CN106327013A - Power transmission line inspection path planning method and system - Google Patents

Abstract

The invention discloses a power transmission line inspection path planning method and system. The method comprises the steps that preset parameter information is initialized; tower risk operation factor original data are preprocessed, and a Bayesian network model is established and the tower risk operation condition probability of the corresponding tower risk operation factors is calculated according to the preprocessed data; an inter-tower inspection time model is established according to the tower parameters and the inter-tower path difficulty coefficient; a comprehensive inspection model is established according to the tower risk operation condition probability and the inter-tower inspection time model; and the comprehensive model is solved by utilizing a preset intelligent algorithm according to the preset intelligent algorithm parameters, and the optimal inspection path after optimization is outputted when the iterative termination conditions are met. Two factors of inspection time of inspectors and the tower risk probability are considered, optimization is performed by utilizing the preset intelligent algorithm and the inspection path is scientifically formulated so that the conventional inspection path planning method of depending on leadership decision or experiential decision can be eliminated, and the inspection efficiency can be enhanced.

Description

A kind of power transmission line polling path method and system for planning

Technical field

The present invention relates to technical field of power systems, particularly to a kind of power transmission line polling path method and system for planning.

Background technology

Transmission line of electricity is the important component part of power system, and its safe operation is the important leverage of system monolithic stability. But transmission line of electricity and auxiliary device thereof are exposed in field, this method of operation is inherently by environmental factors, anthropic factor Affect with equipment oneself factor etc..

Current domestic polling transmission line mode includes that manual inspection, unmanned plane are patrolled and examined and the mode such as patrols and examines with vehicle；? Vehicle is patrolled and examined to patrol and examine with unmanned plane and be there is a lot of intelligent algorithm optimization polling path in application, calculates including population The intelligent algorithms such as method, genetic algorithm, ant group algorithm, utilize the intelligent algorithm can be scientific and reasonable in unmanned plane and vehicle are patrolled and examined Polling path is planned, improves and patrol and examine efficiency；But due to the complexity of shaft tower environment, a lot of situations cannot use vapour Car is patrolled and examined and is patrolled and examined two ways with unmanned plane, it is necessary to rely on manual inspection mode.The planning of Traditional Man power transmission line polling path is many Depending on Leader's intention, experienced inspector formulate polling path, there is the strongest subjectivity in the mode of this dependence experience Property, lack science, and cannot the risk factor that are subject to of anticipation shaft tower, encouraged transmission line of electricity the most to a certain extent Risk runs probability.Formulate patrolling transmission line path and can effectively promote human resources and saving expense, so power transmission line It is necessary that path planning is maked an inspection tour on road.

Summary of the invention

It is an object of the invention to provide a kind of power transmission line polling path method and system for planning, considered inspector and patrolled Inspection time and two kinds of factors of shaft tower occurrence risk probability, utilize predetermined intelligent algorithm optimization to formulate polling path, improve and patrol and examine effect Rate.

For solving above-mentioned technical problem, the present invention provides a kind of power transmission line polling path planing method, including:

Initialize predefined parameter information；Wherein, described predefined parameter information includes that shaft tower parameter, shaft tower risk run factor Path difficulty coefficient and predetermined intelligent algorithm parameter between initial data, shaft tower；

Described shaft tower risk is run factor initial data and carries out pretreatment, according to pretreated data, set up pattra leaves This network model and calculate corresponding shaft tower risk run factor shaft tower risk service condition probability；

According to path difficulty coefficient between described shaft tower parameter and described shaft tower, set up monitoring time model between tower；

According to monitoring time model between described shaft tower risk service condition probability and described tower, set up and comprehensively patrol and examine model；

According to predetermined intelligent algorithm parameter, utilize predetermined intelligent algorithm that aggregative model is solved, when satisfied termination changes During for condition, output is optimum polling path after optimizing.

Wherein, described shaft tower risk is run factor initial data and carries out pretreatment, including:

Run factor initial data according to shaft tower risk, set up initial decision table；

According to described initial decision table, every kind of shaft tower risk is run the Feature Mapping of factor to predetermined interval interior, and The feature utilizing concrete numerical value and every kind of shaft tower risk to run factor carries out one_to_one corresponding, forms the initial decision after quantifying Table.

Wherein, according to pretreated data, set up Bayesian network model, including:

It is input in original Bayesian network model calculate by the data in the initial decision table after described quantization, builds Vertical Bayesian network model.

Wherein, according to pretreated data, the shaft tower risk operation bar calculating corresponding shaft tower risk operation factor is set up Part probability, including:

Utilize described Bayesian network model, be calculated each shaft tower risk fortune in the initial decision table after described quantization The conditional probability of row factor；

According to described conditional probability and described Bayesian network model, obtain corresponding shaft tower risk by probability calculation and run The shaft tower risk service condition probability of factor；Wherein,

Shaft tower risk runs the shaft tower excessive risk service condition probability of factor:

$Pf=P\left(B_1\right|A)=\frac{P\left(B_1\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)}{P\left(B_1\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)+P\left(B_2\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)}$

Shaft tower risk runs the shaft tower low-risk service condition probability of factor:

$Pn=P\left(B_2\right|A)=\frac{P\left(B_2\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)}{P\left(B_1\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)+P\left(B_2\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)}$

Wherein, pole tower operation state variable B={B₁、B₂}={ excessive risk is run, low-risk is run } represent, shaft tower wind Factor { C is run in danger₁C₂C₃。。。。。C₉Represent, P (B₁) and P (B₂) represent that the history excessive risk of shaft tower is run and history respectively Low-risk runs probability；P(C_i|B₁) represent that shaft tower excessive risk under conditions of different shaft tower risk operation factors is run general Rate.

Wherein, between described tower monitoring time model particularly as follows:

$T_{i,j}=R(i,j)\·\sqrt{{(X_j-X_i)}^2+{(Y_j-Y_i)}^2}$

Wherein, (i j) represents the path difficulty coefficient between shaft tower i to shaft tower j to R；X (i), X (j) represent shaft tower i, j's Abscissa, Y (i), Y (j) represent the vertical coordinate of shaft tower i, j.

Wherein, described comprehensively patrol and examine model particularly as follows:

$F_{ij}=\mathrm{\α}\·R(i,j)\·\underset{i=1}{\overset{D-1}{\Σ}}{T}_{i,j}+\mathrm{\β}\·\underset{i=1}{\overset{D-1}{\Σ}}{P}_j/P_i$

Wherein, F_ijFor object function, D is shaft tower number to be inspected, P_i、P_jThe risk probability of shaft tower i and j respectively, α and β is weight coefficient, and (i j) represents the path difficulty coefficient between shaft tower i to shaft tower j, T to R_{I, j}For monitoring time model between tower.

The present invention also provides for a kind of power transmission line polling path planning system, including:

Initialization module, is used for initializing predefined parameter information；Wherein, described predefined parameter information include shaft tower parameter, Shaft tower risk runs path difficulty coefficient and predetermined intelligent algorithm parameter between factor initial data, shaft tower；

Shaft tower risk service condition probabilistic module, carries out pre-place for described shaft tower risk is run factor initial data Reason, according to pretreated data, sets up Bayesian network model and calculates the shaft tower risk of corresponding shaft tower risk operation factor Service condition probability；

Monitoring time model module between tower, for according to path difficulty coefficient between described shaft tower parameter and described shaft tower, builds Monitoring time model between vertical tower；

Comprehensively patrol and examine model module, for according to monitoring time mould between described shaft tower risk service condition probability and described tower Type, sets up and comprehensively patrols and examines model；

Optimum polling path module, for according to predetermined intelligent algorithm parameter, utilizes predetermined intelligent algorithm to aggregative model Solving, when satisfied termination iterated conditional, output is optimum polling path after optimizing.

Wherein, described shaft tower risk service condition probabilistic module, including:

Conditional probability unit, is used for utilizing described Bayesian network model, is calculated the initial decision after described quantization In table, each shaft tower risk runs the conditional probability of factor；

Shaft tower risk service condition probability unit is for according to described conditional probability and described Bayesian network model, logical Cross probability calculation and obtain the shaft tower risk service condition probability of corresponding shaft tower risk operation factor；Wherein,

Shaft tower risk runs the shaft tower excessive risk service condition probability of factor:

$Pf=P\left(B_1\right|A)=\frac{P\left(B_1\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)}{P\left(B_1\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)+P\left(B_2\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)}$

Shaft tower risk runs the shaft tower low-risk service condition probability of factor:

$Pn=P\left(B_2\right|A)=\frac{P\left(B_2\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)}{P\left(B_1\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)+P\left(B_2\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)}$

Wherein, pole tower operation state variable B={B₁、B₂}={ excessive risk is run, low-risk is run } represent, shaft tower wind Factor { C is run in danger₁C₂C₃。。。。。C₉Represent, P (B₁) and P (B₂) represent that the history excessive risk of shaft tower is run and history respectively Low-risk runs probability；P(C_i|B₁) represent that shaft tower excessive risk under conditions of different shaft tower risk operation factors is run general Rate.

Wherein, between described tower monitoring time model module particularly as follows: according to path between described shaft tower parameter and described shaft tower Difficulty coefficient, sets up monitoring time model between tower

Wherein, (i j) represents the path difficulty coefficient between shaft tower i to shaft tower j to R；X (i), X (j) represent shaft tower i, j's Abscissa, Y (i), Y (j) represent the vertical coordinate of shaft tower i, j.

Wherein, described comprehensively model module is patrolled and examined particularly as follows: according to described shaft tower risk service condition probability and described tower Between monitoring time model, set up comprehensively patrol and examine model

Wherein, wherein, F_ijFor object function, D is shaft tower number to be inspected, P_i、P_jThe risk being shaft tower i and j respectively is general Rate, α and β is weight coefficient, and (i j) represents the path difficulty coefficient between shaft tower i to shaft tower j, T to R_{I, j}For monitoring time between tower Model.

A kind of power transmission line polling path planing method provided by the present invention, including: initialize predefined parameter information；To bar Tower risk is run factor initial data and is carried out pretreatment, according to pretreated data, sets up Bayesian network model and calculates Corresponding shaft tower risk runs the shaft tower risk service condition probability of factor；According to difficulty coefficient in path between shaft tower parameter and shaft tower, Set up monitoring time model between tower；According to monitoring time model between shaft tower risk service condition probability and tower, set up and comprehensively patrol and examine Model；According to predetermined intelligent algorithm parameter, utilize predetermined intelligent algorithm that aggregative model is solved, when satisfied termination iteration bar During part, output is optimum polling path after optimizing；

Visible, the method has considered inspector's monitoring time and two kinds of factors of shaft tower occurrence risk probability, utilizes pre- Determining intelligent algorithm optimization, science formulates polling path, and that breaks away from that conventional situation relies on managerial decision or empirical decision making patrols and examines road Footpath planing method, improves and patrols and examines efficiency；The present invention also provides for a kind of power transmission line polling path planning system, has above-mentioned useful effect Really, do not repeat them here.

Accompanying drawing explanation

In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing In having technology to describe, the required accompanying drawing used is briefly described, it should be apparent that, the accompanying drawing in describing below is only this Inventive embodiment, for those of ordinary skill in the art, on the premise of not paying creative work, it is also possible to according to The accompanying drawing provided obtains other accompanying drawing.

The flow chart of the power transmission line polling path planing method that Fig. 1 is provided by the embodiment of the present invention；

The schematic diagram of the Bayesian network model that Fig. 2 is provided by the embodiment of the present invention；

The schematic diagram of the optimum polling path that Fig. 3 is provided by the embodiment of the present invention；

The structured flowchart of the power transmission line polling path planning system that Fig. 4 is provided by the embodiment of the present invention.

Detailed description of the invention

The core of the present invention is to provide a kind of power transmission line polling path method and system for planning, has considered inspector and has patrolled Inspection time and two kinds of factors of shaft tower occurrence risk probability, utilize predetermined intelligent algorithm optimization to formulate polling path, improve and patrol and examine effect Rate.

For making the purpose of the embodiment of the present invention, technical scheme and advantage clearer, below in conjunction with the embodiment of the present invention In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is The a part of embodiment of the present invention rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art The every other embodiment obtained under not making creative work premise, broadly falls into the scope of protection of the invention.

Refer to the flow chart of the power transmission line polling path planing method that Fig. 1, Fig. 1 are provided by the embodiment of the present invention；Should Method may include that

S100, initialization predefined parameter information；Wherein, described predefined parameter information includes that shaft tower parameter, shaft tower risk are transported Path difficulty coefficient and predetermined intelligent algorithm parameter between row factor initial data, shaft tower；

Wherein, predefined parameter information here specifically can set according to the actually used situation of user, it is considered to because of Element can be determined by user, such as shaft tower risk run factor initial data include weather conditions, geologic(al) factor, the tour cycle, (user can be to shaft tower risk here for historical load, temperature factor, operation time, abnormal frequency, material rate, electric pressure Operation factor increases and decreases)；Predetermined intelligent algorithm parameter includes lateral cross rate, crossed longitudinally rate, population, iterations (being determined according to the parameter requirements that selected intelligent algorithm is concrete)；Shaft tower parameter includes shaft tower number, shaft tower coordinate；Shaft tower Between path difficulty coefficient determined (elapsed time, road conditions when coefficient is in order to distinguish inspection here by the road condition grade that each shaft tower is corresponding The corresponding elapsed time length of difference).

S110, described shaft tower risk is run factor initial data carry out pretreatment, according to pretreated data, set up Bayesian network model and calculate corresponding shaft tower risk run factor shaft tower risk service condition probability；

Wherein, described shaft tower risk is run factor initial data and carry out pretreatment, including the statistical classification of initial data Deng operation, can conveniently be input to that original Bayesian network model carries out model training through pretreated data and obtain The most available Bayesian network model；And be calculated under selected shaft tower risk operation conditions according to Bayesian network model Shaft tower risk service condition probability；And shaft tower risk service condition probability here can include excessive risk service condition probability And/or low-risk service condition probability.

Concrete, described shaft tower risk operation factor initial data is carried out pretreatment can be with including:

Run factor initial data according to shaft tower risk, set up initial decision table；Wherein, initial decision table can be such that

According to described initial decision table, every kind of shaft tower risk is run the Feature Mapping of factor to predetermined interval interior, and The feature utilizing concrete numerical value and every kind of shaft tower risk to run factor carries out one_to_one corresponding, forms the initial decision after quantifying Table.

Concrete, according to initial decision table, need the i.e. shaft tower risk of influence factor in above-mentioned initial data is run factor Carry out its quantizing process of quantification treatment be by the Feature Mapping of every kind of influence factor to certain interval in, and with concrete numerical value Represent different characteristic therein, such as weather conditions etc..

Optionally, according to pretreated data, set up Bayesian network model, including:

It is input in original Bayesian network model calculate by the data in the initial decision table after described quantization, builds Vertical Bayesian network model.

Concrete calculating process can be divided into 5 steps, specific as follows:

1, the conditional mutual information between shaft tower risk influence on system operation factor: I is calculated_p(C_i；C_j| C), i, j=1,2 ... .., n (conditional mutual information refer to a variable comprise another variable number) wherein C be shaft tower risk run influence factor；

2, one is generated with Ip (Ci；Cj | C) it is the Weight non-directed graph of arc, i, j=1,2 ... .., n.

3, a weight limit spanning tree is found

4, arrange with the root node figure outside for all limits of starting point.

5, generate with the arc between variable node and attribute node.

The Bayesian network model set up after above-mentioned 5 steps can be as shown in Figure 2.

Optionally, according to pretreated data, the shaft tower risk operation calculating corresponding shaft tower risk operation factor is set up Conditional probability, including:

Utilize described Bayesian network model, be calculated each shaft tower risk fortune in the initial decision table after described quantization The conditional probability of row factor；

According to described conditional probability and described Bayesian network model, obtain corresponding shaft tower risk by probability calculation and run The shaft tower risk service condition probability of factor；Wherein,

Shaft tower risk runs the shaft tower excessive risk service condition probability of factor:

$Pf=P\left(B_1\right|A)=\frac{P\left(B_1\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)}{P\left(B_1\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)+P\left(B_2\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)}$

Shaft tower risk runs the shaft tower low-risk service condition probability of factor:

$Pn=P\left(B_2\right|A)=\frac{P\left(B_2\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)}{P\left(B_1\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)+P\left(B_2\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)}$

Wherein, pole tower operation state variable B={B₁、B₂}={ excessive risk is run, low-risk is run } represent, shaft tower wind Factor { C is run in danger₁C₂C₃。。。。。C₉Represent, P (B₁) and P (B₂) represent that the history excessive risk of shaft tower is run and history respectively Low-risk runs probability；P(C_i|B₁) represent that shaft tower excessive risk under conditions of different shaft tower risk operation factors is run general Rate.

Concrete, calculate the condition of each attribute in the initial decision table after quantization by Bayesian network model general Rate, on the premise of obtaining conditional probability and Bayesian network model, can show that by probability calculation the excessive risk of sample is transported Row probability.

S120, according to path difficulty coefficient between described shaft tower parameter and described shaft tower, set up monitoring time model between tower；

Wherein, when shaft tower parameter includes shaft tower number and shaft tower coordinate, then monitoring time model between the tower set up particularly as follows:

$T_{i,j}=R(i,j)\·\sqrt{{(X_j-X_i)}^2+{(Y_j-Y_i)}^2}$

Wherein, (i j) represents the path difficulty coefficient between shaft tower i to shaft tower j to R；X (i), X (j) represent shaft tower i, j's Abscissa, Y (i), Y (j) represent the vertical coordinate of shaft tower i, j.This model convenience of calculation, and can go out between tower with the quantization of fair relatively Monitoring time.Here this model can also otherwise be calculated.

S130, according to monitoring time model between described shaft tower risk service condition probability and described tower, set up and comprehensively patrol and examine Model；

Wherein, model here needs the situation considering concrete model obtained above to be determined, and utilizes and uses The concrete model that above-mentioned steps obtains, the most here comprehensively patrol and examine model particularly as follows:

$F_{ij}=\mathrm{\α}\·R(i,j)\·\underset{i=1}{\overset{D-1}{\Σ}}{T}_{i,j}+\mathrm{\β}\·\underset{i=1}{\overset{D-1}{\Σ}}{P}_j/P_i$

Wherein, F_ijFor object function, D is shaft tower number to be inspected, P_i、P_jThe risk probability of shaft tower i and j respectively, α and β is weight coefficient, and (i j) represents the path difficulty coefficient between shaft tower i to shaft tower j, T to R_{I, j}For monitoring time model between tower.

S140, according to predetermined intelligent algorithm parameter, utilize predetermined intelligent algorithm that aggregative model is solved, when satisfied end Only during iterated conditional, output is optimum polling path after optimizing.

Wherein, for the inspection path after being optimized, the intelligent algorithm time searching process of practicality and high efficiency here, such as Use genetic algorithm, particle algorithm, in length and breadth crossover algorithm etc., can select according to user's request, the most important meet can Determine optimal path carrying out optimizing, concrete algorithm is not limited.

Optionally, crossover algorithm in length and breadth can be utilized here repeatedly to solve comprehensively patrolling and examining model, intersect calculation in length and breadth Method is a kind of intelligent algorithm, including the crossed longitudinally two parts of lateral cross, has ability of searching optimum in application planning problem Strong feature.

Based on technique scheme, the power transmission line polling path planing method that the embodiment of the present invention provides, patrolled by foundation Inspection person patrols and examines time of cost and pole tower operation risk is target, owing to shaft tower is numerous, and the complexity of shaft tower local environment, often Inspector's monitoring time between shaft tower cannot accurately be refined, the present embodiment take to utilize air line distance between shaft tower with this two The difficult coefficient product representation monitoring time of road conditions between seat shaft tower；Polling transmission line purpose is to get rid of shaft tower and power transmission line event Barrier, the shaft tower the most preferentially patrolling and examining occurrence risk probability bigger is particularly important, and the present embodiment utilizes the initial data of shaft tower, Set up Bayesian network model, calculate the probability of every shaft tower occurrence risk；Patrol in conjunction with pole tower operation risk probability and inspector The inspection time, two targets set up aggregative model, utilized predetermined intelligent algorithm to be optimized this model and solved, patrol and examine for power transmission line Scientific and effective polling path is provided, enables inspector preferentially patrolling and examining the bar that occurrence risk probability is bigger when patrolling and examining operation Tower and ensure that monitoring time is the shortest, improves and patrols and examines efficiency.

In order to the beneficial effect of data processing method that the present invention propose is better described, test underneath with example Card:

Table 1 below is the coordinate position of 30 shaft towers, and wherein X is the abscissa of shaft tower, and Y is the vertical coordinate of shaft tower；The most several The shaft tower initial data in year, sets up Bayesian network model, such as Fig. 2, utilizes Bayesian network to be calculated the operation wind of shaft tower Danger probability is shown in Table 2；Wherein table 3 is the difficult coefficient in shaft tower path.

Table 1 shaft tower coordinate

Table 2 pole tower operation risk probability

Table 3 shaft tower path difficulty coefficient

From the foregoing, at the path difficulty coefficient of known shaft tower coordinate parameters, pole tower operation risk probability and shaft tower, build Vertical inspector's monitoring time and the aggregative model of pole tower operation risk, utilize predetermined intelligent algorithm to be optimized this model and ask Solve, obtain optimum polling path, as shown in Figure 3.Visible the method not only allows for inspector and completes patrol task and to spend Time, consider simultaneously shaft tower occur risk probability, during patrol task, it is possible to preferentially patrol and examine occurrence risk probability Bigger shaft tower, what guarantee monitoring time was shorter simultaneously completes task, has science and reasonability.

The power transmission line polling path planning system provided the embodiment of the present invention below is introduced, transmission of electricity described below Line polling path planning system can be mutually to should refer to above-described power transmission line polling path planing method.

Refer to the structured flowchart of the power transmission line polling path planning system that Fig. 4, Fig. 4 are provided by the embodiment of the present invention； This system may include that

Initialization module 100, is used for initializing predefined parameter information；Wherein, described predefined parameter information includes that shaft tower is joined Number, shaft tower risk run path difficulty coefficient and predetermined intelligent algorithm parameter between factor initial data, shaft tower；

Shaft tower risk service condition probabilistic module 200, carries out pre-for described shaft tower risk is run factor initial data Process, according to pretreated data, set up Bayesian network model and calculate the shaft tower wind of corresponding shaft tower risk operation factor Danger service condition probability；

Monitoring time model module 300 between tower, is used for according to path difficulty coefficient between described shaft tower parameter and described shaft tower, Set up monitoring time model between tower；

Comprehensively patrol and examine model module 400, for according to when patrolling and examining between described shaft tower risk service condition probability and described tower Between model, set up comprehensively patrol and examine model；

Optimum polling path module 500, for according to predetermined intelligent algorithm parameter, utilizes predetermined intelligent algorithm to comprehensive mould Type solves, and when satisfied termination iterated conditional, output is optimum polling path after optimizing.

Optional based on above-described embodiment, described shaft tower risk service condition probabilistic module 200, including:

Conditional probability unit, is used for utilizing described Bayesian network model, is calculated the initial decision after described quantization In table, each shaft tower risk runs the conditional probability of factor；

Shaft tower risk service condition probability unit is for according to described conditional probability and described Bayesian network model, logical Cross probability calculation and obtain the shaft tower risk service condition probability of corresponding shaft tower risk operation factor；Wherein,

Shaft tower risk runs the shaft tower excessive risk service condition probability of factor:

$Pf=P\left(B_1\right|A)=\frac{P\left(B_1\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)}{P\left(B_1\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)+P\left(B_2\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)}$

Shaft tower risk runs the shaft tower low-risk service condition probability of factor:

$Pn=P\left(B_2\right|A)=\frac{P\left(B_2\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)}{P\left(B_1\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)+P\left(B_2\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)}$

Wherein, pole tower operation state variable B={B₁、B₂}={ excessive risk is run, low-risk is run } represent, shaft tower wind Factor { C is run in danger₁C₂C₃。。。。。C₉Represent, P (B₁) and P (B₂) represent that the history excessive risk of shaft tower is run and history respectively Low-risk runs probability；P(C_i|B₁) represent that shaft tower excessive risk under conditions of different shaft tower risk operation factors is run general Rate.

Optional based on above-described embodiment, monitoring time model module 300 between described tower is particularly as follows: join according to described shaft tower Path difficulty coefficient between several and described shaft tower, sets up monitoring time model between tower $T_{i,j}=R(i,j)\·\sqrt{{(X_j-X_i)}^2+{(Y_j-Y_i)}^2};$

Wherein, (i j) represents the path difficulty coefficient between shaft tower i to shaft tower j to R；X (i), X (j) represent shaft tower i, j's Abscissa, Y (i), Y (j) represent the vertical coordinate of shaft tower i, j.

Optional based on above-mentioned any embodiment, described comprehensively patrol and examine model module 400 particularly as follows: according to described shaft tower wind Monitoring time model between danger service condition probability and described tower, sets up and comprehensively patrols and examines model

Wherein, wherein, F_ijFor object function, D is shaft tower number to be inspected, P_i、P_jThe risk being shaft tower i and j respectively is general Rate, α and β is weight coefficient, and (i j) represents the path difficulty coefficient between shaft tower i to shaft tower j, T to R_{I, j}For monitoring time between tower Model.

In description, each embodiment uses the mode gone forward one by one to describe, and what each embodiment stressed is real with other Executing the difference of example, between each embodiment, identical similar portion sees mutually.For device disclosed in embodiment Speech, owing to it corresponds to the method disclosed in Example, so describe is fairly simple, relevant part sees method part explanation ?.

Professional further appreciates that, in conjunction with the unit of each example that the embodiments described herein describes And algorithm steps, it is possible to electronic hardware, computer software or the two be implemented in combination in, in order to clearly demonstrate hardware and The interchangeability of software, the most generally describes composition and the step of each example according to function.These Function performs with hardware or software mode actually, depends on application-specific and the design constraint of technical scheme.Specialty Technical staff specifically should can be used for using different methods to realize described function to each, but this realization should not Think beyond the scope of this invention.

The method described in conjunction with the embodiments described herein or the step of algorithm can direct hardware, processor be held The software module of row, or the combination of the two implements.Software module can be placed in random access memory (RAM), internal memory, read-only deposit Reservoir (ROM), electrically programmable ROM, electrically erasable ROM, depositor, hard disk, moveable magnetic disc, CD-ROM or technology In any other form of storage medium well known in field.

Above power transmission line polling path method and system for planning provided by the present invention is described in detail.Herein Applying specific case to be set forth principle and the embodiment of the present invention, the explanation of above example is only intended to help Understand method and the core concept thereof of the present invention.It should be pointed out that, for those skilled in the art, do not taking off On the premise of the principle of the invention, it is also possible to the present invention is carried out some improvement and modification, these improve and modification also falls into this In invention scope of the claims.

Claims (10)

1. a power transmission line polling path planing method, it is characterised in that including:

Initialize predefined parameter information；Wherein, described predefined parameter information includes that shaft tower parameter, shaft tower risk operation factor is original Path difficulty coefficient and predetermined intelligent algorithm parameter between data, shaft tower；

Described shaft tower risk is run factor initial data and carries out pretreatment, according to pretreated data, set up Bayesian network Network model and calculate corresponding shaft tower risk run factor shaft tower risk service condition probability；

According to path difficulty coefficient between described shaft tower parameter and described shaft tower, set up monitoring time model between tower；

According to monitoring time model between described shaft tower risk service condition probability and described tower, set up and comprehensively patrol and examine model；

According to predetermined intelligent algorithm parameter, utilize predetermined intelligent algorithm that aggregative model is solved, when satisfied termination iteration bar During part, output is optimum polling path after optimizing.

Power transmission line polling path planing method the most according to claim 1, it is characterised in that described shaft tower risk is run Factor initial data carries out pretreatment, including:

Run factor initial data according to shaft tower risk, set up initial decision table；

According to described initial decision table, every kind of shaft tower risk is run the Feature Mapping of factor to predetermined interval interior, and utilize Concrete numerical value and every kind of shaft tower risk are run the feature of factor and are carried out one_to_one corresponding, form the initial decision table after quantifying.

Power transmission line polling path planing method the most according to claim 2, it is characterised in that according to pretreated number According to, set up Bayesian network model, including:

It is input in original Bayesian network model calculate by the data in the initial decision table after described quantization, sets up shellfish Ye Si network model.

Power transmission line polling path planing method the most according to claim 3, it is characterised in that according to pretreated number According to, set up the shaft tower risk service condition probability calculating corresponding shaft tower risk operation factor, including:

Utilize described Bayesian network model, be calculated in the initial decision table after described quantization each shaft tower risk run because of The conditional probability of element；

According to described conditional probability and described Bayesian network model, obtain corresponding shaft tower risk by probability calculation and run factor Shaft tower risk service condition probability；Wherein,

Shaft tower risk runs the shaft tower excessive risk service condition probability of factor:

$Pf=P\left(B_1\right|A)=\frac{P\left(B_1\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)}{P\left(B_1\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)+P\left(B_2\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)}$

Shaft tower risk runs the shaft tower low-risk service condition probability of factor:

$Pn=P\left(B_2\right|A)=\frac{P\left(B_2\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)}{P\left(B_1\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)+P\left(B_2\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)}$

Wherein, pole tower operation state variable B={B₁、B₂}={ excessive risk is run, low-risk is run } represent, shaft tower risk is transported Row factor { C₁C₂C₃.....C₉Represent, P (B₁) and P (B₂) represent that the history excessive risk of shaft tower is run and the low wind of history respectively Probability is run in danger；P(C_i|B₁) represent that shaft tower excessive risk under conditions of different shaft tower risk operation factors runs probability.

Power transmission line polling path planing method the most according to claim 4, it is characterised in that monitoring time mould between described tower Type particularly as follows:

$T_{i,j}=R(i,j)\·\sqrt{{(X_j-X_i)}^2+{(Y_j-Y_i)}^2}$

Wherein, (i j) represents the path difficulty coefficient between shaft tower i to shaft tower j to R；X (i), X (j) represent the horizontal seat of shaft tower i, j Mark, Y (i), Y (j) represent the vertical coordinate of shaft tower i, j.

6. according to the power transmission line polling path planing method described in claim 4 or 5, it is characterised in that described comprehensively patrol and examine mould Type particularly as follows:

$F_{ij}=\mathrm{\α}\·R(i,j)\·\underset{i=1}{\overset{D-1}{\Σ}}{T}_{i,j}+\mathrm{\β}\·\underset{i=1}{\overset{D-1}{\Σ}}{P}_j/P_i$

Wherein, F_ijFor object function, D is shaft tower number to be inspected, P_i、P_jBeing the risk probability of shaft tower i and j respectively, α and β is for adding Weight coefficient, (i j) represents the path difficulty coefficient between shaft tower i to shaft tower j, T to R_i,jFor monitoring time model between tower.

7. a power transmission line polling path planning system, it is characterised in that including:

Initialization module, is used for initializing predefined parameter information；Wherein, described predefined parameter information includes shaft tower parameter, shaft tower Risk runs path difficulty coefficient and predetermined intelligent algorithm parameter between factor initial data, shaft tower；

Shaft tower risk service condition probabilistic module, carries out pretreatment, root for described shaft tower risk is run factor initial data Data after Data preprocess, set up Bayesian network model and calculate the shaft tower risk operation bar of corresponding shaft tower risk operation factor Part probability；

Monitoring time model module between tower, for according to path difficulty coefficient between described shaft tower parameter and described shaft tower, sets up tower Between monitoring time model；

Comprehensively patrol and examine model module, be used for according to monitoring time model between described shaft tower risk service condition probability and described tower, Set up and comprehensively patrol and examine model；

Optimum polling path module, for according to predetermined intelligent algorithm parameter, utilizes predetermined intelligent algorithm to carry out aggregative model Solving, when satisfied termination iterated conditional, output is optimum polling path after optimizing.

Power transmission line polling path planning system the most according to claim 7, it is characterised in that described shaft tower risk runs bar Part probabilistic module, including:

Conditional probability unit, is used for utilizing described Bayesian network model, is calculated in the initial decision table after described quantization Each shaft tower risk runs the conditional probability of factor；

Shaft tower risk service condition probability unit, for according to described conditional probability and described Bayesian network model, by generally Rate is calculated corresponding shaft tower risk and runs the shaft tower risk service condition probability of factor；Wherein,

Shaft tower risk runs the shaft tower excessive risk service condition probability of factor:

$Pf=P\left(B_1\right|A)=\frac{P\left(B_1\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)}{P\left(B_1\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)+P\left(B_2\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)}$

Shaft tower risk runs the shaft tower low-risk service condition probability of factor:

$Pn=P\left(B_2\right|A)=\frac{P\left(B_2\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)}{P\left(B_1\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)+P\left(B_2\right)\underset{i=1}{\overset{9}{\Π}}P\left(C_i\right|B_1)}$

Wherein, pole tower operation state variable B={B₁、B₂}={ excessive risk is run, low-risk is run } represent, shaft tower risk is transported Row factor { C₁C₂C₃.....C₉Represent, P (B₁) and P (B₂) represent that the history excessive risk of shaft tower is run and the low wind of history respectively Probability is run in danger；P(C_i|B₁) represent that shaft tower excessive risk under conditions of different shaft tower risk operation factors runs probability.

Power transmission line polling path planning system the most according to claim 8, it is characterised in that monitoring time mould between described tower Pattern block is particularly as follows: according to path difficulty coefficient between described shaft tower parameter and described shaft tower, set up monitoring time model between tower

Wherein, (i j) represents the path difficulty coefficient between shaft tower i to shaft tower j to R；X (i), X (j) represent the horizontal seat of shaft tower i, j Mark, Y (i), Y (j) represent the vertical coordinate of shaft tower i, j.

Power transmission line polling path planning system the most according to claim 8 or claim 9, it is characterised in that described comprehensively patrol and examine mould Pattern block is particularly as follows: according to monitoring time model between described shaft tower risk service condition probability and described tower, set up and comprehensively patrol and examine Model

Wherein, wherein, F_ijFor object function, D is shaft tower number to be inspected, P_i、P_jThe risk probability of shaft tower i and j respectively, α and β is weight coefficient, and (i j) represents the path difficulty coefficient between shaft tower i to shaft tower j, T to R_i,jFor monitoring time model between tower.