Power transmission line state evaluation method and device

Abstract

The invention relates to the technical field of power transmission engineering, and particularly provides a power transmission line state evaluation method and device, and the method comprises the steps: enabling the meteorological data of a power transmission line tower line system to serve as the input of a pre-trained RBF neural network model, obtaining vibration amplitudes of various structural units in the power transmission line tower line system output by a pre-trained RBF neural network model; selecting a finite element simulation model to perform simulation calculation based on the vibration amplitudes of the various structural units and the corresponding checking calculation thresholds thereof to obtain stress ratios of the various structural units; obtaining the maximum value in the stress ratios of the various structural units, and performing state evaluation on the power transmission line based on the maximum value; wherein the types of the structural units comprise wires and iron towers, and the finite element simulation model comprises a tower line system model, an iron tower monomer model and a wire monomer model. According to the scheme, the tower line system mechanical state evaluation triggering standard is established, and the finite element simulation calculation is combined, so that the state of the power transmission line can be accurately evaluated.

Description

Technical Field

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

[0002] Overhead transmission lines are extremely susceptible to adverse environmental conditions during operation, such as severe convection, typhoons, and freezing rain. These conditions can lead to serious faults, including wire breakage, wind deflection, and electrical discharges. Transmission towers are also susceptible to damage and even tower collapse. These faults can significantly impact the safe operation of the power grid and cause significant economic losses. Therefore, transmission line condition assessment is crucial.

[0003] At present, the work of transmission line status assessment is mainly based on machine learning methods. With the help of deep learning of historical monitoring data, a transmission line disaster risk model is established, and finally a transmission line risk assessment method is formed to achieve pre-disaster warning and rapid perception of transmission line disasters during disasters.

[0004] Establishing a transmission line disaster probability model based on machine learning methods can achieve rapid calculation and early warning of transmission line disasters. However, this requires the collection of a large amount of historical monitoring data, including a certain number of fault data samples, to accurately map the monitoring data to the presence of transmission line faults. However, in reality, the number of line faults detected by online monitoring devices is limited. The risk model trained under these data conditions has large errors and is unable to accurately assess the status of transmission lines.

[0005] Finite element simulation analysis is also used in many power line monitoring applications. This method offers high accuracy and is more capable of reflecting the true state of transmission lines. However, this time-consuming simulation analysis cannot provide continuous early warnings for transmission line failures. Therefore, in practical applications, calculations are performed only under certain conditions, such as high wind speeds, heavy rainfall, and snowfall. This method only accounts for extreme weather conditions and tends to overlook potential transmission line failures under certain specific conditions.

[0006] In this context, it is difficult to meet the actual transmission line operation and maintenance needs by only using machine learning methods to evaluate the status of transmission lines. Summary of the Invention

[0007] In order to overcome the above-mentioned defects, the present invention proposes a method and device for evaluating the status of a transmission line.

[0008] In a first aspect, a method for evaluating a transmission line state is provided, the method comprising:

[0009] The meteorological data of the transmission line tower system is used as the input of the pre-trained RBF neural network model, and the vibration amplitude of various structural units in the transmission line tower system is obtained as the output of the pre-trained RBF neural network model;

[0010] Based on the vibration amplitudes of the various structural units and their corresponding verification thresholds, a finite element simulation model is selected to perform simulation calculations to obtain stress ratios of the various structural units;

[0011] The maximum value of the stress ratio of each structural unit is obtained, and the state of the transmission line is evaluated based on the maximum value.

[0012] Preferably, the training process of the pre-trained RBF neural network model includes:

[0013] Training data is constructed using historical meteorological data of the transmission line tower system and the corresponding vibration amplitudes of various structural units;

[0014] The initial RBF neural network model is trained using the training data to obtain the pre-trained RBF neural network model.

[0015] Preferably, the finite element simulation model is selected based on the vibration amplitudes of the various structural units and their corresponding verification thresholds to perform simulation calculations to obtain stress ratios of the various structural units, including:

[0016] When the vibration amplitude of the structural unit is between the first threshold value of the structural unit verification and the second threshold value of the structural unit verification, the monomer model corresponding to the structural unit is selected for true calculation to obtain the stress ratio of the structural unit;

[0017] When the vibration amplitude of the structural unit exceeds the second threshold value of the structural unit verification, the tower-line system model is selected for true calculation to obtain the stress ratio of the structural unit.

[0018] Furthermore, the process of obtaining the first threshold value calculated by the structural unit and the second threshold value calculated by the structural unit includes:

[0019] Based on the historical vibration amplitude data of the structural unit, the kernel density algorithm is used to fit the amplitude cumulative probability density distribution function of the structural unit;

[0020] The amplitude corresponding to the first probability threshold on the curve corresponding to the amplitude cumulative probability density distribution function is used as the structural unit to verify the first threshold, and the amplitude corresponding to the second probability threshold on the curve corresponding to the amplitude cumulative probability density distribution function is used as the structural unit to verify the second threshold.

[0021] Furthermore, the first probability threshold is 80%, and the second probability threshold is 95%.

[0022] Furthermore, the amplitude cumulative probability density distribution function of the structural unit is as follows:

[0023]

[0024] In the above formula, f(x) is the probability density distribution of the vibration amplitude x of the structural unit, N is the number of historical vibration amplitude data samples of the structural unit, K(x-α i ) is about x-α i The kernel function, α i is the value corresponding to the i-th historical vibration amplitude data sample of the structural unit.

[0025] Furthermore, the above-mentioned i The kernel function is as follows:

[0026]

[0027] Preferably, the meteorological data includes at least one of the following: wind speed, wind direction, temperature, and humidity.

[0028] Furthermore, before using the meteorological data of the transmission line tower system as the input of the pre-trained RBF neural network model, the method includes:

[0029] The wind speed is pre-processed as follows:

[0030] v in =v / v0

[0031] Pre-process the wind direction as follows:

[0032]

[0033] In the above formula, v in is the pre-processed wind speed data, v is the measured wind speed data, v0 is the design wind speed, d in is the preprocessed wind direction data, θ is the measured wind direction, and θ0 is the conductor direction angle.

[0034] Preferably, the performing status assessment on the transmission line based on the maximum value includes:

[0035] When the maximum value is less than 90%, the transmission line is in a low-risk state;

[0036] When the maximum value is between 90% and 110%, the transmission line is in a medium risk state;

[0037] When the maximum value exceeds 110%, the transmission line is in a high-risk state.

[0038] In a second aspect, a transmission line status assessment device is provided, the transmission line status assessment device comprising:

[0039] The first analysis module is used to use the meteorological data of the transmission line tower system as the input of the pre-trained RBF neural network model to obtain the vibration amplitude of various structural units in the transmission line tower system output by the pre-trained RBF neural network model;

[0040] A second analysis module is used to select a finite element simulation model to perform simulation calculation based on the vibration amplitudes of the various structural units and their corresponding verification thresholds to obtain stress ratios of the various structural units;

[0041] The third analysis module is used to obtain the maximum value of the stress ratio of each type of structural unit and perform a status assessment on the transmission line based on the maximum value.

[0042] Preferably, the training process of the pre-trained RBF neural network model includes:

[0043] Training data is constructed using historical meteorological data of the transmission line tower system and the corresponding vibration amplitudes of various structural units;

[0044] The initial RBF neural network model is trained using the training data to obtain the pre-trained RBF neural network model.

[0045] Preferably, the second analysis module is specifically used to:

[0046] When the vibration amplitude of the structural unit is between the first threshold value of the structural unit verification and the second threshold value of the structural unit verification, the monomer model corresponding to the structural unit is selected for true calculation to obtain the stress ratio of the structural unit;

[0047] When the vibration amplitude of the structural unit exceeds the second threshold value of the structural unit verification, the tower-line system model is selected for true calculation to obtain the stress ratio of the structural unit.

[0048] Furthermore, the process of obtaining the first threshold value calculated by the structural unit and the second threshold value calculated by the structural unit includes:

[0049] Based on the historical vibration amplitude data of the structural unit, the kernel density algorithm is used to fit the amplitude cumulative probability density distribution function of the structural unit;

[0050] The amplitude corresponding to the first probability threshold on the curve corresponding to the amplitude cumulative probability density distribution function is used as the structural unit to verify the first threshold, and the amplitude corresponding to the second probability threshold on the curve corresponding to the amplitude cumulative probability density distribution function is used as the structural unit to verify the second threshold.

[0051] Furthermore, the first probability threshold is 80%, and the second probability threshold is 95%.

[0052] Furthermore, the amplitude cumulative probability density distribution function of the structural unit is as follows:

[0053]

[0054] In the above formula, f(x) is the probability density distribution of the vibration amplitude x of the structural unit, N is the number of historical vibration amplitude data samples of the structural unit, K(x-α i ) is about x-α i The kernel function, α i is the value corresponding to the i-th historical vibration amplitude data sample of the structural unit.

[0055] Furthermore, the above-mentioned i The kernel function is as follows:

[0056]

[0057] Preferably, the meteorological data includes at least one of the following: wind speed, wind direction, temperature, and humidity.

[0058] Furthermore, before using the meteorological data of the transmission line tower system as the input of the pre-trained RBF neural network model, the method includes:

[0059] The wind speed is pre-processed as follows:

[0060] v in =v / v0

[0061] Pre-process the wind direction as follows:

[0062]

[0063] In the above formula, v in is the pre-processed wind speed data, v is the measured wind speed data, v0 is the design wind speed, d in is the preprocessed wind direction data, θ is the measured wind direction, and θ0 is the conductor direction angle.

[0064] Preferably, the third analysis module is specifically used to:

[0065] When the maximum value is less than 90%, the transmission line is in a low-risk state;

[0066] When the maximum value is between 90% and 110%, the transmission line is in a medium risk state;

[0067] When the maximum value exceeds 110%, the transmission line is in a high-risk state.

[0068] In a third aspect, a computer device is provided, comprising: one or more processors;

[0069] The processor is configured to execute one or more programs;

[0070] When the one or more programs are executed by the one or more processors, the transmission line state assessment method is implemented.

[0071] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed, the transmission line status assessment method is implemented.

[0072] The above one or more technical solutions of the present invention have at least one or more of the following beneficial effects:

[0073] The present invention provides a method and device for assessing the condition of a transmission line, comprising: using meteorological data of a transmission line tower-line system as input to a pre-trained RBF neural network model to obtain the vibration amplitudes of various structural units in the transmission line tower-line system output by the pre-trained RBF neural network model; selecting a finite element simulation model based on the vibration amplitudes of the various structural units and their corresponding verification thresholds to perform simulation calculations to obtain stress ratios of the various structural units; obtaining the maximum value among the stress ratios of the various structural units, and assessing the condition of the transmission line based on the maximum value; wherein the types of structural units include conductors and towers, and the finite element simulation models include a tower-line system model, a tower unit model, and a conductor unit model. The technical solution provided by the present invention can be applied to assessing the mechanical condition of transmission lines in strong winds, clarifies simulation calculation standards, and, in combination with finite element simulation calculations, obtains the mechanical condition of the transmission line and provides a risk level classification standard for the transmission line system, providing a basis for transmission line operation and maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 1 is a flow chart showing the main steps of the method for evaluating the state of a transmission line according to an embodiment of the present invention;

[0075] Figure 2 is a schematic diagram of monitoring data according to an embodiment of the present invention;

[0076] Figure 3 is a graph of the cumulative probability density distribution and threshold value of an embodiment of the present invention;

[0077] Figure 4 This is a diagram of the risk verification model prediction results of an embodiment of the present invention;

[0078] Figure 5 This is a structural diagram of a tower line system model according to an embodiment of the present invention;

[0079] Figure 6 It is a structural diagram of a single iron tower model according to an embodiment of the present invention. DETAILED DESCRIPTION

[0080] The specific embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0081] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0082] As disclosed in the background, overhead transmission lines are highly susceptible to adverse environmental conditions during operation, such as severe convection, typhoons, and freezing rain. These conditions can lead to serious faults, including wire breakage, wind-induced discharges, and damage to transmission towers, including damage to their components and even tower collapse. These faults can significantly impact the safe operation of the power grid and cause significant economic losses. Therefore, transmission line status assessment is crucial.

[0083] At present, the work of transmission line status assessment is mainly based on machine learning methods. With the help of deep learning of historical monitoring data, a transmission line disaster risk model is established, and finally a transmission line risk assessment method is formed to achieve pre-disaster warning and rapid perception of transmission line disasters during disasters.

[0084] Establishing a transmission line disaster probability model based on machine learning methods can achieve rapid calculation and early warning of transmission line disasters. However, this requires the collection of a large amount of historical monitoring data, including a certain number of fault data samples, to accurately map the monitoring data to the presence of transmission line faults. However, in reality, the number of line faults detected by online monitoring devices is limited. The risk model trained under these data conditions has large errors and is unable to accurately assess the status of transmission lines.

[0085] Finite element simulation analysis is also used in many power line monitoring applications. This method offers high accuracy and is more capable of reflecting the true state of transmission lines. However, this time-consuming simulation analysis cannot provide continuous early warnings for transmission line failures. Therefore, in practical applications, calculations are performed only under certain conditions, such as high wind speeds, heavy rainfall, and snowfall. This method only accounts for extreme weather conditions and tends to overlook potential transmission line failures under certain specific conditions.

[0086] In this context, it is difficult to meet the actual transmission line operation and maintenance needs by only using machine learning methods to evaluate the status of transmission lines.

[0087] To improve the above-mentioned problems, the present invention provides a method and apparatus for assessing the condition of a transmission line, comprising: using meteorological data of a transmission line tower-line system as input to a pre-trained RBF neural network model, obtaining the vibration amplitudes of various structural units in the transmission line tower-line system output by the pre-trained RBF neural network model; selecting a finite element simulation model based on the vibration amplitudes of the various structural units and their corresponding verification thresholds to perform simulation calculations, obtaining the stress ratios of the various structural units; obtaining the maximum value among the stress ratios of the various structural units, and assessing the condition of the transmission line based on the maximum value; wherein the types of structural units include conductors and towers, and the finite element simulation models include a tower-line system model, a tower unit model, and a conductor unit model. The technical solution provided by the present invention can be applied to assessing the mechanical condition of transmission lines in strong winds, clarifies simulation calculation standards, and, in combination with finite element simulation calculations, obtains the mechanical condition of the transmission line, provides a risk level classification standard for the transmission line system, and provides a basis for transmission line operation and maintenance.

[0088] The above scheme is described in detail below.

[0089] Example 1

[0090] See attached Figure 1 , Figure 1 FIG. 1 is a flow chart showing the main steps of a method for evaluating the state of a transmission line according to an embodiment of the present invention. Figure 1 As shown, the transmission line status assessment method in the embodiment of the present invention mainly includes the following steps:

[0091] Step S101: using meteorological data of the transmission line tower system as input to a pre-trained RBF neural network model, and obtaining vibration amplitudes of various structural units in the transmission line tower system output by the pre-trained RBF neural network model;

[0092] Step S102: selecting a finite element simulation model to perform simulation calculation based on the vibration amplitudes of the various structural units and their corresponding verification thresholds to obtain stress ratios of the various structural units;

[0093] Step S103: obtaining the maximum value of the stress ratios of various structural units, and performing a state assessment on the transmission line based on the maximum value;

[0094] The types of the structural units include: conductors and towers, and the finite element simulation model includes: a tower-line system model, a tower single body model and a conductor single body model.

[0095] The technical solution provided by this invention utilizes historical monitoring data to establish an early warning model based on machine learning methods for transmission line monitoring and early warning. Simulation calculation thresholds are set based on the model. Finite element simulation analysis is performed when the transmission line reaches a certain risk level, forming a data-driven and online simulation-integrated state assessment system. This system is applicable to mechanical state assessment of transmission lines in strong winds. It defines simulation calculation standards, combines finite element simulation calculations to determine the mechanical state of transmission lines, and provides a risk classification standard for transmission line systems, providing a basis for transmission line operation and maintenance.

[0096] In this embodiment, the training process of the pre-trained RBF neural network model includes:

[0097] Training data is constructed using historical meteorological data of the transmission line tower system and the corresponding vibration amplitudes of various structural units;

[0098] The initial RBF neural network model is trained using the training data to obtain the pre-trained RBF neural network model.

[0099] In this embodiment, the finite element simulation model is selected based on the vibration amplitudes of the various structural units and their corresponding verification thresholds for simulation calculation to obtain the stress ratios of the various structural units, including:

[0100] When the vibration amplitude of the structural unit is between the first threshold value of the structural unit verification and the second threshold value of the structural unit verification, the monomer model corresponding to the structural unit is selected for true calculation to obtain the stress ratio of the structural unit;

[0101] When the vibration amplitude of the structural unit exceeds the second threshold value of the structural unit verification, the tower-line system model is selected for true calculation to obtain the stress ratio of the structural unit.

[0102] In one embodiment, the process of obtaining the first threshold value calculated by the structural unit and the second threshold value calculated by the structural unit includes:

[0103] Based on the historical vibration amplitude data of the structural unit, the kernel density algorithm is used to fit the amplitude cumulative probability density distribution function of the structural unit;

[0104] The amplitude corresponding to the first probability threshold on the curve corresponding to the amplitude cumulative probability density distribution function is used as the structural unit to verify the first threshold, and the amplitude corresponding to the second probability threshold on the curve corresponding to the amplitude cumulative probability density distribution function is used as the structural unit to verify the second threshold.

[0105] In one embodiment, the first probability threshold is 80%, and the second probability threshold is 95%.

[0106] In one embodiment, the amplitude cumulative probability density distribution function of the structural unit is as follows:

[0107]

[0108] In the above formula, f(x) is the probability density distribution of the vibration amplitude x of the structural unit, N is the number of historical vibration amplitude data samples of the structural unit, K(x-α i ) is about x-α i The kernel function, α i is the value corresponding to the i-th historical vibration amplitude data sample of the structural unit.

[0109] In one embodiment, the i The kernel function is as follows:

[0110]

[0111] In this embodiment, the meteorological data includes at least one of the following: wind speed, wind direction, temperature, and humidity.

[0112] In one embodiment, before using the meteorological data of the transmission line tower system as input to the pre-trained RBF neural network model, the method includes:

[0113] The wind speed is pre-processed as follows:

[0114] v in =v / v0

[0115] Pre-process the wind direction as follows:

[0116]

[0117] In the above formula, v in is the pre-processed wind speed data, v is the measured wind speed data, v0 is the design wind speed, d in is the preprocessed wind direction data, θ is the measured wind direction, θ0 is the conductor strike angle, which is the angle between the conductor strike and the north direction. As the conductor rotates clockwise, the conductor angle increases and is between 0° and 180°.

[0118] In this embodiment, the state assessment of the transmission line based on the maximum value includes:

[0119] When the maximum value is less than 90%, the transmission line is in a low-risk state;

[0120] When the maximum value is between 90% and 110%, the transmission line is in a medium risk state;

[0121] When the maximum value exceeds 110%, the transmission line is in a high-risk state.

[0122] In a specific implementation, taking a 500kV transmission line within the monitoring and early warning range as an example, there are 20 transmission towers that need to be monitored in this line. To meet the monitoring and early warning needs of this transmission line, meteorological monitoring devices and amplitude monitoring devices have been arranged on the tower-line system of this transmission line. During the long-term monitoring process, two years of meteorological data and amplitude data of conductors and tower cross-arms were obtained. The data sampling frequency is min. -1 .

[0123] Step 1. Obtaining overhead transmission line parameter data

[0124] First, based on the parameter data of the overhead transmission line itself, mainly including the direction of the transmission line conductors and the design wind speed of the tower-line system, the following Table 1 is obtained:

[0125] Table 1

[0126]

[0127] Step 2. Collect historical monitoring data of the transmission line tower system, such as Figure 2 As shown in the figure, a machine learning model training library is constructed. The main input layer data includes wind speed, wind direction, temperature, and humidity. The output layer data includes conductor amplitude data and tower crossarm amplitude data.

[0128] Step 3: Preprocessing of risk calculation model input data

[0129] During the model input data preprocessing process, temperature data and humidity data do not need to be preprocessed and can be directly used as model input data.

[0130] Wind speed data preprocessing requires normalizing the monitored wind speed data using the design wind speed of each tower of the transmission line.

[0131] Step 4: Constructing a probability model for the output data of the risk verification model

[0132] The output data are the conductor vibration amplitude data and the tower pole vibration amplitude data obtained by monitoring. The kernel density method is used to calculate the cumulative probability density distribution of the amplitude.

[0133] The amplitude corresponding to the first probability threshold on the curve corresponding to the amplitude cumulative probability density distribution function is used as the structural unit to verify the first threshold, and the amplitude corresponding to the second probability threshold on the curve corresponding to the amplitude cumulative probability density distribution function is used as the structural unit to verify the second threshold;

[0134] For example, the first probability threshold is 80%, the second probability threshold is 95%, and the selected wire verification threshold is as follows: Figure 3 As shown in (a), the selected tower verification threshold is as follows Figure 3As shown in (b);

[0135] Step 5: Risk Assessment Model Calculation

[0136] The risk budget model uses RBF neural network as the basic framework and modifies the model according to the stress state of towers and conductors in strong wind environment.

[0137] The neural network structure is 4-n-2, that is, there are 4 input layer nodes, n hidden layer nodes and 2 output layer nodes.

[0138] By iteratively training the data for 50,000 times, a risk verification model is obtained. The prediction results of the risk verification model are as follows: Figure 4 shown.

[0139] Step 6: Risk prediction and simulation verification

[0140] Collect the relevant parameters of the target transmission line tower system and use finite element software to build a tower-line system model. There are three types of models: tower-line system model, tower single model, and conductor single model. The conductor single model can directly adopt the tower-line system model. In the model, the tower model is set as a pure rigid component to limit the displacement of the tower. The tower-line system model is as follows: Figure 5 As shown, the tower single body model is as follows Figure 4 shown.

[0141] The meteorological monitoring devices arranged on the target monitoring transmission lines are used to record wind speed, wind direction, temperature and humidity data in real time.

[0142] After preprocessing the monitoring data, the risk calculation model is input to obtain the vibration amplitude data of the conductors and tower crossarms. Based on the table below, it is determined whether the transmission line needs to be verified and what type of verification should be performed. The amplitude verification level is shown in Table 2:

[0143] Table 2

[0144]

[0145]

[0146] Based on the simulation results, the maximum stress of the model unit was extracted, and the ratio of each unit stress to the maximum allowable material stress was calculated, which is the unit stress ratio. Based on the stress ratio, the risk of transmission lines in strong wind environments was assessed and classified according to Table 3 below.

[0147] Table 3

[0148]

[0149] This invention provides a method for assessing the condition of overhead transmission lines, combining neural networks, clustering algorithms, and finite element simulation. This method evaluates the mechanical condition of transmission lines in strong winds. Combining historical monitoring data with transmission line data, it constructs a mechanical condition risk assessment model and defines simulation calculation standards. By combining finite element simulation with the mechanical condition of transmission lines, it establishes a system-level collapse risk classification standard, providing a basis for transmission line operation and maintenance.

[0150] Example 2

[0151] Based on the same inventive concept, the present invention further provides a transmission line status assessment device, the transmission line status assessment device comprising:

[0152] The first analysis module is used to use the meteorological data of the transmission line tower system as the input of the pre-trained RBF neural network model to obtain the vibration amplitude of various structural units in the transmission line tower system output by the pre-trained RBF neural network model;

[0153] A second analysis module is used to select a finite element simulation model to perform simulation calculation based on the vibration amplitudes of the various structural units and their corresponding verification thresholds to obtain stress ratios of the various structural units;

[0154] The third analysis module is used to obtain the maximum value of the stress ratio of each structural unit and perform a state assessment of the transmission line based on the maximum value;

[0155] The types of the structural units include: conductors and towers, and the finite element simulation model includes: a tower-line system model, a tower single body model and a conductor single body model.

[0156] Preferably, the training process of the pre-trained RBF neural network model includes:

[0157] Training data is constructed using historical meteorological data of the transmission line tower system and the corresponding vibration amplitudes of various structural units;

[0158] The initial RBF neural network model is trained using the training data to obtain the pre-trained RBF neural network model.

[0159] Preferably, the second analysis module is specifically used to:

[0160] When the vibration amplitude of the structural unit is between the first threshold value of the structural unit verification and the second threshold value of the structural unit verification, the monomer model corresponding to the structural unit is selected for true calculation to obtain the stress ratio of the structural unit;

[0161] When the vibration amplitude of the structural unit exceeds the second threshold value of the structural unit verification, the tower-line system model is selected for true calculation to obtain the stress ratio of the structural unit.

[0162] Furthermore, the process of obtaining the first threshold value calculated by the structural unit and the second threshold value calculated by the structural unit includes:

[0163] Based on the historical vibration amplitude data of the structural unit, the kernel density algorithm is used to fit the amplitude cumulative probability density distribution function of the structural unit;

[0164] The amplitude corresponding to the first probability threshold on the curve corresponding to the amplitude cumulative probability density distribution function is used as the structural unit to verify the first threshold, and the amplitude corresponding to the second probability threshold on the curve corresponding to the amplitude cumulative probability density distribution function is used as the structural unit to verify the second threshold.

[0165] Furthermore, the first probability threshold is 80%, and the second probability threshold is 95%.

[0166] Furthermore, the amplitude cumulative probability density distribution function of the structural unit is as follows:

[0167]

[0168] In the above formula, f(x) is the probability density distribution of the vibration amplitude x of the structural unit, N is the number of historical vibration amplitude data samples of the structural unit, K(x-α i ) is about x-α i The kernel function, α i is the value corresponding to the i-th historical vibration amplitude data sample of the structural unit.

[0169] Furthermore, the above-mentioned i The kernel function is as follows:

[0170]

[0171] Preferably, the meteorological data includes at least one of the following: wind speed, wind direction, temperature, and humidity.

[0172] Furthermore, before using the meteorological data of the transmission line tower system as the input of the pre-trained RBF neural network model, the method includes:

[0173] The wind speed is pre-processed as follows:

[0174] v in =v / v0

[0175] Pre-process the wind direction as follows:

[0176]

[0177] In the above formula, v in is the pre-processed wind speed data, v is the measured wind speed data, v0 is the design wind speed, d in is the preprocessed wind direction data, θ is the measured wind direction, and θ0 is the conductor direction angle.

[0178] Preferably, the third analysis module is specifically used to:

[0179] When the maximum value is less than 90%, the transmission line is in a low-risk state;

[0180] When the maximum value is between 90% and 110%, the transmission line is in a medium risk state;

[0181] When the maximum value exceeds 110%, the transmission line is in a high-risk state.

[0182] Example 3

[0183] Based on the same inventive concept, the present invention also provides a computer device, which includes a processor and a memory, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or may be 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 the computer storage medium to implement the corresponding method flow or corresponding function, so as to implement the steps of a transmission line status assessment method in the above embodiment.

[0184] Example 4

[0185] Based on the same inventive concept, the present invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device for storing programs and data. It is understandable that the computer-readable storage medium here can include both built-in storage media in the computer device and, of course, extended storage media supported by the computer device. The computer-readable storage medium provides a storage space that stores the operating system of the terminal. In addition, the storage space also stores one or more instructions suitable for being loaded and executed by the processor. These instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the steps of a transmission line status assessment method in the above embodiment.

[0186] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, 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 magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0187] 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 flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, 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 flowcharts and / or block diagrams. 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.

[0188] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work 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 1The function specified in one or more boxes.

[0189] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0190] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the 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 by the scope of protection of the claims of the present invention.

Claims

1. A method for evaluating the state of a transmission line, characterized in that: The method comprises: The meteorological data of the transmission line tower system is used as the input of the pre-trained RBF neural network model, and the vibration amplitude of various structural units in the transmission line tower system is obtained as the output of the pre-trained RBF neural network model; Based on the vibration amplitudes of the various structural units and their corresponding verification thresholds, a finite element simulation model is selected to perform simulation calculations to obtain stress ratios of the various structural units; The maximum value of the stress ratio of each structural unit is obtained, and the state of the transmission line is evaluated based on the maximum value.

2. The method according to claim 1, wherein The training process of the pre-trained RBF neural network model includes: Training data is constructed using historical meteorological data of the transmission line tower system and the corresponding vibration amplitudes of various structural units; The initial RBF neural network model is trained using the training data to obtain the pre-trained RBF neural network model.

3. The method according to claim 1, wherein The finite element simulation model is selected based on the vibration amplitudes of the various structural units and their corresponding verification thresholds to perform simulation calculations to obtain stress ratios of the various structural units, including: When the vibration amplitude of the structural unit is between the first threshold value of the structural unit verification and the second threshold value of the structural unit verification, the monomer model corresponding to the structural unit is selected for true calculation to obtain the stress ratio of the structural unit; When the vibration amplitude of the structural unit exceeds the second threshold value of the structural unit verification, the tower-line system model is selected for true calculation to obtain the stress ratio of the structural unit.

4. The method according to claim 3, wherein The process of obtaining the first threshold value and the second threshold value of the structural unit verification includes: Based on the historical vibration amplitude data of the structural unit, the kernel density algorithm is used to fit the amplitude cumulative probability density distribution function of the structural unit; The amplitude corresponding to the first probability threshold on the curve corresponding to the amplitude cumulative probability density distribution function is used as the structural unit to verify the first threshold, and the amplitude corresponding to the second probability threshold on the curve corresponding to the amplitude cumulative probability density distribution function is used as the structural unit to verify the second threshold.

5. The method according to claim 4, wherein The first probability threshold is 80%, and the second probability threshold is 95%.

6. The method according to claim 4, wherein The cumulative probability density distribution function of the amplitude of the structural unit is as follows: In the above formula, f(x) is the probability density distribution of the vibration amplitude x of the structural unit, N is the number of historical vibration amplitude data samples of the structural unit, K(x-α i ) is about x-α i The kernel function, α i is the value corresponding to the i-th historical vibration amplitude data sample of the structural unit.

7. The method according to claim 6, wherein Regarding x-α i The kernel function is as follows:

8. The method according to claim 1, wherein The meteorological data includes at least one of the following: wind speed, wind direction, temperature, and humidity.

9. The method according to claim 8, wherein Before using the meteorological data of the transmission line tower system as the input of the pre-trained RBF neural network model, the method includes: The wind speed is pre-processed as follows: v in =v / v0 Pre-process the wind direction as follows: In the above formula, v in is the pre-processed wind speed data, v is the measured wind speed data, v0 is the design wind speed, d in is the preprocessed wind direction data, θ is the measured wind direction, and θ0 is the conductor direction angle.

10. The method according to claim 1, wherein The performing of status assessment on the transmission line based on the maximum value includes: When the maximum value is less than 90%, the transmission line is in a low-risk state; When the maximum value is between 90% and 110%, the transmission line is in a medium risk state; When the maximum value exceeds 110%, the transmission line is in a high-risk state.

11. A transmission line status assessment device, characterized in that: The device comprises: The first analysis module is used to use the meteorological data of the transmission line tower system as the input of the pre-trained RBF neural network model to obtain the vibration amplitude of various structural units in the transmission line tower system output by the pre-trained RBF neural network model; A second analysis module is used to select a finite element simulation model to perform simulation calculation based on the vibration amplitudes of the various structural units and their corresponding verification thresholds to obtain stress ratios of the various structural units; The third analysis module is used to obtain the maximum value of the stress ratio of each type of structural unit and perform a status assessment on the transmission line based on the maximum value.

12. The device according to claim 11, wherein The training process of the pre-trained RBF neural network model includes: Training data is constructed using historical meteorological data of the transmission line tower system and the corresponding vibration amplitudes of various structural units; The initial RBF neural network model is trained using the training data to obtain the pre-trained RBF neural network model.

13. The device according to claim 11, wherein The second analysis module is specifically used for: When the vibration amplitude of the structural unit is between the first threshold value of the structural unit verification and the second threshold value of the structural unit verification, the monomer model corresponding to the structural unit is selected for true calculation to obtain the stress ratio of the structural unit; When the vibration amplitude of the structural unit exceeds the second threshold value of the structural unit verification, the tower-line system model is selected for true calculation to obtain the stress ratio of the structural unit.

14. The device according to claim 13, wherein The process of obtaining the first threshold value and the second threshold value of the structural unit verification includes: Based on the historical vibration amplitude data of the structural unit, the kernel density algorithm is used to fit the amplitude cumulative probability density distribution function of the structural unit; The amplitude corresponding to the first probability threshold on the curve corresponding to the amplitude cumulative probability density distribution function is used as the structural unit to verify the first threshold, and the amplitude corresponding to the second probability threshold on the curve corresponding to the amplitude cumulative probability density distribution function is used as the structural unit to verify the second threshold.

15. The device according to claim 14, wherein The first probability threshold is 80%, and the second probability threshold is 95%.

16. The device according to claim 14, wherein The cumulative probability density distribution function of the amplitude of the structural unit is as follows: In the above formula, f(x) is the probability density distribution of the vibration amplitude x of the structural unit, N is the number of historical vibration amplitude data samples of the structural unit, K(x-α i ) is about x-α i The kernel function, α i is the value corresponding to the i-th historical vibration amplitude data sample of the structural unit.

17. The device according to claim 16, characterized in that Regarding x-α i The kernel function is as follows:

18. The device according to claim 11, wherein The meteorological data includes at least one of the following: wind speed, wind direction, temperature, and humidity.

19. The device according to claim 18, wherein Before using the meteorological data of the transmission line tower system as the input of the pre-trained RBF neural network model, the method includes: The wind speed is pre-processed as follows: v in =v / v0 Pre-process the wind direction as follows: In the above formula, v in is the pre-processed wind speed data, v is the measured wind speed data, v0 is the design wind speed, d in is the preprocessed wind direction data, θ is the measured wind direction, and θ0 is the conductor direction angle.

20. The device according to claim 11, wherein The third analysis module is specifically used for: When the maximum value is less than 90%, the transmission line is in a low-risk state; When the maximum value is between 90% and 110%, the transmission line is in a medium risk state; When the maximum value exceeds 110%, the transmission line is in a high-risk state.

21. A computer device, characterized in that: include: one or more processors; The processor is configured to execute one or more programs; When the one or more programs are executed by the one or more processors, the transmission line state assessment method according to any one of claims 1 to 10 is implemented.

22. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the computer program is executed, the method for evaluating the state of a transmission line according to any one of claims 1 to 10 is implemented.

Images