Method and device for evaluating and predicting tree obstacle hidden danger of overhead transmission line, and medium

Through the fuzzy hierarchy analysis method and ant colony algorithm to optimize the GRU model, a tree barrier hidden danger assessment and prediction system was established, which solved the problems of blind spots in the existing technology and achieved accurate prediction and timely prediction of tree barrier hidden dangers. The processing improves the reliability of the power grid operation.

CN118982234APending Publication Date: 2024-11-19GUANGYUAN POWER SUPPLY COMPANY OF STATE GRID SICHUAN ELECTRIC POWER

Patent Information

Application Number
CN202411004057.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-25
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

The existing technology has blind spots in the prediction of tree barrier hidden dangers, weak prediction capabilities, and the inability to accurately predict tree barrier hidden dangers, and lacks advanced data analysis and prediction models, resulting in untimely handling of hidden dangers.

Method used

The fuzzy hierarchical analysis method is used to establish a tree barrier potential assessment index system, determine the weight of each indicator, and use the ant colony algorithm to optimize the gated cycle unit (GRU) model to avoid local optimization, improve prediction accuracy, and capture the time dependence of tree barrier potential hazards predicts the risk of hidden dangers in future tree obstacles.

Benefits of technology

It improves the accuracy and efficiency of predicting hidden dangers in tree barriers, and can scientifically formulate tree barrier cleaning plans, reduce economic losses, and improve the reliability of power grid operation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118982234A_ABST
    Figure CN118982234A_ABST
Patent Text Reader

Abstract

The invention discloses an overhead transmission line tree obstacle hidden danger evaluation and prediction method and device and a medium, and the method comprises the steps: collecting tree obstacle data of an overhead transmission line, and constructing a tree obstacle hidden danger evaluation system; obtaining a weight coefficient of each parameter according to the tree obstacle hidden danger evaluation system; a weighted scoring model is constructed based on the weight coefficient to score the tree barrier hidden danger, a fuzzy analytic hierarchy process is responsible for establishing a tree barrier hidden danger evaluation index system and determining the weight of each index, the fuzzy weight of the state parameter is obtained through analytic hierarchy process and fuzzy comprehensive evaluation, reliable input data is provided for a subsequent prediction model, and the prediction accuracy of the tree barrier hidden danger is improved. The ant colony algorithm is adopted to optimize the gating circulation unit, the tree obstacle hidden danger prediction model is constructed through the network to predict the tree obstacle hidden danger risk of the power transmission line, the prediction capability can be improved, and the tree obstacle hidden danger can be accurately predicted.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of tree obstacle processing, and in particular to a method, device and medium for evaluating and predicting tree obstacle hazards of overhead power transmission lines. Background Art

[0002] At present, my country mainly uses cables and overhead lines for power transmission. With the expansion of the scale of the power grid, the construction of cross-regional transmission lines has gradually increased, which has brought pressure to the safe operation of the power grid. Therefore, it is necessary to conduct safety inspections on power transmission lines. In the safety inspection of transmission lines, tree barrier hazards are an important inspection content. The distance between the transmission line and the trees is less than the safety standard, which can easily cause the trees to burn and then cause wildfires, causing the transmission line to trip and affect the stable operation of the power system. In order to better deal with the hidden dangers of tree barriers and ensure the stable operation of the transmission line, the staff needs to monitor the growth height of the tree barriers and the distance between them and the transmission lines, assess the risk of tree barrier hazards, and handle the hidden danger information in a timely manner. The traditional inspection method of transmission channels mainly relies on manual inspection, which has high requirements on the professional skills and geographical environment of inspectors, and there are blind spots in the inspection. In addition, existing technologies mostly rely on manual inspection, which has high labor intensity, low efficiency and high cost. It is limited by weather conditions; the coverage is not comprehensive and there are blind spots in the inspection; the prediction ability is weak, and there is a lack of advanced data analysis and prediction models, which cannot accurately predict the development trend of tree obstacle hazards; there is a lack of early warning mechanism, which leads to untimely handling of hazards. Summary of the invention

[0003] The technical problem to be solved by the present invention is that the existing technology adopts manual methods when predicting tree barrier hazards, which is not fully covered and has inspection blind spots, weak prediction ability, and cannot accurately predict tree barrier hazards. The purpose is to provide a method, device and medium for evaluating and predicting tree barrier hazards of overhead transmission lines. First, the fuzzy hierarchical analysis method is used to establish a tree barrier hazard evaluation index system, determine the weight of each index, and obtain the fuzzy weight of the state parameter through hierarchical analysis and fuzzy comprehensive evaluation to provide reliable input data for the subsequent prediction model. Secondly, the ant colony algorithm (ACO) is used to optimize the initial weights and thresholds of the gated recurrent unit (GRU), effectively avoiding the GRU model from falling into the local optimum and improving its generalization and prediction accuracy. Finally, the GRU model is used to capture the time dependence of the tree barrier hazard score, predict the tree barrier hazard risk of the transmission line within a certain period of time in the future, and improve the prediction ability and accurately predict the tree barrier hazard.

[0004] The present invention is achieved through the following technical solutions:

[0005] A first aspect of the present invention provides a method for evaluating and predicting tree obstacle hazards of overhead transmission lines, comprising the following specific steps:

[0006] Collect tree obstacle data for overhead power transmission lines and build a tree obstacle hazard assessment system;

[0007] The weight coefficients of various parameters are obtained according to the tree barrier hazard assessment system;

[0008] Normalize the tree obstacle data, and build a weighted scoring model based on the processed data and the weight coefficient;

[0009] Score tree obstacle hazards based on a weighted scoring model;

[0010] Ant colony algorithm is used to optimize the gated recurrent unit and construct a tree obstacle hazard prediction model through the network;

[0011] The tree barrier prediction model is trained according to the scores, and the trained tree barrier prediction model is used to predict the tree barrier risk of the transmission line.

[0012] The present invention firstly establishes a tree barrier hidden danger assessment index system through fuzzy hierarchical analysis method, determines the weight of each index, obtains the fuzzy weight of the state parameter through hierarchical analysis and fuzzy comprehensive evaluation, and provides reliable input data for the subsequent prediction model. Secondly, the ant colony algorithm (ACO) is used to optimize the initial weight and threshold of the gated recurrent unit (GRU), effectively avoiding the GRU model from falling into the local optimum, and improving its generalization and prediction accuracy. Finally, the GRU model is used to capture the time dependence of the tree barrier hidden danger score, and the tree barrier hidden danger risk of the transmission line in a certain period of time in the future is predicted, which can improve the prediction ability and accurately predict the tree barrier hidden danger.

[0013] Furthermore, the overhead transmission line tree obstacle data includes:

[0014] Record the tree species, age, height, longitude and latitude, altitude, historical growth information, line height, slope and line sag of the tree barrier.

[0015] Furthermore, the specific steps of constructing the tree barrier hazard assessment system include:

[0016] The tree barrier data of overhead transmission lines are classified, including tree species information, transmission line information and geographic information, to obtain the predicted state parameters of tree barrier height.

[0017] Furthermore, the weight coefficients of various parameters are obtained according to the tree barrier hazard assessment system, and the specific steps include:

[0018] A hierarchical model is constructed, including a target layer and a criterion layer, wherein the target layer includes the weight coefficients of the state parameters; the criterion layer includes tree species, tree age, tree height, longitude and latitude, altitude, historical growth information, line height and line sag;

[0019] The judgment matrix is ​​constructed based on the parameters of the hierarchical model, and triangular fuzzy numbers are used to represent the relative importance of pairwise comparison of the judgment matrix parameters.

[0020] According to the expert scoring method, pairwise comparison is performed to construct a fuzzy judgment matrix

[0021] Calculate the fuzzy weight vector through the fuzzy judgment matrix;

[0022] The fuzzy weight vector is defuzzified using the centroid method to obtain the weight value;

[0023] The defuzzified weights are normalized to obtain the weight coefficients of each parameter.

[0024] Furthermore, the step of calculating the weight coefficient includes:

[0025]

[0026] in, represents a triangular fuzzy number, l is the minimum value, m is the middle value, u is the maximum value, and w i is the weight value, w i ′ represents the weight coefficient, i=1,2,3,…,n.

[0027] Furthermore, the normalization of the tree barrier data specifically includes:

[0028]

[0029] Among them, X n represents the data after normalization, X represents the data before processing, and X max , X min Respectively represent the maximum and minimum values ​​of each state parameter data in the data set.

[0030] Furthermore, the construction of the weighted scoring model specifically includes:

[0031] Obtain the weight coefficients w1, w2…w9, and the state parameter values ​​corresponding to the weight coefficients are X1, X2…X9, and the weighted scoring model is obtained as follows:

[0032] S=(w1×X1+w2×X2+...+w9×X9)×100

[0033] Where S is the predicted tree obstacle hazard score.

[0034] Furthermore, the scoring of tree obstacle hazards based on the weighted scoring model specifically includes:

[0035] Based on historical data and experience, tree obstacle hazards are divided into four states and a scoring template is obtained:

[0036] Scoring is performed according to the scoring template for tree obstacle hazards.

[0037] A second aspect of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a method for assessing and predicting tree obstacle hazards of overhead transmission lines is implemented.

[0038] A third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for assessing and predicting tree obstacle hazards of overhead power transmission lines.

[0039] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0040] Firstly, the fuzzy analytic hierarchy process is used to establish a tree barrier hidden danger assessment index system and determine the weight of each index. Through hierarchical analysis and fuzzy comprehensive evaluation, the fuzzy weight of the state parameter is obtained to provide reliable input data for the subsequent prediction model. Secondly, the ant colony algorithm (ACO) is used to optimize the initial weights and thresholds of the gated recurrent unit (GRU), effectively avoiding the GRU model from falling into the local optimum and improving its generalization and prediction accuracy. Finally, the GRU model is used to capture the time dependence of the tree barrier hidden danger score and predict the tree barrier hidden danger risk of the transmission line in a certain period of time in the future, which can improve the prediction ability and accurately predict the tree barrier hidden danger. It provides guidance for the scientific formulation of effective and reasonable tree barrier clearing plans, which is of great significance to reducing the economic losses caused by tree barrier hidden dangers and improving the reliability of power grid operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without creative work. In the drawings:

[0042] Figure 1 is a flow chart of the evaluation and prediction method in an embodiment of the present invention;

[0043] Figure 2 It is a tree barrier hidden danger assessment state parameter indicator system in an embodiment of the present invention;

[0044] Figure 3 The process of obtaining the weight coefficients of each state parameter in the embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.

[0046] As a possible implementation, Figure 1 As shown, this embodiment provides a method for evaluating and predicting tree barrier hazards of overhead transmission lines. In this implementation, firstly, a tree barrier hazard evaluation index system is established through the fuzzy analytic hierarchy process, and the weight of each index is determined. Through hierarchical analysis and fuzzy comprehensive evaluation, the fuzzy weight of the state parameter is obtained to provide reliable input data for the subsequent prediction model. Secondly, the ant colony algorithm (ACO) is used to optimize the initial weight and threshold of the gated recurrent unit (GRU), effectively avoiding the GRU model from falling into the local optimum, and improving its generalization and prediction accuracy. Finally, the GRU model is used to capture the time dependence of the tree barrier hazard score, and the tree barrier hazard risk of the transmission line in a certain period of time in the future is predicted, which can improve the prediction ability and accurately predict the tree barrier hazard.

[0047] In some possible implementations, the overhead transmission line tree obstacle data includes:

[0048] Record the tree species, age, height, longitude and latitude, altitude, historical growth information, line height, slope and line sag of the tree barrier.

[0049] In some possible implementations, the specific steps of constructing a tree barrier hazard assessment system include:

[0050] The tree barrier data of overhead transmission lines are classified, including tree species information, transmission line information and geographic information, to obtain the predicted state parameters of tree barrier height.

[0051] In some possible implementations, the weight coefficients of various parameters are obtained according to the tree barrier hazard assessment system, and the specific steps include:

[0052] A hierarchical model is constructed, including a target layer and a criterion layer, wherein the target layer includes the weight coefficients of the state parameters; the criterion layer includes tree species, tree age, tree height, longitude and latitude, altitude, historical growth information, line height and line sag;

[0053] A 9×9 judgment matrix is ​​constructed based on the parameters of the hierarchical model, and triangular fuzzy numbers are used to represent the relative importance of pairwise comparisons of the judgment matrix parameters. The specific triangular fuzzy number is expressed as represents a triangular fuzzy number, l is the minimum value, m is the middle value, and u is the maximum value;

[0054] According to the expert scoring method, pairwise comparison is performed to construct a fuzzy judgment matrix

[0055] Calculate the fuzzy weight vector through the fuzzy judgment matrix

[0056] Use the centroid method to defuzzify the fuzzy weight vector and get the weight value

[0057] The defuzzified weights are normalized to obtain the weight coefficients of each parameter.

[0058] In some possible implementations, the tree barrier data is normalized, specifically including:

[0059]

[0060] Among them, X n represents the data after normalization, X represents the data before processing, and X max , X min Respectively represent the maximum and minimum values ​​of each state parameter data in the data set.

[0061] In some possible implementations, constructing a weighted scoring model specifically includes:

[0062] Obtain the weight coefficients w1, w2…w9, and the state parameter values ​​corresponding to the weight coefficients are X1, X2…X9, and the weighted scoring model is obtained as follows:

[0063] S=(w1×X1+w2×X2+...+w9×X9)×100

[0064] Where S is the predicted tree obstacle hazard score.

[0065] Based on historical data and experience, tree obstacle hazards are divided into four states and a scoring template is obtained:

[0066]

[0067] Scoring is performed according to the scoring template for tree obstacle hazards.

[0068] In some possible implementations, a fuzzy analytic hierarchy process (FAHP) is combined with an ant colony algorithm (ACO) to optimize a tree barrier hazard prediction model of a gated recurrent unit (GRU) neural network. First, the fuzzy analytic hierarchy process is responsible for establishing a tree barrier hazard assessment index system and determining the weight of each index; through hierarchical analysis and fuzzy comprehensive evaluation, the fuzzy weights of the state parameters are obtained to provide reliable input data for subsequent prediction models. Secondly, the ant colony algorithm (ACO) is used to optimize the initial weights and thresholds of the gated recurrent unit (GRU), effectively avoiding the GRU model from falling into local optimality and improving its generalization and prediction accuracy. Specifically, FAHP can establish an effective tree barrier assessment system and indicator weights, providing theoretical support and reliable data input for tree barrier hazard assessment; the ACO algorithm can optimize the initial weights and thresholds of GRU, effectively preventing the GRU model from falling into local optimality, and improving its generalization and prediction accuracy; the GRU algorithm can better capture the long-term dependencies in time series data, has a relatively simple structure, fewer parameters, higher training efficiency, and stronger generalization ability and robustness.

[0069] As a possible implementation method, this example evaluates and predicts tree barrier hazards of a transmission line of the State Grid Guangyuan Power Supply Company. In this experiment, 100 recording points were selected, and the training set and the test set were divided into a ratio of 3:1. The experimental results are shown in Table 1:

[0070] Table 1. Experimental evaluation and prediction results of recording points

[0071] Record point number Assessment score Assessment Status Prediction score Prediction status 1 90.1 normal / / 2 91.2 normal / / 3 92.4 normal / / … … … … … 98 82.3 Notice 83.5 Notice 99 84.5 Notice 83.9 Notice 100 81.2 Notice 80.8 Notice

[0072] The experimental results show that the classification accuracy of the test set reaches more than 95%, which proves the effectiveness of the present invention.

[0073] As a possible implementation, this embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, a method for assessing and predicting tree obstacle hazards of overhead transmission lines is implemented.

[0074] As a possible implementation, this embodiment provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for assessing and predicting tree obstacle hazards of overhead transmission lines.

[0075] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for assessing and predicting tree obstacle hazards of overhead transmission lines, characterized in that: The specific steps include: Collect tree obstacle data for overhead power transmission lines and build a tree obstacle hazard assessment system; The weight coefficients of various parameters are obtained according to the tree barrier hazard assessment system; Normalize the tree obstacle data, and build a weighted scoring model based on the processed data and the weight coefficient; Score tree obstacle hazards based on a weighted scoring model; Ant colony algorithm is used to optimize the gated recurrent unit and construct a tree obstacle hazard prediction model through the network; The tree barrier hazard prediction model is trained according to the scores, and the trained tree barrier hazard prediction model is used to predict the tree barrier hazard risk of the transmission line.

2. The method for evaluating and predicting tree obstacle hazards of overhead power transmission lines according to claim 1, characterized in that: The overhead transmission line tree obstacle data includes: Record the tree species, age, height, longitude and latitude, altitude, historical growth information, line height, slope and line sag of the tree barrier.

3. The method for evaluating and predicting tree obstacle hazards of overhead power transmission lines according to claim 2, characterized in that: The specific steps of constructing the tree barrier hazard assessment system include: The tree barrier data of overhead transmission lines are classified, including tree species information, transmission line information and geographic information, to obtain the predicted state parameters of tree barrier height.

4. The method for evaluating and predicting tree obstacle hazards of overhead power transmission lines according to claim 2, characterized in that: The weight coefficients of various parameters are obtained according to the tree barrier hazard assessment system, and the specific steps include: A hierarchical model is constructed, including a target layer and a criterion layer, wherein the target layer includes the weight coefficients of the state parameters; the criterion layer includes tree species, tree age, tree height, longitude and latitude, altitude, historical growth information, line height and line sag; The judgment matrix is ​​constructed based on the parameters of the hierarchical model, and triangular fuzzy numbers are used to represent the relative importance of pairwise comparison of the judgment matrix parameters. According to the expert scoring method, pairwise comparison is performed to construct a fuzzy judgment matrix Calculate the fuzzy weight vector through the fuzzy judgment matrix; The fuzzy weight vector is defuzzified using the centroid method to obtain the weight value; The defuzzified weights are normalized to obtain the weight coefficients of each parameter.

5. The method for evaluating and predicting tree obstacle hazards of overhead power transmission lines according to claim 4, characterized in that: The step of calculating the weight coefficient comprises: in, represents a triangular fuzzy number, l is the minimum value, m is the middle value, u is the maximum value, and w i is the weight value, w i ′ represents the weight coefficient, i=1,2,3,…,n.

6. The method for evaluating and predicting tree obstacle hazards of overhead power transmission lines according to claim 1, characterized in that: The normalization processing of the tree barrier data specifically includes: Among them, X n represents the data obtained after normalization, X represents the data before processing, and X max , X min Respectively represent the maximum and minimum values ​​of each state parameter data in the data set.

7. The method for evaluating and predicting tree obstacle hazards of overhead power transmission lines according to claim 1, characterized in that: The constructing of the weighted scoring model specifically includes: Obtain the weight coefficients w1, w2…w9, and the state parameter values ​​corresponding to the weight coefficients are X1, X2…X9, and the weighted scoring model is obtained as follows: S=(w1×X1+w2×X2+...+w9×X9)×100 Where S is the predicted tree obstacle hazard score.

8. The method for evaluating and predicting tree obstacle hazards of overhead power transmission lines according to claim 1, characterized in that: The scoring of tree obstacle hazards based on the weighted scoring model specifically includes: Based on historical data and experience, tree obstacle hazards are divided into four states and a scoring template is obtained: Scoring is performed according to the scoring template for tree obstacle hazards.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method for assessing and predicting tree obstacle hazards in overhead transmission lines as described in any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for assessing and predicting tree obstacle hazards in overhead transmission lines as described in any one of claims 1 to 8 is implemented.

Citation Information

Patent Citations

  • Cable multimode safe operation evaluation method based on fuzzy analytic hierarchy process (FAHP)

    CN102496069A

  • Method, device and realization device for predicting hidden trouble of tree barrier of transmission line

    CN109215065A

  • Single-tree obstacle hidden danger evaluation processing method for backpack laser radar equipment

    CN112668885A

  • Overhead transmission line corridor vegetation growth analysis and early warning method

    CN113919215A

  • Overhead transmission line fault prediction method and device, equipment and storage medium

    CN117131947A

Cited By

  • Tree obstacle assessment method and system

    CN119228225A

  • A tree obstacle assessment method and system

    CN119228225B

  • Power distribution network tree line contradiction processing method

    CN121052601A