A method and apparatus for evaluating the equipment of a power transmission line.

Abstract

The present application provides a method and device for judging equipment of a power transmission line. The power transmission line is in a preset environment. Since in the optimized artificial fish school algorithm, the moving step and visible distance of the artificial fish will decrease with the increase of the number of iterations, in the early stage of the algorithm, since the larger moving step and visible distance are conducive to accelerating the clustering behavior and tail-chasing behavior of the artificial fish school, the artificial fish school can be accelerated to converge to the local optimal position and the global optimal position; and in the later stage of the algorithm, since the smaller moving step and visible distance are conducive to the artificial fish near the extreme value to accurately find the position of the adjacent extreme value, the artificial fish school can be accelerated to find the global optimal position; therefore, the state of the power transmission line closest to the fault or when the fault occurs can be quickly obtained, so that the equipment fault of the power transmission line can be quickly diagnosed, and then the equipment judgment method can more quickly realize the prediction of the equipment fault of the power transmission line in a certain environment.

Description

Technical Field

[0001] The present invention relates to the technical field of power transmission, and in particular to a method and device for evaluating equipment of a power transmission line. Background Art

[0002] With the rapid development of my country's economy, the demand for electric energy is constantly increasing, so the reliability requirements for the power transmission network are also gradually increasing. In the power transmission network, since the transmission line is a key part, the safe operation of the transmission line is extremely important to the reliability of the transmission network.

[0003] Since transmission lines are in complex and harsh environments for a long time, such as lightning, strong winds, heavy rain, high temperature and other environments, transmission lines have become the weakest link in the transmission network. Therefore, it is necessary to scientifically and accurately judge the equipment status of the transmission lines in a certain environment in order to predict equipment failures of the transmission lines.

[0004] At present, the commonly used methods for judging the status of transmission line equipment include artificial intelligence technical methods such as Bayesian networks, Markov chains, evidence theory, and fuzzy theory; although these methods for judging the status of transmission line equipment based on intelligent optimization algorithms can overcome problems such as fault diagnosis with incomplete information and greatly improve the accuracy of equipment fault diagnosis, this type of optimization algorithm causes the judgment method of the status of transmission line equipment to be time-consuming and have low prediction accuracy for equipment faults.

[0005] Therefore, how to more quickly predict equipment failures of transmission lines in a certain environment is a technical problem that needs to be solved urgently. Summary of the invention

[0006] In view of this, the present invention provides a method and a device for determining equipment of a power transmission line, so as to more quickly predict equipment failures of the power transmission line under a certain environment.

[0007] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0008] On one hand, the present application provides a method for determining equipment of a power transmission line, wherein the power transmission line is in a preset environment; the method for determining equipment of the power transmission line comprises:

[0009] detecting the state of the power transmission line at different times;

[0010] Optimization is performed using the optimized artificial fish swarm algorithm and the detection results; in the artificial fish swarm algorithm, the moving step length and the visible distance of the artificial fish decrease as the number of iterations increases;

[0011] The optimization result is used to diagnose equipment faults of the transmission line.

[0012] Optionally, the functional relationship between the moving step length and the number of iterations, and the functional relationship between the visible distance and the number of iterations are respectively:

[0013]

[0014]

[0015] Among them, step is the moving step length, Max_S is the maximum moving step length of the artificial fish, Min_S is the minimum moving step length of the artificial fish; visual is the visible distance, Max_V is the maximum visible distance of the artificial fish, Min_V is the minimum visible distance of the artificial fish; Max_gen is the maximum number of iterations; Iter is the current number of iterations of the artificial fish.

[0016] Optionally, the artificial fish swarm algorithm comprises:

[0017] Evaluate the status of all the artificial fish and record the status of the artificial fish that best meets the user's set requirements;

[0018] Set the number of iterations to 1 and start iteration;

[0019] Determining each of the moving steps and each of the visible distances according to the number of iterations;

[0020] Each of the artificial fish updates its own state by performing foraging, grouping and tail-chasing behaviors;

[0021] Comparing the states of the artificial fish with the recorded states of the artificial fish, and recording the state of the artificial fish that better meets the user's set requirements;

[0022] Determine whether the iteration stop condition is met;

[0023] If the iteration stop condition is met, the recorded state of the artificial fish is output;

[0024] If the iteration stop condition is not met, the number of iterations is increased by 1 and the process returns to the step of determining each moving step length and each visible distance according to the number of iterations.

[0025] Optionally, the iteration stop condition includes:

[0026] The recorded state of the artificial fish meets the user's setting requirements; or,

[0027] The number of iterations reaches a preset number.

[0028] Optionally, after detecting the state of the transmission line, the method further includes:

[0029] The principal component analysis method is used to simplify the components of each of the detection results.

[0030] Optionally, after simplifying the components of each of the test results, the method further includes:

[0031] A population initialization model based on space transformation is used to perform data screening on each of the detection results.

[0032] Optionally, the population initialization model is an STS-R model.

[0033] On the other hand, the present application provides a device for determining equipment of a power transmission line, wherein the power transmission line is in a preset environment; the device for determining equipment of the power transmission line comprises: a detection module, an optimization module and a diagnosis module connected in sequence; wherein:

[0034] The detection module is used to detect the state of the power transmission line at different times;

[0035] The optimization module is used to perform optimization using the optimized artificial fish swarm algorithm and each of the detection results; in the artificial fish swarm algorithm, the moving step length and the visible distance of the artificial fish decrease as the number of iterations increases;

[0036] The diagnosis module is used to perform equipment fault diagnosis on the power transmission line using the optimization result.

[0037] Optionally, it also includes: a component simplification module; wherein:

[0038] The component reduction module is arranged between the detection module and the optimization module;

[0039] The component simplification module is used to simplify the components of each of the detection results using the principal component analysis method.

[0040] Optionally, it also includes: a data screening module: wherein:

[0041] The data screening module is arranged between the component reduction module and the optimization module;

[0042] The data screening module is used to perform data screening on each of the detection results using a population initialization model based on space transformation.

[0043] It can be seen from the above technical solution that the present invention provides a method for judging equipment of a power transmission line, and the power transmission line is in a preset environment. Since in the optimized artificial fish school algorithm, the moving step length and the visible distance of the artificial fish will decrease with the increase of the number of iterations, the moving step length and the visible distance of the artificial fish are larger in the early stage of the algorithm, and smaller in the later stage of the algorithm. In the early stage of the algorithm, since a larger moving step size and visible distance are conducive to accelerating the clustering and tail-chasing behavior of the artificial fish school, the convergence of the artificial fish school to the local optimal position and the global optimal position can be accelerated; and in the later stage of the algorithm, since a smaller moving step size and visible distance are conducive to accelerating the foraging behavior of the artificial fish school, that is, it is conducive to the artificial fish near the extreme value to accurately find the position of the adjacent extreme value, it can accelerate the artificial fish school to find the global optimal position; therefore, by using the optimized artificial fish school algorithm to search for the best among the various detection results of the transmission line, the state of the transmission line closest to the fault or when a fault occurs can be quickly obtained, so that the equipment fault of the transmission line can be quickly diagnosed, that is, the prediction of the equipment fault of the transmission line in a preset environment can be realized, and then the equipment analysis method of the transmission line provided in the present application can more quickly realize the prediction of the equipment failure of the transmission line in a certain environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0045] Figure 1 A schematic diagram of a flow chart of a method for analyzing and determining equipment of a power transmission line provided in an embodiment of the present application;

[0046] Figure 2 The optimized artificial fish swarm algorithm provided in the embodiment of the present application;

[0047] Figure 3 and Figure 4 Schematic diagrams of two implementation methods of the equipment analysis method of the power transmission line provided in the embodiments of the present application;

[0048] Figure 5-Figure 7 The following are structural schematic diagrams of three implementation modes of the equipment analysis and judgment device for the power transmission line provided in the embodiments of the present application. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] In this application, the terms "comprises", "comprising" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element.

[0051] In order to more quickly predict equipment failures of a power transmission line in a certain environment, an embodiment of the present application provides a method for analyzing equipment of a power transmission line, and the power transmission line is in a preset environment.

[0052] Among them, the preset environment is the environment in which the equipment failure of the transmission line needs to be predicted. It is not specifically limited here and can be determined according to the specific situation, all of which are within the protection scope of this application.

[0053] The specific process of the equipment evaluation method for the transmission line is as follows: Figure 1 As shown, it specifically includes the following steps:

[0054] S110, detecting the status of the power transmission line at different times.

[0055] Among them, different moments can be selected randomly, continuously, or even according to a certain rule. In real-time applications, including but not limited to this, no specific limitation is made here, depending on the specific circumstances, and all are within the scope of protection of this application.

[0056] In addition, status detection is the detection of the current operating status of the transmission line. The detection results may include the current and voltage of each section in the transmission line. In practical applications, this includes but is not limited to this. No specific limitation is made here and it may depend on the specific situation. All of them are within the scope of protection of this application.

[0057] S120, using the optimized artificial fish swarm algorithm and each detection result to perform optimization.

[0058] Generally, the optimization is to find the artificial fish that best meets the set requirements, that is, the optimal solution; in step S120, the optimization is specifically to find the state of the power transmission line that is closest to the fault or when the fault occurs.

[0059] In addition, in the optimized artificial fish swarm algorithm, the moving step size and visible distance of the artificial fish decrease with the increase of the number of iterations; it can be deduced that: in the optimized artificial fish swarm algorithm, the moving step size and visible distance of the artificial fish are larger in the early stage of the algorithm and smaller in the later stage of the algorithm.

[0060] Since a larger moving step size and visible distance are conducive to accelerating the clustering and tail-chasing behaviors of the artificial fish school, the artificial fish school can be accelerated to converge to the local optimal position and the global optimal position in the early stage of the algorithm; since a smaller moving step size and visible distance are conducive to accelerating the foraging behavior of the artificial fish school, that is, it is conducive to the artificial fish near the extreme value to accurately find the position of the adjacent extreme value, the artificial fish school can be accelerated to find the global optimal position in the later stage of the algorithm. Therefore, step S120 improves the optimization speed in each detection result.

[0061] It should be noted that the moving step length and visible distance of the artificial fish are the same as the concepts in the artificial fish school algorithm in the prior art, and will not be explained here; in addition, except for slight differences in the values ​​of the moving step length and visible distance of the artificial fish, the optimized artificial fish school algorithm is basically the same as the artificial fish school algorithm in the prior art. The detailed steps of the optimized artificial fish school algorithm will be specifically described below, which will not be repeated here. Please refer to the following description.

[0062] S130. Perform equipment fault diagnosis on the transmission line using the optimization result.

[0063] From the above-mentioned concept of optimization, it can be known that the optimization result is the state of the transmission line closest to the fault or when the fault occurs. Therefore, the essence of step S130 is: according to the state of the transmission line closest to the fault or when the fault occurs, diagnose the cause of the fault of the transmission line, for example, a certain section of the line is broken, and then realize the prediction of the equipment failure of the transmission line under the preset environment.

[0064] To sum up, by using the optimized artificial fish swarm algorithm and the various detection results of the transmission line to perform optimization, the state of the transmission line closest to the fault or when the fault occurs can be quickly obtained, so that the equipment fault of the transmission line can be quickly diagnosed, that is, the equipment failure of the transmission line in a preset environment can be predicted. Furthermore, the equipment analysis method for the transmission line provided in the present application can more quickly realize the prediction of the equipment failure of the transmission line in a certain environment, thereby making the equipment failure diagnosis process of the transmission line in a certain environment simpler.

[0065] Another embodiment of the present application provides a functional relationship in which the moving step length of the artificial fish decreases as the number of algorithm iterations increases. The functional relationship can be expressed by the following functional expression:

[0066]

[0067] Among them, step is the moving step of the artificial fish, Max_S is the maximum moving step of the artificial fish, Min_S is the minimum moving step of the artificial fish, Max_gen is the maximum number of iterations, and Iter is the current number of iterations of the artificial fish.

[0068] It should be noted that Max_S and Min_S are pre-set during the initialization of the artificial fish to avoid the infinite reduction of the visual distance of the artificial fish.

[0069] The above is only a functional relationship in which the moving step length of the artificial fish decreases as the number of algorithm iterations increases. In practical applications, including but not limited to this, no specific limitation is made here and it can be determined according to the specific circumstances, all of which are within the scope of protection of this application.

[0070] This embodiment also provides a functional relationship that the visual distance of the artificial fish decreases as the number of algorithm iterations increases. The functional relationship can be expressed by the following functional expression:

[0071]

[0072] Among them, visual is the visual distance of the artificial fish, Max_V is the maximum visual distance of the artificial fish, Min_V is the minimum visual distance of the artificial fish, Max_gen is the maximum number of iterations, and Iter is the current number of iterations of the artificial fish.

[0073] It should be noted that the visual distance and moving step length of the artificial fish decay in the form of a power function.

[0074] And it decays faster at the beginning of the iteration, so the values ​​of Max_V and Min_V can be appropriately increased to enhance the foraging ability of the artificial fish.

[0075] It should be noted that Max_V and Min_V are pre-set during the initialization of the artificial fish to avoid the infinite reduction of the visual distance of the artificial fish.

[0076] The above is only a functional relationship in which the visual distance of the artificial fish decreases as the number of algorithm iterations increases. In practical applications, including but not limited to this, no specific limitation is made here and it can be determined according to the specific circumstances, all of which are within the scope of protection of this application.

[0077] The following is a brief introduction to the optimized artificial fish swarm algorithm, as described below:

[0078] In the optimized artificial fish swarm algorithm, a group of artificial fish are randomly generated as the initial parameter value of the algorithm. Assume that the state of the artificial fish is represented by X = (X1, X2, ..., X n ), the food concentration at the current location of the artificial fish is represented by the objective function F(X), and the distance between different artificial fish is represented by D ij =|X i -X j | is used to represent the visual distance of the artificial fish, that is, the visual distance is represented by visual, the moving step of the artificial fish is represented by step, and the crowding factor is represented by δ.

[0079] In actual applications, artificial fish individuals will find and move toward places that meet their food needs through foraging, grouping, and chasing behaviors. The following is a detailed description of these three behaviors, as follows:

[0080] (1) Foraging behavior

[0081] It is believed that artificial fish individuals can perceive the amount of food or food concentration in the water through vision or taste, and choose the direction of action according to the perceived amount of food or food concentration. The specific process is: the artificial fish randomly selects another state Xj, that is, another position, within its own visual distance. If the objective function value of the obtained state is greater than the objective function value of the current state, that is, the food concentration of the other position is greater than the food concentration of the current position, then the artificial fish moves one step in the direction of the selected state, otherwise it reselects a new state; and after a certain number of selections, if the above conditions are still not met, it moves one step randomly.

[0082] The above process is described in mathematical language as follows:

[0083]

[0084] X next =X i +Rand()·step,F(X j )≤F(X i )

[0085] Among them, X i is the current state of the artificial fish; F(X i ) is the objective function value of the current state of the artificial fish, that is, the food concentration at the current position; X i Any state within the visual distance of the artificial fish; F(X j ) is the objective function value of any state within the visual range of the artificial fish, that is, the food concentration at any position within the visual range of the artificial fish; X nextis the next state of the artificial fish; step is the moving step of the artificial fish; rand() generates random values ​​in the interval [0,1].

[0086] (2) Group behavior

[0087] The artificial fish explores the number of partners within its visual distance and calculates the central position of the partners. Then, the food concentration at the central position of the partners is compared with the food concentration at the current position of the artificial fish, that is, the objective function value of the state at the central position of the partners is compared with the objective function value of the state of the artificial fish. If the food concentration at the central position of the partner is greater than the food concentration at the current position of the artificial fish, and the area around the central position of the partner is not very crowded, the artificial fish moves one step toward the central position of the partner, otherwise it performs foraging behavior.

[0088] In summary, artificial fish schools need to follow two rules when gathering: 1) try to move towards the center position of their companions within the visible distance; 2) avoid overcrowding.

[0089] The above process is described in mathematical language as follows:

[0090]

[0091] Among them, X i is the current state of the artificial fish; F(X i ) is the objective function value of the current state of the artificial fish, that is, the food concentration at the current position; X C is the state of the partner's center position within the visual distance of the artificial fish; F(X C ) is the objective function value of the state at the center position of the partner within the visual range of the artificial fish, that is, the food concentration at the center position of the partner within the visual range of the artificial fish; X next is the next state of the artificial fish; step is the moving step of the artificial fish; rand() generates random values ​​in the interval [0,1]; ns is the number of partners within the visual distance of the artificial fish; n is the total number of artificial fish; δ is the crowding factor.

[0092] (3) Rear-end collision

[0093] When one or more artificial fish find food, the artificial fish near them will follow, causing the artificial fish farther away to follow as well. Specifically: within the visual distance of the artificial fish, the partner with the best state objective function value is determined as the best partner, that is, the partner with the highest food concentration at its location is determined as the best partner, and the food concentration at the location of the best partner is compared with the food concentration at its own location. If the food concentration at the location of the best partner is greater than the food concentration at its own location and is not too crowded, the artificial fish moves one step toward the best partner, otherwise it performs foraging behavior.

[0094] The above process is described in mathematical language as follows:

[0095]

[0096] Among them, Xi is the current state of the artificial fish; F(Xi) is the objective function value of the current state of the artificial fish, that is, the food concentration at the current position; Xmax is the state of the optimal partner within the visual distance of the artificial fish; F(Xmax) is the objective function value of the state of the optimal partner within the visual distance of the artificial fish, that is, the food concentration at the position of the optimal partner within the visual distance of the artificial fish; Xnext is the next state of the artificial fish; step is the moving step of the artificial fish; Rand() generates random values ​​in the interval [0, 1]; ns is the number of partners within the visual distance of the artificial fish; n is the total number of artificial fish; δ is the crowding factor.

[0097] A specific implementation of the optimized artificial fish swarm algorithm is given below. The specific process is as follows: Figure 2 As shown, the following steps are included:

[0098] S210: Evaluate the status of all artificial fishes, and record the status of the artificial fish that best meets the user's set requirements.

[0099] S220, set the number of iterations to 1, and start iteration.

[0100] S230: Determine the moving step length of each artificial fish and the visual distance of each artificial fish according to the number of iterations.

[0101] S240, each artificial fish updates its own state by performing foraging behavior, grouping behavior and tail-chasing behavior.

[0102] S250: Compare the states of the artificial fish with the recorded states of the artificial fish, and record the state of the artificial fish that better meets the user's set requirements.

[0103] S260: Determine whether the iteration stop condition is met.

[0104] If the iteration stop condition is met, step S270 is executed; if the iteration stop condition is not met, step S280 is executed first, and then the process returns to execute step S230.

[0105] S270: Output the recorded state of the artificial fish.

[0106] S280: Increase the number of iterations by 1.

[0107] Optionally, the iteration stop condition may be: the recorded state of the artificial fish meets the user setting requirements, or the number of iterations reaches a preset number; in practical applications, including but not limited to this, no specific limitation is made here, it may depend on the specific circumstances, and is within the scope of protection of this application.

[0108] Among them, the preset number of times is the total number of iterations preset according to actual conditions, which is not specifically limited here and is within the protection scope of this application.

[0109] The above is only a specific implementation of the optimized artificial fish swarm algorithm. In practical applications, including but not limited to this, no specific limitation is made here and it may be determined according to the specific circumstances, all of which are within the scope of protection of this application.

[0110] Another embodiment of the present application also provides another implementation method of the device identification method of the power transmission line, and its specific process is as follows: Figure 3 As shown, the specific process is substantially the same as the specific process of the above embodiment, except that: in this embodiment, after step S110, the following steps are further included:

[0111] S310, using principal component analysis to simplify the components of each test result.

[0112] Usually, component simplification is to convert multiple components into a few components, which is equivalent to retaining low-order principal components and ignoring high-order principal components; in step S310, component simplification is specifically to convert multiple parameters in each detection result, such as current and voltage, into a few parameters.

[0113] In this embodiment, the principal component analysis method is used to simplify the components of each test result, which can avoid the influence of redundant indicators, thereby reducing the analysis time and speeding up the analysis speed.

[0114] The following is a brief introduction to the principal component analysis method, as follows:

[0115] Principal component analysis is a vector dimensionality reduction method based on linear transformation. Its core idea is to project the data onto several coordinate axes that maximize the data variance through coordinate rotation, that is, to find a new orthogonal basis, so as to obtain the representation of the data in the new space, so as to eliminate the multicollinearity of the original data and achieve the purpose of data dimensionality reduction.

[0116] Usually, the easiest way to obtain a low-dimensional subspace is to perform a linear transformation on the original high-dimensional space. Assume that the original high-dimensional space is a d-dimensional space, and its sample set X = {x1, x2, …, x m}∈R d×m , after transformation, we get n-dimensional space, whose sample set Z = U T X.

[0117] Among them, n< <d;:U∈R d×m is the transformation matrix, that is, the new orthogonal basis to be found, U is specifically an orthogonal matrix consisting of the eigenvectors corresponding to the first n items with the largest eigenvalues ​​of the covariance of X; Z∈R d×m It is the projection of the sample in the new space, which is the low-dimensional approximation of the high-dimensional X after dimensionality reduction.

[0118] The following is a brief introduction to the specific process of principal component analysis, as described below:

[0119] 1) De-mean the sample features, that is, centralize the data.

[0120] Specifically, for each feature of the sample, the value of the current feature is subtracted from the mean μ of the feature in the sample set. j , that is: the jth feature of the i-th sample is: in,

[0121] , the mean vector of all features is: μ = (μ1, μ2, ..., μ d ), μ∈R d .

[0122] 2) Calculate the sample covariance matrix Σ = XX T .

[0123] 3) For the covariance matrix Σ=XX T Perform eigenvalue decomposition and take the eigenvectors u1,u2,…,u corresponding to the largest first l eigenvalues l Constitute the transformation matrix U;

[0124] 4) Generate the sample set Z after dimensionality reduction = {-1, -2, ..., z m}, z i =U T x i , i=1,2,3...,m.

[0125] 5) Output Z∈R d×m ,

[0126] It should be noted that the principal component analysis method belongs to the existing technology. The above is only a brief introduction to the principal component analysis method. Other contents can refer to the existing technology and will not be repeated here.

[0127] Another embodiment of the present application also provides another implementation method of the device identification method of the power transmission line, and its specific process is as follows: Figure 4 As shown, the specific process is substantially the same as the specific process of the above embodiment, except that: in this embodiment, after step S310, the following steps are further included:

[0128] S410, using a population initialization model based on space transformation to perform data screening on each detection result.

[0129] Usually, data screening is to screen out a small amount of representative data from a large amount of data and remove duplicate data. In step S410, data screening specifically includes: screening out a small amount of representative test results from each test result and removing duplicate test results.

[0130] It should be noted that, in order to ensure that the test results after data screening are more representative, it is necessary to ensure that the number of test results before data screening is much larger than the number of test results after screening, that is, it is necessary to ensure that a large number of tests are performed in step S110. In practical applications, the number of test results before data screening is usually 10 times the number of parameters included in the test results.

[0131] Preferably, the population initialization model based on spatial transformation is an STS-R model; in practical applications, including but not limited to this, no specific limitation is made here, and it can be determined according to the specific circumstances, all of which are within the scope of protection of this application.

[0132] In this embodiment, by using a population initialization model based on space transformation and performing data screening on each detection result, the diversity of the initial population can be improved, thereby avoiding the problem of falling into a local optimal solution, that is, improving the judgment effect.

[0133] The following is a brief introduction to the population initialization model based on spatial transformation, as follows:

[0134] Firstly, an initial artificial fish swarm of size N is randomly generated in the candidate area. During the generation process, the best point set method can be used to make the generated population more uniform. The size of N is usually 10 times the dimension of the variable.

[0135] After that, set the maximum number of iterations. Take the STS-R model as an example. The details are as follows:

[0136] Let x be a solution in the current search space S, x∈[a, b], and transform the search space S * The solution x in * Defined as: * =Δ-x; where Δ is a computable value, x * ∈[Δ-b,Δ-a].

[0137] In the STS-R model, let Δ = k(a+b), and let k = r, and r = rand(0,1), where rand(0,1) is a random number between [0,1]. Then: x * =r(a+b)-x, and x∈[a,b], so x *∈[r(a+b)-b,r(a+b)-a], so the center position of the transformation space is located at a point between -(a+b) / 2 and (a+b) / 2.

[0138] When the space is n-dimensional, the above formula becomes: When initializing, let vector X = (x1, x2, x3...x n ) is a solution in n-dimensional space, and function f(x) is a function for calculating the fitness of the solution, then according to the space transformation method STS, is the solution about X in the corresponding transformation space. If the fitness f(x * ) is greater than f(x), then update the solution X to X * , otherwise, solution X is retained.

[0139] In summary, by simultaneously calculating the fitness of the individuals in the artificial fish population in the transformed space and the original space and continuously selecting the optimal value from them, a more accurate approximation value of the current candidate solution is obtained.

[0140] It should be noted that the population initialization model based on space transformation belongs to the prior art. The above is only a brief introduction to the population initialization model based on space transformation. Other contents can refer to the prior art and will not be repeated here.

[0141] Another embodiment of the present application provides a device for judging an output line. The output line is in a preset environment. The specific structure of the device judging device is as follows: Figure 5 As shown, it specifically includes: a detection module 100, an optimization module 200 and a diagnosis module 300.

[0142] Among them, the sampling end of the detection module 100 is set at the corresponding sampling point of the output line, the output end of the detection module 100 is connected to the input end of the optimization module 200, the output end of the optimization module 200 is connected to the input end of the diagnosis module 300, and the output end of the diagnosis module 300 serves as the output end of the equipment analysis device of the output line.

[0143] The detection module 100 is used to detect the status of the transmission line at different times; the optimization module 200 is used to perform optimization using the optimized artificial fish swarm algorithm and the detection results; the diagnosis module 300 is used to perform equipment fault diagnosis on the transmission line using the optimization results.

[0144] It should be noted that the functions of the detection module 100, the optimization module 200 and the diagnosis module 300 have been described in detail in the above embodiments, and will not be repeated here. Please refer to the above implementation mode.

[0145] This embodiment also provides another implementation of the device for judging the output line, and its specific structure is as follows: Figure 6As shown, this embodiment is substantially the same as the above embodiment, except that: based on the above embodiment, this embodiment further includes: a component reduction module 400.

[0146] The component simplification module 400 is disposed between the detection module 100 and the optimization module 200 and is used to simplify the components of each detection result by using the principal component analysis method.

[0147] It should be noted that the functions of the component reduction module 400 have been described in detail in the above embodiments, which will not be repeated here. Please refer to the above implementation mode.

[0148] This embodiment also provides another implementation of the device for judging the output line, and its specific structure is as follows: Figure 7 As shown, this embodiment is substantially the same as the above embodiment, except that: based on the above embodiment, this embodiment further includes: a data screening module 500.

[0149] The data screening module 500 is arranged between the component reduction module 400 and the optimization module 200; the data screening module 500 is used to perform data screening on each detection result by using a population initialization model based on space transformation.

[0150] It should be noted that the functions of the data screening module 500 have been described in detail in the above embodiments and will not be repeated here. Please refer to the above implementation mode.

[0151] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without creative work.

[0152] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0153] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for evaluating equipment of a power transmission line, characterized in that: The transmission line is in a preset environment; The equipment analysis method of the transmission line comprises: At different times, the state of the transmission line is detected to obtain detection results; Using principal component analysis to simplify the components of each of the test results; Using a population initialization model based on space transformation, data screening is performed on each of the detection results; The optimized artificial fish school algorithm and the detection results are used to search for the best artificial fish that best meets the user's set requirements, wherein the artificial fish that meets the user's set requirements is the state of the power transmission line that is closest to the fault or when the fault occurs; the state of the power transmission line includes the current and voltage of each section of the power transmission line; in the artificial fish school algorithm, the moving step length and the visible distance of the artificial fish decrease as the number of iterations increases; Performing equipment fault diagnosis on the power transmission line using the optimization result, wherein the optimization result is the state of the power transmission line closest to the fault or when the fault occurs; The artificial fish swarm algorithm comprises: Evaluate the status of all the artificial fish and record the status of the artificial fish that best meets the user's set requirements; Set the number of iterations to 1 and start iteration; Determining each of the moving steps and each of the visible distances according to the number of iterations; Each of the artificial fish updates its own state by performing foraging, grouping and tail-chasing behaviors; Comparing the states of the artificial fish with the recorded states of the artificial fish, and recording the state of the artificial fish that better meets the user's set requirements; Determine whether the iteration stop condition is met; If the iteration stop condition is met, the recorded state of the artificial fish is output; If the iteration stop condition is not met, the number of iterations is increased by 1 and the process returns to the step of determining each moving step length and each visible distance according to the number of iterations; The functional relationship between the moving step length and the number of iterations, and the functional relationship between the visible distance and the number of iterations are respectively: Among them, step is the moving step length, Max_S is the maximum moving step length of the artificial fish, Min_S is the minimum moving step length of the artificial fish; visual is the visible distance, Max_V is the maximum visible distance of the artificial fish, Min_V is the minimum visible distance of the artificial fish; Max_gen is the maximum number of iterations; iter is the current number of iterations of the artificial fish.

2. The method for evaluating equipment of a power transmission line according to claim 1, characterized in that: The iteration stop condition includes: The recorded state of the artificial fish meets the user's setting requirements; or, The number of iterations reaches a preset number.

3. The method for evaluating equipment of a power transmission line according to claim 1, characterized in that: The population initialization model is the STS-R model.

4. A device for analyzing and judging equipment of a power transmission line, characterized in that: The transmission line is in a preset environment; the equipment analysis and judgment device of the transmission line comprises: a detection module, a component reduction module, a data screening module, an optimization module and a diagnosis module connected in sequence; wherein: The detection module is used to detect the state of the transmission line at different times to obtain detection results; The component simplification module is used to simplify the components of each of the test results using a principal component analysis method; The data screening module is used to perform data screening on each of the detection results using a population initialization model based on space transformation; The optimization module is used to optimize using the optimized artificial fish school algorithm and each of the detection results to find the artificial fish that best meets the user's set requirements, and the artificial fish that meets the user's set requirements is the state of the power transmission line that is closest to the fault or when the fault occurs; the state of the transmission line includes the current and voltage of each section of the transmission line; in the artificial fish school algorithm, the moving step length and visible distance of the artificial fish decrease as the number of iterations increases; The diagnosis module is used to perform equipment fault diagnosis on the power transmission line using the optimization result, wherein the optimization result is the state of the power transmission line closest to the fault or when the fault occurs; The artificial fish swarm algorithm comprises: Evaluate the status of all the artificial fish and record the status of the artificial fish that best meets the user's set requirements; Set the number of iterations to 1 and start iteration; Determining each of the moving steps and each of the visible distances according to the number of iterations; Each of the artificial fish updates its own state by performing foraging, grouping and tail-chasing behaviors; Comparing the states of the artificial fish with the recorded states of the artificial fish, and recording the state of the artificial fish that better meets the user's set requirements; Determine whether the iteration stop condition is met; If the iteration stop condition is met, the recorded state of the artificial fish is output; If the iteration stop condition is not met, the number of iterations is increased by 1 and the process returns to the step of determining each moving step length and each visible distance according to the number of iterations; The functional relationship between the moving step length and the number of iterations, and the functional relationship between the visible distance and the number of iterations are respectively: Among them, step is the moving step length, Max_S is the maximum moving step length of the artificial fish, Min_S is the minimum moving step length of the artificial fish; visual is the visible distance, Max_V is the maximum visible distance of the artificial fish, Min_V is the minimum visible distance of the artificial fish; Max_gen is the maximum number of iterations; iter is the current number of iterations of the artificial fish.

Images