Collaborative plotting avoidance method and system for three-dimensional situation symbols of power grid

Abstract

The invention discloses a power grid three-dimensional situation symbol-oriented collaborative plotting avoidance method and system, and the method comprises the steps: obtaining various types of remote sensing data of a target power grid, determining an initial position symbol corresponding to the remote sensing data, and constructing a neighborhood matrix according to each initial position symbol; clustering each initial position symbol according to a spatial clustering algorithm to obtain each clustering center; performing conflict type detection on a neighborhood matrix of the initial position symbol corresponding to a non-central point of each clustering center; performing priority evaluation based on the conflict type detection result to determine conflict symbols which do not meet a preset condition; and processing the conflict symbols according to a fused response surface analysis method and a simulated annealing algorithm to determine optimal position symbol information. According to the collaborative plotting avoidance method for the three-dimensional situation symbols of the power grid, collaborative plotting is carried out on various three-dimensional situation symbols of the power grid, so that the accuracy and the high efficiency of survey data of the power grid are ensured.

Description

Technical Field

[0001] The present invention relates to the field of mapping technology, and in particular to a collaborative mapping avoidance method and system for power grid three-dimensional situation symbols. Background Art

[0002] When dealing with the spatial layout in power grid survey, the traditional power grid survey collaborative algorithm lacks comprehensiveness, only solves spatial overlap, and does not comprehensively consider complex specifications and scenarios, which affects layout optimization. In addition, the power grid survey project has the characteristics of multi-department and multi-professional collaboration. The early algorithm optimization methods are single and difficult to cope with large-scale complex data. The quality and efficiency of marking are limited. The collaborative marking framework lacks multi-user collaboration, real-time synchronization and dynamic feedback, resulting in data operation conflicts and inefficient team collaboration, affecting project progress and quality. Therefore, it has become an urgent problem to form a comprehensive and standardized avoidance strategy and realize effective collaboration and conflict resolution among multiple users. Summary of the invention

[0003] The present invention provides a collaborative plotting and avoidance method and system for three-dimensional situation symbols of power grid, so as to solve the technical problem of conflict of three-dimensional situation symbols of power grid, and to achieve the effect of effective collaboration and avoidance of three-dimensional situation symbols of power grid.

[0004] In order to solve the above technical problems, an embodiment of the present invention provides a collaborative plotting avoidance method for power grid three-dimensional situation symbols, which obtains various types of remote sensing data of the target power grid, determines the initial position symbols corresponding to the remote sensing data, and constructs a neighborhood matrix according to each of the initial position symbols;

[0005] Clustering the initial position symbols according to a spatial clustering algorithm to obtain cluster centers, wherein the center point of each cluster center is determined by the selected initial position symbol;

[0006] Performing conflict type detection on the neighborhood matrix of the initial position symbol corresponding to the non-central point of each cluster center to obtain a conflict type detection result;

[0007] Performing a priority evaluation based on the conflict type detection result, and screening each of the initial position symbols according to the evaluation result to determine the conflict symbols that do not meet the preset conditions;

[0008] The conflicting symbols are processed according to the fused response surface analysis method and simulated annealing algorithm to determine the position symbol information corresponding to the remote sensing data.

[0009] As one preferred solution, constructing a neighborhood matrix according to each of the initial position symbols includes:

[0010] Determine the center point of the initial position symbol corresponding to the remote sensing data;

[0011] Based on the symbol center point, the preset offset distance and the preset offset angle, a corresponding neighborhood matrix is ​​constructed.

[0012] As one preferred solution, the types of the offset distance include Euclidean distance, dot product distance and Mahalanobis distance;

[0013] The step of constructing a corresponding neighborhood matrix based on the symbol center point, a preset offset distance, and a preset offset angle includes:

[0014] The first spatial adjacency matrix is ​​calculated using the Euclidean distance as the measure;

[0015] The second space adjacency matrix is ​​calculated using the dot product distance as the measure;

[0016] The third space adjacency matrix is ​​calculated using the Mahalanobis distance as the measure;

[0017] According to the entropy weight method, the first adjacency matrix, the second spatial adjacency matrix and the third spatial adjacency matrix are processed to obtain a neighborhood matrix.

[0018] As one of the preferred solutions, the conflict type detection is performed on the neighborhood matrix of the initial position symbol corresponding to the non-central point of each cluster center to obtain the conflict type detection result, including:

[0019] The overlap of the initial position symbols corresponding to the remote sensing data, the proximity of the initial position symbols corresponding to the remote sensing data and the key components of the power grid, the clarity of the initial position symbols corresponding to the remote sensing data, and the uniformity of the distribution of the initial position symbols corresponding to the remote sensing data are processed according to a preset weighted calculation formula to obtain a conflict type detection result.

[0020] As one of the preferred solutions, the conflicting symbols are processed according to the fused response surface analysis method and simulated annealing algorithm to determine the position symbol information corresponding to the remote sensing data, including:

[0021] Establishing a response surface analysis model for the conflict symbol to obtain a first response variable;

[0022] Performing random perturbations on the conflicting symbols to obtain new solutions, and processing the new solutions according to the response surface analysis method to obtain a second response variable;

[0023] When the new solution satisfies the first constraint, the position corresponding to the second response variable is the optimal new position. When the new solution satisfies the second constraint, the new solution is accepted with a certain probability, and the temperature T continues to be iterated. When the temperature T drops to a preset minimum value, the iteration is terminated and the position symbol information corresponding to the response variable is output.

[0024] Another embodiment of the present invention provides a collaborative plotting and avoidance system for power grid three-dimensional situation symbols, including:

[0025] An acquisition module, used to acquire various types of remote sensing data of the target power grid, determine the initial position symbols corresponding to the remote sensing data, and construct a neighborhood matrix according to each of the initial position symbols;

[0026] A clustering module, used for clustering the initial position symbols according to a spatial clustering algorithm to obtain cluster centers, wherein the center point of each cluster center is determined by the selected initial position symbol;

[0027] A detection module, used for performing conflict type detection on the neighborhood matrix of the initial position symbol corresponding to the non-central point of each cluster center to obtain a conflict type detection result;

[0028] A screening module, used for performing a priority evaluation based on the conflict type detection result, and screening each of the initial position symbols according to the evaluation result to determine the conflict symbols that do not meet the preset conditions;

[0029] The processing module is used to process the conflicting symbols according to the fused response surface analysis method and simulated annealing algorithm to determine the position symbol information corresponding to the remote sensing data.

[0030] As one preferred solution, constructing a neighborhood matrix according to each of the initial position symbols includes:

[0031] Determine the center point of the initial position symbol corresponding to the remote sensing data;

[0032] Based on the symbol center point, the preset offset distance and the preset offset angle, a corresponding neighborhood matrix is ​​constructed.

[0033] As one preferred solution, the types of the offset distance include Euclidean distance, dot product distance and Mahalanobis distance;

[0034] The system further comprises:

[0035] The calculation module is used to calculate the first space adjacency matrix using Euclidean distance as the measurement, calculate the second space adjacency matrix using dot product distance as the measurement, and calculate the third space adjacency matrix using Mahalanobis distance as the measurement. According to the entropy weight method, the first space adjacency matrix, the second space adjacency matrix and the third space adjacency matrix are processed to obtain a neighborhood matrix.

[0036] As one of the preferred solutions, the conflict type detection is performed on the neighborhood matrix of the initial position symbol corresponding to the non-central point of each cluster center to obtain the conflict type detection result, including:

[0037] The overlap of the initial position symbols corresponding to the remote sensing data, the proximity of the initial position symbols corresponding to the remote sensing data and the key components of the power grid, the clarity of the initial position symbols corresponding to the remote sensing data, and the uniformity of the distribution of the initial position symbols corresponding to the remote sensing data are processed according to a preset weighted calculation formula to obtain a conflict type detection result.

[0038] As one preferred solution, the system further includes:

[0039] An analysis module is used to establish a response surface analysis model for the conflict symbol to obtain a first response variable, randomly perturb the conflict symbol to obtain a new solution, and process the new solution according to the response surface analysis method to obtain a second response variable. When the new solution satisfies the first constraint condition, the position corresponding to the second response variable is the optimal new position. When the new solution satisfies the second constraint condition, the new solution is accepted with a certain probability, and the temperature T is continued to be iterated. When the temperature T is reduced to a preset minimum value, the iteration is terminated and the position symbol information corresponding to the response variable is output.

[0040] Compared with the prior art, the embodiments of the present invention have the following advantages:

[0041] (1) A multi-dimensional comprehensive analysis of power grid survey specifications and actual application scenarios has been formed, which can adaptively optimize the evaluation system according to actual collaborative mapping needs, ensuring the comprehensiveness of the evaluation process;

[0042] (2) The severity of data conflicts is automatically evaluated through response surface analysis and simulated annealing algorithm, and the new position corresponding to the three-dimensional situation symbol is determined according to the preset strategy and weight, thereby ensuring the accuracy and efficiency of power grid survey data. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a schematic flow chart of a collaborative plotting and avoidance method for power grid three-dimensional situation symbols in one embodiment of the present invention;

[0044] Figure 2 It is a structural block diagram of a collaborative plotting and avoidance system for power grid three-dimensional situation symbols in one embodiment of the present invention;

[0045] Figure 3 It is a schematic diagram of a collaborative plotting avoidance strategy process for power grid three-dimensional situation symbols in one embodiment of the present invention.

[0046] Reference numerals:

[0047] 11. Acquisition module; 12. Clustering module; 13. Detection module; 14. Screening module; 15. Processing module. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] In the description of this application, the terms "first", "second", "third", etc. are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", "third", etc. may explicitly or implicitly include one or more of the feature. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0050] In the description of the present application, it should be noted that, unless otherwise expressly specified and limited, the terms "vertical", "horizontal", "left", "right", "upper", "lower" and similar expressions used herein are for illustrative purposes only, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0051] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as those commonly understood by those skilled in the art. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood by specific circumstances.

[0052] An embodiment of the present invention provides a collaborative plotting avoidance method for power grid three-dimensional situation symbols. For details, see Figure 1 , Figure 1 The figure shows a schematic flow chart of a collaborative plotting and avoidance method for power grid three-dimensional situation symbols in one embodiment of the present invention, which includes steps S1 to S4:

[0053] S1: Obtain various types of remote sensing data of the target power grid, determine the initial position symbols corresponding to the remote sensing data, and construct a neighborhood matrix according to each initial position symbol;

[0054] S2: clustering each initial position symbol according to a spatial clustering algorithm to obtain each cluster center, wherein the center point of each cluster center is determined by the selected initial position symbol;

[0055] S3: Perform conflict type detection on the neighborhood matrix of the initial position symbol corresponding to the non-central point of each cluster center to obtain the conflict type detection result;

[0056] S4: performing a priority evaluation based on the conflict type detection result, and screening each initial position symbol according to the evaluation result to determine the conflict symbols that do not meet the preset conditions;

[0057] S5: Process the conflicting symbols according to the fused response surface analysis method and simulated annealing algorithm to determine the location symbol information corresponding to the remote sensing data.

[0058] In the above step S1, the step of constructing a neighborhood matrix according to each initial position symbol includes: determining the center point of the initial position symbol corresponding to each remote sensing data, taking each symbol as a graph node, taking the spatial information of the pixel point as the node information, and using Euclidean distance (Euclidean distance, Ed), dot product distance (Dot-product distance, Dd), and Mahalanobis distance (Mahalanobis Distance, Md) as three distance measures to calculate the neighbor value between each pair of pixel nodes, and obtaining A Ed , A Dd and A Md Three different adjacency matrices are weighted and fused using the entropy weight method to obtain the neighborhood matrix N i .

[0059] Euclidean distance describes the absolute distance between two samples, which is essentially the calculation of the nearest neighbor value between two plotted symbols. The calculation formula is:

[0060]

[0061] Among them, A Ed ij Indicates the symbol center x i and x j The spatial position of A is calculated using the Euclidean distance to obtain the similarity value. Ed It is the spatial adjacency matrix obtained by measuring the Euclidean distance.

[0062] The dot product distance is related to the position of two symbols and the angle between them. It is not affected by high dimensions and can better utilize the directional information of the data, which plays a certain role in offsetting the high-dimensional problem of Euclidean distance. The calculation formula is as follows:

[0063] ADdij =x i x j cos(θ)

[0064] Among them, x i and x j Indicates the modulus of the symbol, cos() represents the cosine angle between two plotted symbols, describing the directional characteristics of the two plotted symbols, A Ddij It represents the neighbor value calculated by dot product distance between two symbols, and ADd represents the spatial adjacency matrix obtained by measuring dot product distance.

[0065] The Mahalanobis distance is calculated using the covariance matrix of two plotted symbols, which can also be called the covariance distance. It corrects the problem of inconsistent and correlated scales of various dimensions in the Euclidean distance to a certain extent.

[0066]

[0067] Where ∑ represents the covariance matrix of the two plotted symbols, A Md ij Represents the similarity between two plotted symbols calculated using the Mahalanobis distance, A Md Represents the spatial adjacency matrix obtained using the Mahalanobis distance as the measure.

[0068] Neighborhood matrix N i The spatial adjacency matrix weights are calculated by the entropy weight method:

[0069] N i =W Ed ·A Ed +W Dd ·A Dd +W Md ·A Md

[0070] W Ed , W Dd and W Md Represents the weight coefficient that can be learned iteratively with an initial value of 1.

[0071] In the above step S2, each initial position symbol is clustered according to the spatial clustering algorithm to obtain each cluster center, wherein the center point of each cluster center is determined by the selected initial position symbol. The spatial clustering algorithm is preferably a K-means spatial clustering algorithm, and may also be a clustering algorithm that plays the same role, which is not specifically limited here.

[0072] In step S3, conflict type detection includes detecting one or more of four aspects: the overlap of the initial position symbols corresponding to the remote sensing data, the proximity of the initial position symbols corresponding to the remote sensing data and the key components of the power grid, the clarity of the initial position symbols corresponding to the remote sensing data, and the uniformity of the distribution of the initial position symbols corresponding to the remote sensing data.

[0073] The overlap of the initial position symbols corresponding to the remote sensing data can be quantified by calculating the overlapping area of ​​the neighborhood matrix of the two symbols, where the two symbols are P 1 and P 2 , their overlapping area can be expressed as O(P 1 ,P 2 ):

[0074]

[0075] Where n is the symbol P 1 The number of m is the symbol P 2 The number of

[0076] The proximity of the initial position symbol corresponding to the remote sensing data to the key components of the power grid can be evaluated by calculating the distance between the symbol center and the grid element it represents.

[0077] Let the center of symbol P be P s (x i ,y i ), the center of the grid element it represents is C E , then the closeness P(S) can be expressed as:

[0078]

[0079] Where d(PS,CE) is the Euclidean distance between the symbol P and the specified grid element, and k is a positive regulation parameter with an initial value of 1.

[0080] The clarity of the initial position symbol corresponding to the remote sensing data is determined by the visual attributes of the symbol, including one or more of color contrast, size or shape, which are not specifically limited here.

[0081] Then the clarity C(S) can be expressed as:

[0082] C(S) = α·log(1+C S )+β·log(1+S S )-γ·F S

[0083] Among them, the color contrast of symbol P is C S , size is S S , the shape complexity is F S, α, β, γ are weight coefficients used to adjust the importance of each factor.

[0084] The uniformity of the symbol distribution of the initial position corresponding to the remote sensing data is quantified by evaluating the uniformity of the distribution of the symbol P in space. Let D(S) be the entropy of the symbol distribution, which can be expressed as

[0085]

[0086] Among them, p i is the proportion of symbols in the ith region, which is calculated by comparing the number of symbols in each region with the total number of symbols.

[0087] The conflict type detection result obtained in step S3 is obtained by processing the overlap of the initial position symbols corresponding to the remote sensing data, the proximity of the initial position symbols corresponding to the remote sensing data and the key components of the power grid, the clarity of the initial position symbols corresponding to the remote sensing data, and the uniformity of the distribution of the initial position symbols corresponding to the remote sensing data through a preset weighted calculation formula, and the weighted calculation formula is:

[0088] Q(P)=w 1 ·O(P 1 ,P 2 )+w 2 ·P(S)+w 3 ·C(S)+w 4 ·D(S)

[0089] Among them, Q(P) represents the conflict type detection result, w 1 -w 4 is the corresponding weight coefficient.

[0090] In step S4, priority evaluation is performed based on the conflict type detection result, and each initial position symbol is screened according to the evaluation result to determine the conflict symbols that do not meet the preset conditions, where the priority is defined as P s :

[0091] P s =1-Q(P)

[0092] Among all symbols, according to P s Sort from high to low and select those symbols in areas with large overlap, poor user feedback or unbalanced load to move. The preset conditions are:

[0093] P s >threshold

[0094] Where threshold is a threshold value, which is the ratio of the number of symbols moved in a specific time period to the total number of symbols. If this ratio is too high, it means that the symbols move too frequently and the threshold needs to be increased; if the conflict resolution is not effective enough, the threshold may need to be lowered.

[0095] The above conflicting symbols are processed according to the fused response surface analysis method and simulated annealing algorithm, and a response surface analysis method model is established for the conflicting symbols to obtain the first response variable. The model is:

[0096]

[0097] Among them, Y is the response variable, β 0 , β i and β ij are model parameters, ε is the error term, and x i and x j are the center coordinates of the two conflicting symbols.

[0098] Assume that a transmission line symbol L and a substation symbol E overlap, x i and xj represent the central coordinates of L and E respectively. The model parameter β is obtained by response surface analysis. i and β ij , these parameters can be understood as how Y will change if L or E is moved a certain distance. i For L to be negative, this means that moving L can reduce the overlap; if β ij is positive, which means that moving L and E together will reduce their overlap.

[0099] From the current conflict symbol P(x 0 ,y 0 ) and generate new solutions by random perturbations. New solutions can be achieved by adding small random changes:

[0100] x′=x 0 +Δx

[0101] y′=y 0 +Δy

[0102] where Δx, Δy are random variables drawn from a normal distribution.

[0103] Bring the new solution into the response surface analysis model to obtain the second response variable Y′;

[0104] When the new solution satisfies the first constraint, that is, ΔY<0, the corresponding position of the second response variable is the optimal new position. When the new solution satisfies the second constraint, that is, ΔY>0, the new solution is accepted with a certain probability. The probability calculation formula is:

[0105]

[0106] Among them, ΔY=YY′;

[0107] Continue to iterate the temperature T. When the temperature T drops to the preset minimum value, terminate the iteration and output the position symbol information corresponding to the response variable.

[0108] The optimized position is updated to the power grid survey system in real time, and user feedback is collected. Users can review and manually adjust the results of automatic avoidance through the interface, and the system makes dynamic adjustments based on the feedback. Then, based on user feedback and system performance monitoring, the updated temperature T and avoidance strategy in the optimization algorithm are continuously iterated and adjusted. LOD and image pyramid technology are used to realize dynamic loading of remote sensing data and adaptive adjustment of the level of detail, realize efficient fusion of different remote sensing data in power grid survey, and improve the accuracy and visualization of survey data.

[0109] For details, see Figure 2 , Figure 2 The structure block diagram of the collaborative plotting and avoidance system for power grid three-dimensional situation symbols in one embodiment of the present invention is shown, including:

[0110] The acquisition module 11 is used to acquire various types of remote sensing data of the target power grid, determine the initial position symbols corresponding to the remote sensing data, and construct a neighborhood matrix according to each initial position symbol;

[0111] A clustering module 12 is used to cluster the initial position symbols according to a spatial clustering algorithm to obtain cluster centers, wherein the center point of each cluster center is determined by the selected initial position symbol;

[0112] A detection module 13 is used to perform conflict type detection on the neighborhood matrix of the initial position symbol corresponding to the non-central point of each cluster center to obtain a conflict type detection result;

[0113] A screening module 14 is used to perform a priority evaluation based on the conflict type detection result, and screen each initial position symbol according to the evaluation result to determine the conflict symbols that do not meet the preset conditions;

[0114] The processing module 15 is used to process the conflicting symbols according to the fused response surface analysis method and simulated annealing algorithm to determine the position symbol information corresponding to the remote sensing data.

[0115] Furthermore, in the above embodiment, constructing a neighborhood matrix according to each initial position symbol includes:

[0116] Determine the center point of the initial position symbol corresponding to the remote sensing data;

[0117] Based on the symbol center point, the preset offset distance and the preset offset angle, a corresponding neighborhood matrix is ​​constructed.

[0118] Further, in the above embodiment, the types of the offset distance include Euclidean distance, dot product distance and Mahalanobis distance;

[0119] The system further comprises:

[0120] The calculation module is used to calculate the first adjacency matrix using Euclidean distance as the measurement, calculate the second spatial adjacency matrix using dot product distance as the measurement, and calculate the third spatial adjacency matrix using Mahalanobis distance as the measurement. According to the entropy weight method, the first adjacency matrix, the second spatial adjacency matrix and the third spatial adjacency matrix are processed to obtain a neighborhood matrix.

[0121] Furthermore, in the above embodiment, the conflict type detection is performed on the neighborhood matrix of the initial position symbol corresponding to the non-central point of each cluster center to obtain the conflict type detection result, including:

[0122] According to the preset weighted calculation formula, the overlap of the initial position symbols corresponding to the remote sensing data, the proximity of the initial position symbols corresponding to the remote sensing data and the key components of the power grid, the clarity of the initial position symbols corresponding to the remote sensing data, and the uniformity of the distribution of the initial position symbols corresponding to the remote sensing data are processed to obtain the conflict type detection result.

[0123] Furthermore, in the above embodiment, the system further includes:

[0124] The analysis module is used to establish a response surface analysis model for the conflicting symbols, obtain the first response variable, perform random perturbations on the conflicting symbols to obtain a new solution, and obtain the second response variable from the new solution according to the response surface analysis method. When the new solution satisfies the first constraint condition, the position corresponding to the second response variable is the optimal new position. When the new solution satisfies the second constraint condition, the new solution is accepted with a certain probability, and the temperature T is continued to be iterated. When the temperature T is reduced to a preset minimum value, the iteration is terminated and the position symbol information corresponding to the response variable is output.

[0125] For details, see Figure 3 , Figure 3The present invention is a flowchart of a collaborative plotting avoidance strategy for power grid three-dimensional situation symbols in one embodiment of the present invention. The collaborative plotting avoidance strategy for power grid three-dimensional situation symbols includes: clustering each initial position symbol according to a spatial clustering algorithm to obtain each cluster center, wherein the center point of each cluster center is determined by the selected initial position symbol; detecting and marking potential conflicts between symbol groups; performing priority evaluation on the conflict type detection results; screening each initial position symbol according to the evaluation results to determine conflict symbols that do not meet preset conditions, and among all symbols, sorting them from high to low according to priority, and selecting those symbols in areas with large overlapping areas, poor user feedback or unbalanced loads for movement; using response surface analysis to determine the size and direction of the impact of each conflict symbol on the response variable Y; and using simulated annealing algorithm to find the optimal new position for the symbol to be moved.

[0126] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A collaborative plotting and avoidance method for power grid three-dimensional situation symbols, characterized in that: include: Acquire various types of remote sensing data of the target power grid, determine the initial position symbols corresponding to the remote sensing data, and construct a neighborhood matrix according to each of the initial position symbols; Clustering the initial position symbols according to a spatial clustering algorithm to obtain cluster centers, wherein the center point of each cluster center is determined by the selected initial position symbol; Performing conflict type detection on the neighborhood matrix of the initial position symbol corresponding to the non-central point of each cluster center to obtain a conflict type detection result; Performing a priority evaluation based on the conflict type detection result, and screening each of the initial position symbols according to the evaluation result to determine the conflict symbols that do not meet the preset conditions; The conflicting symbols are processed according to the fused response surface analysis method and simulated annealing algorithm to determine the position symbol information corresponding to the remote sensing data.

2. The collaborative plotting and avoidance method for power grid three-dimensional situation symbols according to claim 1, characterized in that: The step of constructing a neighborhood matrix according to each of the initial position symbols comprises: Determine the center point of the initial position symbol corresponding to each of the remote sensing data; Based on the symbol center point, the preset offset distance and the preset offset angle, a corresponding neighborhood matrix is ​​constructed.

3. The collaborative plotting and avoidance method for power grid three-dimensional situation symbols according to claim 2, characterized in that: The types of the offset distance include Euclidean distance, dot product distance and Mahalanobis distance; The step of constructing a corresponding neighborhood matrix based on the symbol center point, a preset offset distance, and a preset offset angle includes: The first spatial adjacency matrix is ​​calculated using the Euclidean distance as the measure; The second space adjacency matrix is ​​calculated using the dot product distance as the measure; The third space adjacency matrix is ​​calculated using the Mahalanobis distance as the measure; According to the entropy weight method, the first spatial adjacency matrix, the second spatial adjacency matrix and the third spatial adjacency matrix are processed to obtain a neighborhood matrix.

4. The method for collaborative plotting and avoiding three-dimensional situation symbols of power grid according to claim 1, characterized in that: The performing conflict type detection on the neighborhood matrix of the initial position symbol corresponding to the non-central point of each cluster center to obtain the conflict type detection result includes: The overlap of the initial position symbols corresponding to the remote sensing data, the proximity of the initial position symbols corresponding to the remote sensing data and the key components of the power grid, the clarity of the initial position symbols corresponding to the remote sensing data, and the uniformity of the distribution of the initial position symbols corresponding to the remote sensing data are processed according to a preset weighted calculation formula to obtain a conflict type detection result.

5. The method for collaborative plotting and avoiding three-dimensional situation symbols of power grid according to claim 1, characterized in that: The step of processing the conflicting symbols according to the fused response surface analysis method and simulated annealing algorithm to determine the position symbol information corresponding to the remote sensing data includes: Establishing a response surface analysis model for the conflict symbol to obtain a first response variable; Performing random perturbations on the conflicting symbols to obtain new solutions, and processing the new solutions according to the response surface analysis method to obtain a second response variable; When the new solution satisfies the first constraint, the position corresponding to the second response variable is the optimal new position. When the new solution satisfies the second constraint, the new solution is accepted with a certain probability, and the temperature T continues to be iterated. When the temperature T drops to a preset minimum value, the iteration is terminated and the position symbol information corresponding to the response variable is output.

6. A collaborative plotting and avoidance system for power grid three-dimensional situation symbols, characterized in that: include: An acquisition module, used to acquire various types of remote sensing data of the target power grid, determine the initial position symbols corresponding to the remote sensing data, and construct a neighborhood matrix according to each of the initial position symbols; A clustering module, used for clustering the initial position symbols according to a spatial clustering algorithm to obtain cluster centers, wherein the center point of each cluster center is determined by the selected initial position symbol; A detection module, used for performing conflict type detection on the neighborhood matrix of the initial position symbol corresponding to the non-central point of each cluster center to obtain a conflict type detection result; A screening module, used for performing a priority evaluation based on the conflict type detection result, and screening each of the initial position symbols according to the evaluation result to determine the conflict symbols that do not meet the preset conditions; The processing module is used to process the conflicting symbols according to the fused response surface analysis method and simulated annealing algorithm to determine the position symbol information corresponding to the remote sensing data.

7. The collaborative plotting and avoidance system for power grid three-dimensional situation symbols according to claim 6, characterized in that: The step of constructing a neighborhood matrix according to each of the initial position symbols comprises: Determine the center point of the initial position symbol corresponding to the remote sensing data; Based on the symbol center point, the preset offset distance and the preset offset angle, a corresponding neighborhood matrix is ​​constructed.

8. The collaborative plotting and avoidance system for power grid three-dimensional situation symbols according to claim 7, characterized in that: The types of the offset distance include Euclidean distance, dot product distance and Mahalanobis distance; The system further comprises: A calculation module is used to calculate the first spatial adjacency matrix using Euclidean distance as a measure, calculate the second spatial adjacency matrix using dot product distance as a measure, and calculate the third spatial adjacency matrix using Mahalanobis distance as a measure. According to the entropy weight method, the first spatial adjacency matrix, the second spatial adjacency matrix and the third spatial adjacency matrix are processed to obtain a neighborhood matrix.

9. The collaborative plotting and avoidance system for power grid three-dimensional situation symbols according to claim 6, characterized in that: The performing conflict type detection on the neighborhood matrix of the initial position symbol corresponding to the non-central point of each cluster center to obtain the conflict type detection result includes: The overlap of the initial position symbols corresponding to the remote sensing data, the proximity of the initial position symbols corresponding to the remote sensing data and the key components of the power grid, the clarity of the initial position symbols corresponding to the remote sensing data, and the uniformity of the distribution of the initial position symbols corresponding to the remote sensing data are processed according to a preset weighted calculation formula to obtain a conflict type detection result.

10. The collaborative plotting and avoidance system for power grid three-dimensional situation symbols according to claim 6, characterized in that: The system further comprises: An analysis module is used to establish a response surface analysis model for the conflict symbol to obtain a first response variable, randomly perturb the conflict symbol to obtain a new solution, and process the new solution according to the response surface analysis method to obtain a second response variable. When the new solution satisfies the first constraint condition, the position corresponding to the second response variable is the optimal new position. When the new solution satisfies the second constraint condition, the new solution is accepted with a certain probability, and the temperature T is continued to be iterated. When the temperature T is reduced to a preset minimum value, the iteration is terminated and the position symbol information corresponding to the response variable is output.

Images