Transmission tower conductor galloping early warning method combined with multi-factor coupling model

Abstract

The invention relates to the technical field of power transmission line galloping early warning, in particular to a power transmission tower wire galloping early warning method combined with a multi-factor coupling model, and the method comprises the steps: comparing the differences between all types of feature values of each wire at the current moment and the effective values of the feature values, and determining a bearing deviation; comparing the displacement speed of each position point on each lead in any direction with the deviation of a fitting result, and determining a lead galloping transmission value; analyzing the distance from each position point on each lead to the power transmission tower at the current moment, and determining a lead galloping judgment value in combination with the bearing deviation and the lead galloping transmission value so as to obtain corrected displacement data; and obtaining a conductor galloping model by adopting sparse regression, and carrying out early warning on conductor galloping. The invention aims to improve the accuracy of transmission tower wire galloping early warning.

Description

Technical Field

[0001] This application relates to the technical field of transmission line galloping warning, and specifically relates to a method for warning of conductor galloping on transmission towers by combining a multi-factor coupling model. Background Art

[0002] Transmission towers are important structures in the power system for supporting and fixing transmission lines. They are usually supported by steel or concrete, and the key task of transmitting electrical energy from the power station to the user end is achieved by erecting the transmission lines. The location selection of transmission towers often depends on the specific terrain structure. Due to the limitations of power stations, transmission towers are usually built in areas with large terrain undulations and obvious height differences. Under cold climate conditions, transmission lines are prone to icing due to weather such as rain, snow, and freezing rain. Icing will change the aerodynamic characteristics of the conductors, resulting in the phenomenon of conductor galloping under the action of wind load. Conductor galloping is a low-frequency, large-amplitude periodic vibration, which can cause fatigue damage to the conductors, short circuits between adjacent conductors, arc discharges, and even damage to the structure of the transmission tower. Therefore, a warning method based on conductor galloping on transmission towers is needed.

[0003] Currently, in the process of analyzing conductor galloping on transmission towers, only the vertical-horizontal coupling galloping mode is analyzed, while the galloping phenomenon of the conductor in the axial direction under icing conditions is ignored. In actual operation, due to the failure to fully consider the influence of conductor axial galloping, the accuracy of conductor galloping analysis is not high, resulting in the warning system being unable to accurately predict the dynamic behavior of the conductors and reducing the accuracy of conductor galloping warning. Summary of the Invention

[0004] In order to solve the above technical problems, this application provides a method for warning of conductor galloping on transmission towers by combining a multi-factor coupling model to solve the existing problems.

[0005] The method for warning of conductor galloping on transmission towers by combining a multi-factor coupling model of this application adopts the following technical solutions: An embodiment of this application provides a method for warning of conductor galloping on transmission towers by combining a multi-factor coupling model. The method includes the following steps: Data acquisition: Real-time obtain various characteristic values of each conductor on the transmission tower, displacement data and displacement velocities of all position points on each conductor in different directions, as well as real-time wind speed and wind direction; Galloping analysis: Analyze the distribution of various characteristic values of the conductors and displacement deviations to determine the corrected displacement data. Specifically: Analyze the distribution of the squares of various characteristic values of each conductor within a preset time period before the current moment to determine the effective values of various characteristic values of each conductor at the current moment. Compare the differences between all types of characteristic values of each conductor at the current moment and their effective values to determine the bearing deviation of each conductor at the current moment; Fit the displacement velocity of all position points on each wire at the current moment in any direction, compare the deviation between the displacement velocity of each position point on each wire in any direction and the fitting result, and determine the wire galloping transfer value of each position point on each wire in any direction at the current moment; Analyze the distance from each position point on each wire to the transmission tower at the current moment, and combine the bearing deviation and the wire galloping transfer value to determine the wire galloping judgment value of each position point on each wire in any direction at the current moment; Based on the wire galloping judgment value, for any direction, select the abnormal position points from all position points on each wire at the current moment, and correct the displacement of all abnormal position points in any direction to obtain the corrected displacement data of all position points on each wire in any direction at the current moment; Wire health management: Use sparse regression to model the corrected displacement data of all position points on each wire at the current moment in any direction, all types of characteristic values of each wire, as well as wind speed and wind direction, to obtain the wire galloping model of each wire at the current moment and give an early warning of wire galloping.

[0006] Preferably, the characteristic values at least include: tensile value, inclination value and axial angle.

[0007] Preferably, the effective value of all types of characteristic values of each wire at the current moment is: the square root of the mean of the squared values of all types of characteristic values of each wire within a preset time period before the current moment.

[0008] Preferably, the expression of the bearing deviation of each wire at the current moment is: ; where, represents the bearing deviation of the j-th wire at the current moment; represents the effective value of the i-th type of characteristic value of the j-th wire at the current moment; represents the i-th type of characteristic value of the j-th wire at the current moment; n represents the total number of categories of characteristic values.

[0009] Preferably, the expression of the wire galloping transfer value of each position point on each wire in any direction at the current moment is: ; where, represents the wire galloping transfer value of the k-th position point on the j-th wire in the m-th direction at the current moment; represents the deviation between the displacement velocity of the k-th position point on the j-th wire in the m-th direction and the fitting result at the current moment; represents the mean of the deviations between the displacement velocities of the k-th position point on the j-th wire in all directions and the fitting result at the current moment.

[0010] Preferably, the expression of the conductor galloping determination value at each position point on each conductor at the current moment in any direction is: ; in the formula, represents the conductor galloping determination value of the position point k on the j-th conductor at the current moment in the direction m; represents the distance from the position point k on the j-th conductor to the transmission tower at the current moment; ln( ) represents the logarithmic function with the natural constant as the true number; norm[ ] represents the normalization function.

[0011] Preferably, the method for obtaining the abnormal position points is: Taking the conductor galloping determination values of all position points on each conductor at the current moment in any direction as the input of the threshold segmentation algorithm, outputting the segmentation threshold, and marking the position points where the conductor galloping determination value is greater than the segmentation threshold as the abnormal position points of each conductor at the current moment in any direction.

[0012] Preferably, the method for obtaining the corrected displacement data of all position points on each conductor at the current moment in any direction is: Among all position points on each conductor at the current moment, keeping the displacement data at non-abnormal position points unchanged, removing the displacement data at abnormal position points in the direction m, filling the missing displacement data at abnormal position points by using the non-linear interpolation method, and taking the filled data as the corrected displacement data at abnormal position points. Traversing all directions, the corrected displacement data of all position points on each conductor at the current moment in any direction is obtained.

[0013] Preferably, the method for obtaining the conductor galloping model of each conductor at the current moment is: Taking the corrected displacement data of all position points on each conductor at the current moment in any direction, all types of characteristic values of each conductor, as well as the wind speed and wind direction as the input of the sparse regression, and taking the output equation as the conductor galloping model of each conductor at the current moment.

[0014] Preferably, the early warning of conductor galloping includes: Taking the conductor galloping models of all conductors at the current moment as the input of the neural network, outputting the distance between two conductors. If the distance between two conductors at the current moment is less than the preset safety distance threshold, triggering the conductor galloping safety warning, otherwise, not triggering the conductor galloping safety warning.

[0015] This application has at least the following beneficial effects: This application collects relevant data during the galloping of the conductor in real time. By analyzing the distribution of conductor eigenvalue and displacement deviation, a bearing deviation is constructed, which reflects the influence of the conductor galloping amplitude on the transmission tower, and can timely detect abnormal conditions during the conductor galloping, so as to take corresponding measures to ensure the safe operation of the transmission line. Further, by analyzing the displacement characteristics of the conductor in different directions, a conductor galloping transfer value is constructed, which reflects the galloping transfer characteristics between each position point of the conductor, helps to judge the abnormal conditions of conductor galloping, improves the accuracy of conductor galloping early warning, and thus ensures the safe operation of the transmission line. Further, by comprehensively considering the bearing deviation, the conductor galloping transfer value and the distance from the position point to the transmission tower, a conductor galloping judgment value is constructed, which quantifies the severity of conductor galloping, so as to timely detect abnormal galloping conditions and improve the accuracy of conductor galloping early warning. Further, based on the conductor galloping judgment value, the displacement data is corrected to obtain a conductor galloping model, so as to predict the development trend of conductor galloping and improve the accuracy of conductor galloping early warning. This application combines a multi-factor coupling model to realize the prediction and early warning of conductor galloping on transmission towers, and improves the accuracy of conductor galloping early warning on transmission towers. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained according to these drawings.

[0017] Figure 1 It is a flowchart of the steps of a method for early warning of conductor galloping on a transmission tower combining a multi-factor coupling model provided by an embodiment of the present application; Figure 2 It is a schematic diagram of the acquisition process of corrected displacement data provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] In order to further elaborate on the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the following combines the drawings and preferred embodiments to describe in detail the specific implementation manner, structure, characteristics and effects of the method for early warning of conductor galloping on a transmission tower combining a multi-factor coupling model according to the present application. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art belonging to the technical field of the present application.

[0020] The following specifically describes the specific solution of the transmission tower conductor galloping warning method combining a multi-factor coupling model with reference to the accompanying drawings.

[0021] A transmission tower conductor galloping warning method combining a multi-factor coupling model provided by an embodiment of the present application specifically provides the following transmission tower conductor galloping warning method combining a multi-factor coupling model. Please refer to Figure 1 This method includes the following steps: Step S1: Data collection: Real-time obtain various characteristic values of each conductor on the transmission tower, displacement data and displacement speeds of all position points on each conductor in different directions, as well as real-time wind speed and wind direction.

[0022] To achieve accurate warning of the conductor galloping process in the transmission tower, data collection of the conductors on the transmission tower is required. Specifically: Respectively use a tension detector, an inclination detector, and a fiber optic gyroscope to collect various characteristic values of each conductor on the transmission tower in real time, that is, the tension value, the inclination value, and the axial angle. At the same time, position points are set at equal intervals on the conductor, and a displacement sensor is used to obtain the displacement data and displacement speeds of all position points on each conductor in different directions in real time, and a wind speed sensor and a wind direction sensor are used to collect the wind speed and wind direction in the environment where the conductor is located in real time, providing basic data support for the health management and galloping warning of the conductor.

[0023] It should be noted that during the conductor galloping process, the conductor galloping is often low-frequency galloping with low frequency and large amplitude. Therefore, in this embodiment, the data collection frequency is 1 Hz, and the interval between position points is 0.5 m. Implementers can also set the values of the collection frequency and the interval between position points according to specific situations. This embodiment does not make special restrictions.

[0024] So far, by collecting information such as the displacement data, wind speed, and wind direction of the conductor in real time, the galloping state of the conductor is continuously monitored. Using data analysis technology, in-depth analysis of various characteristic values of the conductor is carried out to identify the normal operation range and potential abnormal modes of the conductor, so as to issue a warning to prompt the maintenance personnel to conduct health management on the conductor.

[0025] Step S2: Galloping analysis: Analyze the distribution of various characteristic values of the conductor and the displacement deviation to determine the corrected displacement data.

[0026] In the process of traditional conductor galloping modeling, it is assumed that the conductor has a circular cross-section characteristic. After the conductor is ice-covered, only the weight of the conductor is changed, and the aerodynamic conditions of the conductor are not changed in the actual process. At the same time, the conductor is considered to be rigid. Therefore, there are only vertical and horizontal movements at the same position point of the conductor. In the actual process, in order to reduce the influence of thermal expansion and contraction of the conductor between adjacent transmission towers, there is a certain length margin when the conductor is erected. When the conductor is in an ice-covered state, there is an ice-covered cross-section on the back side of the conductor under the action of gravity, which affects the aerodynamic layout of the conductor. Therefore, there is an axial movement in the actual conductor galloping process, and a three-degree-of-freedom modeling of the conductor galloping is required.

[0027] In addition, due to the limitations of the data sensor acquisition accuracy and environmental noise, the accuracy of the conductor galloping in the actual modeling model deviates greatly from the actual galloping situation. Therefore, it is necessary to analyze the distribution of various characteristic values of the conductor and the displacement deviation, determine the corrected displacement data, so as to improve the model establishment accuracy. The specific process is as follows: S201: Analyze the distribution of the squares of various characteristic values of each conductor within a preset time period before the current moment, determine the effective values of various characteristic values of each conductor at the current moment, compare the differences between all types of characteristic values of each conductor at the current moment and their effective values, and determine the bearing deviation of each conductor at the current moment.

[0028] In the process of conductor galloping modeling, the accuracy of the final galloping model depends on the accuracy of the conductor displacement data. In the actual acquisition process, it is easily affected by the terrain distribution and wind vibration between transmission towers, and the data accuracy in conductor galloping modeling is low. Especially during the conductor galloping process, the axial movement amount is often small and is more easily affected by environmental noise. Therefore, it is necessary to preprocess the acquired data.

[0029] It should be noted that in the state of no wind and no ice cover, the shapes and weights of the six-conductor bundle are defaulted to be the same, and the meteorological and rainfall conditions meet the basic conditions for conductor icing.

[0030] Taking a single conductor as an example, the characteristic values collected at the connection of each conductor to the transmission tower include the tension value, the inclination angle value, and the axial angle. The galloping degree of the conductor can be reflected through the characteristic values. When the conductor gallops under the action of wind force, the conductor approximately presents the characteristics of periodic galloping, so that the characteristic values of the conductor present the characteristics of approximate periodic fluctuations. Therefore, when the numerical value of the characteristic value fluctuation is larger within a period of time and the gap from the initial value of the conductor characteristic is larger, it indicates that the galloping situation of the conductor is greater at this time.

[0031] Therefore, based on the above analysis, by analyzing the distribution of various characteristic values, the bearing deviation of each conductor at the current moment is determined, specifically: Take the square root of the mean of the squared values of various characteristic values of each wire within a preset time period before the current moment, and denote it as the effective value of various characteristic values of each wire at the current moment; It should be noted that the value of the preset time period is set artificially. In this embodiment, the value of the preset time period is 5 minutes. The implementer can also set it according to specific circumstances by himself / herself, and this embodiment does not make special restrictions.

[0032] Furthermore, based on the difference between various characteristic values of each wire and its effective value at the current moment, determine the load deviation of each wire at the current moment. The specific expression is: The load deviation of the j-th wire at the current moment The expression is: ; In the formula, represents the effective value of the i-th type of characteristic value of the j-th wire at the current moment; represents the i-th type of characteristic value of the j-th wire at the current moment; n represents the total number of types of characteristic values.

[0033] It can be analyzed from the load deviation of each wire at the current moment that: if the difference between the effective value of the i-th type of characteristic value of the j-th wire and the corresponding characteristic value at the current moment is larger, the load deviation is larger, which means that the amplitude of the wire galloping is larger and may cause a larger dynamic load on the tower structure; on the contrary, if the difference between the effective value of the i-th type of characteristic value of the j-th wire and the corresponding characteristic value at the current moment is smaller, the load deviation is smaller, which means that the amplitude of the wire galloping is smaller, the impact on the tower structure is smaller, and the safety is higher.

[0034] So far, by accurately calculating the load deviation of the wire, a quantitative index is provided for the early warning of wire galloping, which helps to identify the potential safety risks of wire galloping, timely conduct health management on the wire, and ensure the stable operation of the transmission tower wire.

[0035] S202: Fit the displacement velocity of all position points on each wire at the current moment in any direction, compare the deviation between the displacement velocity of each position point on each wire in any direction and the fitting result, and determine the wire galloping transfer value of each position point on each wire in any direction at the current moment.

[0036] During the actual wire galloping process between transmission towers, since the wire is a whole, the galloping displacements and velocities between various position points on a single wire have certain transfer characteristics, that is, the galloping situation of a certain position point on a single wire is at a certain moment point in the whole galloping cycle.

[0037] Based on the above analysis, by comparing the deviation between the displacement velocity of each position point on each wire in any direction and the fitting result, the wire galloping transfer value of each position point on each wire in any direction at the current moment is determined, specifically as follows: Fit the displacement velocity of all position points on each wire in any direction at the current moment. Among them, in this embodiment, the least squares fitting method is used to fit the displacement velocity. In the actual application process, as other implementation manners, the implementer can also use other fitting methods such as polynomial fitting in combination with specific situations. Regarding the selection of the fitting method, this embodiment does not make special restrictions.

[0038] Among them, the least squares fitting method is a well-known technology, and its specific fitting principle process will not be elaborated here.

[0039] Furthermore, determine the wire galloping transfer value, and the specific expression is: The wire galloping transfer value of the position point k on the j-th wire in the direction m at the current moment The expression is: ; In the formula, represents the deviation between the displacement velocity of the position point k on the j-th wire in the direction m at the current moment and the fitting result; represents the average value of the deviations between the displacement velocities of the position point k on the j-th wire in all directions and the fitting result at the current moment.

[0040] It should be supplemented that the deviation between the displacement velocity and the fitting result in the expression of the wire galloping transfer value is the result of taking the absolute value of the difference between the displacement velocity and the fitting result.

[0041] It should be noted that for a single position point, there may be three degrees of freedom of displacement modes. In this embodiment, at least three directions, namely the horizontal direction x, the axial direction y, and the vertical direction z, are considered.

[0042] It can be understood from the wire galloping transfer value of each position point on each wire in any direction at the current moment that if the difference between the deviation between the displacement velocity of the position point k on the j-th wire in the direction m at the current moment and the fitting result and the average value of the deviations is smaller, then the wire galloping transfer value of the position point k on the j-th wire in the direction m at the current moment is smaller, indicating that the measured displacement velocity at the position point k in the direction m is normal; on the contrary, if the difference between the deviation between the displacement velocity of the position point k on the j-th wire in the direction m at the current moment and the fitting result and the average value of the deviations is larger, then the wire galloping transfer value of the position point k on the j-th wire in the direction m at the current moment is larger, indicating that the measured displacement velocity at the position point k in the direction m is abnormal.

[0043] So far, by comparing the deviation between the actual displacement linear velocity and the fitting result, the conductor galloping transfer value is calculated, which helps to monitor the real-time state of the conductor and is crucial for conductor galloping early warning and the health management of the conductor, ensuring the safe and stable operation of the transmission line.

[0044] S203: Analyze the distances from each position point on each conductor at the current moment to the transmission tower, and combine the bearing deviation and the conductor galloping transfer value to determine the conductor galloping judgment value in any direction for each position point on each conductor at the current moment.

[0045] During the process of conductor galloping transfer, the galloping parameters between individual position points are similar throughout the conductor. The greater the deviation of the conductor galloping transfer function, the greater the possibility that the measured value in this direction is abnormal, and filtering and screening are required.

[0046] Therefore, analyze the distances from each position point on each conductor at the current moment to the transmission tower, and combine the bearing deviation and the conductor galloping transfer value to determine the conductor galloping judgment value in any direction for each position point on each conductor at the current moment. Specifically: The conductor galloping judgment value of position point k on the j-th conductor at the current moment in direction m The expression is: ; In the formula, represents the distance from position point k on the j-th conductor to the transmission tower at the current moment; ln( ) represents the logarithmic function with the natural constant as the true number; norm[ ] represents the normalization function.

[0047] It can be understood from the conductor galloping judgment value of each position point on each conductor in any direction at the current moment that if the bearing deviation of the j-th conductor at the current moment is greater, it means that the tension of the conductor on the tower is abnormal, and it is more likely to be caused by abnormal conductor galloping. The greater the conductor galloping transfer value of position point k on the j-th conductor in direction m at the current moment, it means that the conductor galloping is abnormal in the m direction at position point k, and the smaller the distance, it means that position point k is closer to the transmission tower, and the conductor galloping is more restricted by the tower. Therefore, the greater the comprehensive conductor galloping judgment value, the more serious the galloping problem; on the contrary, if the bearing deviation of the j-th conductor at the current moment is smaller, it means that the tension of the conductor on the tower is close to normal. The smaller the conductor galloping transfer value of position point k on the j-th conductor in direction m at the current moment, it means that the conductor galloping is normal in the m direction at position point k, and the greater the distance, it means that position point k is farther away from the transmission tower, and the conductor galloping is more free. Therefore, the smaller the comprehensive conductor galloping judgment value, the less serious the galloping problem.

[0048] At this point, based on the three key factors of the distance from the location point to the pole tower, the load deviation and the conductor galloping transfer value, the abnormal degree of the conductor galloping in any direction is quantified, and the conductor galloping judgment value is obtained. The health status of the conductor can be effectively monitored, providing a basis for conductor galloping warning and health management, and ensuring the safety of the transmission line.

[0049] S204: Based on the wire galloping determination value, for any direction, an abnormal position point is selected from all position points on each wire at the current moment, and the displacement of all abnormal position points in any direction is corrected to obtain corrected displacement data of all position points on each wire at the current moment in any direction.

[0050] The wire galloping judgment value of all position points on each wire in any direction at the current moment is used as the input of the threshold segmentation algorithm, and the segmentation threshold is output. The position point where the wire galloping judgment value is greater than the segmentation threshold is recorded as the abnormal position point of each wire in any direction at the current moment.

[0051] It should be noted that the maximum inter-class variance algorithm is used in this embodiment to obtain the segmentation threshold. In actual application, as other implementation methods, implementers can also use other methods such as cross-validation in combination with specific circumstances. This embodiment does not impose any special restrictions.

[0052] In addition, it should be understood that there are many commonly used nonlinear interpolation methods. In this embodiment, the spline interpolation method is used to fill in the missing data. In actual application, as other implementation methods, the implementer may also use other nonlinear interpolation methods such as radial basis function interpolation. Regarding the selection of nonlinear interpolation methods, this embodiment does not impose any special restrictions.

[0053] Among them, the maximum inter-class variance and spline interpolation are both well-known technologies, and their specific principles are not described in detail again.

[0054] Furthermore, among all the position points on each conductor at the current moment, the displacement data at the non-abnormal position points are kept unchanged, the displacement data at the abnormal position points in the direction m are eliminated, and the vacant displacement data at the abnormal position points are filled with a nonlinear interpolation method. The filled data are used as the corrected displacement data at the abnormal position points, and all directions are traversed to obtain the corrected displacement data of all the position points on each conductor at the current moment in any direction.

[0055] Preferably, the schematic diagram of the correction displacement data acquisition process provided in this embodiment is as follows: Figure 2 shown.

[0056] Thus, by using the corrected displacement data of all position points on each wire in any direction, the data quality is improved, providing accurate basic data for wire health management and galloping early warning. The corrected displacement data is the key to ensuring the safe operation of the transmission line, enabling more accurate monitoring and analysis of wire galloping, and taking timely measures for wire galloping early warning and health management to prevent potential risks.

[0057] Step S3: Wire health management: Use sparse regression to model the corrected displacement data of all position points on each wire in any direction, all types of characteristic values of each wire, as well as wind speed and wind direction at the current moment, to obtain the wire galloping model of each wire at the current moment and issue an early warning for wire galloping.

[0058] Take the corrected displacement data of all position points on each wire in any direction, all types of characteristic values of each wire, as well as wind speed and wind direction at the current moment as the input of sparse identification of nonlinear dynamics (SINDy), and the output equation is used as the wire galloping model of each wire at the current moment. Among them, in this embodiment, the function library in the sparse identification of nonlinear dynamics (SINDy) includes nonlinear basis functions such as polynomial functions, trigonometric functions, exponential functions, and power functions.

[0059] In this embodiment, use a long short-term memory network (LSTM) to predict the wire galloping model of each wire at the current moment to obtain the distance between two wires at the current moment. If the distance between two wires at the current moment is less than the preset safety distance threshold, trigger a wire galloping safety warning and send a warning prompt to the operation and maintenance personnel to enable the operation and maintenance personnel to take measures for wire galloping health management; otherwise, if the distance between two wires at the current moment is greater than or equal to the preset safety distance threshold, do not trigger a wire galloping safety warning.

[0060] It should be noted that the value of the preset safety distance threshold of the wire usually depends on various factors, including the material of the wire, design standards, environmental conditions, voltage level of the line, and relevant standards. In this embodiment, it is assumed that the wire operates at 110 kV. At this time, the value of the preset safety distance is 2 m. Implementers can also set it according to specific situations, and this embodiment does not make special restrictions.

[0061] Among them, the sparse identification of nonlinear dynamics (SINDy) and the long short-term memory network (LSTM) are both well-known technologies, and their specific principle processes will not be elaborated here.

[0062] It should be noted that: the above order of the embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. In addition, the specific embodiments of this specification have been described. Moreover, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0063] The various embodiments in this specification are all described in a progressive manner. For the same or similar parts between the various embodiments, reference can be made to each other, and the key point of each embodiment is to illustrate the differences from other embodiments.

[0064] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; modifying the technical solutions recorded in the foregoing embodiments, or equivalently replacing some of the technical features, does not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the various embodiments of the present application, and should all be included within the protection scope of the present application.

Claims

1. A transmission tower conductor galloping warning method combining a multi-factor coupling model is characterized in that: The method comprises the following steps: Data collection: Real-time acquisition of various characteristic values ​​of each conductor on the transmission tower, displacement data and displacement speed of all position points on each conductor in different directions, as well as real-time wind speed and direction; Galloping analysis: Analyze the distribution of various characteristic values ​​and displacement deviation of the conductor to determine the corrected displacement data, specifically: Analyze the distribution of the squares of various characteristic values ​​of each conductor within a preset time before the current moment, determine the effective value of various characteristic values ​​of each conductor at the current moment, compare the difference between all characteristic values ​​of each conductor at the current moment and its effective value, and determine the load deviation of each conductor at the current moment; Fit the displacement speed of all position points on each wire in any direction at the current moment, compare the deviation between the displacement speed of each position point on each wire in any direction and the fitting result, and determine the wire galloping transfer value of each position point on each wire in any direction at the current moment; Analyze the distance from each position point on each conductor to the transmission tower at the current moment, and determine the conductor galloping determination value of each position point on each conductor in any direction at the current moment in combination with the load deviation and the conductor galloping transfer value; Based on the wire galloping determination value, for any direction, an abnormal position point is selected from all position points on each wire at the current moment, and the displacement of all abnormal position points in any direction is corrected to obtain corrected displacement data of all position points on each wire at the current moment in any direction; Wire health management: Sparse regression is used to model the corrected displacement data of all position points on each wire in any direction at the current moment, all class feature values ​​of each wire, and wind speed and direction, to obtain the wire dancing model of each wire at the current moment and issue an early warning for wire dancing.

2. The transmission tower conductor galloping early warning method combined with a multi-factor coupling model as claimed in claim 1 is characterized in that: The characteristic values ​​at least include: tension value, inclination value and axial angle.

3. The transmission tower conductor galloping early warning method combined with a multi-factor coupling model as claimed in claim 1 is characterized in that: The effective value of each characteristic value of each conductor at the current moment is: the square root of the average of the square values ​​of each characteristic value of each conductor within a preset time period before the current moment.

4. The transmission tower conductor galloping early warning method combined with a multi-factor coupling model as claimed in claim 1 is characterized in that: The expression of the load deviation of each wire at the current moment is: ; In the formula, represents the load deviation of the jth conductor at the current moment; It represents the effective value of the ith characteristic value of the jth conductor at the current moment; represents the i-th eigenvalue of the j-th wire at the current moment; n represents the total number of eigenvalue categories.

5. The transmission tower conductor galloping early warning method combined with a multi-factor coupling model as claimed in claim 4 is characterized in that: The expression of the wire galloping transfer value of each position point on each wire in any direction at the current moment is: ; In the formula, It represents the wire dancing transfer value of the position point k on the jth wire in the direction m at the current moment; Indicates the deviation between the displacement velocity of point k on the jth wire in direction m and the fitting result at the current moment; It represents the mean deviation of the displacement velocity of the position point k on the j-th wire in all directions and the fitting result at the current moment.

6. The transmission tower conductor galloping early warning method combined with a multi-factor coupling model as claimed in claim 5 is characterized in that: The expression of the wire galloping determination value of each position point on each wire in any direction at the current moment is: ; In the formula, represents the wire galloping determination value of the j-th wire at the current moment at the position point k in the direction m; represents the distance from the position k on the jth conductor to the transmission tower at the current moment; ln( ) represents the logarithmic function with natural constants as real numbers; norm[ ] represents the normalization function.

7. The transmission tower conductor galloping early warning method combined with a multi-factor coupling model as claimed in claim 1 is characterized in that: The method for obtaining the abnormal location point is: The wire galloping judgment value of all position points on each wire in any direction at the current moment is used as the input of the threshold segmentation algorithm, and the segmentation threshold is output. The position point where the wire galloping judgment value is greater than the segmentation threshold is recorded as the abnormal position point of each wire in any direction at the current moment.

8. The transmission tower conductor galloping early warning method combined with a multi-factor coupling model as claimed in claim 1 is characterized in that: The method for obtaining the corrected displacement data of all position points on each wire in any direction at the current moment is: Among all the position points on each conductor at the current moment, the displacement data at the non-abnormal position points are kept unchanged, the displacement data at the abnormal position points in direction m are eliminated, and the vacant displacement data at the abnormal position points are filled with nonlinear interpolation method. The filled data are used as the corrected displacement data at the abnormal position points, and all directions are traversed to obtain the corrected displacement data of all the position points on each conductor at the current moment in any direction.

9. The transmission tower conductor galloping early warning method combined with a multi-factor coupling model as claimed in claim 1, characterized in that: The method for obtaining the wire dancing model of each wire at the current moment is: The corrected displacement data of all position points on each conductor in any direction at the current moment, all class feature values ​​of each conductor, and wind speed and direction are used as the input of sparse regression, and the output equation is used as the conductor galloping model of each conductor at the current moment.

10. The transmission tower conductor galloping early warning method combined with a multi-factor coupling model as claimed in claim 1, characterized in that: The early warning of wire galloping includes: The wire dancing model of all wires at the current moment is used as the input of the neural network, and the distance between two wires is output. If the distance between two wires at the current moment is less than the preset safety distance threshold, the wire dancing safety warning is triggered, otherwise, the wire dancing safety warning is not triggered.

Images