1. The high-voltage transmission line state evaluation method based on the association rule Bayesian network is characterized by comprising the following steps of:

s1, constructing a circuit basic state evaluation parameter system;

s2, establishing a key state parameter evaluation model of the power transmission line, and constructing a line evaluation key parameter system;

s3, establishing a Bayesian network-based line state evaluation graph model and a mathematical model;

s4, learning a Bayesian network algorithm model of the power transmission line;

and S5, evaluating the state of the power transmission line.

2. The high-voltage transmission line state evaluation method based on the association rule Bayesian network as recited in claim 1, wherein: in S1, 84 basic state parameters that actually reflect the operation state of the line are screened out by the big data, and 8 component states of "foundation", "tower", "fitting", "insulator", "ground wire", "grounding device", "accessory facility" and "channel environment" are respectively reflected.

3. The high-voltage transmission line state evaluation method based on the association rule Bayesian network as recited in claim 1, wherein: in S2, first:

establishing a transaction database of the deterioration of the transmission line components: i ═ fault in the transmission line };

item set X for deterioration of state parameter of component_i,jThe j state parameter in the ith component is deteriorated;

item set of component deterioration Y_iFailure of the ith component.

Secondly, a base state quantity X is calculated_ij→Y_iThe degree of support of (c). The formula of the support degree is shown as the following formula:

finally, the basic state quantity X is calculated_i,j→Y_iThe confidence of (c). The confidence formula is shown in the following formula (2):

wherein: y in the formulae (1) and (2)_iRepresentative member, X_i,jRepresents a state variable, f (X)_i,j∪Y_i) Is a component Y_iAnd a state parameter X_i,jThe number of simultaneous degradations. f (X)_i,j) Is the number of degradations occurring in the overall transaction database I. i is (1, L,8) and j is X_i,jThe total number of basic state parameter variables of the corresponding component.

4. The high-voltage transmission line state evaluation method based on the association rule Bayesian network as recited in claim 1, wherein: in S3, a power transmission line evaluation graph model is first established, and a primary node is set to be Z ═ power transmission line variable }; the secondary nodes are 8 component variable sets Y, and Y is { Y ═ Y }₁,Y₂,Y₃,Y₄,Y₅,Y₆,Y₇,Y₈The methods are respectively as follows: y is₁Base, Y₂Tower, Y₃Hardware, Y₄1 { insulator }, Y₅Ground wire, Y₅Ground, Y₇Attached facility, Y₈Channel environment; the three-level node is a state parameter variable X_ijAnd the total number of the variables is 37, and the variables are respectively parent nodes corresponding to 8 components, and then a mathematical evaluation model is established according to the graph model.

5. The high-voltage transmission line state evaluation method based on the association rule Bayesian network as recited in claim 4, wherein: the mathematical evaluation model is as follows:

(1) establishing a power transmission line state parameter evaluation model: by x_kFour operating states "normal", "caution", "severe", "abnormal" representing state variables {1,2,3,4 };

(2) establishing a variable state evaluation model of the transmission line component: by y_kThe four operating states of the component, "normal", "caution", "severe", "abnormal", are represented by {1,2,3,4}, and the calculation model is as follows:

wherein: i is (1,2, L,8) and j is X_ijThe total number of state parameter variables of the corresponding component, j ═ 1,2, L, j)

(3) Establishing a power transmission line state evaluation model: according to the operating state (y) of 8 components of the line_k1,2,3,4), deducing the running state of the line, and using z to calculate_kThe four operation states of the power transmission line are expressed by {1,2,3,4}, and the calculation model is as follows:

wherein: i is (1,2, L,8) and j is X_ijAnd j is equal to (1,2, L, j) of the state parameter variable total number of the corresponding part.

6. The high-voltage transmission line state evaluation method based on the association rule Bayesian network as recited in claim 1, wherein: in S4, in order to prevent the situation of data loss and inaccurate evaluation result, the MLE and EM algorithms are combined to learn the bayesian parameters, so that the calculated conditional probability is more accurate and more practical, that is, the prior probability P (Y) is calculated according to the training samples_i＝y_k)、P(Z＝z_k) And conditional probability P (X)_ij＝x_k|Y_i＝y_k)、P(Y_i＝y_k|Z＝z_k) The learning model is as follows:

(1) prior probability P (Y)_i＝y_k) The calculation of (2): probability of component variable P (Y)_i＝y_k)

Wherein: i is (1,2, L,8) and j is X_ijAnd j is equal to (1,2, L, j) of the state parameter variable total number of the corresponding part.

7. The high-voltage transmission line state evaluation method based on the association rule Bayesian network as recited in claim 6, wherein: the detailed calculation is as follows: the training sample counts the running data of a certain line at n moments, and Y is set_iThe number of normal, attention, abnormal and serious at the statistical moment is a_t,b_t,c_t,d_tTotal number of samples is s_t＝a_t+b_t+c_t+d_tAnd t is (1, L, n), the state probability calculation model of the state parameter variable is:

probability of normal state:

note the probability of the state:

probability of severe state:

probability of abnormal state:

the component variable P (Y) can be calculated by the above calculation method_i＝y_k) Prior probability of (d):

(2) prior probability P (Z ═ Z)_k) The calculation of (2): calculating the probability P (Z) of the line in four operation states_k)

(3)P(X_ij＝x_k|Y_i＝y_k) Conditional probability of (2):

according to Bayes' theorem, the state parameter X_ijHas a conditional probability of P (X)_ij＝x_k|Y_i＝y_k) I.e. in part Y_iOn the premise of occurrence, corresponding state parameter X_ijThe probability of occurrence;

(4)P(Y_i＝y_k|Z＝z_k) Conditional probability of (2):

from Bayes' theorem, the conditional probability of a part is P (Y)_i| Z), i.e. solving for component Y on the premise that transmission line Z occurs_iThe probability of occurrence;

8. the high-voltage transmission line state evaluation method based on the association rule Bayesian network as recited in claim 5, wherein: in S5, the specific implementation method of the power transmission line state may be briefly summarized as 5 steps:

(1) judging the state of the state parameter: respectively judging X according to the data of the power transmission line to be evaluated and the evaluation standard of the state parameter_1,j＝{X₁₁,X₁₂,X₁₃,X₁₄,X₁₅,X₁₆State attributes of the 6 states;

(2) solving the prior probability P (Y)_i＝y_k): separately obtain P (Y)₁＝1),P(Y₁＝2),P(Y₁＝3),P(Y₁4), probability of the current event;

(3) solving for conditional probability P (X)_ij＝x_k|Y_i＝y_k)；

(4) Solving the posterior probability: according to the formulaRespectively solving new samples Y₁＝y_k(1,2,3,4), and then comparing the probability sizes in the four states according to a formula (3);

(5) similarly, the operation states of the remaining 7 components are deduced in the same way, and then the state of the line is evaluated according to the line evaluation mathematical model formula (4).

9. The high-voltage transmission line state evaluation method based on the association rule bayesian network according to claim 8, characterized in that: and (4) in which operation state the probability is the maximum, the component is in which state.

10. The high-voltage transmission line state evaluation method based on the association rule bayesian network according to claim 8, characterized in that: and in the step (5), the state of the line is evaluated according to a line evaluation mathematical model formula (4), and the state of the line is calculated.

Background

The transmission line is a key part of a power system, is a 'life line' for transmitting electric energy, the safe and stable operation of the whole power grid is influenced by the operating state of the transmission line, and the transmission line is easily influenced by the environment and the terrain. In order to grasp the running condition of the line in time, the line must be maintained in a state. The premise of state maintenance is that the running state of the line is evaluated, the running state of the line is grasped, and then a reasonable and effective maintenance scheme is formulated. However, the number of the power transmission line state evaluation parameters is large and complex, and with the development of the smart grid, the state data of the line also increases explosively, and if a large amount of state data is evaluated, the accuracy and the evaluation efficiency of the evaluation result are affected.

And the transmission line often faces huge challenge in the operation process, it needs to pass through high and cold hills, highways and various complex geographical environments, and is in open field for a long time, the operation environment is complicated, and in addition, many elements of the transmission line can not only be damaged by mechanical external force and electric load, but also be influenced by natural factors such as ice, snow, thunder and lightning, and the operation state of the transmission line is easy to be influenced.

Disclosure of Invention

The invention aims to provide a high-voltage transmission line state evaluation method based on an association rule Bayesian network, so as to solve the problems in the prior art in the background technology.

The high-voltage transmission line state evaluation method based on the association rule Bayesian network comprises the following steps:

s1, constructing a circuit basic state evaluation parameter system;

s2, establishing a key state parameter evaluation model of the power transmission line, and constructing a line evaluation key parameter system;

s3, establishing a Bayesian network-based line state evaluation graph model and a mathematical model;

s4, learning a Bayesian network algorithm model of the power transmission line;

and S5, evaluating the state of the power transmission line.

Preferably, in S1, 84 basic state parameters that actually reflect the operation state of the line are screened out through the big data, and 8 component states of "foundation", "tower", "fitting", "insulator", "ground wire", "grounding device", "accessory facility", and "channel environment" are respectively reflected.

Preferably, in S2, first:

establishing a transaction database of the deterioration of the transmission line components: i ═ fault in the transmission line };

item set X for deterioration of state parameter of component_i,jThe j state parameter in the ith component is deteriorated;

item set of component deterioration Y_iFailure of the ith component;

secondly, a base state quantity X is calculated_i,j→Y_iThe support degree of (A) is represented by the following formulaShown in the figure:

finally, the basic state quantity X is calculated_i,j→Y_iThe confidence coefficient formula is shown in the following formula (2):

wherein: y in the formulae (1) and (2)_iRepresentative member, X_i,jRepresents a state variable, f (X)_i,j∪Y_i) Is a component Y_iAnd a state parameter X_i,jNumber of simultaneous deteriorations, f (X)_i,j) To determine the number of degradations in the transaction database I, I is (1, L,8) and j is X_i,jThe total number of basic state parameter variables of the corresponding component.

Preferably, in S3, a power transmission line evaluation graph model is first established, and a primary node is set to be Z ═ transmission line variable }; the secondary nodes are 8 component variable sets Y, and Y is { Y ═ Y }₁,Y₂,Y₃,Y₄,Y₅,Y₆,Y₇,Y₈The methods are respectively as follows: y is₁Base, Y₂Tower, Y₃Hardware, Y₄1 { insulator }, Y₅Ground wire, Y₅Ground, Y₇Attached facility, Y₈Channel environment; the three-level node is a state parameter variable X_ij37 variables are respectively negative nodes corresponding to 8 components;

and then establishing a mathematical evaluation model according to the graph model.

Preferably, the mathematical evaluation model is as follows:

(1) establishing a power transmission line state parameter evaluation model: by x_kFour operating states "normal", "caution", "severe", "abnormal" representing state variables {1,2,3,4 };

(2) establishing a transmission lineComponent variable state evaluation model: by y_kThe four operating states of the component, "normal", "caution", "severe", "abnormal", are represented by {1,2,3,4}, and the calculation model is as follows:

wherein: i is (1,2, L,8) and j is X_ijThe total number of state parameter variables of the corresponding component, j ═ 1,2, L, j)

(3) Establishing a power transmission line state evaluation model: according to the operating state (y) of 8 components of the line_k1,2,3,4), deducing the running state of the line, and using z to calculate_kThe four operation states of the power transmission line are expressed by {1,2,3,4}, and the calculation model is as follows:

wherein: i is (1,2, L,8) and j is X_ijAnd j is equal to (1,2, L, j) of the state parameter variable total number of the corresponding part.

Preferably, in S4, in order to prevent the situation of data missing and inaccurate estimation result, the MLE and EM algorithms are combined to learn the bayesian parameter, so that the calculated conditional probability is more accurate and more practical, that is, the prior probability P (Y) is calculated according to the training sample_i＝y_k)、P(Z＝z_k) And conditional probability P (X)_ij＝x_k|Y_i＝y_k)、P(Y_i＝y_k|Z＝z_k) The learning model is as follows:

(1) prior probability P (Y)_i＝y_k) The calculation of (2): probability of component variable P (Y)_i＝y_k)

Wherein: i is (1,2, L,8) and j is X_ijAnd j is equal to (1,2, L, j) of the state parameter variable total number of the corresponding part.

Preferably, the detailed calculation is as follows: the training sample counts the running data of a certain line at n moments, and Y is set_iThe number of normal, attention, abnormal and serious at the statistical moment is a_t,b_t,c_t,d_tTotal number of samples is s_t＝a_t+b_t+c_t+d_tAnd t is (1, L, n), the state probability calculation model of the state parameter variable is:

probability of normal state:

note the probability of the state:

probability of severe state:

probability of abnormal state:

the component variable P (Y) can be calculated by the above calculation method_i＝y_k) Prior probability of (d):

(2) prior probability P (Z ═ Z)_k) The calculation of (2): calculating the probability P (Z) of the line in four operation states_k)

(3)P(X_ij＝x_k|Y_i＝y_k) Conditional probability of (2):

according to Bayes' theorem, the state parameter X_ijHas a conditional probability of P (X)_ij＝x_k|Y_i＝y_k) I.e. in part Y_iOn the premise of occurrence, corresponding state parameter X_ijThe probability of occurrence;

(4)P(Y_i＝y_k|Z＝z_k) Conditional probability of (2):

from Bayes' theorem, the conditional probability of a part is P (Y)_iI Z), i.e. solving for component Y on the premise that transmission line Z occurs_iThe probability of occurrence;

preferably, in S5, the specific implementation method of the power transmission line state may be briefly summarized as 5 steps:

(1) judging the state of the state parameter: respectively judging X according to the data of the power transmission line to be evaluated and the evaluation standard of the state parameter_1,j＝{X₁₁,X₁₂,X₁₃,X₁₄,X₁₅,X₁₆State attributes of the 6 states;

(2) solving the prior probability P (Y)_i＝y_k): separately obtain P (Y)₁＝1),P(Y₁＝2),P(Y₁＝3),P(Y₁4), probability of failure;

(3) solving for conditional probability P (X)_ij＝x_k|Y_i＝y_k)；

(4) Solving the posterior probability: according to the formulaRespectively solving new samples Y₁＝y_k(1,2,3,4), and then comparing the probability sizes in the four states according to a formula (3);

(5) similarly, the operation states of the remaining 7 components were inferred in the same manner.

Preferably, in the step (4), the component is in which state in which the probability is the highest in which operating state.

Preferably, in the step (5), the state of the line is evaluated according to a line evaluation mathematical model formula (4), and the state of the line is calculated.

The invention has the beneficial effects that: the method analyzes the main fault types and the influence conditions of the power transmission line in the operation process, and selects 8 components and 84 index state parameters capable of reflecting the operation state of the power transmission line by combining the evaluation guide rule and the actual operation experience of the line to form a basic state evaluation parameter system; quantifying the basic parameters by utilizing the support degree and the confidence degree of the association rule method, and selecting the index parameters which can most accurately reflect the line state to form a key parameter system;

according to the power transmission line state evaluation key parameter system table, a Bayesian network-based line state evaluation graph model and a mathematical model are constructed, empirical data are used for parameter learning of the model, and the operation state of a line is deduced according to a Bayesian classification algorithm.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:

FIG. 1 is a schematic diagram of the method of the present invention;

FIG. 2 is a flow chart of the extraction of key state quantities of the power transmission line according to the present invention;

FIG. 3 is a diagram of a Bayesian network for power transmission line operating condition evaluation according to the present invention;

FIG. 4 is a flow chart of a transmission line evaluation algorithm of the present invention;

FIG. 5 is a table of transmission line base state parameters of the present invention;

fig. 6 is a key parameter system table of the power transmission line of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more clear, the technical solutions of the present application will be clearly and completely described below with reference to the specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The technical solutions provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings.

Referring to fig. 1 to 6, the method for evaluating the state of the high voltage transmission line based on the association rule bayesian network includes the following steps:

s1, constructing a circuit basic state evaluation parameter system;

s2, establishing a key state parameter evaluation model of the power transmission line, and constructing a line evaluation key parameter system;

s3, establishing a Bayesian network-based line state evaluation graph model and a mathematical model;

s4, learning a Bayesian network algorithm model of the power transmission line;

and S5, evaluating the state of the power transmission line.

In the step S1, 84 basic state parameters that actually reflect the operation state of the line are screened out by the big data, 8 component states of "foundation", "tower", "fitting", "insulator", "ground wire", "grounding device", "accessory facility" and "channel environment" are respectively reflected, and X is used to select the basic state parameters_iThe basic state quantity is shown in detail in fig. 5.

As shown in fig. 2, in the S2, first:

establishing a transaction database of the deterioration of the transmission line components: i ═ fault in the transmission line };

item set X for deterioration of state parameter of component_i,jThe j state parameter in the ith component is deteriorated;

item set of component deterioration Y_iFailure of the ith component;

secondly, a base state quantity X is calculated_i,j→Y_iThe formula of the support degree is shown as the following formula:

finally, the basic state quantity X is calculated_i,j→Y_iThe confidence coefficient formula is shown in the following formula (2):

wherein: y in the formulae (1) and (2)_iRepresentative member, X_i,jRepresents a state variable, f (X)_i,j∪Y_i) Is a component Y_iAnd a state parameter X_i,jNumber of simultaneous deteriorations, f (X)_i,j) To determine the number of degradations in the transaction database I, I is (1, L,8) and j is X_i,jThe total number of basic state parameter variables of the corresponding component. Wherein the support sup (X) of the current state quantity_i,j→Y_i)>0.7, it is defined as a frequent item set, otherwise, it is an infrequent item set, if it is determined that a certain state quantity is already a frequent item set, its confidence is continuously calculated, if con (X)_i,j→Y_i)<0.5, the state quantity cannot be used as a key parameter for evaluating the fault component, otherwise, a frequent item set is output; support of a certain state quantity sup (X)_i,j→Y_i)<0.7, the confidence calculation is not performed, and the result is directly output to be 0.

And selecting the frequent item sets with the association rule value larger than 0.7 and the confidence value larger than 0.5 as a key parameter system according to the judgment conditions of the frequent item sets of the association rules. Therefore, 37 state quantities can be selected from 84 basic states to serve as key indexes for evaluating the power transmission line, a key index system is formed, and the key state quantities corresponding to 8 components one to one are shown in an attached table 2.

In S3, a power transmission line evaluation graph model is first established, and a primary node is set to be Z ═ power transmission line variable }; the secondary node being a componentThe variable set Y is 8 in total, and Y is { Y ═ Y₁,Y₂,Y₃,Y₄,Y₅,Y₆,Y₇,Y₈The methods are respectively as follows: y is₁Base, Y₂Tower, Y₃Hardware, Y₄1 { insulator }, Y₅Ground wire, Y₅Ground, Y₇Attached facility, Y₈Channel environment; the three-level node is a state parameter variable X_ij37 variables are respectively negative nodes corresponding to 8 components;

then, a mathematical evaluation model is established according to the graph model, wherein the mathematical evaluation model is as follows:

(1) establishing a power transmission line state parameter evaluation model: by x_kFour operating states "normal", "caution", "severe", "abnormal" representing state variables {1,2,3,4 };

(2) establishing a variable state evaluation model of the transmission line component: by y_kThe four operating states of the component, "normal", "caution", "severe", "abnormal", are represented by {1,2,3,4}, and the calculation model is as follows:

wherein: i is (1,2, L,8) and j is X_ijThe total number of state parameter variables of the corresponding component, j ═ 1,2, L, j)

(3) Establishing a power transmission line state evaluation model: according to the operating state (y) of 8 components of the line_k1,2,3,4), deducing the running state of the line, and using z to calculate_kThe four operation states of the power transmission line are expressed by {1,2,3,4}, and the calculation model is as follows:

wherein: i is (1,2, L,8) and j is X_ijAnd j is equal to (1,2, L, j) of the state parameter variable total number of the corresponding part.

The above-mentionedIn S4, in order to prevent the condition of data loss and inaccurate evaluation result, the MLE algorithm and the EM algorithm are combined to learn Bayesian parameters, so that the calculated conditional probability is more accurate and more practical, namely, the prior probability P (Y) is calculated according to the training samples_i＝y_k)、P(Z＝z_k) And conditional probability P (X)_ij＝x_k|Y_i＝y_k)、P(Y_i＝y_k|Z＝z_k) The learning model is as follows:

(1) prior probability P (Y)_i＝y_k) The calculation of (2): probability of component variable P (Y)_i＝y_k)

Wherein: i is (1,2, L,8) and j is X_ijAnd j is equal to (1,2, L, j) of the state parameter variable total number of the corresponding part.

The detailed calculation is as follows: the training sample counts the running data of a certain line at n moments, and Y is set_iThe numbers of the occurrence of normality, caution, abnormality and severity are respectively a_t,b_t,c_t,d_tTotal number of samples is s_t＝a_t+b_t+c_t+d_tAnd t is (1, L, n), the state probability calculation model of the state parameter variable is:

probability of normal state:

note the probability of the state:

probability of severe state:

probability of abnormal state:

the component variable P (Y) can be calculated by the above calculation method_i＝y_k) Prior probability of (d):

(2) prior probability P (Z ═ Z)_k) The calculation of (2): calculating the probability P (Z) of the line in four operation states_k)

(3)P(X_ij＝x_k|Y_i＝y_k) Conditional probability of (2):

according to Bayes' theorem, the state parameter X_ijHas a conditional probability of P (X)_ij＝x_k|Y_i＝y_k) I.e. in part Y_iOn the premise of occurrence, corresponding state parameter X_ijThe probability of occurrence;

(4)P(Y_i＝y_k|Z＝z_k) Conditional probability of (2):

from Bayes' theorem, the conditional probability of a part is P (Y)_iI Z), i.e. solving for component Y on the premise that transmission line Z occurs_iThe probability of occurrence;

in S5, the specific implementation method of the power transmission line state may be briefly summarized as 5 steps:

(1) judging the state of the state parameter: respectively judging X according to the data of the power transmission line to be evaluated and the evaluation standard of the state parameter_1,j＝{X₁₁,X₁₂,X₁₃,X₁₄,X₁₅,X₁₆State of 6 statesA state attribute;

(2) solving the prior probability P (Y)_i＝y_k): separately obtain P (Y)₁＝1),P(Y₁＝2),P(Y₁＝3),P(Y₁4), probability of failure;

(3) solving for conditional probability P (X)_ij＝x_k|Y_i＝y_k)；

(4) Solving the posterior probability: according to the formulaRespectively solving new samples Y₁＝y_k(1,2,3 and 4), and then comparing the probability in the four states according to a formula (3), wherein the probability in which operation state is the highest, and the component is in which state;

(5) similarly, the operating states of the remaining 7 components are deduced in the same way, and the state of the line is evaluated according to a line evaluation mathematical model formula (4) to calculate the state of the line.

In conclusion; firstly, extracting key state evaluation parameters of the power transmission line through an association rule algorithm; the line is then evaluated in conjunction with a bayesian network algorithm. The Bayesian network algorithm has the advantages that the causal relationship among random variables is visually expressed in a graph mode, the probability theory and the graph theory are closely combined, and the method is suitable for describing the complex relationship among events and the uncertain relationship among conditions in a complex system. The method is a visualization method and a visualization tool which can be used for analyzing and resolving the uncertainty problem, so that a Bayesian network algorithm is selected to evaluate the running state of the power transmission line.

The invention solves the defects of the existing line evaluation technology, provides the power transmission line running state evaluation method based on the association rule method and the Bayesian network, researches and solves the problems of large and complex number of power transmission line state evaluation parameters, low evaluation accuracy and low evaluation efficiency, improves the evaluation accuracy and evaluation efficiency of the power transmission line, is beneficial to quickly knowing the running state of the line, can more quickly identify the defect part, is convenient for operation and inspection personnel to overhaul and maintain, effectively shortens the overhaul time and improves the running stability of the power grid.

The method mainly aims at evaluating and analyzing the running condition of the power transmission line, and evaluates 8 important parts of a foundation, a tower, a hardware, an insulator, a conducting ground wire, a grounding device, an accessory facility and a channel environment of the power transmission line through detection, monitoring and other data. Firstly, combining the evaluation guide rule and the actual operation experience of the line, quantizing basic parameters by utilizing the support degree and the confidence degree of an association rule method, and excavating index parameters capable of reflecting the state of the operation state of the power transmission line from huge data to form a key parameter system; and then, according to a key parameter system table for power transmission line state evaluation, a Bayesian network-based line state evaluation graph model and a mathematical model are constructed, empirical data are utilized to carry out parameter learning on the model, and the running state of the line is deduced according to a Bayesian classification algorithm.

The method can master the running condition of the power transmission line in advance according to the evaluation result, and make efficient and economic overhaul plans and maintenance measures in advance to avoid the occurrence of fault conditions. Therefore, the running state of the power transmission line can be accurately known, the service life of the power transmission line can be prolonged by an effective means, the economic loss is reduced, and the safe and stable running of the power transmission line and the whole power grid is ensured.

The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.