CN113919215A - Overhead transmission line corridor vegetation growth analysis early warning method - Google Patents
Overhead transmission line corridor vegetation growth analysis early warning method Download PDFInfo
- Publication number
- CN113919215A CN113919215A CN202111160921.0A CN202111160921A CN113919215A CN 113919215 A CN113919215 A CN 113919215A CN 202111160921 A CN202111160921 A CN 202111160921A CN 113919215 A CN113919215 A CN 113919215A
- Authority
- CN
- China
- Prior art keywords
- tree
- growth
- height
- transmission line
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000005540 biological transmission Effects 0.000 title claims abstract description 39
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000004458 analytical method Methods 0.000 title claims abstract description 13
- 238000009826 distribution Methods 0.000 claims abstract description 33
- 230000004888 barrier function Effects 0.000 claims abstract description 7
- 238000011156 evaluation Methods 0.000 claims description 12
- 238000005457 optimization Methods 0.000 claims description 8
- 210000000481 breast Anatomy 0.000 claims description 6
- 239000003102 growth factor Substances 0.000 claims description 6
- 238000004088 simulation Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 abstract description 5
- 238000004140 cleaning Methods 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 13
- 241000894007 species Species 0.000 description 9
- 241000196324 Embryophyta Species 0.000 description 7
- 238000013398 bayesian method Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 244000099147 Ananas comosus Species 0.000 description 1
- 235000007119 Ananas comosus Nutrition 0.000 description 1
- 244000080767 Areca catechu Species 0.000 description 1
- 235000006226 Areca catechu Nutrition 0.000 description 1
- 235000017166 Bambusa arundinacea Nutrition 0.000 description 1
- 235000017491 Bambusa tulda Nutrition 0.000 description 1
- 244000060011 Cocos nucifera Species 0.000 description 1
- 235000013162 Cocos nucifera Nutrition 0.000 description 1
- 244000004281 Eucalyptus maculata Species 0.000 description 1
- 240000003537 Ficus benghalensis Species 0.000 description 1
- 244000043261 Hevea brasiliensis Species 0.000 description 1
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 240000000233 Melia azedarach Species 0.000 description 1
- 244000082204 Phyllostachys viridis Species 0.000 description 1
- 235000015334 Phyllostachys viridis Nutrition 0.000 description 1
- 235000008331 Pinus X rigitaeda Nutrition 0.000 description 1
- 241000018646 Pinus brutia Species 0.000 description 1
- 235000011613 Pinus brutia Nutrition 0.000 description 1
- 240000001987 Pyrus communis Species 0.000 description 1
- 235000014443 Pyrus communis Nutrition 0.000 description 1
- 239000011425 bamboo Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000005315 distribution function Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000013316 zoning Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/08—Probabilistic or stochastic CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/04—Power grid distribution networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Human Resources & Organizations (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Algebra (AREA)
- Probability & Statistics with Applications (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Computing Systems (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
Abstract
The invention provides an overhead transmission line corridor vegetation growth analysis and early warning method, which comprises the following steps: s101, generating a tree obstacle hidden danger database, determining prior information and sample information of power transmission line corridor passage trees according to the tree obstacle hidden danger database, and constructing prior distribution of a Bayesian estimation method; s102, establishing a forest growth equation based on a nonlinear regression model, and determining an initial value of the forest growth equation; s103, obtaining posterior information based on prior distribution according to Bayes theorem, and calculating posterior distribution of unknown parameters in a forest growth equation according to the posterior information to obtain a tree height growth model; and S104, performing tree barrier analysis according to the limited parameters based on the tree height growth model. The method can predict the growth height of the trees in the corridor passage of the power transmission line, thereby assisting an operation and maintenance unit to compile a tree obstacle cleaning plan and reducing the risk of the trees on the safe operation of the line.
Description
Technical Field
The invention relates to the technical field of vegetation growth analysis, in particular to an early warning method for vegetation growth in an overhead transmission line corridor.
Background
The vegetation in tropical regions grows fast, the plants are various and are the source and the habitat of tropical rain forests and tropical season rain forests, the types of the vegetation in the tropical forests are complex, the vertical zoning is obvious, the vegetation has the characteristics of mixed crossing, multiple layers, different ages, evergreen, high trunk, wide crowns and the like, and representative plants include eucalyptus, areca catechu, rubber trees, bamboo forests, coconut trees, chinaberry trees, banyan trees, pine trees, pear trees, pineapple trees and the like. The high-stem plants grow fast, and the phenomena of annual cutting and annual growth often occur in the operation and maintenance process of the power transmission line. When trees near the power transmission line grow too high, the branches swing due to the strong wind and can touch the wires to cause electric leakage, and even break the wires. When trees under the power transmission line are too high, the trees can touch the wires to cause electric leakage and short circuit, and even cause power failure accidents. One of the difficulties of tree obstacle processing is estimating the distance from the tree to the electric wire, the traditional operation mode is that the electric transmission line is often observed manually, the workload is large, the distance from the arc to the top of the tree is observed manually and mentally calculated, personnel are required to observe from various angles, and errors caused by the observation angle and illusion of the personnel are difficult to avoid. At the present stage, the distance between the arc sag of the electric wire and the tree is accurately measured, and the distance is measured mainly by measuring instruments such as a height measuring rod and a theodolite, so that the workload of line patrol personnel is increased and the efficiency is low when the instruments are carried.
Disclosure of Invention
In view of the above, the invention aims to provide an overhead transmission line corridor vegetation growth analysis and early warning method, which is used for carrying out prediction analysis on the growth condition of a tree barrier by establishing a tree growth prediction model.
In order to achieve the aim, the invention provides an overhead transmission line corridor vegetation growth analysis and early warning method, which comprises the following steps:
s101, generating a tree obstacle hidden danger database, determining prior information and sample information of power transmission line corridor passage trees according to the tree obstacle hidden danger database, and constructing prior distribution of a Bayesian estimation method;
s102, establishing a forest growth equation based on a nonlinear regression model, and determining an initial value of the forest growth equation;
s103, obtaining posterior information based on prior distribution according to Bayes theorem, and calculating posterior distribution of unknown parameters in a forest growth equation according to the posterior information to obtain a tree height growth model;
and S104, performing tree barrier analysis according to the limited parameters based on the tree height growth model.
Further, the generating of the tree obstacle hidden danger database specifically includes the following steps:
s201, acquiring a vector file of the full-network overhead transmission line, and acquiring the voltage grade and the sideline extension distance information of the transmission line based on the vector file of the full-network overhead transmission line;
s202, determining a power line protection area according to the voltage grade of the power transmission line and the sideline extension distance information;
s203, collecting tree obstacle hidden danger data in the power line protection area, and generating a tree obstacle hidden danger database according to the tree obstacle hidden danger data.
Further, the tree obstacle hidden danger data comprises tree species, tree age, canopy intensity, plant number, current tree height, current breast diameter, current horizontal distance from a lead and vertical distance.
Further, the expression of the forest tree growth equation is as follows:
h represents the height of the tree, t represents the age of the tree, A is larger than 0 and k is larger than 0 in forest growth equation parameters A, B, k and m, the parameter A represents the final value of the equation, namely the maximum value of the tree growth, the parameter B is related to a tree growth factor, the size of the growth factor when t is 0 is determined, the parameter m is related to the shape of the equation curve, the position of an inflection point is determined, the value of the inflection point is related to equation simulation accuracy, the higher the inflection point accuracy is, the higher the equation simulation accuracy is, the higher the parameter k is related to the tree growth speed, and the growth rate of the tree is represented.
Further, the method for calculating the posterior distribution of the unknown parameters in the forest growth equation according to the posterior information comprises the following steps:
s301, inputting an unknown parameter initial value of a forest growing equation;
s302, generating tree evaluation information based on a tree obstacle hidden danger database, and estimating prior information according to the tree evaluation information, wherein the tree evaluation information comprises tree species, the existing height, natural production characteristics, regional differences, manual intervention modes, plant density and voltage levels, and influences on tree growth;
s303, calculating prior distribution under the condition of information according to the prior information;
s304, calculating a likelihood function and a total probability function of a given parameter;
and S305, obtaining posterior distribution of unknown parameters according to prior distribution, a likelihood function and a full probability function based on Bayesian theorem.
Further, the method between step S103 and step S104 further includes the steps of: and performing loop iteration on the tree height growth model based on a Bayesian estimation theory, and performing optimization adjustment on model parameters.
Further, the tree height growth model is subjected to loop iteration based on the Bayesian estimation theory, model parameters are subjected to optimization adjustment, and the method specifically comprises the following steps:
s401, selecting a tree seed sample based on the point cloud which can be added with light in the test point area, measuring the current tree height of the tree seed sample, calculating the growth height of the tree seed sample after the preset time length by adopting a tree height growth model, and recording the growth height;
s402, after a preset time, measuring the actual growth height of the tree seed sample based on the visible light point cloud generated by secondary visible light data acquisition, comparing and evaluating the actual growth height of the tree seed sample with the growth height calculated by the tree height growth model, judging that the precision of the model is unqualified if the accuracy is lower than a preset threshold value, and continuously optimizing the tree height growth model; otherwise, stopping the loop iteration to obtain the final tree height growth model.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides a method for analyzing vegetation growth in an overhead transmission line corridor, which is characterized in that a forest growth equation is established based on a nonlinear regression model, the prior information and sample information of trees in a transmission line corridor channel are used as random variables, a tree height growth model is obtained based on Bayesian theorem estimation, and the tree growth height of the transmission line corridor channel can be predicted based on the tree height growth model, so that an operation and maintenance unit is assisted to compile a tree obstacle cleaning plan, and the risk of safe operation of the trees on the line is reduced.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is apparent that the drawings in the following description are only preferred embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained based on these drawings without inventive efforts.
Fig. 1 is a schematic overall flow chart of a method for analyzing and warning vegetation growth in an overhead transmission line corridor according to an embodiment of the invention.
Fig. 2 is a schematic diagram of a tree obstacle hidden danger database generation process provided in the embodiment of the present invention.
Fig. 3 is a schematic diagram of a posterior distribution calculation process of position parameters of a forest growth equation provided in an embodiment of the present invention.
Fig. 4 is a schematic flow chart of the accuracy testing of the tree height growth model provided by the embodiment of the invention.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, the illustrated embodiments are provided to illustrate the invention and not to limit the scope of the invention.
Referring to fig. 1, the embodiment provides an overhead transmission line corridor vegetation growth analysis and early warning method, which includes the following steps:
s101, generating a tree obstacle hidden danger database, determining prior information and sample information of power transmission line corridor passage trees according to the tree obstacle hidden danger database, and constructing prior distribution of a Bayesian estimation method.
S102, establishing a forest growth equation based on the nonlinear regression model, and determining an initial value of the forest growth equation.
S103, posterior information is obtained based on prior distribution according to Bayes' theorem, and posterior distribution of unknown parameters in the forest growth equation is calculated according to the posterior information to obtain a tree height growth model.
And S104, performing tree barrier analysis according to the limited parameters based on the tree height growth model.
In the embodiment, a tree height growth model is estimated based on a Bayesian method by taking a tree growth equation as a basis and utilizing prior information and sample information of trees in a corridor channel of a power transmission line as random variables.
As an optional implementation manner, referring to fig. 2, in step S101, the generating a tree obstacle hidden danger database specifically includes the following steps:
s201, acquiring a vector file of the full-network overhead transmission line, and acquiring the voltage grade and the sideline extension distance information of the transmission line based on the vector file of the full-network overhead transmission line.
S202, determining a power line protection area according to the voltage grade of the power transmission line and the sideline extension distance information.
S203, collecting tree obstacle hidden danger data in the power line protection area, and generating a tree obstacle hidden danger database according to the tree obstacle hidden danger data.
Illustratively, the tree obstacle hidden danger data comprises tree species, tree age, canopy density, plant number, current tree height, current breast height, current horizontal distance and vertical distance from a lead and the like of a forest in the power line protection area.
In step S102, the forest growth equation is established based on a nonlinear regression model, and the formula is as follows:
h represents the height of the tree, t represents the age of the tree, A is larger than 0 and k is larger than 0 in forest growth equation parameters A, B, k and m, the parameter A represents the final value of the equation, namely the maximum value of the tree growth, the parameter B is related to a tree growth factor, the size of the growth factor when t is 0 is determined, the parameter m is related to the shape of the equation curve, the position of an inflection point is determined, the value of the inflection point is related to equation simulation accuracy, the higher the inflection point accuracy is, the higher the equation simulation accuracy is, the higher the parameter k is related to the tree growth speed, and the growth rate of the tree is represented. The main influence of each site parameter on each parameter in the forest growth equation is summarized as follows:
the parameter k has larger correlation with the forest age, the standing index, the average breast diameter and the forest density, and the forest age has the largest influence on the value of the parameter k;
the correlation of the forest age, the average tree height, the average breast diameter and the density to the parameter m is weakened in sequence;
the significant influence of the forest stand factor average tree height, the average breast diameter and the density on the parameter B is weakened in sequence.
Referring to fig. 3, in step S103, obtaining posterior information based on prior distribution according to bayesian theorem, and calculating posterior distribution of unknown parameters in the forest growth equation according to the posterior information specifically includes the following steps:
s301, inputting an unknown parameter initial value of a forest growing equation.
S302, generating forest evaluation information based on a tree obstacle hidden danger database, and estimating prior information according to the forest evaluation information, wherein the forest evaluation information comprises forest tree species, existing heights, natural production characteristics, regional differences, manual intervention modes, plant densities, voltage levels and the like in the power line protection area, and influences on tree growth are caused.
And S303, calculating prior distribution under the condition of information according to the prior information.
And S304, calculating a likelihood function and a total probability function of the given parameters.
And S305, obtaining posterior distribution of unknown parameters according to prior distribution, a likelihood function and a full probability function based on Bayesian theorem.
The basic method of Bayesian inference is to combine the prior information of unknown parameters with sample information, then obtain posterior information according to Bayesian theorem, and then infer the distribution of unknown parameters according to the posterior information. Let y be (y1, y2, y3, …) as data vector and θ be (θ 1, θ 2, θ 3, …) as parameter vector, then according to bayesian theory, the basic formula is:
p(y,θ)=p(y|θ)p(θ)=p(θ|y)p(y)
wherein p is a probability distribution function or a density function. As for the parameter θ, the estimation can be performed by using a least square method or a maximum likelihood estimation method in the conventional method. In the Bayes method, the uncertainty of the parameter theta is described through probability distribution, and then the parameter theta is estimated, according to Bayes conditional probability, the conditional probability distribution of theta is as follows:
among them, for the continuous type θ, there is p (y) E [ p (y | θ) ] ═ p (y | θ) p (θ) d (θ). In the bayesian method, the conditional distribution p (θ | y) of θ in a given sample y is the posterior distribution of the parameter to be obtained, p (y | θ) is the likelihood function of y in a given θ, and p (θ) is the prior distribution of θ.
As an optional implementation manner, a step is further included between step S103 and step S104; and performing loop iteration on the tree height growth model based on a Bayesian estimation theory, and performing optimization adjustment on model parameters.
Illustratively, referring to fig. 4, the performing loop iteration on the tree height growth model based on the bayesian estimation theory and performing optimization adjustment on the model parameters specifically includes the following steps:
s401, selecting a tree species sample by taking the point cloud which can be added with light in the test point area as basic data, measuring the current tree height of the tree species sample, calculating the growth height of the tree species sample after the preset time length by adopting a tree height growth model, and recording the growth height.
S402, after a preset time, measuring the actual growth height of the tree seed sample based on the visible light point cloud generated by secondary visible light data acquisition, comparing and evaluating the actual growth height of the tree seed sample with the growth height calculated by the tree height growth model, judging that the precision of the model is unqualified if the accuracy is lower than a preset threshold value, and continuously optimizing the tree height growth model; otherwise, stopping the loop iteration to obtain the final tree height growth model.
Illustratively, the tree height growth model optimization employs a bayesian method to find the value that minimizes the objective function by building a surrogate function (probabilistic model) based on past evaluation results of the objective function. The Bayesian method is different from the random or grid search in that it refers to the previous evaluation result when trying the next set of hyper-parameters, thereby improving the efficiency and reducing the calculation amount. The evaluation of the hyper-parameters is costly because it requires training the model once using the hyper-parameters to be evaluated, while many deep learning models require hours and days to complete training, and evaluating the model takes a lot of time and other resources. The Bayes method uses a continuously updated probability model, and concentrates promising hyperparameters by deducing past results, so that the optimization efficiency can be effectively improved.
After the final tree height growth model is obtained, tree barrier analysis can be carried out on the basis of the tree height growth model by inputting limiting parameters such as line names, voltage levels, tree species names and growth years, the growth heights of the trees in corresponding areas are predicted and displayed in a table form, and meanwhile, the trees with different heights can be marked in a virtual three-dimensional space through different highlight colors, so that a tree barrier cleaning plan can be conveniently made by an operation and maintenance unit, and the influence of overhigh trees on the safe operation of the overhead transmission line is avoided. And the obstacle clearing period can be automatically calculated according to growth models of different tree species in different regions, and an obstacle clearing plan list is generated, so that support is provided for operation and maintenance units to reasonably arrange obstacle clearing work.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (7)
1. The method for analyzing and early warning the vegetation growth in the corridor of the overhead transmission line is characterized by comprising the following steps:
s101, generating a tree obstacle hidden danger database, determining prior information and sample information of power transmission line corridor passage trees according to the tree obstacle hidden danger database, and constructing prior distribution of a Bayesian estimation method;
s102, establishing a forest growth equation based on a nonlinear regression model, and determining an initial value of the forest growth equation;
s103, obtaining posterior information based on prior distribution according to Bayes theorem, and calculating posterior distribution of unknown parameters in a forest growth equation according to the posterior information to obtain a tree height growth model;
and S104, performing tree barrier analysis according to the limited parameters based on the tree height growth model.
2. The method for analyzing and warning the vegetation growth in the corridor of the overhead transmission line according to claim 1, wherein the generating of the tree obstacle hidden danger database specifically comprises the following steps:
s201, acquiring a vector file of the full-network overhead transmission line, and acquiring the voltage grade and the sideline extension distance information of the transmission line based on the vector file of the full-network overhead transmission line;
s202, determining a power line protection area according to the voltage grade of the power transmission line and the sideline extension distance information;
s203, collecting tree obstacle hidden danger data in the power line protection area, and generating a tree obstacle hidden danger database according to the tree obstacle hidden danger data.
3. The method of claim 2, wherein the tree obstacle hidden danger data includes tree species, tree age, canopy, number of plants, current tree height, current breast height, current horizontal distance from a wire, and vertical distance from a wire.
4. The method of claim 1, wherein the expression of the forest growth equation is as follows:
h represents the height of the tree, t represents the age of the tree, A is larger than 0 and k is larger than 0 in forest growth equation parameters A, B, k and m, the parameter A represents the final value of the equation, namely the maximum value of the tree growth, the parameter B is related to a tree growth factor, the size of the growth factor when t is 0 is determined, the parameter m is related to the shape of the equation curve, the position of an inflection point is determined, the value of the inflection point is related to equation simulation accuracy, the higher the inflection point accuracy is, the higher the equation simulation accuracy is, the higher the parameter k is related to the tree growth speed, and the growth rate of the tree is represented.
5. The method for analyzing and early warning the vegetation growth in the corridor of the overhead transmission line according to claim 1, wherein posterior information is obtained based on prior distribution according to Bayes' theorem, and posterior distribution of unknown parameters in a forest growth equation is calculated according to the posterior information, comprising the following steps:
s301, inputting an unknown parameter initial value of a forest growing equation;
s302, generating tree evaluation information based on a tree obstacle hidden danger database, and estimating prior information according to the tree evaluation information, wherein the tree evaluation information comprises tree species, the existing height, natural production characteristics, regional differences, manual intervention modes, plant density and voltage levels, and influences on tree growth;
s303, calculating prior distribution under the condition of information according to the prior information;
s304, calculating a likelihood function and a total probability function of a given parameter;
and S305, obtaining posterior distribution of unknown parameters according to prior distribution, a likelihood function and a full probability function based on Bayesian theorem.
6. The method for analyzing and warning the vegetation growth in the corridor of the overhead transmission line according to claim 1, wherein the step S103 and the step S104 further comprise the steps of: and performing loop iteration on the tree height growth model based on a Bayesian estimation theory, and performing optimization adjustment on model parameters.
7. The method for analyzing and warning the vegetation growth in the corridor of the overhead transmission line according to claim 6, wherein the tree height growth model is subjected to loop iteration based on Bayes estimation theory, and model parameters are subjected to adjustment optimization, and the method specifically comprises the following steps:
s401, selecting a tree seed sample based on the point cloud which can be added with light in the test point area, measuring the current tree height of the tree seed sample, calculating the growth height of the tree seed sample after the preset time length by adopting a tree height growth model, and recording the growth height;
s402, after a preset time, measuring the actual growth height of the tree seed sample based on the visible light point cloud generated by secondary visible light data acquisition, comparing and evaluating the actual growth height of the tree seed sample with the growth height calculated by the tree height growth model, judging that the precision of the model is unqualified if the accuracy is lower than a preset threshold value, and continuously optimizing the tree height growth model; otherwise, stopping the loop iteration to obtain the final tree height growth model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111160921.0A CN113919215A (en) | 2021-09-30 | 2021-09-30 | Overhead transmission line corridor vegetation growth analysis early warning method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111160921.0A CN113919215A (en) | 2021-09-30 | 2021-09-30 | Overhead transmission line corridor vegetation growth analysis early warning method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113919215A true CN113919215A (en) | 2022-01-11 |
Family
ID=79237410
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111160921.0A Pending CN113919215A (en) | 2021-09-30 | 2021-09-30 | Overhead transmission line corridor vegetation growth analysis early warning method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113919215A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114739451A (en) * | 2022-03-22 | 2022-07-12 | 国网山东省电力公司超高压公司 | Transmission conductor safety early warning method under millimeter wave radar monitoring |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105069287A (en) * | 2015-07-27 | 2015-11-18 | 广西电网有限责任公司电力科学研究院 | Prediction method of forest growth of overhead transmission line passageway |
CN105447625A (en) * | 2015-11-12 | 2016-03-30 | 北京林业大学 | Automatic identification method for tree obstacle hidden troubles of overhead transmission line passage way |
CN105447623A (en) * | 2015-11-12 | 2016-03-30 | 北京林业大学 | Tree obstacle hidden trouble automatic pre-warning system for overhead transmission line and pre-warning method for above system |
CN106485254A (en) * | 2016-09-28 | 2017-03-08 | 国家电网公司 | A kind of electric transmission line channel topographical features change extraction method |
US20190228362A1 (en) * | 2016-07-15 | 2019-07-25 | University Of Connecticut | Systems and methods for outage prediction |
CN111340317A (en) * | 2020-05-19 | 2020-06-26 | 北京数字绿土科技有限公司 | Automatic early warning method for tree obstacle hidden danger of overhead transmission line and electronic equipment |
-
2021
- 2021-09-30 CN CN202111160921.0A patent/CN113919215A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105069287A (en) * | 2015-07-27 | 2015-11-18 | 广西电网有限责任公司电力科学研究院 | Prediction method of forest growth of overhead transmission line passageway |
CN105447625A (en) * | 2015-11-12 | 2016-03-30 | 北京林业大学 | Automatic identification method for tree obstacle hidden troubles of overhead transmission line passage way |
CN105447623A (en) * | 2015-11-12 | 2016-03-30 | 北京林业大学 | Tree obstacle hidden trouble automatic pre-warning system for overhead transmission line and pre-warning method for above system |
US20190228362A1 (en) * | 2016-07-15 | 2019-07-25 | University Of Connecticut | Systems and methods for outage prediction |
CN106485254A (en) * | 2016-09-28 | 2017-03-08 | 国家电网公司 | A kind of electric transmission line channel topographical features change extraction method |
CN111340317A (en) * | 2020-05-19 | 2020-06-26 | 北京数字绿土科技有限公司 | Automatic early warning method for tree obstacle hidden danger of overhead transmission line and electronic equipment |
Non-Patent Citations (1)
Title |
---|
黄维;黄志都;王乐;蒋圣超;俸波;: "架空输电线路走廊树障隐患动态管理及预警分析" * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114739451A (en) * | 2022-03-22 | 2022-07-12 | 国网山东省电力公司超高压公司 | Transmission conductor safety early warning method under millimeter wave radar monitoring |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110837926B (en) | Tobacco main pest and disease damage prediction method based on big data | |
CN102183621B (en) | Aquaculture dissolved oxygen concentration online forecasting method and system | |
CN105808948A (en) | Automatic correctional multi-mode value rainfall ensemble forecast method | |
CN110162872B (en) | Biomass estimation method fusing sample plot data and forest resource clearing data | |
CN109215065A (en) | Screen of trees hidden danger prediction technique, device and the realization device of transmission line of electricity | |
CN105069287A (en) | Prediction method of forest growth of overhead transmission line passageway | |
CN105447623A (en) | Tree obstacle hidden trouble automatic pre-warning system for overhead transmission line and pre-warning method for above system | |
CN109034641A (en) | Defect of pipeline prediction technique and device | |
CN111460990A (en) | Big data-based alpine pastoral area grassland insect pest monitoring and early warning system and method | |
CN103020743B (en) | Wind energy turbine set ultra-short term wind speed forecasting method | |
JP6820625B1 (en) | Servers, forest data utilization systems, forest data utilization methods and programs | |
CN109325633A (en) | A kind of weather forecast set member choosing method and system | |
CN113919215A (en) | Overhead transmission line corridor vegetation growth analysis early warning method | |
CN109214591A (en) | A kind of xylophyta ground biomass prediction technique and system | |
CN106910022B (en) | Wheat colony lodging-resistant critical wind speed determination and calculation method | |
CN110782089B (en) | Forest thinning method and system | |
CN111427101A (en) | Thunderstorm strong wind grading early warning method, system, storage medium and computer program | |
CN113821895B (en) | Method and device for constructing power transmission line icing thickness prediction model and storage medium | |
CN110175371A (en) | A kind of greening residue theoretical amount statistical calculation method | |
CN109685242A (en) | Photovoltaic ultra-short term combination forecasting method based on Adaboost algorithm | |
CN110969303B (en) | Tree height prediction method based on rational Charles model | |
Li et al. | Three-dimensional visualization simulation of Chinese Fir stand growth based on unity3D | |
CN107977727A (en) | A kind of method that probability is blocked based on social development and climatic factor prediction cable network | |
Aman et al. | Construction of local volume table for natural mangroves in Peninsular Malaysia: case study of Sungai Merbok Forest Reserve, Kedah | |
Wang et al. | Research and analysis of carbon sequestration prediction scheme based on multi-model |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220111 |