Power transmission infrastructure line anti-galloping design method and device

Abstract

The invention relates to a power transmission infrastructure line anti-galloping design method and device. The method comprises the following steps: collecting related information of a power transmission infrastructure line and construction meteorological conditions of prediction time; based on a preset design scheme of multiple groups of initial phase-to-phase spacer parameters, the related information of the power transmission capital construction line and the construction meteorological conditions of the prediction time, utilizing a pre-established galloping parameter prediction model to predict and obtain multiple groups of galloping characteristic parameter data of the prediction time; determining an optimal design scheme of phase-to-phase spacer parameters according to the multiple groups of galloping characteristic parameter data of the prediction time; and according to the optimal design scheme of the phase-to-phase spacer parameters, anti-galloping design of the power transmission capital construction line is carried out. According to the technical scheme provided by the invention, the galloping risk of different phase-to-phase spacer design schemes is automatically adjusted and judged, the labor cost is reduced, and the ice-resistant and galloping-proof capability and the severe weather resistance of the power transmission line are comprehensively improved, so that the safe operation level of the power transmission line is improved, and the power demand of production and living is guaranteed.

Description

Technical Field

[0001] The invention belongs to the technical field of power transmission line galloping prevention and control in the infrastructure construction stage, and specifically relates to a power transmission line galloping prevention design method and device. Background Art

[0002] Due to the harsh environment of overhead wires, eccentric ice is easily formed on the wires, and with the effect of strong winds, it is easy to cause dancing and damage. The wires of infrastructure lines are not energized, and their temperature is more affected by the environment. Therefore, they are more susceptible to ice dancing than operating lines, so the prevention and control requirements and difficulties are greater.

[0003] At present, the galloping prevention and control methods for infrastructure lines only refer to the structural reliability, do not comprehensively consider the historical prevention and control effects, and mostly rely on manual experience, and the values ​​of relevant parameters are not quantified and objective. Summary of the invention

[0004] In order to overcome the problems existing in the above-mentioned related technologies, the present application provides a method and device for designing anti-dancing of power transmission infrastructure lines.

[0005] According to a first aspect of an embodiment of the present application, a method for designing a power transmission infrastructure line anti-dancing is provided, comprising:

[0006] Collect relevant information of power transmission infrastructure lines and forecast construction weather conditions at the time;

[0007] Based on the preset multiple groups of initial design schemes of phase-to-phase spacing rod parameters, the relevant information of the power transmission infrastructure line and the construction meteorological conditions at the predicted time, a pre-established dancing parameter prediction model is used to predict multiple groups of dancing characteristic parameter data at the predicted time;

[0008] Determine the optimal design scheme of interphase spacing rod parameters according to the plurality of groups of dancing characteristic parameter data of the predicted time;

[0009] According to the optimal design scheme of phase-to-phase spacer parameters, anti-dancing design of power transmission infrastructure lines is carried out.

[0010] Preferably, the relevant information of the power transmission infrastructure line includes: structural parameters and topographic parameters of the line under construction;

[0011] The characteristics of the structural parameters of the line under construction include: conductor cross-sectional area, elastic modulus, operating tension, number of splits, span, hanging height, height difference and line strike angle;

[0012] The characteristics of the topographic and geomorphic parameters include: basic topography and basic landforms. The basic topography includes: plains, hills, low mountains, medium mountains and high mountains; the basic landforms include: built-up areas, grasslands, forests, deserts and rivers and lakes.

[0013] Preferably, the characteristics of the interphase spacer parameters include: rod material, length, stiffness, damping, connecting plate cross-sectional area, shed diameter and installation position;

[0014] The characteristics of the construction meteorological conditions include: temperature, precipitation, wind speed, wind direction, humidity, irradiance, ice shape and ice thickness;

[0015] The characteristics of the dancing characteristic parameters include: dancing amplitude, dancing frequency and whether the operation is damaged; wherein, when the operation is damaged, the characteristic of whether the operation is damaged also includes the degree of damage.

[0016] Preferably, the design scheme based on the preset multiple groups of initial phase spacing rod parameters, the relevant information of the transmission infrastructure line and the construction meteorological conditions at the predicted time, using the pre-established dancing parameter prediction model, predicts multiple groups of dancing characteristic parameter data at the predicted time, including:

[0017] Taking the design scheme of each set of initial interphase spacing bar parameters, the relevant information of the power transmission infrastructure line and the construction meteorological conditions at the predicted time as the input of the dancing parameter prediction model, outputting the dancing characteristic parameter data at the predicted time corresponding to the design scheme of each set of initial interphase spacing bar parameters;

[0018] The dancing characteristic parameter data at the predicted time corresponding to the design schemes of all groups of initial interphase spacer rod parameters are the plurality of groups of dancing characteristic parameter data at the predicted time.

[0019] Preferably, the design scheme for determining the optimal interphase spacing rod parameters according to the plurality of groups of dancing characteristic parameter data of the predicted time includes:

[0020] From the plurality of groups of dancing characteristic parameter data of the prediction time, selecting the initial design scheme of the interphase spacing rod parameters corresponding to the dancing characteristic parameter data that meets the first preset condition as the design scheme of the interphase spacing rod parameters to be determined;

[0021] Based on the design schemes of the interphase spacer parameters to be determined, a nonlinear dynamics method is used to simulate and calculate the dancing amplitude and dancing frequency corresponding to each design scheme of the interphase spacer parameters to be determined;

[0022] Determine whether the dancing amplitude and dancing frequency corresponding to the design schemes of the pending interphase spacing rod parameters meet the second preset condition. If there is a design scheme of the pending interphase spacing rod parameters whose corresponding dancing amplitude and dancing frequency meet the second preset condition, then the design scheme of the pending interphase spacing rod parameters is the optimal design scheme of the interphase spacing rod parameters; if the dancing amplitude and dancing frequency corresponding to the design schemes of all the pending interphase spacing rod parameters do not meet the second preset condition, adjust the multiple groups of initial design schemes of the interphase spacing rod parameters, and use the adjusted multiple groups of initial design schemes of the interphase spacing rod parameters to re-determine the optimal design scheme of the interphase spacing rod parameters. Preferably, the acquisition process of the pre-established dancing parameter prediction model includes:

[0023] The input sample set is constructed by using the collected historical construction meteorological conditions, historical structural parameters of the line under construction, historical topographic parameters and historical phase spacing bar parameters;

[0024] Using the collected historical dancing feature parameters, an output sample set is constructed;

[0025] The improved neural network model is trained using the input sample set and the output sample set to obtain the dancing parameter prediction model.

[0026] Preferably, the improved neural network model comprises: an input layer, a first hidden layer, a second hidden layer and an output layer connected in sequence;

[0027] The first hidden layer includes: a first neuron, a second neuron and a third neuron;

[0028] The second hidden layer includes: a fourth neuron and a fifth neuron;

[0029] The input of the input layer is the structural parameters of the line under construction, topographic parameters, phase spacing parameters and construction meteorological conditions, and the output of the input layer is the input of the first hidden layer;

[0030] The input of the second hidden layer is the output of the first hidden layer, and the output of the second hidden layer is the input of the output layer;

[0031] The output of the output layer is dancing feature parameters.

[0032] Preferably, the input sample set includes: construction meteorological condition sample set Q i , the sample set of structural parameters of the line under construction C j , topographic and geomorphic parameter sample set D k and interphase spacer parameter sample set B m ;

[0033] Among them, i∈[1,M], M is the total number of features in the construction meteorological conditions; j∈[1,N], N is the total number of features in the structural parameters of the line under construction; k∈[1,P], P is the total number of features in the terrain parameters; m∈[1,E], E is the total number of features in the phase spacing parameters.

[0034] Preferably, the process of acquiring the function of the first neuron includes:

[0035] Performing standardization on each feature in the input sample set to obtain a standardized input sample set;

[0036] Calculate the covariance between the features in the input sample set after standardization;

[0037] The function of the first neuron is calculated by using the covariance between the features in the input sample set after the standardization process.

[0038] Preferably, the calculation formula of the function of the first neuron includes:

[0039]

[0040] In the above formula, F1 is the function of the first neuron, EigentValues|| is the eigenvalue of the 3×3 covariance matrix in the brackets||, and cov(Q i ,C j ) is the covariance of the features in the construction meteorological conditions sample set and the features in the structural parameters sample set of the line under construction, cov(Q i ,D k ) is the covariance of the characteristics in the construction meteorological conditions sample set and the characteristics in the topographic parameters sample set, cov(Q i ,B m ) is the covariance of the characteristics in the construction meteorological conditions sample set and the characteristics in the interphase spacing bar parameter sample set, cov(C j ,Q i ) is the covariance of the features in the sample set of structural parameters of the line under construction and the features in the sample set of construction meteorological conditions, cov(C j ,D k ) is the covariance of the features in the sample set of structural parameters of the line under construction and the features in the sample set of topographic parameters, cov(C j ,B m ) is the covariance of the features in the sample set of the structural parameters of the line under construction and the features in the sample set of the phase spacing rod parameters, cov(B m ,Q i ) is the covariance of the characteristics of the interphase spacing rod parameter sample set and the characteristics of the construction meteorological condition sample set, cov(Bm ,C j ) is the covariance of the features in the sample set of interphase spacing bar parameters and the features in the sample set of the structure parameters of the line under construction, cov(B m ,D k ) is the covariance of the features in the sample set of interlaced interval bar parameters and the features in the sample set of topographic parameters.

[0041] Preferably, the process of acquiring the function of the second neuron includes:

[0042] Remove null value rows and outlier rows in the input sample set;

[0043] Normalize the input sample set after removing null value rows and outlier rows;

[0044] Calculate the cosine similarity between the features in the input sample set after normalization;

[0045] The similarity matrix of the input sample set after normalization is obtained by using the cosine similarity between the features in the input sample set after normalization, and the similarity matrix of the input sample set after normalization is a function of the second neuron.

[0046] Preferably, the calculation formula for the cosine similarity between the features in the input sample set after normalization includes:

[0047]

[0048] In the above formula, y1∈[1,H], y2∈[1,H], H is the total number of features in the input sample set after normalization; cos(θ y1,y2 ) is the cosine similarity between any two features y1 and y2 in the input sample set after normalization, p y1 is the vector of feature y1 in the input sample set after normalization, p y2 is the vector of feature y2 in the input sample set after normalization, ||p y1 || is the vector p y1 The module of ||p y2 || is the vector p y2 Model.

[0049] Preferably, the calculation formula of the similarity matrix of the input sample set after normalization includes:

[0050]

[0051] In the above formula, h∈[1,H], H is the total number of features in the input sample set after normalization; F2 is the similarity matrix of the input sample set after normalization, cos(θ1,θ1) is the cosine similarity between the first feature and the first feature in the input sample set after normalization, cos(θ1,θ2) is the cosine similarity between the first feature and the second feature in the input sample set after normalization, and cos(θ1,θ2) is the cosine similarity between the first feature and the second feature in the input sample set after normalization. h ) is the cosine similarity between the first feature and the hth feature in the input sample set after normalization, cos(θ1, θ H ) is the cosine similarity between the first feature and the Hth feature in the input sample set after normalization, cos(θ2, θ1) is the cosine similarity between the second feature and the first feature in the input sample set after normalization, cos(θ2, θ2) is the cosine similarity between the second feature and the second feature in the input sample set after normalization, and cos(θ2, θ h ) is the cosine similarity between the second feature and the hth feature in the input sample set after normalization, cos(θ2,θ H ) is the cosine similarity between the second feature and the Hth feature in the input sample set after normalization, cos(θ h , θ1) is the cosine similarity between the hth feature and the first feature in the input sample set after normalization, cos(θ h , θ2) is the cosine similarity between the hth feature and the second feature in the input sample set after normalization, cos(θ h ,θ h ) is the cosine similarity between the hth feature and the hth feature in the input sample set after normalization, cos(θ h ,θ H ) is the cosine similarity between the hth feature and the Hth feature in the input sample set after normalization, cos(θ H , θ1) is the cosine similarity between the Hth feature and the first feature in the input sample set after normalization, cos(θ H , θ2) is the cosine similarity between the Hth feature and the second feature in the input sample set after normalization, cos(θ H ,θ h ) is the cosine similarity between the Hth feature and the hth feature in the input sample set after normalization, cos(θ H ,θ H ) is the cosine similarity between the Hth feature and the Hth feature in the input sample set after normalization.

[0052] Preferably, the process of acquiring the function of the third neuron includes:

[0053] The features in the input sample set are clustered using a mean square value clustering method to obtain four clusters; the four clusters include: a cluster corresponding to a construction meteorological condition sample set, a cluster corresponding to a sample set of structural parameters of the line under construction, a cluster corresponding to a sample set of topographic parameters, and a cluster corresponding to a sample set of interphase spacing rod parameters;

[0054] Calculate the centroid of each cluster;

[0055] The minimum value of the standard deviation of the distance from each sample point in the four clusters to all the mass centers is calculated using the mass center of each cluster, and the minimum value of the standard deviation of the distance from each sample point in the four clusters to all the mass centers is a function of the third neuron.

[0056] Preferably, the calculation formula for the minimum value of the standard deviation of the distance from each sample point to all centroids in the four clusters includes:

[0057] F3=min[(x r -p′1) 2 +(x r -p′2) 2 +(x r -p′3) 2 +(x r -p′4) 2 ]

[0058] In the above formula, r∈[1,R], R is the total number of sample points in the four clusters; F3 is the minimum value of the standard deviation of the distance from each sample point to all centroids in the four clusters, x r is the rth sample point in the four clusters, p′1 is the centroid of the cluster corresponding to the construction meteorological condition sample set, p′2 is the centroid of the cluster corresponding to the sample set of the structural parameters of the line under construction, p′3 is the centroid of the cluster corresponding to the sample set of the topographic parameters, and p′4 is the centroid of the cluster corresponding to the sample set of the phase spacing rod parameters.

[0059] Preferably, the calculation formula of the function of the fourth neuron includes:

[0060]

[0061] In the above formula, H1(A, F, S) is the function of the fourth neuron, A is the dancing amplitude, F is the dancing frequency, S is the damage quantification value, max() is the maximum value of the matrix element, Round() is to round the value in brackets to an integer, F1 is the function of the first neuron, and F2 is the function of the second neuron; e1, e2, e3, e4 and e5 are all coefficients, and they are positive numbers.

[0062] Preferably, the calculation formula of the function of the fifth neuron includes:

[0063]

[0064] In the above formula, H2(A, F, S) is the function of the fifth neuron, A is the dancing amplitude, F is the dancing frequency, S is the damage quantification value, max() is the maximum value of the matrix element, F2 is the function of the second neuron, F3 is the function of the third neuron, and H1(A, F, S) is the function of the fourth neuron.

[0065] According to a second aspect of an embodiment of the present application, there is provided a transmission infrastructure line anti-dancing design device, comprising:

[0066] A collection unit is used to collect relevant information of power transmission infrastructure lines and construction meteorological conditions at the predicted time;

[0067] A prediction unit, for predicting multiple groups of dancing characteristic parameter data at the prediction time based on multiple groups of preset initial phase-to-phase spacing bar parameter design schemes, relevant information of the power transmission infrastructure line and the construction meteorological conditions at the prediction time, using a pre-established dancing parameter prediction model;

[0068] A determination unit, used to determine the optimal design scheme of the interphase spacing rod parameters according to the plurality of groups of dancing characteristic parameter data of the predicted time;

[0069] The design unit is used to perform anti-dancing design of the power transmission infrastructure line according to the optimal design scheme of the phase-to-phase spacing rod parameters.

[0070] According to a third aspect of an embodiment of the present application, there is provided an electronic device, comprising: at least one processor and a memory; the memory and the processor are connected via a bus;

[0071] The memory is used to store one or more programs;

[0072] When the one or more programs are executed by the at least one processor, the power transmission infrastructure line anti-dancing design method is implemented.

[0073] According to a fourth aspect of an embodiment of the present application, a readable storage medium is provided, on which an execution program is stored. When the execution program is executed, the transmission infrastructure line anti-dancing design method is implemented.

[0074] The technical solution provided by the present invention has the following beneficial effects:

[0075] The present invention provides a method and device for designing anti-dancing of power transmission infrastructure lines. The method and device collect relevant information of the power transmission infrastructure lines and the construction meteorological conditions at the predicted time, and predict multiple groups of dancing characteristic parameter data at the predicted time based on the design scheme of multiple groups of preset initial phase-to-phase spacer parameters, relevant information of the power transmission infrastructure lines and the construction meteorological conditions at the predicted time, and use the pre-established dancing parameter prediction model to predict multiple groups of dancing characteristic parameter data at the predicted time. The optimal design scheme of the phase-to-phase spacer parameters is determined according to the multiple groups of dancing characteristic parameter data at the predicted time. The anti-dancing design of the power transmission infrastructure lines is performed according to the optimal design scheme of the phase-to-phase spacer parameters, and the automatic adjustment and judgment of the dancing risks of different phase-to-phase spacer design schemes are realized, the labor cost is reduced, the anti-icing and anti-dancing capabilities of the power transmission lines are comprehensively improved, and the ability of the power transmission lines to resist severe weather is effectively improved, thereby improving the safe operation level of the power transmission lines and fully guaranteeing the electricity demand for production and life. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] 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 some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0077] Figure 1 It is a flow chart of a method for designing anti-dancing of power transmission infrastructure lines provided by an embodiment of the present invention;

[0078] Figure 2 is a schematic diagram of an improved neural network model provided by an embodiment of the present invention;

[0079] Figure 3 It is a structural block diagram of a power transmission infrastructure line anti-dancing design device provided by an embodiment of the present invention;

[0080] Figure 4 It is a structural block diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0081] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the following embodiments are part of the embodiments of the present invention, rather than 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.

[0082] Embodiment 1

[0083] The purpose of the present invention is to use artificial intelligence methods to study and model infrastructure line galloping cases, analyze, summarize and optimize different factors, independently carry out the optimization design of parameters such as structural stiffness and damping, and automatically find the optimal structural implementation plan. Specifically, the present invention provides a power transmission infrastructure line anti-galloping design method, such as Figure 1 As shown, the following steps are included:

[0084] Step 101: Collect relevant information of power transmission infrastructure lines and construction meteorological conditions at the predicted time;

[0085] Step 102: Based on the preset multiple sets of initial design schemes of phase-to-phase spacing bar parameters, relevant information of the power transmission infrastructure line and the construction meteorological conditions at the predicted time, a pre-established dancing parameter prediction model is used to predict multiple sets of dancing characteristic parameter data at the predicted time;

[0086] Step 103: determining the optimal design scheme of interphase spacing rod parameters according to multiple groups of dancing characteristic parameter data of predicted time;

[0087] Step 104: Perform anti-dancing design of the power transmission infrastructure line according to the optimal design scheme of phase-to-phase spacer parameters.

[0088] Furthermore, the relevant information of the power transmission infrastructure line includes: the structural parameters of the line under construction and the topographic parameters;

[0089] The characteristics of the structural parameters of the line under construction include: conductor cross-sectional area, elastic modulus, operating tension, number of splits, span, hanging height, height difference and line strike angle;

[0090] The characteristics of topographic and geomorphic parameters include: basic topography and basic landforms. The basic topography includes: plains, hills, low mountains, medium mountains and high mountains; the basic landforms include: built-up areas, grasslands, forests, deserts and rivers and lakes.

[0091] Furthermore, the characteristics of the interphase spacer parameters include: rod material, length, stiffness, damping, connecting plate cross-sectional area, shed diameter and installation position;

[0092] The characteristics of construction meteorological conditions include: temperature, precipitation, wind speed, wind direction, humidity, irradiance, ice cover shape and ice cover thickness;

[0093] The characteristics of the dancing characteristic parameters include: dancing amplitude, dancing frequency and whether the operation is damaged; wherein, when the operation is damaged, the characteristic of whether the operation is damaged also includes the degree of damage.

[0094] Further, step 102 includes:

[0095] Step 1021: using the design scheme of each group of initial interphase spacing parameters, relevant information of the power transmission infrastructure line and the construction meteorological conditions at the predicted time as inputs of the dancing parameter prediction model, and outputting the dancing characteristic parameter data at the predicted time corresponding to the design scheme of each group of initial interphase spacing parameters;

[0096] Step 1022: The dancing characteristic parameter data at the predicted time corresponding to the design schemes of all groups of initial interphase spacer parameters are multiple groups of dancing characteristic parameter data at the predicted time.

[0097] Further, step 103 includes:

[0098] Step 1031: selecting, from a plurality of groups of dancing characteristic parameter data at predicted times, an initial design scheme of interphase spacing rod parameters corresponding to the dancing characteristic parameter data satisfying a first preset condition as a design scheme of interphase spacing rod parameters to be determined;

[0099] Step 1032: Based on the design schemes of the interphase spacer parameters to be determined, a nonlinear dynamic method is used to simulate and calculate the dancing amplitude and dancing frequency corresponding to each design scheme of the interphase spacer parameters to be determined;

[0100] Step 1033: Determine whether the dancing amplitude and dancing frequency corresponding to each design scheme of the pending interphase spacing bar parameters meet the second preset condition. If there is a design scheme of the pending interphase spacing bar parameters whose corresponding dancing amplitude and dancing frequency meet the second preset condition, then the design scheme of the pending interphase spacing bar parameters is the optimal design scheme of the interphase spacing bar parameters; if the dancing amplitude and dancing frequency corresponding to all the design schemes of the pending interphase spacing bar parameters do not meet the second preset condition, adjust the design schemes of multiple groups of initial interphase spacing bar parameters, and use the adjusted multiple groups of initial interphase spacing bar parameters design schemes to re-determine the optimal design scheme of the interphase spacing bar parameters.

[0101] It should be noted that the present invention does not limit the "first preset condition" and the "second preset condition", which can be set by those skilled in the art according to engineering needs, experimental data or expert experience. For example, the first preset condition may be, but is not limited to: the dancing amplitude in the dancing characteristic parameter data at the predicted time is less than 1 and less than or equal to 20% of the phase spacing, the dancing frequency in the dancing characteristic parameter data at the predicted time is greater than 3Hz, and whether the running damage in the dancing characteristic parameter data at the predicted time is not damaged; the second preset condition may be, but is not limited to: the dancing amplitude corresponding to the design scheme of the to-be-determined phase-to-phase spacing bar parameter is less than 1 and less than or equal to 20% of the phase spacing, the dancing frequency corresponding to the design scheme of each to-be-determined phase-to-phase spacing bar parameter is greater than 3Hz, and whether the running damage in the dancing characteristic parameter data at the predicted time corresponding to the design scheme of the to-be-determined phase-to-phase spacing bar parameter is not damaged; wherein, the phase spacing is the distance between the transmission lines connected at both ends of the phase spacing bar.

[0102] It can be understood that after the improved neural network training is completed, a mapping relationship can be obtained that reflects the dancing characteristics of the under-construction line and the construction meteorological conditions, the main structural parameters of the under-construction line, the topographic parameters and the key parameter set - the design and installation plan of the phase spacer.

[0103] Furthermore, after the training of the improved neural network is completed, in the design stage of the transmission line project, the parameters of the transmission equipment, the topography, the long-term observed local meteorological conditions, and the weather conditions of the future period of the line under construction can be used as input conditions, combined with different interphase spacer design and installation schemes, based on the first hidden layer and the second hidden layer, to judge the dancing characteristics of different periods;

[0104] Under the same conditions, the design and installation scheme of the interphase spacer rods with the least obvious dancing characteristics and the lowest degree of damage (for example, the dancing amplitude in the dancing characteristic parameter data at the predicted time is less than 1 and less than or equal to 20% of the phase spacing, the dancing frequency in the dancing characteristic parameter data at the predicted time is greater than 3Hz, and whether the running is damaged in the dancing characteristic parameter data at the predicted time is no damage) is taken as the optimal design scheme;

[0105] After determining the optimal design solution, traditional mechanical methods, such as finite element analysis, analytical analysis and other nonlinear dynamic methods, can be used to simulate and calculate the dancing amplitude and frequency characteristics, and then determine whether it has sufficient stability characteristics in terms of mechanical properties;

[0106] The simulation results meet the following requirements: the dancing amplitude corresponding to the design scheme of the interphase spacing bar parameters to be determined is less than 1 and less than or equal to 20% of the phase spacing, the dancing frequency corresponding to the design scheme of each interphase spacing bar parameter to be determined is greater than 3Hz, and the dancing characteristic parameter data of the predicted time corresponding to the design scheme of the interphase spacing bar parameters to be determined is not damaged during operation, which means that the scheme has sufficient anti-dancing ability; if the effect does not meet the requirements, adjust the design and installation parameters to determine the interphase spacing bar design and installation scheme corresponding to the best effect;

[0107] Design the processing equipment and complete the installation layout according to the verified phase-to-phase spacer design and installation plan to ensure that the conductor has sufficient anti-dancing ability.

[0108] The present invention utilizes a large amount of galloping case data, an artificial neural network research and judgment model for different lines, different weather conditions, and different phase-to-phase spacer design schemes, and combines traditional nonlinear dynamics methods to estimate the inhibitory effect of different phase-to-phase spacers on the conductor galloping amplitude. If the effect is not good, the design scheme is automatically adjusted according to the mapping relationship until the optimal scheme and the best anti-galloping effect are achieved.

[0109] The present invention focuses on the characteristics of the conductors in the infrastructure stage, constructs an artificial neural network, and clarifies the influence of different interphase spacer design schemes on the conductor galloping characteristics in the infrastructure stage. The present invention combines the artificial neural network with the analytical method in the traditional mechanics method, and automatically adjusts and judges the amplitude law risk of different interphase spacer design schemes according to the above influence law.

[0110] Furthermore, the method further comprises: Step 100: establishing a dancing parameter prediction model; Step 100, comprising:

[0111] Step 1001: construct an input sample set using the collected historical construction meteorological conditions, historical structural parameters of the line under construction, historical topographic parameters, and historical phase spacing bar parameters;

[0112] Step 1002: construct an output sample set using the collected historical dancing feature parameters;

[0113] Step 1003: Using the input sample set and the output sample set, the improved neural network model is trained to obtain a dancing parameter prediction model.

[0114] It is understandable that the galloping cases of the under-construction lines with phase spacers installed in the early stage were collected and sorted out to obtain the historical construction meteorological conditions, the historical main structure parameters of the under-construction lines, the historical topographic parameters, the historical phase spacer parameters and the historical galloping characteristic parameters, a total of five categories and 36 parameters, and some non-quantitative parameters were manually defined as quantitative parameters, and the fields, contents and values ​​of the data were sorted, cleaned, evaluated and merged to preliminarily form a standardized data set of the galloping of the under-construction lines with phase spacers, which includes: the above-mentioned input sample set and output sample set.

[0115] Using deep learning methods, an artificial intelligence neural network including an input layer, two hidden layers and an output layer, i.e., an improved neural network model, is constructed. Based on the normalized data set of the line galloping under construction, supervised learning of the nonlinear function in the hidden layer is performed. Furthermore, the improved neural network model includes: an input layer, a first hidden layer, a second hidden layer and an output layer connected in sequence;

[0116] The first hidden layer includes: a first neuron, a second neuron and a third neuron;

[0117] The second hidden layer includes: the fourth neuron and the fifth neuron;

[0118] The input of the input layer is the structural parameters of the line under construction, topographic parameters, phase spacing parameters and construction meteorological conditions, and the output of the input layer is the input of the first hidden layer;

[0119] The input of the second hidden layer is the output of the first hidden layer, and the output of the second hidden layer is the input of the output layer;

[0120] The output of the output layer is the dancing feature parameters.

[0121] Furthermore, the input sample set includes: construction meteorological condition sample set Q i , the sample set of structural parameters of the line under construction C j , topographic and geomorphic parameter sample set D k and interphase spacer parameter sample set B m ;

[0122] Among them, i∈[1,M], M is the total number of features in the construction meteorological conditions; j∈[1,N], N is the total number of features in the structural parameters of the line under construction; k∈[1,P], P is the total number of features in the terrain parameters; m∈[1,E], E is the total number of features in the phase spacing parameters.

[0123] For example, Figure 2 As shown, the construction meteorological condition sample set Q iThe sample set C of the structural parameters of the line under construction includes 8 characteristics: temperature, precipitation, wind speed, wind direction, humidity, irradiance, ice shape and ice thickness; j The sample set D includes eight characteristics: conductor cross-sectional area, elastic modulus, operating tension, number of splits, span, hanging height, height difference and line strike angle; the sample set D k There are 10 features in it: plains, hills, low mountains, medium mountains, high mountains, built-up areas, grasslands, forests, deserts, and rivers and lakes; the interlaced spacer parameter B m The sample set includes 7 features: rod material, length, stiffness, damping, cross-sectional area of ​​the connecting plate, shed diameter and installation position; the dancing feature parameter sample set W n There are three features: dancing amplitude, dancing frequency and whether the operation is damaged. When the operation is damaged, the feature whether the operation is damaged also includes the degree of damage.

[0124] It is understandable that, since the collected historical data is in multiple groups, each feature in the input sample set corresponds to multiple sample data. For example, if the historical data for 10 days from January 1 to January 10 is collected, each feature corresponds to 10 sample data. In some embodiments, the expression of the input sample set is as follows:

[0125]

[0126] In the above formula, h∈[1,H], H is the total number of features in the input sample set; h′∈[1,H′], H′ is the total number of sample data corresponding to each feature in the input sample set; S is the input sample set, is the first sample data corresponding to the first feature in the input sample set, is the second sample data corresponding to the first feature in the input sample set, is the h′th sample data corresponding to the first feature in the input sample set, is the H′th sample data corresponding to the first feature in the input sample set, is the first sample data corresponding to the second feature in the input sample set, is the second sample data corresponding to the second feature in the input sample set, is the h′th sample data corresponding to the second feature in the input sample set, is the H′th sample data corresponding to the second feature in the input sample set, is the first sample data corresponding to the hth feature in the input sample set, is the second sample data corresponding to the hth feature in the input sample set, is the h′th sample data corresponding to the hth feature in the input sample set, is the H′th sample data corresponding to the hth feature in the input sample set, is the first sample data corresponding to the Hth feature in the input sample set, is the second sample data corresponding to the Hth feature in the input sample set, is the h′th sample data corresponding to the Hth feature in the input sample set, is the H′th sample data corresponding to the Hth feature in the input sample set.

[0127] Furthermore, the process of obtaining the function of the first neuron includes:

[0128] Step a: Standardize each feature in the input sample set to obtain a standardized input sample set;

[0129] Step b: Calculate the covariance between the features in the input sample set after standardization;

[0130] It is understandable that the calculation method of the "covariance" involved in the embodiments of the present invention is well known to those skilled in the art, and therefore, its specific implementation method is not described in detail. In some embodiments, the calculation formula of the covariance between the features in the input sample set includes:

[0131]

[0132]

[0133] In the above formula, i∈[1,M], M is the total number of features in the construction meteorological conditions; j∈[1,N], N is the total number of features in the structural parameters of the line under construction; k∈[1,P], P is the total number of features in the topographic parameters; m∈[1,E], E is the total number of features in the phase spacing parameters; i″∈[1,M″], M″ is the total amount of sample data corresponding to each feature in the construction meteorological conditions; j″∈[1,N″], N″ is the total amount of sample data corresponding to each feature in the structural parameters of the line under construction; k″∈[1,P″], P″ is the total amount of sample data corresponding to each feature in the topographic parameters; m″∈[1,E″], E″ is the total amount of sample data corresponding to each feature in the phase spacing parameters; cov(Q i ,C j ) is the covariance of the features in the construction meteorological conditions sample set and the features in the structural parameters sample set of the line under construction, cov(Q i ,D k ) is the covariance of the characteristics in the construction meteorological conditions sample set and the characteristics in the topographic parameters sample set, cov(Q i ,B m) is the covariance of the characteristics in the construction meteorological conditions sample set and the characteristics in the interphase spacing bar parameter sample set, cov(C j ,Q i ) is the covariance of the features in the sample set of structural parameters of the line under construction and the features in the sample set of construction meteorological conditions, cov(C j ,D k ) is the covariance of the features in the sample set of structural parameters of the line under construction and the features in the sample set of topographic parameters, cov(C j ,B m ) is the covariance of the features in the sample set of the structural parameters of the line under construction and the features in the sample set of the phase spacing rod parameters, cov(B m ,Q i ) is the covariance of the characteristics of the interphase spacing rod parameter sample set and the characteristics of the construction meteorological condition sample set, cov(B m ,C j ) is the covariance of the features in the sample set of interphase spacing bar parameters and the features in the sample set of the structure parameters of the line under construction, cov(B m ,D k ) is the covariance of the features in the sample set of interlaced bar parameters and the features in the sample set of topographic parameters; x i,i″ is the i″th sample data corresponding to the i-th feature in the construction meteorological condition sample set, x j,j″ is the j″th sample data corresponding to the jth feature in the sample set of the structural parameters of the line under construction, x k,k″ is the k″th sample data corresponding to the kth feature in the topographic parameter sample set, x m,m″ is the m″th sample data corresponding to the mth feature in the interphase spacer parameter sample set; is the mean value of the i-th feature in the construction meteorological condition sample set, is the mean value of the jth feature in the sample set of structural parameters of the line under construction, is the mean value of the kth feature in the topographic parameter sample set, is the mean value of the mth feature in the interphase spacing bar parameter sample set;

[0134] Step c: using the covariance between the features in the input sample set after the standardization process, the function of the first neuron is calculated, and the function of the first neuron can also be called the eigenvalue function;

[0135] Specifically, the calculation formula of the function of the first neuron includes:

[0136]

[0137] In the above formula, F1 is the function of the first neuron, EigentValues|| is the eigenvalue of the 3×3 covariance matrix in the brackets||, and cov(Q i ,C j ) is the covariance of the features in the construction meteorological conditions sample set and the features in the structural parameters sample set of the line under construction, cov(Q i ,D k ) is the covariance of the characteristics in the construction meteorological conditions sample set and the characteristics in the topographic parameters sample set, cov(Q i ,B m ) is the covariance of the characteristics in the construction meteorological conditions sample set and the characteristics in the interphase spacing bar parameter sample set, cov(C j ,Q i ) is the covariance of the features in the sample set of structural parameters of the line under construction and the features in the sample set of construction meteorological conditions, cov(C j ,D k ) is the covariance of the features in the sample set of structural parameters of the line under construction and the features in the sample set of topographic parameters, cov(C j ,B m ) is the covariance of the features in the sample set of the structural parameters of the line under construction and the features in the sample set of the phase spacing rod parameters, cov(B m ,Q i ) is the covariance of the characteristics of the interphase spacing rod parameter sample set and the characteristics of the construction meteorological condition sample set, cov(B m ,C j ) is the covariance of the features in the sample set of interphase spacing bar parameters and the features in the sample set of the structure parameters of the line under construction, cov(B m ,D k ) is the covariance of the features in the sample set of interlaced interval bar parameters and the features in the sample set of topographic parameters.

[0138] It should be noted that the method of "standardizing each feature in the input sample set" involved in the embodiment of the present invention is well known to those skilled in the art, and therefore, its specific implementation method will not be described in detail. Each feature in the input sample set is standardized to eliminate the dimensional and order of magnitude differences that may exist between different features. In some embodiments, standardization can be achieved by, but is not limited to, subtracting the mean of each feature and dividing it by its standard deviation. For example, first highlight the data column with a span greater than 2000m, eliminate the wind speed greater than 25m / s, and eliminate the data rows with an ice thickness of 0 but a dancing amplitude greater than 0.

[0139] It can be understood that the size of the eigenvalue can reflect the importance of the corresponding eigenvector in the data. Smaller eigenvalues ​​may correspond to noise or redundant information in the data, while larger eigenvalues ​​correspond to key features in the data. Therefore, by analyzing the eigenvalues, important features can be selectively retained, thereby simplifying the data and improving the performance of the improved neural network model.

[0140] It is understandable that the calculation method of the "covariance" involved in the embodiments of the present invention is well known to those skilled in the art, and therefore, its specific implementation method will not be described in detail. In some embodiments,

[0141] Furthermore, the process of obtaining the function of the second neuron includes:

[0142] Step d: Remove the null value rows and outlier rows in the input sample set;

[0143] Step e: normalize the input sample set after removing the null value rows and outlier rows;

[0144] It should be noted that the methods of “removing null value rows and outlier rows from the input sample set” and “normalizing the input sample set after removing null value rows and outlier rows” involved in the embodiments of the present invention are well known to those skilled in the art, and therefore, the specific implementation thereof will not be described in detail.

[0145] Step f: Calculate the cosine similarity between the features in the input sample set after normalization;

[0146] Specifically, the calculation formula for the cosine similarity between the features in the input sample set after normalization includes:

[0147]

[0148] In the above formula, y1∈[1,H], y2∈[1,H], H is the total number of features in the input sample set after normalization; cos(θ y1,y2 ) is the cosine similarity between any two features y1 and y2 in the input sample set after normalization, p y1 is the vector of feature y1 in the input sample set after normalization, p y2 is the vector of feature y2 in the input sample set after normalization, ||p y1 || is the vector p y1 The module of ||p y2 || is the vector p y2 Model;

[0149] It can be understood that each feature corresponds to multiple sample data, so p y1 and py2 are actually the vectors of sample data columns corresponding to features y1 and y2 in the input sample set after normalization. For example, the input sample set after normalization is as follows. Assuming that y1 is the first feature in the input sample set after normalization, then p y1 is the vector of the sample data column corresponding to the first feature in the input sample set after normalization, ||p y1 || is the vector p y1 The modulus of y2 is the second feature in the input sample set after normalization, then p y2 is the vector of the sample data column corresponding to the first feature in the input sample set after normalization, ||p y2 || is the vector p y2 Model;

[0150] The expression of the input sample set after normalization is:

[0151]

[0152] The expression of the sample data column corresponding to the first feature in the input sample set after normalization is:

[0153]

[0154] The expression of the sample data column corresponding to the second feature in the input sample set after normalization is:

[0155]

[0156] In the above formula, h∈[1,H], H is the total number of features in the input sample set after normalization; h′∈[1,H′], H′ is the total number of sample data corresponding to each feature in the input sample set after normalization; S′ is the input sample set after normalization, is the first sample data corresponding to the first feature in the input sample set after normalization. is the second sample data corresponding to the first feature in the input sample set after normalization. is the h′th sample data corresponding to the first feature in the input sample set after normalization. is the H′th sample data corresponding to the first feature in the input sample set after normalization. is the first sample data corresponding to the second feature in the input sample set after normalization. is the second sample data corresponding to the second feature in the input sample set after normalization. is the h′th sample data corresponding to the second feature in the input sample set after normalization. is the H′th sample data corresponding to the second feature in the input sample set after normalization. is the first sample data corresponding to the hth feature in the input sample set after normalization. is the second sample data corresponding to the hth feature in the input sample set after normalization. is the h′th sample data corresponding to the hth feature in the input sample set after normalization. is the H′th sample data corresponding to the hth feature in the input sample set after normalization. is the first sample data corresponding to the Hth feature in the input sample set after normalization. is the second sample data corresponding to the Hth feature in the input sample set after normalization. is the h′th sample data corresponding to the Hth feature in the input sample set after normalization. is the H′th sample data corresponding to the Hth feature in the input sample set after normalization;

[0157] Step g: using the cosine similarity between the features in the normalized input sample set, obtaining a similarity matrix of the normalized input sample set, the similarity matrix of the normalized input sample set is a function of the second neuron, and the function of the second neuron can also be called a principal component function;

[0158] Specifically, the cosine similarity values ​​between each pair of features are stored in an H×H matrix (H is the total number of features in the input sample set after normalization, and H is also the number of rows and columns of the input sample set after normalization). This matrix is ​​called a similarity matrix. The calculation formula of the similarity matrix of the input sample set after normalization includes:

[0159]

[0160] In the above formula, h∈[1,H], H is the total number of features in the input sample set after normalization; F2 is the similarity matrix of the input sample set after normalization, cos(θ1,θ1) is the cosine similarity between the first feature and the first feature in the input sample set after normalization, cos(θ1,θ2) is the cosine similarity between the first feature and the second feature in the input sample set after normalization, and cos(θ1,θ2) is the cosine similarity between the first feature and the second feature in the input sample set after normalization. h ) is the cosine similarity between the first feature and the hth feature in the input sample set after normalization, cos(θ1, θH ) is the cosine similarity between the first feature and the Hth feature in the input sample set after normalization, cos(θ2, θ1) is the cosine similarity between the second feature and the first feature in the input sample set after normalization, cos(θ2, θ2) is the cosine similarity between the second feature and the second feature in the input sample set after normalization, and cos(θ2, θ h ) is the cosine similarity between the second feature and the hth feature in the input sample set after normalization, cos(θ2,θ H ) is the cosine similarity between the second feature and the Hth feature in the input sample set after normalization, cos(θ h , θ1) is the cosine similarity between the hth feature and the first feature in the input sample set after normalization, cos(θ h , θ2) is the cosine similarity between the hth feature and the second feature in the input sample set after normalization, cos(θ h ,θ h ) is the cosine similarity between the hth feature and the hth feature in the input sample set after normalization, cos(θ h ,θ H ) is the cosine similarity between the hth feature and the Hth feature in the input sample set after normalization, cos(θ H , θ1) is the cosine similarity between the Hth feature and the first feature in the input sample set after normalization, cos(θ H , θ2) is the cosine similarity between the Hth feature and the second feature in the input sample set after normalization, cos(θ H ,θ h ) is the cosine similarity between the Hth feature and the hth feature in the input sample set after normalization, cos(θ H ,θ H ) is the cosine similarity between the Hth feature and the Hth feature in the input sample set after normalization.

[0161] It should be noted that the similarity matrix of the normalized input sample set shows the similarity between all the features in the data set. By examining the similarity matrix, you can find which features are very similar to each other (cosine similarity is close to 1) or very dissimilar (cosine similarity is close to -1).

[0162] Furthermore, the process of obtaining the function of the third neuron includes:

[0163] Step h: clustering the features in the input sample set using the mean square value clustering method to obtain four clusters; the four clusters include: a cluster corresponding to the construction meteorological condition sample set, a cluster corresponding to the structural parameter sample set of the line under construction, a cluster corresponding to the topographic parameter sample set, and a cluster corresponding to the phase spacing rod parameter sample set;

[0164] Step i: Calculate the centroid of each cluster;

[0165] It should be noted that the calculation method of the "center of mass of a cluster" involved in the embodiments of the present invention is well known to those skilled in the art, and therefore, its specific implementation method is not described in detail. In some embodiments, the calculation formula of the center of mass of each cluster includes:

[0166]

[0167] In the above formula, i′∈[1,M′], M′ is the total number of sample points in the cluster corresponding to the construction meteorological condition sample set; j′∈[1,N′], N′ is the total number of sample points in the cluster corresponding to the structural parameter sample set of the under-construction line; k′∈[1,P′], P′ is the total number of sample points in the cluster corresponding to the topographic parameter sample set; m′∈[1,W′], W′ is the total number of sample points in the cluster corresponding to the phase spacing bar parameter sample set; p′1 is any sample point in the cluster corresponding to the construction meteorological condition sample set, p i′ is the i′th sample point in the cluster corresponding to the construction meteorological condition sample set, ||p′1-p i′ || 2 The sample points p′1 and p in the cluster corresponding to the construction meteorological condition sample set are i′ The Euclidean distance between the sample point p′1 and all the sample points in the cluster corresponding to the construction meteorological condition sample set is the smallest, and the sample point p′1 is the centroid of the cluster corresponding to the construction meteorological condition sample set; p′2 is any sample point in the cluster corresponding to the structural parameter sample set of the line under construction, p j′ is the j′th sample point in the cluster corresponding to the sample set of the structural parameters of the line under construction, ||p′2-p j′ || 2 The sample points p′2 and p in the cluster corresponding to the sample set of the structural parameters of the line under construction are j′ The Euclidean distance between the sample point p′2 and all the sample points in the cluster corresponding to the sample set of the structural parameters of the line under construction is the smallest, and the sample point p′2 is the centroid of the cluster corresponding to the sample set of the structural parameters of the line under construction; p′3 is any sample point in the cluster corresponding to the sample set of the topographic parameters, p k′ is the k′th sample point in the cluster corresponding to the topographic parameter sample set, ||p′3-p k′ || 2is the cluster sample point p′3 and sample point p corresponding to the topographic parameter sample set k′ The Euclidean distance between the sample point p′3 and all the sample points in the cluster corresponding to the topographic and geomorphic parameter sample set is the smallest, and the sample point p′3 is the centroid of the cluster corresponding to the topographic and geomorphic parameter sample set; p′4 is any sample point in the cluster corresponding to the interlaced interval bar parameter sample set, p m′ is the m′th sample point in the cluster corresponding to the sample set of interlaced bar parameters, ||p′4-p m′ || 2 The cluster sample point p′4 and the sample point p corresponding to the interlaced bar parameter sample set m′ The Euclidean distance between the sample point p′4 and all the sample points in the cluster corresponding to the inter-phase spacing bar parameter sample set is the smallest, and the sample point p′4 is the centroid of the cluster corresponding to the inter-phase spacing bar parameter sample set;

[0168] Step j: using the centroid of each cluster, calculate the minimum value of the standard deviation of the distance from each sample point in the four clusters to all the centroids. The minimum value of the standard deviation of the distance from each sample point in the four clusters to all the centroids is the function of the third neuron. The function of the third neuron can also be called the standard deviation function.

[0169] Specifically, the calculation formula for the minimum value of the standard deviation of the distance from each sample point to all centroids in the four clusters includes:

[0170] F3=min[(x r -p′1) 2 +(x r -p′2) 2 +(x r -p′3) 2 +(x r -p′4) 2 ]

[0171] In the above formula, r∈[1,R], R is the total number of sample points in the four clusters; F3 is the minimum value of the standard deviation of the distance from each sample point to all centroids in the four clusters, x r is the rth sample point in the four clusters, p′1 is the centroid of the cluster corresponding to the construction meteorological condition sample set, p′2 is the centroid of the cluster corresponding to the sample set of the structural parameters of the line under construction, p′3 is the centroid of the cluster corresponding to the sample set of the topographic parameters, and p′4 is the centroid of the cluster corresponding to the sample set of the phase spacing rod parameters.

[0172] It should be noted that the standard deviation of a sample cluster is usually used to describe the range of data variation and the stability of the data. In the fields of data analysis, statistical modeling, quality control, etc., the standard deviation of a sample cluster is an important indicator to improve the accuracy and efficiency of the dancing parameter prediction model in predicting dancing characteristic parameter data.

[0173] Clearly input sample set Q i , C j , D k , B m After the eigenvalue function F1, principal component function F2 and standard deviation function F3 are calculated, the key factors, typical features and discrete degree in the input sample set can be quantified respectively, and then the data set can be divided into two categories: slight dancing and severe dancing. The relevant mapping relationship of slight dancing is mainly reflected in the H1 function, and the relevant mapping relationship of severe dancing is mainly reflected in the H2 function. For example, if the following three conditions are met at the same time: the dancing amplitude is less than 1, the dancing frequency is greater than 3Hz and there is no equipment damage, it is defined as slight dancing; if any of the above three conditions are not met, it is classified as severe dancing.

[0174] In some optional embodiments, for the slight dancing function H1, the top max parameters with higher importance are selected according to F1 (the max value is determined by the last parameter ranked in the interphase spacer parameter set, for example, the rod body parameter is the 16th in the F1 function importance ranking and the last in the interphase spacer parameter set, then the top 16 parameters are fitted to reflect the design and installation scheme of the interphase spacer and its influence on the dancing characteristics.

[0175] Furthermore, the calculation formula of the function of the fourth neuron includes:

[0176]

[0177] In the above formula, H1(A, F, S) is the function of the fourth neuron, A is the dancing amplitude, F is the dancing frequency, S is the damage quantification value, max() is the maximum value of the matrix elements, Round() is rounding the values ​​in brackets to integers, F1 is the function of the first neuron, and F2 is the function of the second neuron; e1, e2, e3, e4 and e5 are all coefficients, and are positive numbers.

[0178] It should be noted that the embodiments of the present invention do not limit "e1, e2, e3, e4 and e5", which can be set by those skilled in the art according to engineering needs, experimental data or expert experience, for example, e1 = 4.12, e2 = 0.36, e3 = 1.58, e4 = 2.1, e5 = 0.58.

[0179] For the severely dancing sample data, it is necessary to further consider the influence of F2 and F3 on the basis of H1. Furthermore, the calculation formula of the function of the fifth neuron includes:

[0180]

[0181] In the above formula, H2(A, F, S) is the function of the fifth neuron, A is the dancing amplitude, F is the dancing frequency, S is the damage quantification value, max() is the maximum value of the matrix element, F2 is the function of the second neuron, F3 is the function of the third neuron, and H1(A, F, S) is the function of the fourth neuron.

[0182] The present invention provides a method for designing anti-dancing of power transmission infrastructure lines. The method collects relevant information of the power transmission infrastructure lines and the construction meteorological conditions at the predicted time, and predicts multiple groups of dancing characteristic parameter data at the predicted time based on the design schemes of multiple groups of preset initial phase-to-phase spacer parameters, relevant information of the power transmission infrastructure lines and the construction meteorological conditions at the predicted time, and uses a pre-established dancing parameter prediction model to predict multiple groups of dancing characteristic parameter data at the predicted time. The method determines the optimal design scheme of the phase-to-phase spacer parameters according to the multiple groups of dancing characteristic parameter data at the predicted time, and performs anti-dancing design of the power transmission infrastructure lines according to the optimal design scheme of the phase-to-phase spacer parameters, thereby realizing automatic adjustment and judging the dancing risks of different phase-to-phase spacer design schemes, reducing labor costs, comprehensively improving the anti-icing and anti-dancing capabilities of the power transmission lines, and effectively improving the ability of the power transmission lines to resist severe weather, thereby improving the safe operation level of the power transmission lines and fully guaranteeing the electricity demand for production and life.

[0183] Embodiment 2

[0184] The present invention also provides a power transmission infrastructure line anti-dancing design device, such as Figure 3 As shown, including:

[0185] A collection unit is used to collect relevant information of power transmission infrastructure lines and construction meteorological conditions at the predicted time;

[0186] A prediction unit, for predicting multiple groups of dancing characteristic parameter data at the prediction time based on multiple groups of preset initial phase-to-phase spacing bar parameter design schemes, relevant information of the power transmission infrastructure line and the construction meteorological conditions at the prediction time, using a pre-established dancing parameter prediction model;

[0187] A determination unit, used to determine the optimal design scheme of the interphase spacing rod parameters according to the plurality of groups of dancing characteristic parameter data of the predicted time;

[0188] The design unit is used to perform anti-dancing design of the power transmission infrastructure line according to the optimal design scheme of the phase-to-phase spacing rod parameters.

[0189] Furthermore, the relevant information of the power transmission infrastructure line includes: the structural parameters of the line under construction and the topographic parameters;

[0190] The characteristics of the structural parameters of the line under construction include: conductor cross-sectional area, elastic modulus, operating tension, number of splits, span, hanging height, height difference and line strike angle;

[0191] The characteristics of topographic and geomorphic parameters include: basic topography and basic landforms. The basic topography includes: plains, hills, low mountains, medium mountains and high mountains; the basic landforms include: built-up areas, grasslands, forests, deserts and rivers and lakes.

[0192] Furthermore, the characteristics of the interphase spacer parameters include: rod material, length, stiffness, damping, connecting plate cross-sectional area, shed diameter and installation position;

[0193] The characteristics of construction meteorological conditions include: temperature, precipitation, wind speed, wind direction, humidity, irradiance, ice cover shape and ice cover thickness;

[0194] The characteristics of the dancing characteristic parameters include: dancing amplitude, dancing frequency and whether the operation is damaged; wherein, when the operation is damaged, the characteristic of whether the operation is damaged also includes the degree of damage.

[0195] Furthermore, the prediction unit is specifically used for:

[0196] The design scheme of each set of initial interphase spacing bar parameters, the relevant information of the transmission infrastructure line and the construction meteorological conditions at the prediction time are used as the input of the dancing parameter prediction model, and the dancing characteristic parameter data at the prediction time corresponding to the design scheme of each set of initial interphase spacing bar parameters are output;

[0197] The dancing characteristic parameter data at the prediction time corresponding to the design schemes of all groups of initial interphase spacing rod parameters are multiple groups of dancing characteristic parameter data at the prediction time.

[0198] Further, the unit is determined, specifically for:

[0199] From a plurality of groups of dancing characteristic parameter data of the prediction time, selecting an initial design scheme of interphase spacing rod parameters corresponding to the dancing characteristic parameter data satisfying a first preset condition as a design scheme of interphase spacing rod parameters to be determined;

[0200] Based on the design schemes of the interphase spacer parameters to be determined, the dancing amplitude and dancing frequency corresponding to each design scheme of the interphase spacer parameters to be determined are obtained by simulation and calculation using a nonlinear dynamics method;

[0201] Determine whether the dancing amplitude and dancing frequency corresponding to the design schemes of the pending interphase spacing bar parameters meet the second preset condition. If there is a design scheme of the pending interphase spacing bar parameters whose corresponding dancing amplitude and dancing frequency meet the second preset condition, then the design scheme of the pending interphase spacing bar parameters is the optimal design scheme of the interphase spacing bar parameters; if the dancing amplitude and dancing frequency corresponding to the design schemes of all the pending interphase spacing bar parameters do not meet the second preset condition, adjust the design schemes of multiple groups of initial interphase spacing bar parameters, and use the adjusted design schemes of the multiple groups of initial interphase spacing bar parameters to re-determine the optimal design scheme of the interphase spacing bar parameters.

[0202] Furthermore, the device further comprises: an establishing unit, used to establish a pre-established dancing parameter prediction model; an establishing unit, specifically used to:

[0203] The input sample set is constructed by using the collected historical construction meteorological conditions, historical structural parameters of the line under construction, historical topographic parameters and historical phase spacing bar parameters;

[0204] Using the collected historical dancing feature parameters, an output sample set is constructed;

[0205] The improved neural network model is trained using the input sample set and the output sample set to obtain the dancing parameter prediction model.

[0206] Furthermore, the improved neural network model includes: an input layer, a first hidden layer, a second hidden layer, and an output layer connected in sequence;

[0207] The first hidden layer includes: a first neuron, a second neuron and a third neuron;

[0208] The second hidden layer includes: the fourth neuron and the fifth neuron;

[0209] The input of the input layer is the structural parameters of the line under construction, topographic parameters, phase spacing parameters and construction meteorological conditions, and the output of the input layer is the input of the first hidden layer;

[0210] The input of the second hidden layer is the output of the first hidden layer, and the output of the second hidden layer is the input of the output layer;

[0211] The output of the output layer is the dancing feature parameters.

[0212] Furthermore, the input sample set includes: construction meteorological condition sample set Q i , the sample set of structural parameters of the line under construction C j , topographic and geomorphic parameter sample set D k and interphase spacing bar parameter sample set B m ;

[0213] Among them, i∈[1,M], M is the total number of features in the construction meteorological conditions; j∈[1,N], N is the total number of features in the structural parameters of the line under construction; k∈[1,P], P is the total number of features in the terrain parameters; m∈[1,E], E is the total number of features in the phase spacing parameters.

[0214] Furthermore, the device further includes: a first acquisition unit, configured to acquire a function of the first neuron; the first acquisition unit is specifically configured to:

[0215] Standardize each feature in the input sample set to obtain a standardized input sample set;

[0216] Calculate the covariance between the features in the input sample set after standardization;

[0217] The function of the first neuron is calculated using the covariance between the features in the input sample set after the standardization process.

[0218] Furthermore, the calculation formula of the function of the first neuron includes:

[0219]

[0220] In the above formula, F1 is the function of the first neuron, EigentValues|| is the eigenvalue of the 3×3 covariance matrix in the brackets||, and cov(Q i ,C j ) is the covariance of the features in the construction meteorological conditions sample set and the features in the structural parameters sample set of the line under construction, cov(Q i ,D k ) is the covariance of the characteristics in the construction meteorological conditions sample set and the characteristics in the topographic parameters sample set, cov(Q i ,B m ) is the covariance of the characteristics in the construction meteorological conditions sample set and the characteristics in the interphase spacing bar parameter sample set, cov(C j ,Q i ) is the covariance of the features in the sample set of structural parameters of the line under construction and the features in the sample set of construction meteorological conditions, cov(C j ,D k ) is the covariance of the features in the sample set of structural parameters of the line under construction and the features in the sample set of topographic parameters, cov(C j ,B m ) is the covariance of the features in the sample set of the structural parameters of the line under construction and the features in the sample set of the phase spacing rod parameters, cov(B m ,Q i) is the covariance of the characteristics of the interphase spacing rod parameter sample set and the characteristics of the construction meteorological condition sample set, cov(B m ,C j ) is the covariance of the features in the sample set of interphase spacing bar parameters and the features in the sample set of the structure parameters of the line under construction, cov(B m ,D k ) is the covariance of the features in the sample set of interlaced interval bar parameters and the features in the sample set of topographic parameters.

[0221] Furthermore, the device further includes: a second acquisition unit, used to acquire the function of the second neuron; the second acquisition unit is specifically used to:

[0222] Remove null value rows and outlier rows in the input sample set;

[0223] Normalize the input sample set after removing null value rows and outlier rows;

[0224] Calculate the cosine similarity between the features in the input sample set after normalization;

[0225] The similarity matrix of the input sample set after normalization is obtained by using the cosine similarity between the features in the input sample set after normalization. The similarity matrix of the input sample set after normalization is a function of the second neuron.

[0226] Furthermore, the calculation formula of the cosine similarity between the features in the input sample set after normalization includes:

[0227]

[0228] In the above formula, y1∈[1,H], y2∈[1,H], H is the total number of features in the input sample set after normalization; cos(θ y1,y2 ) is the cosine similarity between any two features y1 and y2 in the input sample set after normalization, p y1 is the vector of feature y1 in the input sample set after normalization, p y2 is the vector of feature y2 in the input sample set after normalization, ||p y1 || is the vector p y1 The module of ||p y2 || is the vector p y2 Model.

[0229] Furthermore, the calculation formula of the similarity matrix of the input sample set after normalization includes:

[0230]

[0231] In the above formula, h∈[1,H], H is the total number of features in the input sample set after normalization; F2 is the similarity matrix of the input sample set after normalization, cos(θ1,θ1) is the cosine similarity between the first feature and the first feature in the input sample set after normalization, cos(θ1,θ2) is the cosine similarity between the first feature and the second feature in the input sample set after normalization, and cos(θ1,θ2) is the cosine similarity between the first feature and the second feature in the input sample set after normalization. h ) is the cosine similarity between the first feature and the hth feature in the input sample set after normalization, cos(θ1, θ H ) is the cosine similarity between the first feature and the Hth feature in the input sample set after normalization, cos(θ2, θ1) is the cosine similarity between the second feature and the first feature in the input sample set after normalization, cos(θ2, θ2) is the cosine similarity between the second feature and the second feature in the input sample set after normalization, and cos(θ2, θ h ) is the cosine similarity between the second feature and the hth feature in the input sample set after normalization, cos(θ2,θ H ) is the cosine similarity between the second feature and the Hth feature in the input sample set after normalization, cos(θ h , θ1) is the cosine similarity between the hth feature and the first feature in the input sample set after normalization, cos(θ h , θ2) is the cosine similarity between the hth feature and the second feature in the input sample set after normalization, cos(θ h ,θ H ) is the cosine similarity between the hth feature and the hth feature in the input sample set after normalization, cos(θ h ,θ H ) is the cosine similarity between the hth feature and the Hth feature in the input sample set after normalization, cos(θ H , θ1) is the cosine similarity between the Hth feature and the first feature in the input sample set after normalization, cos(θ H , θ2) is the cosine similarity between the Hth feature and the second feature in the input sample set after normalization, cos(θ H ,θ h ) is the cosine similarity between the Hth feature and the hth feature in the input sample set after normalization, cos(θ H ,θ H ) is the cosine similarity between the Hth feature and the Hth feature in the input sample set after normalization.

[0232] Furthermore, the device further includes: a third acquisition unit, used to acquire a function of a third neuron; the third acquisition unit is specifically used to:

[0233] The features in the input sample set are clustered using the mean square value clustering method to obtain four clusters; the four clusters include: the cluster corresponding to the construction meteorological conditions sample set, the cluster corresponding to the structural parameters sample set of the under-construction line, the cluster corresponding to the topographic parameters sample set, and the cluster corresponding to the phase spacing rod parameters sample set;

[0234] Calculate the centroid of each cluster;

[0235] Using the centroid of each cluster, the minimum value of the standard deviation of the distance from each sample point in the four clusters to all the centroids is calculated, and the minimum value of the standard deviation of the distance from each sample point in the four clusters to all the centroids is a function of the third neuron.

[0236] Furthermore, the calculation formula for the minimum value of the standard deviation of the distance from each sample point to all centroids in the four clusters includes:

[0237] F3=min[(x r -p′1) 2 +(x r -p′2) 2 +(x r -p′3) 2 +(x r -p′4) 2 ]

[0238] In the above formula, r∈[1,R], R is the total number of sample points in the four clusters; F3 is the minimum value of the standard deviation of the distance from each sample point to all centroids in the four clusters, x r is the rth sample point in the four clusters, p′1 is the centroid of the cluster corresponding to the construction meteorological condition sample set, p′2 is the centroid of the cluster corresponding to the sample set of the structural parameters of the line under construction, p′3 is the centroid of the cluster corresponding to the sample set of the topographic parameters, and p′4 is the centroid of the cluster corresponding to the sample set of the phase spacing rod parameters.

[0239] Furthermore, the calculation formula of the function of the fourth neuron includes:

[0240]

[0241] In the above formula, H1(A, F, S) is the function of the fourth neuron, A is the dancing amplitude, F is the dancing frequency, S is the damage quantification value, max() is the maximum value of the matrix element, Round() is to round the value in brackets to an integer, F1 is the function of the first neuron, and F2 is the function of the second neuron; e1, e2, e3, e4 and e5 are all coefficients, and they are positive numbers.

[0242] Furthermore, the calculation formula of the function of the fifth neuron includes:

[0243]

[0244] In the above formula, H2(A, F, S) is the function of the fifth neuron, A is the dancing amplitude, F is the dancing frequency, S is the damage quantification value, max() is the maximum value of the matrix element, F2 is the function of the second neuron, F3 is the function of the third neuron, and H1(A, F, S) is the function of the fourth neuron.

[0245] It can be understood that the device embodiment provided above corresponds to the method embodiment described above, and the corresponding specific contents can be referenced to each other and will not be repeated here.

[0246] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.

[0247] Embodiment 3

[0248] like Figure 4 As shown, the present invention also provides an electronic device, which may be a computer device, a single-chip device, an intelligent mobile device, etc. The electronic device in this embodiment may include a processor, a memory, a transceiver component, etc. The memory, the processor, and the transceiver component are connected via a bus; the memory may be used to store an execution program, and an exemplary execution program may include instructions; the processor is used to execute the instructions stored in the memory. The memory may also be used to store data, which may be called and / or modified when the instructions are executed.

[0249] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions in a storage medium to implement the corresponding method flow or corresponding functions, so as to implement the steps of a power transmission infrastructure line anti-dance design method in the above embodiment.

[0250] Embodiment 4

[0251] Based on the same inventive concept, the present invention also provides a readable storage medium, specifically an electronic device readable storage medium (Memory), which is a memory device in the electronic device for storing programs and data. It can be understood that the storage medium here can include both the built-in storage medium in the electronic device and the extended storage medium supported by the electronic device. The storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and these instructions can be one or more execution programs (including program codes). It should be noted that the storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The processor loads and executes one or more instructions stored in the storage medium, which can implement the steps of a power transmission infrastructure line anti-dance design method in the above embodiment.

[0252] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0253] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0254] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0255] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0256] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for designing anti-dancing of power transmission infrastructure lines, characterized in that: include: Collect relevant information of power transmission infrastructure lines and forecast construction weather conditions at the time; Based on the preset multiple groups of initial design schemes of phase-to-phase spacing rod parameters, the relevant information of the power transmission infrastructure line and the construction meteorological conditions at the predicted time, a pre-established dancing parameter prediction model is used to predict multiple groups of dancing characteristic parameter data at the predicted time; Determine the optimal design scheme of interphase spacing rod parameters according to the plurality of groups of dancing characteristic parameter data of the predicted time; According to the optimal design scheme of phase-to-phase spacer parameters, anti-dancing design of power transmission infrastructure lines is carried out.

2. The method according to claim 1, characterized in that The relevant information of the power transmission infrastructure line includes: the structural parameters of the line under construction and the topographic parameters; The characteristics of the structural parameters of the line under construction include: conductor cross-sectional area, elastic modulus, operating tension, number of splits, span, hanging height, height difference and line strike angle; The characteristics of the topographic and geomorphic parameters include: basic topography and basic landforms. The basic topography includes: plains, hills, low mountains, medium mountains and high mountains; the basic landforms include: built-up areas, grasslands, forests, deserts and rivers and lakes.

3. The method according to claim 1, characterized in that The characteristics of the interphase spacer parameters include: rod material, length, stiffness, damping, connecting plate cross-sectional area, shed diameter and installation position; The characteristics of the construction meteorological conditions include: temperature, precipitation, wind speed, wind direction, humidity, irradiance, ice shape and ice thickness; The characteristics of the dancing characteristic parameters include: dancing amplitude, dancing frequency and whether the operation is damaged; wherein, when the operation is damaged, the characteristic of whether the operation is damaged also includes the degree of damage.

4. The method according to claim 1, characterized in that The design scheme based on the preset multiple groups of initial phase-to-phase spacing rod parameters, the relevant information of the transmission infrastructure line and the construction meteorological conditions at the predicted time, using the pre-established dancing parameter prediction model, predicts multiple groups of dancing characteristic parameter data at the predicted time, including: Taking the design scheme of each set of initial interphase spacing bar parameters, the relevant information of the power transmission infrastructure line and the construction meteorological conditions at the predicted time as the input of the dancing parameter prediction model, outputting the dancing characteristic parameter data at the predicted time corresponding to the design scheme of each set of initial interphase spacing bar parameters; The dancing characteristic parameter data at the predicted time corresponding to the design schemes of all groups of initial interphase spacer rod parameters are the plurality of groups of dancing characteristic parameter data at the predicted time.

5. The method according to claim 1, characterized in that The method of determining the optimal design scheme of interphase spacing rod parameters according to the plurality of groups of dancing characteristic parameter data of the predicted time includes: From the plurality of groups of dancing characteristic parameter data of the prediction time, selecting the initial design scheme of the interphase spacing rod parameters corresponding to the dancing characteristic parameter data that meets the first preset condition as the design scheme of the interphase spacing rod parameters to be determined; Based on the design schemes of the interphase spacer parameters to be determined, a nonlinear dynamics method is used to simulate and calculate the dancing amplitude and dancing frequency corresponding to each design scheme of the interphase spacer parameters to be determined; Determine whether the dancing amplitude and dancing frequency corresponding to the design schemes of the pending interphase spacing rod parameters meet the second preset condition. If there is a design scheme of the pending interphase spacing rod parameters whose corresponding dancing amplitude and dancing frequency meet the second preset condition, then the design scheme of the pending interphase spacing rod parameters is the optimal design scheme of the interphase spacing rod parameters; if the dancing amplitude and dancing frequency corresponding to the design schemes of all the pending interphase spacing rod parameters do not meet the second preset condition, adjust the multiple groups of initial design schemes of the interphase spacing rod parameters, and use the adjusted multiple groups of initial design schemes of the interphase spacing rod parameters to re-determine the optimal design scheme of the interphase spacing rod parameters.

6. The method according to claim 1, characterized in that The process of acquiring the pre-established dancing parameter prediction model includes: The input sample set is constructed by using the collected historical construction meteorological conditions, historical structural parameters of the line under construction, historical topographic parameters and historical phase spacing bar parameters; Using the collected historical dancing feature parameters, an output sample set is constructed; The improved neural network model is trained using the input sample set and the output sample set to obtain the dancing parameter prediction model.

7. The method according to claim 6, characterized in that The improved neural network model comprises: an input layer, a first hidden layer, a second hidden layer and an output layer connected in sequence; The first hidden layer includes: a first neuron, a second neuron and a third neuron; The second hidden layer includes: a fourth neuron and a fifth neuron; The input of the input layer is the structural parameters of the line under construction, the topographic parameters, the phase spacing parameters and the construction meteorological conditions, and the output of the input layer is the input of the first hidden layer; The input of the second hidden layer is the output of the first hidden layer, and the output of the second hidden layer is the input of the output layer; The output of the output layer is dancing feature parameters.

8. The method according to claim 7, characterized in that The input sample set includes: construction meteorological condition sample set Q i , the sample set of structural parameters of the line under construction C j , topographic and geomorphic parameter sample set D k and interphase spacing bar parameter sample set B m ; Among them, i∈[1,M], M is the total number of features in the construction meteorological conditions; j∈[1,N], N is the total number of features in the structural parameters of the line under construction; k∈[1,P], P is the total number of features in the terrain parameters; m∈[1,E], E is the total number of features in the phase spacing parameters.

9. The method according to claim 8, characterized in that The process of acquiring the function of the first neuron includes: Performing standardization on each feature in the input sample set to obtain a standardized input sample set; Calculate the covariance between the features in the input sample set after standardization; The function of the first neuron is calculated by using the covariance between the features in the input sample set after the standardization process.

10. The method according to claim 9, characterized in that The calculation formula of the function of the first neuron includes: In the above formula, F1 is the function of the first neuron, EigentValues|| is the eigenvalue of the 3×3 covariance matrix in the brackets||, and cov(Q i ,C j ) is the covariance of the features in the construction meteorological conditions sample set and the features in the structural parameters sample set of the line under construction, cov(Q i ,D k ) is the covariance of the characteristics in the construction meteorological conditions sample set and the characteristics in the topographic parameters sample set, cov(Q i ,B m ) is the covariance of the characteristics in the construction meteorological conditions sample set and the characteristics in the interphase spacing bar parameter sample set, cov(C j ,Q i ) is the covariance of the features in the sample set of structural parameters of the line under construction and the features in the sample set of construction meteorological conditions, cov(C j ,D k ) is the covariance of the features in the sample set of structural parameters of the line under construction and the features in the sample set of topographic parameters, cov(C j ,B m ) is the covariance of the features in the sample set of the structural parameters of the line under construction and the features in the sample set of the phase spacing rod parameters, cov(B m ,Q i ) is the covariance of the characteristics of the interphase spacing rod parameter sample set and the characteristics of the construction meteorological condition sample set, cov(B m ,C j ) is the covariance of the features in the sample set of interphase spacing bar parameters and the features in the sample set of the structure parameters of the line under construction, cov(B m ,D k ) is the covariance of the features in the sample set of interlaced bar parameters and the features in the sample set of topographic parameters.

11. The method according to claim 8, characterized in that The process of acquiring the function of the second neuron includes: Remove null value rows and outlier rows in the input sample set; Normalize the input sample set after removing null value rows and outlier rows; Calculate the cosine similarity between the features in the input sample set after normalization; The similarity matrix of the input sample set after normalization is obtained by using the cosine similarity between the features in the input sample set after normalization, and the similarity matrix of the input sample set after normalization is a function of the second neuron.

12. The method according to claim 11, characterized in that The calculation formula of the cosine similarity between the features in the input sample set after normalization includes: In the above formula, y1∈[1,H], y2∈[1,H], H is the total number of features in the input sample set after normalization; cos(θ y1,y2 ) is the cosine similarity between any two features y1 and y2 in the input sample set after normalization, p y1 is the vector of feature y1 in the input sample set after normalization, p y2 is the vector of feature y2 in the input sample set after normalization, ||p y1 || is the vector p y1 The module of ||p y2 || is the vector p y2 Model.

13. The method according to claim 11, characterized in that The calculation formula of the similarity matrix of the input sample set after normalization includes: In the above formula, h∈[1,H], H is the total number of features in the input sample set after normalization; F2 is the similarity matrix of the input sample set after normalization, cos(θ1,θ1) is the cosine similarity between the first feature and the first feature in the input sample set after normalization, cos(θ1,θ2) is the cosine similarity between the first feature and the second feature in the input sample set after normalization, and cos(θ1,θ2) is the cosine similarity between the first feature and the second feature in the input sample set after normalization. h ) is the cosine similarity between the first feature and the hth feature in the input sample set after normalization, cos(θ1, θ H ) is the cosine similarity between the first feature and the Hth feature in the input sample set after normalization, cos(θ2, θ1) is the cosine similarity between the second feature and the first feature in the input sample set after normalization, cos(θ2, θ2) is the cosine similarity between the second feature and the second feature in the input sample set after normalization, and cos(θ2, θ h ) is the cosine similarity between the second feature and the hth feature in the input sample set after normalization, cos(θ2,θ H ) is the cosine similarity between the second feature and the Hth feature in the input sample set after normalization, cos(θ h , θ1) is the cosine similarity between the hth feature and the first feature in the input sample set after normalization, cos(θ h , θ2) is the cosine similarity between the hth feature and the second feature in the input sample set after normalization, cos(θ h ,θ h ) is the cosine similarity between the hth feature and the hth feature in the input sample set after normalization, cos(θ h ,θ H ) is the cosine similarity between the hth feature and the Hth feature in the input sample set after normalization, cos(θ H , θ1) is the cosine similarity between the Hth feature and the first feature in the input sample set after normalization, cos(θ H , θ2) is the cosine similarity between the Hth feature and the second feature in the input sample set after normalization, cos(θ H ,θ h ) is the cosine similarity between the Hth feature and the hth feature in the input sample set after normalization, cos(θ H ,θ H ) is the cosine similarity between the Hth feature and the Hth feature in the input sample set after normalization.

14. The method according to claim 8, characterized in that The process of acquiring the function of the third neuron includes: The features in the input sample set are clustered using a mean square value clustering method to obtain four clusters; the four clusters include: a cluster corresponding to a construction meteorological condition sample set, a cluster corresponding to a sample set of structural parameters of the line under construction, a cluster corresponding to a sample set of topographic parameters, and a cluster corresponding to a sample set of interphase spacing rod parameters; Calculate the centroid of each cluster; The minimum value of the standard deviation of the distance from each sample point in the four clusters to all the mass centers is calculated using the mass center of each cluster, and the minimum value of the standard deviation of the distance from each sample point in the four clusters to all the mass centers is a function of the third neuron.

15. The method according to claim 14, characterized in that The calculation formula for the minimum value of the standard deviation of the distance from each sample point to all centroids in the four clusters includes: F3=min[(x r -p′1) 2 +(x r -p′2) 2 +(x r -p′3) 2 +(x r -p′4) 2 ] In the above formula, r∈[1,R], R is the total number of sample points in the four clusters; F3 is the minimum value of the standard deviation of the distance from each sample point to all centroids in the four clusters, x r is the rth sample point in the four clusters, p′1 is the centroid of the cluster corresponding to the construction meteorological condition sample set, p′2 is the centroid of the cluster corresponding to the sample set of the structural parameters of the line under construction, p3′ is the centroid of the cluster corresponding to the sample set of the topographic parameters, and p′4 is the centroid of the cluster corresponding to the sample set of the phase spacing rod parameters.

16. The method according to claim 8, characterized in that The calculation formula of the function of the fourth neuron includes: In the above formula, H1(A, F, S) is the function of the fourth neuron, A is the dancing amplitude, F is the dancing frequency, S is the damage quantification value, max() is the maximum value of the matrix elements, Round() is rounding the values ​​in brackets to integers, F1 is the function of the first neuron, and F2 is the function of the second neuron; e1, e2, e3, e4 and e5 are all coefficients, and are positive numbers.

17. The method according to claim 8, characterized in that The calculation formula of the function of the fifth neuron includes: In the above formula, H2(A, F, S) is the function of the fifth neuron, A is the dancing amplitude, F is the dancing frequency, S is the damage quantification value, max() is the maximum value of the matrix element, F2 is the function of the second neuron, F3 is the function of the third neuron, and H1(A, F, S) is the function of the fourth neuron.

18. A power transmission infrastructure line anti-dancing design device, characterized in that: include: A collection unit is used to collect relevant information of power transmission infrastructure lines and construction meteorological conditions at the predicted time; A prediction unit, for predicting multiple groups of dancing characteristic parameter data at the prediction time based on multiple groups of preset initial phase-to-phase spacing bar parameter design schemes, relevant information of the power transmission infrastructure line and the construction meteorological conditions at the prediction time, using a pre-established dancing parameter prediction model; A determination unit, used to determine the optimal design scheme of the interphase spacing rod parameters according to the plurality of groups of dancing characteristic parameter data of the predicted time; The design unit is used to perform anti-dancing design of the power transmission infrastructure line according to the optimal design scheme of the phase-to-phase spacing rod parameters.

19. An electronic device, characterized in that: include: at least one processor and memory; The memory and the processor are connected via a bus; The memory is used to store one or more programs; When the one or more programs are executed by the at least one processor, the power transmission infrastructure line anti-dancing design method according to any one of claims 1 to 17 is implemented.

20. A readable storage medium, characterized in that: An execution program is stored thereon, and when the execution program is executed, the power transmission infrastructure line anti-dancing design method as described in any one of claims 1 to 17 is implemented.

Images