of 100 layers. On a 1200-meter line, a total of 24 nodes are set, each of which records the cumulative voltage drop value and temperature rise value from the starting point. At a certain node, the temperature data shows that the conductor temperature reaches 85 degrees, close to the limit value of 90 degrees, indicating that this place is not suitable for setting joints. Through dynamic programming calculation, two alternative joint positions that meet the installation spacing requirements are found at 600 meters and 750 meters. In the stress analysis of the cable bending, the bending angle at a certain place reaches 45 degrees, and the maximum shear stress calculation value reaches 75% of the material strength. The range of 100 meters before and after this bending point is marked as the joint arrangement restriction area. Another 30-degree bending, the stress value is only 45% of the material strength, which can be considered for arranging joints. By superimposing the stress distribution of the entire cable, 5 stress concentration areas are identified, which are excluded from the joint installation scheme.

[0102] In the complete temperature rise curve, the temperature of the outgoing line end of the substation reaches 88 degrees due to the maximum current, the temperature of the middle section fluctuates between 75 degrees and 82 degrees, and the temperature of the end decreases to 65 degrees. In combination with the optimization results of dynamic programming and the stress limiting conditions, the final position of the middle joint is determined at a distance of 720 meters from the substation. The conductor temperature at this position is 78 degrees, which is lower than the limit of 90 degrees; the local stress is only 38% of the material strength, which has sufficient mechanical strength margin; and the position is located in the relatively flat section between the two stress concentration areas. Through this multi-dimensional comprehensive optimization, both the electrical performance of the cable operation and the mechanical reliability of the joint installation position are ensured. At the same time, the selection of the position also balances the voltage drop distribution of the front and rear sections of the cable, with a voltage drop of 2.8% in the front section and a voltage drop of 2.6% in the rear section, which is basically balanced.

[0103] An index of the degree of meandering in the cable trench path is identified, and if the degree of meandering is less than a set degree of meandering index threshold value, it is considered that the cable trench path belongs to a flat area, and the cable electrical parameters are obtained to calculate the maximum allowable distance between adjacent joints, and under the condition of meeting the maximum allowable distance, the cable middle joint is arranged in the flat area, and if the distance between two flat areas is greater than a preset threshold value, an additional middle joint is arranged at the lowest meandering point between the two flat areas, an optimization model is established to minimize the sum of the meandering degree index, and the position of the cable middle joint is optimized and solved to obtain the arrangement scheme of the cable middle joint.

[0104] The degree of meandering value is obtained by calculating the ratio of the actual length between adjacent points to the straight line distance according to the path point coordinates, and the flat area range is determined from the degree of meandering value; the interval distance between adjacent flat areas is calculated according to the flat area range, and the section separation position is determined by the interval distance; the initial joint arrangement scheme is generated in the flat area range by using a genetic algorithm, and the supplementary arrangement position is obtained from the local minimum meandering point; the sum of the meandering degree values of each section is calculated for the initial joint arrangement scheme, and the final middle joint arrangement coordinates are obtained by iterative optimization of the genetic algorithm.

[0105] In addition, specifically, the path point coordinates of the cable trench path are collected at intervals of 20 meters, the degree of meandering value is obtained by calculating the ratio of the actual length at each path point to the straight line distance, the flat area range is marked from the path point with a degree of meandering value less than 1.2, and the maximum allowable distance of adjacent joints is obtained in the interval of 500 to 800 meters. The interval distance between adjacent flat areas is calculated by the path point coordinates, the section separation position is recorded for the area with an interval greater than 1000 meters, and the local minimum meandering point in the non-flat area is calculated based on the deviation rate of the actual path length from the straight line distance.

[0106]

[0107] In the formula, represents a deviation rate based on an actual path length from a straight-line distance, represents an actual path length, represents a straight-line distance between the first point and the last point.

[0108] The genetic algorithm starts from 100 initial solutions to generate initial joint arrangement schemes within the marked flat area. Local minimum meander points are added as supplementary arrangement positions for sections that do not meet the maximum allowed distance limit. The path is segmented according to all joint arrangement positions, the sum of the meandering degree values of each section is calculated, and the genetic algorithm is set to have an upper limit of 200 iterations. In each iteration, the joint arrangement positions are adjusted, and the final arrangement coordinates are obtained based on the meandering degree total sum minimization criterion. The meandering degree of the cable trench path is measured by the ratio of the actual length to the straight-line distance. Using a 20-meter sampling interval, 100 path point coordinates are obtained on a 2-kilometer-long trench. The actual length of a certain section of the path is 560 meters, and the straight-line distance is 480 meters. The calculated meandering degree value is 1.17, which is less than the threshold value of 1.2, and it is determined that this section belongs to the flat area. In the flat area, the maximum allowed distance between adjacent joints depends on the cable specifications. For a 300-square-millimeter cable, the maximum allowed distance is set to 750 meters. The distribution of flat areas is often discontinuous. In a certain trench, three flat areas are identified. The first one is 420 meters long, the second one is 380 meters long, and the third one is 460 meters long. The interval between the first and the second is 1200 meters, which exceeds the threshold value of 1000 meters, and a joint needs to be added in the middle. By calculating the meandering degree of each path point in this 1200-meter section, a local minimum point with a meandering degree of 1.25 is found as a potential joint arrangement position. The genetic algorithm starts from 100 random arrangement schemes for optimization. In the initial schemes, the probability of joint arrangement in the flat area is higher. For each arrangement scheme, check whether the distance between adjacent joints meets the 750-meter limit. If a certain section exceeds the limit, introduce the previously identified local minimum meander point as a new joint position. In a certain iteration, a arrangement scheme contains 5 joints, of which 3 are located in the flat area and 2 are located at the local minimum meandering points. The algorithm continuously optimizes the joint positions through 200 iterations. The meandering degree total sum of the entire path is calculated in each iteration. In the initial stage, the meandering degree total sum of a certain arrangement scheme is 6.8; after optimization, it decreases to 5.4. The final joint arrangement coordinates include: 3 points in the flat area with coordinates (350, 420), (1200, 380), and (2100, 460), and two local minimum meandering points (800, 350) and (1600, 400). This arrangement scheme not only meets the joint spacing limit but also maximizes the use of flat terrain, making the overall meandering degree minimal. Joints arranged in flat areas are convenient for construction and maintenance, and joints added at local minimum meandering points solve the problem of excessive distance between adjacent flat areas.

[0109] S105, calculate the annual maintenance cost, terrain restriction data and construction cost data of each intermediate joint installation position by using the analytic hierarchy process, obtain the evaluation score of each intermediate joint installation position, calculate the distance from each intermediate joint installation position to the actual power supply boundary, obtain multiple distance values, and determine the intermediate joint installation position with a distance value less than a preset distance value and an evaluation score less than a preset evaluation value as the to-be-optimized position.

[0110] In the embodiment, the fault records and maintenance records of the intermediate joint installation positions are obtained, and the annual maintenance cost value is calculated according to the fault records and maintenance records; a three-order judgment matrix is established according to the annual maintenance cost value, terrain restriction data and construction cost data, and a characteristic vector is obtained by evaluating the judgment matrix through a scale value; a weight vector is obtained by normalizing the characteristic vector, and if the consistency ratio of the weight vector is less than a preset threshold, the terrain restriction weight value, the maintenance cost weight value and the construction cost weight value are extracted from the weight vector; the three index data of the intermediate joint installation position and the weight values are weighted and calculated to obtain a comprehensive score, the comprehensive score is interval mapped to obtain an evaluation score, and the intermediate joint installation position sorting result is generated according to the evaluation score.

[0111] According to the actual power supply range boundary, the distance value of the intermediate joint to the boundary is extracted, and the cable joint to be optimized is determined according to the evaluation score being lower than a preset threshold and the distance to the boundary being less than a preset range.

[0112] In an embodiment, the annual maintenance cost, terrain restriction data and construction cost data of each intermediate joint installation position are calculated by using the analytic hierarchy process, and the evaluation score of each intermediate joint installation position is obtained, including:

[0113] A judgment matrix of each intermediate joint installation position is established according to the annual maintenance cost value, terrain restriction data and construction cost data of each intermediate joint installation position;

[0114] Based on the judgment matrix of each intermediate joint installation position, a characteristic vector of each intermediate joint installation position is obtained by calculating using a scale value, the characteristic vector is normalized to obtain a weight vector, and if the consistency ratio of the weight vector is less than a preset ratio, the terrain restriction weight value, the maintenance cost weight value and the construction cost weight value are extracted from the weight vector;

[0115] The terrain restriction weight value, the maintenance cost weight value and the construction cost weight value are weighted and calculated with the corresponding annual maintenance cost value, terrain restriction data and construction cost data to obtain the evaluation score of each intermediate joint installation position.

[0116] In the present embodiment, the failure records and maintenance records of each intermediate joint installation position in the past three years are obtained, the annual maintenance cost is calculated according to the hourly labor unit price of 200 yuan, and the annual failure rate index value is obtained by normalizing the maximum value of the total number of failures of each candidate position. A three-level judgment matrix is established by AHP, the relative importance of the three indexes of terrain restriction, maintenance cost and construction cost is evaluated by 1 to 9 scale, the weight vector is calculated by calculating the eigenvalue and eigenvector of the matrix, and the weight consistency ratio is tested whether it is less than 0.1. The normalized weight value is kept to three decimal places after the matrix eigenvector is normalized, and the terrain restriction weight 0.3, the maintenance cost weight 0.5 and the construction cost weight 0.2 are extracted as the index weight value. Based on the index weight value, the terrain restriction, maintenance cost and construction cost of each intermediate joint installation position are weighted and summed, the weighted result is mapped to the interval of 0 to 100 to obtain the comprehensive evaluation score, and the intermediate joint installation position is sorted in descending order according to the score value. The failure records and maintenance records of the cable joint reflect the operating conditions of different arrangement positions.

[0117] As an example of this embodiment, taking 5 intermediate joint installation positions as an example, the failure records in the past 3 years are 3 times, 2 times, 4 times, 1 time and 2 times, respectively, and the maximum value is 4 times. The annual failure rates obtained by normalization processing are 0.75, 0.5, 1.0, 0.25 and 0.5, respectively. The maintenance man-hour record shows that each failure requires an average of 16 hours of processing, and the annual maintenance cost is 9600 yuan, 6400 yuan, 12800 yuan, 3200 yuan and 6400 yuan, respectively, according to the hourly rate of 200 yuan. The analytic hierarchy process quantifies the relative importance between indicators by constructing a judgment matrix. In the three-order judgment matrix, the importance ratio of maintenance cost to terrain restriction is 3, and the importance ratio of maintenance cost to construction cost is 2, indicating that maintenance cost is the most important among the three indicators. The importance ratio of terrain restriction to construction cost is 1.5, reflecting the influence of terrain factors. By calculating the eigenvector of the matrix and normalizing it, the weight of maintenance cost is 0.5, the weight of terrain restriction is 0.3, and the weight of construction cost is 0.2. The consistency ratio calculation value is 0.05, which is less than the threshold value of 0.1, indicating that the weight distribution is reasonable. After determining the weight, the three indicators of each intermediate joint installation position are quantified. The indicator value of a certain intermediate joint installation position is: terrain restriction 0.8 (1 is the worst, 0 is the best), maintenance cost 0.6, and construction cost 0.4. Multiply these three indicator values by the corresponding weights 0.3, 0.5 and 0.2 respectively, and then sum them up to get the weighted result 0.64. In order to make the evaluation result more intuitive, multiply the weighted result by 100 to map it to the 0 to 100 interval, and get the comprehensive evaluation score of this intermediate joint installation position, which is 36 points. This score reflects the comprehensive performance of the position in the three evaluation dimensions. The same calculation is performed on the 5 candidate positions, and the comprehensive evaluation scores obtained are 65 points, 78 points, 42 points, 83 points and 71 points, respectively. The fourth intermediate joint installation position with the highest score has the highest construction cost, but due to its good terrain conditions and low maintenance cost, it has the best overall performance. The third intermediate joint installation position has the lowest score, mainly affected by the high failure rate and maintenance cost. Through this multi-dimensional quantitative evaluation, both long-term operation and maintenance costs are considered, and terrain and construction factors are also taken into account, making the position selection more objective and reasonable. Different weights are used for different types of indicators, which also reflects the differentiated consideration of the importance of each factor in the evaluation process.

[0118] S105, establishing a polar coordinate sampling network according to the position to be optimized, determining the sampling point positions in the polar coordinate sampling network, calculating the power supply distance and voltage drop amplitude of each sampling point position, selecting the sampling point position with a voltage drop amplitude satisfying a preset condition as the optimized position, and obtaining the final optimized position according to the load density distribution within the actual power supply range boundary.

[0119] In the embodiment, a polar coordinate sampling grid is established according to the position to be optimized, the power supply distance and the voltage drop amplitude are calculated for the sampling grid, and a new arrangement coordinate point is obtained from the sampling points that meet the voltage drop amplitude threshold.

[0120] According to the load distribution layer within the actual power supply range boundary, the power density value is calculated, the cable branch power supply coverage area is calculated for the power density value, and the load density maximum point in the power supply coverage area is obtained as the branch connection point. The position combination is performed on the new arrangement coordinate point and the branch connection point, if the voltage drop amplitude value of the combination scheme is less than the preset threshold, the coordinate combination with the highest evaluation score is determined from the combination schemes that meet the condition.

[0121] In an embodiment, the final optimized position is obtained according to the load density distribution within the actual power supply range boundary, including:

[0122] According to the load density distribution within the actual power supply range boundary, the position with a load density greater than a preset load density threshold is selected as a branch connection point.

[0123] According to the branch connection point and the optimized position, a new position combination is obtained, if the voltage drop amplitude value of the new position combination meets the preset condition, the new position combination is determined as the final optimized position.

[0124] In the embodiment, the actual power supply range boundary layer with a resolution of 10 meters is used, the distance value from the intermediate joint position to the power supply boundary is extracted, the joints with an evaluation score lower than 60 and a distance to the boundary less than 500 meters are marked as to-be-optimized points. At the same time, the coordinate space within a range of 200 meters around the to-be-optimized point is recorded, a polar coordinate search grid is established for each to-be-optimized point, equidistant sampling points are generated within the range of 200 meters, the power supply distance and the voltage drop amplitude of the sampling point position are calculated, and new arrangement coordinate points are extracted from the sampling points that meet the 5% voltage drop amplitude limit.

[0125] Based on the load distribution layer within the actual power supply range boundary, the power density is calculated, the cable branch power supply coverage area is calculated according to the 400 kilovolt ampere capacity limit, and the point with the most concentrated load within the power supply coverage area is selected as the branch connection point. The position combination is performed on the new arrangement coordinate point and the branch connection point, the voltage drop amplitude total value and the joint evaluation score of the combination scheme are calculated, and the coordinate combination with the highest evaluation score is selected as the final arrangement position from the schemes with a voltage drop amplitude less than 5%.

[0126] It should be noted that the 10-meter resolution can accurately reflect the actual power supply range of the substation.

[0127] As an example of the embodiment, in a certain area, there are 8 cable joints to be evaluated, among which the evaluation scores of 3 joints are 52, 48 and 55 respectively, and the distances to the power supply range boundary are 420 meters, 380 meters and 450 meters respectively. The 3 joints meet the condition of evaluation score lower than 60 and distance to the boundary less than 500 meters at the same time, and are marked as to-be-optimized points. Taking one joint with a score of 52 as an example, a sampling grid is generated within a range of 200 meters around the joint. The polar coordinate search constructs the sampling points through two dimensions of angle and radius. Within the range of 200 meters, a direction is taken every 15 degrees and a distance point is taken every 20 meters to form the sampling grid. For a to-be-optimized joint, a total of 96 sampling points are generated.

[0128] By calculating the power supply distance and voltage drop amplitude of each sampling point, it is found that the sampling point at 160 meters from the original position in the direction of north by east 30 degrees has a voltage drop amplitude of 4.2%, which meets the limit requirement of 5%. The load distribution layer shows the spatial distribution characteristics of electricity density. In the power supply area near the to-be-optimized joint, two areas with high electricity density are identified, with unit area load density reaching 350 kilovolt-ampere per square kilometer and 280 kilovolt-ampere per square kilometer respectively. Considering the capacity limit of 400 kilovolt-ampere, the maximum power supply radius of the branch cable is calculated to be 800 meters. Within this range, the center of the area with a load density of 350 kilovolt-ampere per square kilometer is selected as the branch connection point. The final arrangement scheme needs to meet the requirements of voltage drop amplitude and evaluation score at the same time. After combining the new arrangement coordinate point with the branch connection point, multiple feasible schemes are obtained. In one of the schemes, the voltage drop amplitude of the main cable joint after moving to the new position is 4.2%, and the voltage drop amplitude of the branch cable is 3.8%, both of which meet the limit of 5%. At the same time, the evaluation score of the new position is improved to 78, which is significantly improved compared with the original 52. This scheme has the highest evaluation score among all the schemes that meet the voltage drop amplitude requirement, and is therefore selected as the final arrangement scheme. Through this multi-dimensional optimization, both the power supply quality and the rationality of joint arrangement are ensured. For the other two to-be-optimized joints, the same method is used to find their respective optimal arrangement schemes, which improve the evaluation scores from 48 to 72 and from 55 to 75 respectively.

[0129] S106, according to the actual power supply range boundary and the final optimized position, the power supply area of the power distribution network is divided to obtain an initial grid division result, and the grid boundary is corrected based on the initial grid division result to obtain a final result of the grid division of the power distribution network.

[0130] In the embodiment, the initial grid division result is obtained according to the actual power supply range boundary by using the Thiessen polygon algorithm, the load center point coordinates are marked according to the initial grid division result, the circular coverage area is constructed for the load center point coordinates, and the adjacent area intersection area ratio is calculated through the circular coverage area; if the intersection area ratio exceeds the preset threshold value, the grid boundary is adjusted according to the offset, and the boundary correction is performed on the area where the load center point deviates from the original position by more than the set threshold value; the support vector regression algorithm is used to process the load center point coordinates and the power supply radius data, the grid boundary direction is determined according to the processing result, and the grid boundary line is corrected through the grid area data and the load distribution data.

[0131] In an embodiment, the grid boundary correction is performed based on the initial grid division result to obtain the final result of the grid division of the power distribution network, including:

[0132] The coverage area with a preset radius is constructed according to the load center points of each network in the initial grid division result, and a plurality of coverage areas are obtained;

[0133] The proportion of the intersection area of each coverage area and the adjacent coverage area is calculated, and it is judged whether the proportion exceeds the preset proportion of the total area of the coverage area; if it exceeds, the voltage distribution of the coverage area is calculated, and if the voltage distribution reaches the rated voltage, the boundary of the grid corresponding to the coverage area is adjusted according to the preset offset to obtain the adjusted grid boundary;

[0134] The final result of the grid division of the power distribution network is obtained according to the adjusted grid boundary.

[0135] In the embodiment, the Thiessen polygon algorithm is used to preliminarily divide the power supply area, the grids are merged based on the constraint condition of the minimum area of 1 square kilometer, and the load center points of each grid are marked. The circular coverage area with a radius of 3 kilometers is constructed for the load center points, the proportion of the intersection area of adjacent coverage areas is calculated, the voltage distribution in the intersection area is quantified by the voltage drop limit value, and it is judged whether the intersection area exceeds 10% of the total area. In the area where the intersection area exceeds 10%, the grid boundary is adjusted according to the offset of 50 to 100 meters, the boundary correction is performed on the area where the load center point deviates from the original position by more than 500 meters, and the boundary points are smoothed based on the distance threshold of 200 meters. The support vector regression is used to establish the corresponding relationship between the load center coordinates and the power supply radius, the final direction of the grid boundary is determined through the corresponding relationship, and the grid boundary line is corrected according to the grid area and the load distribution.

[0136] As an example in this embodiment, the Voronoi partition divides the initial boundary of the power supply area based on the substation location. There are 5 substations in a certain area, and 5 initial grids are obtained by the Voronoi algorithm, in which the smallest grid area is 0.8 square kilometers, which is less than the threshold of 1 square kilometer, and needs to be merged with the adjacent grid. The areas of the merged 4 grids are 2.4, 1.8, 2.2 and 1.6 square kilometers respectively. The load center in each grid is calculated by weighted average of power consumption, and the offset distance of the obtained load center point relative to the substation is between 300 and 450 meters.

[0137] The circular coverage area reflects the actual power supply capacity of the substation. A circle with a radius of 3 kilometers is drawn to form a coverage area. The coverage circles of two adjacent substations overlap, and the proportion of the overlapping area to the area of a single circle is calculated. In a certain overlapping area, the area proportion reaches 12%, exceeding the threshold of 10%. By calculating the voltage distribution in the overlapping area, it is found that the maximum voltage drop reaches 6.2% of the rated voltage, and the grid boundary needs to be adjusted.

[0138] The boundary adjustment prioritizes the position of the load center. For the area with excessive overlapping area, the boundary is offset to the side with less load. On a certain boundary, the distance from the original boundary to the load center is 420 meters, and after a 75-meter offset adjustment, the distance from the new boundary to the load center becomes 345 meters, meeting the maximum offset limit of 500 meters. After boundary adjustment, a 200-meter distance threshold is used to filter and smooth the boundary points, removing the local jagged boundary. The support vector regression establishes a mapping relationship between the load center position and the power supply radius. In the divided grid, when the load center is 350 meters away from the substation, the actual power supply radius is 2.8 kilometers; when the load center is 420 meters away from the substation, the power supply radius is shortened to 2.6 kilometers. This mapping relationship guides the determination of the final boundary. Through fine-tuning of the boundary line, the grid area and load distribution are more matched. After adjustment, a certain grid has an area of 2.1 square kilometers, the load center is located 380 meters northeast of the substation, and the power supply radius is 2.7 kilometers, forming an independent power supply unit with balanced load distribution and reasonable power supply range.

[0139] The power distribution network whole-process management and control method provided by the embodiment of the present application, as shown in Figure 2 , is a flowchart of the power distribution network whole-process management and control method, which includes steps S201-S204, wherein Figure 2 , S201, obtaining the final result of the power distribution network grid division.

[0140] S201, obtaining the final result of the power distribution network grid division.

[0141] In this embodiment, the final result of the power distribution network grid division is obtained by using the artificial intelligence-based power distribution network grid division method in the above embodiment.

[0142] By dividing the power distribution grid, a large and complex power distribution grid area can be divided into multiple smaller, clear boundary grid units. Each grid has a dedicated operation and maintenance personnel or team responsible for management. This can more finely grasp the equipment operating conditions, fault conditions, etc. in each grid, facilitating quick problem location and taking appropriate measures.

[0143] S202, according to the final result of the power distribution grid division, collecting equipment operating state data according to the sampling interval, quantifying the voltage, current and temperature in the operating state data to obtain the equipment state mapping matrix.

[0144] In this embodiment, the substation layout and cable channel arrangement optimization parameters in each grid are obtained, the equipment operating state data is collected according to a 5-minute sampling interval, and the voltage, current and temperature indicators are quantitatively scored to generate an equipment operating state mapping matrix from the scoring results.

[0145] S203, constructing a construction constraint control matrix according to the equipment state mapping matrix, comparing the construction process monitoring data with the equipment rated value based on the control matrix to obtain a construction quality evaluation index; calculating the equipment operating state score according to the construction quality evaluation index, and marking the equipment as a warning state when the equipment operating state score is lower than a preset operating state evaluation threshold; generating an equipment maintenance cycle according to the warning state.

[0146] In this embodiment, according to the equipment state mapping matrix, a progress quality control matrix under construction constraints, i.e. a construction constraint control matrix, is constructed using deep reinforcement learning. The construction progress deviation is controlled within 10%, the monitoring data in the construction process is compared with the equipment rated value, and the construction quality evaluation index is generated from the real-time monitoring data. According to the monitoring data, the equipment operating state score is calculated, and when the score is lower than 80 points, it is marked as a warning state. A 3- to 6-month maintenance cycle is automatically generated according to the equipment state score, and the maintenance opportunity is determined by historical monitoring data.

[0147] S204, quantitatively statistics the equipment state changes in the equipment maintenance cycle to obtain a statistical result, calculating a maintenance quality score according to the statistical result, correcting the maintenance scheme according to the maintenance quality score, and obtaining an updated equipment inspection and maintenance scheme.

[0148] In this embodiment, the equipment state changes in the maintenance cycle are quantitatively statistics, the maintenance quality score is calculated from the maintenance implementation data, the inspection frequency is corrected by less than 20% according to the score, and the equipment inspection and maintenance procedures are updated based on the correction result.

[0149] It should be noted that the maintenance scheme refers to the inspection frequency.

[0150] As an example of the present embodiment, the power distribution network equipment operating state data includes multiple monitoring indicators. Taking a certain cable line as an example, operating data is collected every 5 minutes, including current load rate, cable surface temperature, insulation resistance value, etc. When the current load rate reaches 85%, the cable surface temperature reaches 65 degrees, and the insulation resistance drops to 70% of the design value, the equipment state score drops to 75 points, triggering the early warning threshold. Through 24 hours of continuous data analysis, it is found that the line often appears overloaded during 14:00-17:00 on weekdays. The quality control of the construction process involves multiple dimensional constraint conditions. In the cable trench construction, the original construction period is 45 days, the actual completion time is 48 days, and the progress deviation is 6.7%, which is within the allowable range of 10%. The construction quality monitoring data shows that the minimum bending radius of the cable laying is 15 times the cable outer diameter, and the trench backfill compactness reaches 95%, which meets the design requirements. Deep reinforcement learning optimizes the construction progress under the premise of ensuring engineering quality by setting a composite reward function of progress and quality.

[0151] The equipment operating state score directly affects the determination of the maintenance period. A recent state score of a certain cable is 82 points, higher than the early warning value of 80 points, and the system automatically sets the maintenance period to 6 months. Another cable with a state score of 76 points due to local overheating has its maintenance period adjusted to 3 months. Historical data analysis shows that equipment with a state score between 75 and 80 points has a significantly increased probability of failure within 3 months. Maintenance quality assessment is achieved through state comparison at multiple time points. After maintenance on a certain early warning cable, its operating state score increased from 76 points to 94 points, and the maintenance quality score was 92 points. Based on this result, the preventive maintenance period in the maintenance plan was shortened by 15%, and the inspection frequency was revised based on the original design parameters. Six-month tracking data shows that after adopting the revised maintenance procedures, the state score of this type of cable has stabilized above 85 points. Through this closed-loop feedback mechanism, the operation and maintenance procedures are continuously optimized in practice, forming a data-driven intelligent operation and maintenance system. In another case, the cable joint with decreased insulation performance was detected and replaced under power, which improved the state score of the entire line by 12 points, verifying the effectiveness of the preventive maintenance strategy.

[0152] The technical features of the above embodiments can be combined in any way. To make the description concise, not all possible combinations of the technical features in the above embodiments are described, but as long as the combinations of the technical features do not exist, they should be considered as within the scope of the present disclosure.

[0153] The above-described specific embodiments further illustrate the purpose, technical solutions and beneficial effects of the present application. It should be understood that the above-described specific embodiments are merely examples of the present application and are not intended to limit the protection scope of the present application. It is particularly pointed out that any modification, equivalent replacement, improvement, etc. made by those skilled in the art within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A distribution network grid division method based on artificial intelligence, characterized in that: include: Obtaining terrain characteristic parameters and power load distribution of a first area within the target distribution network grid area, performing quantitative analysis on the terrain characteristic parameters to obtain a regional winding degree index of the first area, obtaining terrain characteristics based on the regional winding degree index, and obtaining a cable trench path based on the minimum curvature principle and the terrain characteristics; Determining a plurality of grid nodes based on the power load distribution, optimizing each of the grid nodes to obtain a plurality of substation locations to be laid out, determining a target substation based on each of the substation locations, obtaining an optimal path for the cable trench path based on the target substation, and modifying the optimal path based on a path winding degree index to obtain an actual power supply range boundary of the target substation; Based on the cable load value and the path winding degree index within the actual power supply range boundary, a cable segmentation area is obtained, and the cable segmentation area is calculated using a dynamic programming algorithm to obtain multiple alternative joint positions for the cables. The alternative joint positions of each cable are screened according to the temperature rise curve along the cable line to obtain multiple intermediate joint installation positions of the cables within the actual power supply range; Calculating the annual maintenance cost, terrain restriction data, and construction cost data of each intermediate joint installation location using the analytic hierarchy process to obtain an evaluation score for each intermediate joint installation location; calculating the distance from each intermediate joint installation location to the actual power supply boundary to obtain multiple distance values; and determining the intermediate joint installation location having a distance value less than a preset distance value and an evaluation score less than the preset evaluation value as a location to be optimized; Establishing a polar coordinate sampling network based on the position to be optimized, determining the sampling point positions in the polar coordinate sampling network, calculating the power supply distance and voltage drop amplitude of each sampling point position, selecting the sampling point position whose voltage drop amplitude meets a preset condition as the optimized position, and obtaining the final optimized position based on the load density distribution within the boundary of the actual power supply range; The power supply area of ​​the distribution network is divided according to the actual power supply range boundary and the final optimized position to obtain an initial grid division result, and grid boundary correction is performed based on the initial grid division result to obtain a final result of the distribution network grid division.

2. The method for gridding a distribution network based on artificial intelligence according to claim 1, wherein: The quantitative analysis of the terrain characteristic parameters to obtain a regional winding degree index of the first area includes: Calculating, based on the terrain characteristic parameters, a height difference ratio between adjacent sampling points within the first area, and obtaining the slope of the sampling point based on the height difference ratio; Calculate the contour line density distribution within the first area, sample the terrain within the first area at preset intervals based on the contour line density distribution, obtain cross-sectional data, and obtain a regional winding degree index based on the cross-sectional data and the straight-line distance corresponding to the cross-sectional data.

3. The method for gridding a distribution network based on artificial intelligence according to claim 1, wherein: The step of determining a plurality of grid nodes according to the power load distribution, optimizing each of the grid nodes, and obtaining a substation location to be laid out includes: Calculating a load density index according to the power load distribution, and obtaining a normalized load density distribution curve according to the load density index and a load density value greater than a preset density value in the first area; determining a load center coordinate point according to the normalized load density distribution curve, constructing a boundary range according to the load center coordinate point and the positions of power supply points in the first area, and setting grid nodes at preset intervals within the boundary range to obtain a plurality of grid nodes; The grid nodes are screened according to a preset power supply radius to obtain a plurality of screened grid nodes. Simulated annealing algorithm is used to optimize the screened grid nodes to obtain a plurality of substation locations to be laid out.

4. The method for dividing a distribution network grid based on artificial intelligence according to claim 1, wherein: The step of obtaining an optimal cable trench path according to the target substation, and correcting the optimal path according to the path winding index to obtain an actual power supply range boundary of the target substation includes: Calculating the impedance value along the grid node to be searched according to the terrain slope data and the reference impedance value of the target substation; A depth-first algorithm is used to traverse the paths of the grid nodes whose impedance values ​​along the path are less than a preset impedance value threshold to obtain a traversal path set; Calculating the path winding index of each path using the actual length of each path in the traversal path set and the straight-line distance corresponding to each path, and constructing multiple power supply path combinations using a sequence of coordinate points of paths whose path winding index is less than a preset winding index; Based on the impedance value and the length of each path, the total impedance value of each power supply path combination is obtained, and the power supply path combination with the total impedance value less than a preset total impedance value threshold is selected as the actual power supply range boundary.

5. The method for dividing a distribution network grid based on artificial intelligence according to claim 1, wherein: The obtaining of the cable segmentation area based on the cable load value and the path winding degree index in the actual power supply range boundary includes: The current load value within the boundary of the actual power supply range is obtained, and the voltage drop is obtained according to the current load value and the path winding degree index. If the voltage drop is greater than a preset drop threshold, the path within the actual power supply range is segmented to obtain a cable segment area.

6. The method for dividing a distribution network grid based on artificial intelligence according to claim 1, wherein: The dynamic programming algorithm is used to calculate the cable segment area to obtain multiple candidate joint positions, and the candidate joint positions of each cable are screened according to the temperature rise curve along the cable to obtain multiple intermediate joint installation positions of the cable within the actual power supply range, including: According to the cable segment area, a dynamic programming algorithm is used to determine multiple candidate joint positions within a preset spacing range according to a set search depth threshold; Collecting conductor temperature data at each of the candidate joint positions; Performing stress analysis on each of the candidate joint positions to obtain a maximum shear stress distribution value for each of the candidate joint positions, determining a stress limitation area based on the maximum shear stress distribution value, and screening the candidate joint positions to be arranged based on the stress limitation area; If the conductor temperature data corresponding to the alternative joint position to be arranged is less than the preset temperature threshold, and the maximum shear stress distribution value corresponding to the alternative joint position to be arranged is less than the preset material strength, then the alternative joint position to be arranged is determined to be the intermediate joint installation position.

7. The method for gridding a distribution network based on artificial intelligence according to claim 1, wherein: The method of using the analytic hierarchy process to calculate the annual maintenance cost, terrain restriction data, and construction cost data of each intermediate joint installation location to obtain an evaluation score for each intermediate joint installation location includes: Establishing a judgment matrix for each of the intermediate joint installation locations based on the annual maintenance cost value, terrain restriction data, and construction cost data of each of the intermediate joint installation locations; Based on the judgment matrix of each intermediate joint installation position, a scale value is used to perform calculation to obtain a feature vector of each intermediate joint installation position, the feature vector is normalized to obtain a weight vector, and if a consistency ratio of the weight vector is less than a preset ratio, a terrain restriction weight value, a maintenance cost weight value, and a construction cost weight value are extracted from the weight vector; The terrain restriction weight value, the maintenance cost weight value and the construction cost weight value are weighted together with the corresponding annual maintenance cost value, the terrain restriction data and the construction cost data to obtain an evaluation score for each intermediate joint installation position.

8. The method for gridding a distribution network based on artificial intelligence according to claim 1, wherein: The obtaining of a final optimized position according to the load density distribution within the actual power supply range includes: According to the load density distribution within the boundary of the actual power supply range, a location where the load density is greater than a preset load density threshold is selected as a branch connection point; A new position combination is obtained according to the branch connection point and the optimized position. If the voltage drop amplitude of the new position combination meets a preset condition, the new position combination is determined to be the final optimized position.

9. The method for dividing a distribution network grid based on artificial intelligence according to claim 1, wherein: The grid boundary correction is performed based on the initial grid division result to obtain the final result of the distribution network grid division, including: Constructing a coverage area of ​​a preset radius according to the load center point of each network in the initial grid division result to obtain multiple coverage areas; Calculating a ratio of the intersection area of ​​each of the coverage areas with the adjacent coverage areas, determining whether the ratio exceeds a preset ratio of the total area of ​​the coverage areas, and if so, calculating a voltage distribution of the coverage areas; if the voltage distribution reaches a rated voltage, adjusting the boundaries of the grids corresponding to the coverage areas according to a preset offset to obtain adjusted grid boundaries; According to the adjusted grid boundaries, a final result of the distribution network grid division is obtained.

10. A method for controlling the entire process of a distribution network, characterized in that: include: Obtaining a final result of distribution network grid division, wherein the final result of distribution network grid division is obtained by the distribution network grid division method based on artificial intelligence according to any one of claims 1 to 9; According to the final result of the distribution network grid division, the equipment operating status data is collected at sampling intervals, and the voltage, current and temperature in the operating status data are quantitatively scored to obtain an equipment status mapping matrix; A construction constraint control matrix is ​​constructed based on the equipment status mapping matrix, and construction process monitoring data is compared with equipment ratings based on the control matrix to obtain a construction quality assessment index; an equipment operation status score is calculated based on the construction quality assessment index, and when the equipment operation status score is lower than a preset operation status assessment threshold, the equipment is marked as a warning state, and an equipment maintenance cycle is generated based on the warning state; The equipment status changes during the equipment maintenance cycle are quantitatively counted to obtain statistical results, a maintenance quality score is calculated based on the statistical results, and the maintenance plan is revised based on the maintenance quality score to obtain an updated equipment inspection and maintenance plan.

Images