A wind yaw angle prediction method and device for a power transmission line jumper
By acquiring wind and rain loads from power transmission line jumpers, a finite element model was established, and the model was trained using a neural network. This solved the problem of inaccurate wind deflection prediction in existing technologies and achieved more efficient wind deflection prediction.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- GUANGDONG POWER GRID CO LTD
- Filing Date
- 2022-11-28
- Publication Date
- 2026-05-12
AI Technical Summary
Existing transmission line wind deflection monitoring technology does not consider the impact of rainfall on the wind deflection angle of jumpers, resulting in inaccurate wind deflection angle prediction.
By acquiring the horizontal wind load in the direction of the vertical conductor of the power transmission line jumper, the vertical wind load in the direction of the vertical conductor, and the rain load of the jumper, an initial finite element model is established. The wind deflection angle calculation model is trained using a BP neural network model, and the wind deflection angle is predicted by combining real-time wind speed, wind direction, and rainfall intensity.
This improved the accuracy and efficiency of wind deflection angle for power transmission line jumpers, enabling more precise wind deflection angle prediction.
Smart Images
Figure CN115713042B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the technical field of power transmission lines, and in particular to a method and apparatus for predicting the wind deflection angle of power transmission line jumpers. Background Technology
[0002] The wind deflection faults that have occurred on overhead transmission lines are directly related to extreme weather conditions, especially when strong winds are accompanied by rainfall, which makes wind deflection flashover faults more likely to occur. Existing wind deflection monitoring of transmission lines generally relies on analyzing received numerical meteorological data to determine the angle between the transmission line and the wind direction and the random wind speed. Then, it calculates the random wind load and the horizontal displacement of the transmission line, and finally determines the dynamic wind deflection angle of the insulators and forecasts the wind deflection status of the transmission line. This achieves wind deflection forecasting of transmission lines based on numerical meteorological data and the dynamic wind deflection angle of the insulators, or by using dynamic wind speed simulation models and wind deflection angle calculation models to collect relevant information and calculate the simulated wind deflection angle of the transmission line based on dynamic wind.
[0003] Existing transmission line wind deflection monitoring technology does not consider the impact of rainfall on the wind deflection angle of jumpers, and does not establish a finite element model for the wind deflection angle of jumpers, resulting in an inaccurate model and further leading to a large error in the subsequent obtained transmission line wind deflection angle. Summary of the Invention
[0004] The technical problem to be solved by the present invention is to provide a method and device for predicting the wind deflection angle of power transmission line jumpers, so as to improve the accuracy and efficiency of obtaining the wind deflection angle of power transmission line jumpers.
[0005] To address the aforementioned technical problems, this invention provides a method for predicting the wind deflection angle of power transmission line jumpers, comprising:
[0006] Obtain the horizontal wind load, vertical wind load, and rain load on the jumper wires of the transmission line in the direction perpendicular to the conductor;
[0007] Based on the horizontal wind load in the direction of the vertical conductor, the vertical wind load in the direction of the vertical conductor, and the rain load on the jumper, the jumper of the transmission line is modeled to obtain an initial finite element model.
[0008] Based on the initial finite element model, wind deflection angle data under multiple preset working conditions are obtained, and the wind deflection angle data is divided into a model training dataset and a model prediction dataset. The preset working conditions include wind speed, wind direction and rainfall intensity.
[0009] The BP neural network model is trained based on the model training dataset to obtain an initial wind deflection angle calculation model. The model prediction dataset is then input into the initial wind deflection angle calculation model to predict the wind deflection angle, thereby obtaining the optimal wind deflection angle calculation model.
[0010] The real-time wind speed, real-time wind direction, and real-time rainfall intensity are obtained and input into the optimal wind deflection angle calculation model to obtain the predicted wind deflection angle value.
[0011] In one possible implementation, the horizontal wind load and the vertical wind load in the direction perpendicular to the conductor of the transmission line jumper are obtained, specifically including:
[0012] The first wind speed at a reference height of 10m, conductor outer diameter, jumper span, wind pressure non-uniformity coefficient, wind pressure height variation coefficient, conductor shape coefficient, wind load adjustment coefficient, and wind load amplification coefficient are obtained and input into the preset horizontal wind load calculation formula in the vertical conductor direction to obtain the horizontal wind load in the vertical conductor direction. The preset horizontal wind load calculation formula in the vertical conductor direction is as follows:
[0013]
[0014] In the formula, v1 is the first wind speed, D is the outer diameter of the conductor, L is the span of the jumper, α is the wind pressure non-uniformity coefficient, u1 is the wind pressure height variation coefficient, u2 is the conductor shape coefficient, β is the wind load adjustment coefficient, and A is the wind load amplification coefficient.
[0015] Obtain the wind direction angle at a reference height of 10m. Input the wind direction angle and the horizontal wind load in the vertical traverse direction into the preset vertical wind load calculation formula to obtain the vertical wind load in the vertical traverse direction. The preset vertical wind load calculation formula is as follows:
[0016]
[0017] In the formula, φ is the wind direction angle.
[0018] In one possible implementation, obtaining the jumper rain load of the transmission line jumper specifically includes:
[0019] The parameters, including the first wind speed at a reference height of 10m, raindrop diameter, jumper height, jumper height, number of raindrops per unit volume, wind pressure height variation coefficient, rainfall intensity, jumper rain-facing area, and jumper length, are obtained and input into a preset jumper rain load calculation formula to obtain the jumper rain load. The preset jumper rain load calculation formula is as follows:
[0020]
[0021]
[0022] n = 8000e d(4.1B-0.21) ;
[0023] S = πdl / 2;
[0024] In the formula, v1 is the first wind speed, d is the raindrop diameter, v2 is the height of the jumper, H is the height of the jumper, n is the number of raindrops per unit volume, u1 is the wind pressure height variation coefficient, B is the rainfall intensity, S is the rain-facing area of the jumper, and l is the length of the jumper.
[0025] In one possible implementation, the model prediction dataset is input into the initial wind deflection angle calculation model to predict the wind deflection angle, thereby obtaining the optimal wind deflection angle calculation model, specifically including:
[0026] Input the model prediction dataset into the initial wind deflection angle calculation model to obtain the sample prediction value corresponding to each prediction data sample in the model prediction dataset;
[0027] The sample prediction values are input into the average relative error calculation formula to obtain the average relative error value;
[0028] The average relative error value is compared with the preset average relative error threshold. When the average relative error value is less than the preset average relative error threshold, the current initial wind deflection angle calculation model is set as the optimal wind deflection angle calculation model.
[0029] The present invention also provides a wind deflection angle prediction device for power transmission line jumpers, comprising: a load calculation module, a finite element modeling module, a model data partitioning module, an optimal wind deflection angle calculation model construction module, and a wind deflection angle prediction module;
[0030] The load calculation module is used to obtain the horizontal wind load, the vertical wind load, and the rain load of the jumper wire in the direction of the vertical conductor of the transmission line.
[0031] The finite element modeling module is used to model the power transmission line jumper according to the horizontal wind load in the direction of the vertical conductor, the vertical wind load in the direction of the vertical conductor, and the jumper rain load to obtain an initial finite element model.
[0032] The model data partitioning module is used to obtain wind deflection angle data under multiple preset working conditions based on the initial finite element model, and to partition the wind deflection angle data into a model training dataset and a model prediction dataset, wherein the preset working conditions include wind speed, wind direction and rainfall intensity.
[0033] The optimal wind deflection angle calculation model construction module is used to train the BP neural network model based on the model training dataset to obtain an initial wind deflection angle calculation model, and input the model prediction dataset into the initial wind deflection angle calculation model to predict the wind deflection angle to obtain the optimal wind deflection angle calculation model.
[0034] The wind deflection angle prediction module is used to acquire and input real-time wind speed, real-time wind direction and real-time rainfall intensity into the optimal wind deflection angle calculation model to obtain the wind deflection angle prediction value.
[0035] In one possible implementation, the load calculation module is used to obtain the horizontal wind load in the direction perpendicular to the conductor and the vertical wind load in the direction perpendicular to the conductor of the transmission line jumper, specifically including:
[0036] The first wind speed at a reference height of 10m, conductor outer diameter, jumper span, wind pressure non-uniformity coefficient, wind pressure height variation coefficient, conductor shape coefficient, wind load adjustment coefficient, and wind load amplification coefficient are obtained and input into the preset horizontal wind load calculation formula in the vertical conductor direction to obtain the horizontal wind load in the vertical conductor direction. The preset horizontal wind load calculation formula in the vertical conductor direction is as follows:
[0037]
[0038] In the formula, v1 is the first wind speed, D is the outer diameter of the conductor, L is the span of the jumper, α is the wind pressure non-uniformity coefficient, u1 is the wind pressure height variation coefficient, u2 is the conductor shape coefficient, β is the wind load adjustment coefficient, and A is the wind load amplification coefficient.
[0039] Obtain the wind direction angle at a reference height of 10m. Input the wind direction angle and the horizontal wind load in the vertical traverse direction into the preset vertical wind load calculation formula to obtain the vertical wind load in the vertical traverse direction. The preset vertical wind load calculation formula is as follows:
[0040]
[0041] In the formula, φ is the wind direction angle.
[0042] In one possible implementation, the load calculation module is used to obtain the jumper rain load of the transmission line jumper, specifically including:
[0043] The parameters, including the first wind speed at a reference height of 10m, raindrop diameter, jumper height, jumper height, number of raindrops per unit volume, wind pressure height variation coefficient, rainfall intensity, jumper rain-facing area, and jumper length, are obtained and input into a preset jumper rain load calculation formula to obtain the jumper rain load. The preset jumper rain load calculation formula is as follows:
[0044]
[0045]
[0046] n = 8000e d(4.1B-0.21) ;
[0047] S = πdl / 2;
[0048] In the formula, v1 is the first wind speed, d is the raindrop diameter, v2 is the height of the jumper, H is the height of the jumper, n is the number of raindrops per unit volume, u1 is the wind pressure height variation coefficient, B is the rainfall intensity, S is the rain-facing area of the jumper, and l is the length of the jumper.
[0049] In one possible implementation, the optimal wind deflection angle calculation model construction module is used to input the model prediction dataset into the initial wind deflection angle calculation model to predict the wind deflection angle and obtain the optimal wind deflection angle calculation model, specifically including:
[0050] Input the model prediction dataset into the initial wind deflection angle calculation model to obtain the sample prediction value corresponding to each prediction data sample in the model prediction dataset;
[0051] The sample prediction values are input into the average relative error calculation formula to obtain the average relative error value;
[0052] The average relative error value is compared with the preset average relative error threshold. When the average relative error value is less than the preset average relative error threshold, the current initial wind deflection angle calculation model is set as the optimal wind deflection angle calculation model.
[0053] The present invention also provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the wind deflection angle prediction method for transmission line jumpers as described in any of the preceding claims.
[0054] The present invention also provides a computer-readable storage medium comprising a stored computer program, wherein, when the computer program is executed, it controls the device containing the computer-readable storage medium to perform the wind deflection angle prediction method for transmission line jumpers as described in any of the preceding claims.
[0055] This invention provides a method and apparatus for predicting the wind deflection angle of power transmission line jumpers, which has the following advantages compared with the prior art:
[0056] By acquiring and modeling the horizontal wind load, vertical wind load, and rain load on the jumper wires in the direction perpendicular to the conductor, a preliminary finite element model is obtained, considering the influence of wind and rain loads on the wind deflection angle of the jumper wires. The wind deflection angle data obtained from the preliminary finite element model under multiple preset operating conditions are divided into a model training dataset and a model prediction dataset. A BP neural network model is trained based on the model training dataset to obtain an initial wind deflection angle calculation model. The model prediction dataset is input into the initial wind deflection angle calculation model to predict the wind deflection angle, resulting in an optimal wind deflection angle calculation model. This optimal wind deflection angle calculation model is established using a data-driven approach and trained with a large amount of data, making the model more accurate. Real-time wind speed, real-time wind direction, and real-time rainfall intensity are acquired and input into the optimal wind deflection angle calculation model to quickly obtain the predicted wind deflection angle value, improving the efficiency of wind deflection angle acquisition. Compared with existing technologies, the technical solution of this invention can improve the accuracy and efficiency of obtaining the wind deflection angle of transmission line jumper wires. Attached Figure Description
[0057] Figure 1 This is a flowchart illustrating an embodiment of a method for predicting the wind deflection angle of a power transmission line jumper provided by the present invention.
[0058] Figure 2 This is a schematic diagram of the structure of an embodiment of a wind deflection angle prediction device for power transmission line jumpers provided by the present invention;
[0059] Figure 3 This is a schematic diagram of finite element modeling of a power transmission line jumper provided in an embodiment of the present invention;
[0060] Figure 4 This is a schematic diagram illustrating the stress state of a power transmission line jumper under wind and rain loads and its own load, as provided in an embodiment of the present invention. Detailed Implementation
[0061] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0062] Example 1
[0063] See Figure 1 , Figure 1 This is a flowchart illustrating an embodiment of a wind deflection angle prediction method for power transmission line jumpers provided by the present invention. Figure 1 As shown, the method includes steps 101-105, as detailed below:
[0064] Step 101: Obtain the horizontal wind load, vertical wind load, and rain load of the jumper wires in the direction perpendicular to the conductors of the transmission line.
[0065] In one embodiment, the outer diameter D of the conductor and the span L of the jumper are determined based on the selected tension section, i.e., the distance between the two conductor connection points; the design specifications for 10kV-750kV overhead transmission lines (GB50545-2010) are consulted to obtain the parameters, including the first wind speed, wind direction angle, outer diameter of the conductor, span of the jumper, wind pressure non-uniformity coefficient, wind pressure height variation coefficient, conductor shape coefficient, wind load adjustment coefficient, and wind load amplification coefficient at a reference height of 10m.
[0066] In one embodiment, the first wind speed (reference height 10m), conductor outer diameter, jumper span, wind pressure non-uniformity coefficient, wind pressure height variation coefficient, conductor shape coefficient, wind load adjustment coefficient, and wind load amplification coefficient are input into a preset formula for calculating the horizontal wind load in the vertical conductor direction to obtain the horizontal wind load in the vertical conductor direction. The preset formula for calculating the horizontal wind load in the vertical conductor direction is as follows:
[0067]
[0068] In the formula, v1 is the first wind speed, D is the outer diameter of the conductor, L is the span of the jumper, α is the wind pressure non-uniformity coefficient, u1 is the wind pressure height variation coefficient, u2 is the conductor shape coefficient, β is the wind load adjustment coefficient, and A is the wind load amplification coefficient.
[0069] In one embodiment, the wind direction angle is obtained at a reference height of 10m. The wind direction angle and the horizontal wind load in the vertical traverse direction are input into a preset calculation formula for the vertical wind load in the vertical traverse direction to obtain the vertical wind load in the vertical traverse direction. The preset calculation formula for the vertical wind load in the vertical traverse direction is as follows:
[0070]
[0071] In the formula, φ is the wind direction angle.
[0072] In one embodiment, the following parameters are obtained and input into a preset jumper rain load calculation formula: first wind speed (reference height 10m), raindrop diameter, jumper height, jumper height, number of raindrops per unit volume, wind pressure height variation coefficient, rainfall intensity, jumper rain-facing area, and jumper length. The jumper rain load is then obtained. The preset jumper rain load calculation formula is as follows:
[0073]
[0074]
[0075] n = 8000e d(4.1B-0.21) ;
[0076] S = πdl / 2;
[0077] In the formula, v1 is the first wind speed, d is the raindrop diameter, v2 is the height of the jumper, H is the height of the jumper, n is the number of raindrops per unit volume, u1 is the wind pressure height variation coefficient, B is the rainfall intensity, S is the rain-facing area of the jumper, and l is the length of the jumper.
[0078] Step 102: Based on the horizontal wind load in the direction of the vertical conductor, the vertical wind load in the direction of the vertical conductor, and the rain load on the jumper, model the jumper of the transmission line to obtain an initial finite element model.
[0079] In one embodiment, when modeling transmission line jumpers based on the finite element method, it is necessary to define the wind deflection angle, model the transmission line jumpers, find the initial shape, and simulate wind and rain loads.
[0080] In practice, the definition of wind deflection angle specifically involves analyzing the wind load, horizontal wind load perpendicular to the conductor, vertical wind load perpendicular to the conductor, self-weight, and tension on the transmission line jumper. When the transmission line jumper is in equilibrium, theoretically, it is prohibited from moving due to force equilibrium. This corresponds to the maximum wind deflection angle of the transmission line jumper. The tension on the transmission line jumper can be measured by a tension sensor installed at the connection point between the jumper and the transmission line conductor.
[0081] In one embodiment, for the modeling and initial shape finding of transmission line jumpers, specifically, ANSYS software is used to perform finite element modeling of the transmission line jumpers, viewing the transmission line jumpers as a flexible chain with hinges everywhere, such as... Figure 3 As shown, Figure 3 This is a schematic diagram of a finite element model of a power transmission line jumper; the catenary shape represents the initial form of the jumper under its own load. An initial finite element model is created at the position of the jumper string. Using the actual determined material parameters and real constants, a small initial stress is given and a load is applied. Horizontal tension is used as the convergence condition, and the initial finite element model is continuously updated until the initial form of the power transmission line jumper bearing its own load is found.
[0082] In one embodiment, for the simulation of wind and rain loads, specifically, the initial finite element model is established based on a finite number of elements. The concentrated force simulation method is used to simulate the wind and rain loads on each element node in the transmission line jumper. The magnitude of the concentrated force corresponding to the wind load can be calculated as F based on the horizontal wind load in the direction perpendicular to the conductor and the vertical wind load in the direction perpendicular to the conductor obtained in step 101. Wy1 =F WyThe magnitude of the concentrated force corresponding to the rain load can be calculated from the jumper rain load obtained in step 101. R1 =F R s / l, where l is the total length of the jumper and s is the length of each unit. For example... Figure 4 As shown, Figure 4 This is a schematic diagram showing the stress on a power transmission line jumper under wind and rain loads and its own load, where G1 is the self-load force per unit length of jumper.
[0083] Step 103: Based on the initial finite element model, obtain wind deflection angle data under multiple preset working conditions, and divide the wind deflection angle data into a model training dataset and a model prediction dataset. The preset working conditions include wind speed, wind direction, and rainfall intensity.
[0084] In one embodiment, wind deflection angle data under multiple preset operating conditions are acquired; specifically, different wind speeds are selected, wherein the different wind speeds are 0, 2.5, 5, 7.5, 10, 12.5, 15, 17.5, 20, 22.5, 25, 27.5, 30, 32.5, 35, 37.5, 40, 42.5, 45, 47.5, 50, 52.5, and 55, and their units are meters per second; different wind directions are selected, wherein the different wind directions are 0° The following parameters are selected: 30°, 45°, 60°, 90°, 120°, 150°, 180°, 210°, 240°, 270°, 300°, 330°, and 360°. Different rainfall intensities are selected, with values of 0.1, 0.5, 1, 2, 4, 8, 12, 15, 17, 20, 25, and 30 milliseconds per minute. Multiple preset working conditions are obtained by combining different wind speeds, wind directions, and rainfall intensities. Preferably, in this embodiment, 3864 working conditions are generated.
[0085] In one embodiment, wind deflection angle data corresponding to each of the 3864 operating conditions is obtained, and the wind deflection angle data under the 3864 operating conditions is set as the model training dataset.
[0086] In one embodiment, 60 samples are randomly selected from meteorological data and online monitoring data of overhead transmission lines. Each sample includes wind speed, wind direction, rainfall intensity and its corresponding wind deflection angle data, and these 60 samples are set as the model prediction dataset.
[0087] Step 104: Train the BP neural network model based on the model training dataset to obtain an initial wind deflection angle calculation model. Input the model prediction dataset into the initial wind deflection angle calculation model to predict the wind deflection angle and obtain the optimal wind deflection angle calculation model.
[0088] In one embodiment, the model prediction dataset is input into the initial wind deflection angle calculation model to obtain the sample prediction value corresponding to each prediction data sample in the model prediction dataset.
[0089] In one embodiment, the sample predicted value is input into the average relative error calculation formula to obtain the average relative error value; wherein, the average relative error calculation formula is as follows:
[0090]
[0091] In the formula, N is the number of samples in the model prediction dataset, O(i) is the sample prediction value corresponding to the i-th sample in the model prediction dataset, and Y(i) is the actual wind deflection angle data corresponding to the i-th sample in the model prediction dataset, i = 1, 2, 3, ..., N.
[0092] In one embodiment, the fitting effect of the initial wind deflection angle calculation model is evaluated using the average relative error. Specifically, the average relative error value is compared with a preset average relative error threshold. When the average relative error value is less than the preset average relative error threshold, the fitting effect of the initial wind deflection angle calculation model is considered to meet the requirements, and the current initial wind deflection angle calculation model is set as the optimal wind deflection angle calculation model. Preferably, the preset average relative error threshold is set to 10%. Similarly, the preset average relative error threshold can be set based on user needs.
[0093] Step 105: Obtain and input the real-time wind speed, real-time wind direction, and real-time rainfall intensity into the optimal wind deflection angle calculation model to obtain the predicted wind deflection angle value.
[0094] In one embodiment, a wind deflection angle prediction system is established based on the optimal wind deflection angle calculation model, so that the optimal wind deflection angle calculation model in the wind deflection angle prediction system outputs the real-time wind speed, wind direction and rainfall intensity, thereby obtaining the wind deflection angle prediction value.
[0095] Example 2
[0096] See Figure 2 , Figure 2 This is a flowchart illustrating an embodiment of a wind deflection angle prediction device for power transmission line jumpers provided by the present invention, as shown below. Figure 2 As shown, the device includes a load calculation module 201, a finite element modeling module 202, a model data partitioning module 203, an optimal wind deflection angle calculation model construction module 204, and a wind deflection angle prediction module 205, as detailed below:
[0097] The load calculation module 201 is used to obtain the horizontal wind load, the vertical wind load, and the rain load of the jumper wire in the direction perpendicular to the conductor of the transmission line.
[0098] The finite element modeling module 202 is used to model the power transmission line jumper according to the horizontal wind load in the direction of the vertical conductor, the vertical wind load in the direction of the vertical conductor, and the jumper rain load, so as to obtain an initial finite element model.
[0099] The model data partitioning module 203 is used to obtain wind deflection angle data under multiple preset working conditions based on the initial finite element model, and to partition the wind deflection angle data into a model training dataset and a model prediction dataset, wherein the preset working conditions include wind speed, wind direction and rainfall intensity.
[0100] The optimal wind deflection angle calculation model construction module 204 is used to train the BP neural network model based on the model training dataset to obtain an initial wind deflection angle calculation model, and input the model prediction dataset into the initial wind deflection angle calculation model to predict the wind deflection angle to obtain the optimal wind deflection angle calculation model.
[0101] The wind deflection angle prediction module 205 is used to acquire and input real-time wind speed, real-time wind direction and real-time rainfall intensity into the optimal wind deflection angle calculation model to obtain the wind deflection angle prediction value.
[0102] In one embodiment, the load calculation module 201 is used to obtain the horizontal wind load and vertical wind load in the direction of the vertical conductor of the transmission line jumper. Specifically, it includes: obtaining and inputting the first wind speed (with a reference height of 10m), conductor outer diameter, jumper span, wind pressure non-uniformity coefficient, wind pressure height variation coefficient, conductor shape coefficient, wind load adjustment coefficient, and wind load amplification coefficient into a preset calculation formula for the horizontal wind load in the direction of the vertical conductor to obtain the horizontal wind load in the direction of the vertical conductor. The preset calculation formula for the horizontal wind load in the direction of the vertical conductor is as follows:
[0103]
[0104] In the formula, v1 is the first wind speed, D is the outer diameter of the conductor, L is the span of the jumper, α is the wind pressure non-uniformity coefficient, u1 is the wind pressure height variation coefficient, u2 is the conductor shape coefficient, β is the wind load adjustment coefficient, and A is the wind load amplification coefficient.
[0105] In one embodiment, the load calculation module 201 is used to obtain the wind direction angle at a reference height of 10m, and input the wind direction angle and the horizontal wind load in the vertical traverse direction into a preset vertical traverse direction vertical wind load calculation formula to obtain the vertical traverse direction vertical wind load. The preset vertical traverse direction vertical wind load calculation formula is as follows:
[0106]
[0107] In the formula, φ is the wind direction angle.
[0108] In one embodiment, the load calculation module 201 is used to obtain the jumper rain load of the transmission line jumper, specifically including: obtaining and inputting the first wind speed (reference height 10m), raindrop diameter, jumper height, jumper height, number of raindrops per unit volume, wind pressure height variation coefficient, rainfall intensity, jumper rain-facing area, and jumper length into a preset jumper rain load calculation formula to obtain the jumper rain load. The preset jumper rain load calculation formula is as follows:
[0109]
[0110]
[0111] n = 8000e d(4.1B-0.21) ;
[0112] S = πdl / 2;
[0113] In the formula, v1 is the first wind speed, d is the raindrop diameter, v2 is the height of the jumper, H is the height of the jumper, n is the number of raindrops per unit volume, u1 is the wind pressure height variation coefficient, B is the rainfall intensity, S is the rain-facing area of the jumper, and l is the length of the jumper.
[0114] In one embodiment, the optimal wind deflection angle calculation model construction module 204 is used to input the model prediction dataset into the initial wind deflection angle calculation model to predict the wind deflection angle and obtain the optimal wind deflection angle calculation model. Specifically, it includes: inputting the model prediction dataset into the initial wind deflection angle calculation model to obtain the sample prediction value corresponding to each prediction data sample in the model prediction dataset; inputting the sample prediction value into the average relative error calculation formula to obtain the average relative error value; comparing the average relative error value with a preset average relative error threshold, and when the average relative error value is less than the preset average relative error threshold, setting the current initial wind deflection angle calculation model as the optimal wind deflection angle calculation model.
[0115] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the device described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.
[0116] It should be noted that the above-described embodiment of the wind deflection prediction device for transmission line jumpers is merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.
[0117] Based on the above-described embodiments of the wind deflection prediction method for transmission line jumpers, another embodiment of the present invention provides a wind deflection prediction terminal device for transmission line jumpers. The wind deflection prediction terminal device for transmission line jumpers includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the wind deflection prediction method for transmission line jumpers according to any embodiment of the present invention.
[0118] For example, in this embodiment, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in the wind deflection prediction terminal device of the transmission line jumper.
[0119] The wind deflection prediction terminal device for the transmission line jumper can be a computing device such as a desktop computer, laptop, handheld computer, or cloud server. The wind deflection prediction terminal device for the transmission line jumper may include, but is not limited to, a processor and a memory.
[0120] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. This processor is the control center of the wind deflection prediction terminal equipment for the transmission line jumper, connecting various parts of the equipment via various interfaces and lines.
[0121] The memory can be used to store the computer program and / or modules. The processor, by running or executing the computer program and / or modules stored in the memory and calling the data stored in the memory, realizes various functions of the wind deflection prediction terminal device for the transmission line jumper. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function, etc.; the data storage area may store data created based on the use of the mobile phone, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.
[0122] Based on the above-described embodiments of the wind deflection angle prediction method for transmission line jumpers, another embodiment of the present invention provides a storage medium comprising a stored computer program, wherein, when the computer program is running, the device containing the storage medium is controlled to execute the wind deflection angle prediction method for transmission line jumpers according to any embodiment of the present invention.
[0123] In this embodiment, the storage medium is a computer-readable storage medium, and the computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium can include any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.
[0124] In summary, this invention provides a method and apparatus for predicting the wind deflection angle of transmission line jumpers. By acquiring and modeling the transmission line jumpers based on the horizontal wind load, vertical wind load, and rain load in the direction perpendicular to the conductor, the influence of wind and rain loads on the wind deflection angle of the jumpers is considered, resulting in an initial finite element model. Wind deflection angle data under multiple preset operating conditions obtained from the initial finite element model are divided into a model training dataset and a model prediction dataset. A BP neural network model is trained based on the model training dataset to obtain an initial wind deflection angle calculation model. The model prediction dataset is input into the initial wind deflection angle calculation model to predict the wind deflection angle, resulting in an optimal wind deflection angle calculation model. This optimal wind deflection angle calculation model is established using a data-driven approach and trained with a large amount of data, making the model more accurate. By acquiring and inputting real-time wind speed, real-time wind direction, and real-time rainfall intensity into the optimal wind deflection angle calculation model, the predicted wind deflection angle value can be obtained quickly, improving the efficiency of wind deflection angle acquisition. Compared with the prior art, the technical solution of the present invention can improve the accuracy and efficiency of obtaining the wind deflection angle of the jumper wire of the transmission line.
[0125] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and substitutions can be made without departing from the technical principles of the present invention, and these improvements and substitutions should also be considered within the scope of protection of the present invention.
Claims
1. A method for predicting the wind deflection angle of power transmission line jumpers, characterized in that, include: The horizontal wind load, vertical wind load, and rain load on the jumper wires in the direction perpendicular to the conductor are obtained; the specific calculation process for the rain load on the jumper wires is as follows: The parameters, including the first wind speed at a reference height of 10m, raindrop diameter, jumper height, jumper height, number of raindrops per unit volume, wind pressure height variation coefficient, rainfall intensity, jumper rain-facing area, and jumper length, are obtained and input into a preset jumper rain load calculation formula to obtain the jumper rain load. The preset jumper rain load calculation formula is as follows: ； ； ； In the formula, For the first wind speed, For raindrop diameter, At the height of the jumper, For jumper height, The number of raindrops per unit volume The wind pressure height variation coefficient, Rainfall intensity, The area of the jumper wire exposed to rain. This refers to the jumper length; Based on the horizontal wind load in the direction of the vertical conductor, the vertical wind load in the direction of the vertical conductor, and the rain load on the jumper, the jumper of the transmission line is modeled to obtain an initial finite element model. Based on the initial finite element model, wind deflection angle data under multiple preset working conditions are obtained, and the wind deflection angle data is divided into a model training dataset and a model prediction dataset. The preset working conditions include wind speed, wind direction and rainfall intensity. The BP neural network model is trained based on the model training dataset to obtain an initial wind deflection angle calculation model. The model prediction dataset is then input into the initial wind deflection angle calculation model to predict the wind deflection angle, thereby obtaining the optimal wind deflection angle calculation model. The real-time wind speed, real-time wind direction, and real-time rainfall intensity are obtained and input into the optimal wind deflection angle calculation model to obtain the predicted wind deflection angle value.
2. The method for predicting the wind deflection angle of a power transmission line jumper as described in claim 1, characterized in that, Obtain the horizontal wind load and vertical wind load in the direction perpendicular to the conductor of the transmission line jumper, specifically including: The first wind speed at a reference height of 10m, conductor outer diameter, jumper span, wind pressure non-uniformity coefficient, wind pressure height variation coefficient, conductor shape coefficient, wind load adjustment coefficient, and wind load amplification coefficient are obtained and input into the preset horizontal wind load calculation formula in the vertical conductor direction to obtain the horizontal wind load in the vertical conductor direction. The preset horizontal wind load calculation formula in the vertical conductor direction is as follows: = ； In the formula, For the first wind speed, For the outer diameter of the conductor, For jumper spacing, For wind pressure non-uniformity coefficient, The wind pressure height variation coefficient, For the shape factor of the conductor, For wind load adjustment factor, This is the wind load amplification factor; Obtain the wind direction angle at a reference height of 10m. Input the wind direction angle and the horizontal wind load in the vertical traverse direction into the preset vertical wind load calculation formula to obtain the vertical wind load in the vertical traverse direction. The preset vertical wind load calculation formula is as follows: ； In the formula, This is the wind direction angle.
3. The method for predicting the wind deflection angle of a power transmission line jumper as described in claim 1, characterized in that, The model prediction dataset is input into the initial wind deflection calculation model to predict the wind deflection angle, thereby obtaining the optimal wind deflection calculation model, specifically including: Input the model prediction dataset into the initial wind deflection angle calculation model to obtain the sample prediction value corresponding to each prediction data sample in the model prediction dataset; The sample prediction values are input into the average relative error calculation formula to obtain the average relative error value; The average relative error value is compared with the preset average relative error threshold. When the average relative error value is less than the preset average relative error threshold, the current initial wind deflection angle calculation model is set as the optimal wind deflection angle calculation model.
4. A wind deflection angle prediction device for power transmission line jumpers, characterized in that, include: The module includes a load calculation module, a finite element modeling module, a model data partitioning module, an optimal wind deflection angle calculation model construction module, and a wind deflection angle prediction module. The load calculation module is used to obtain the horizontal wind load, the vertical wind load, and the rain load of the jumper wire in the direction of the vertical conductor of the transmission line. The specific process for obtaining the jumper rain load of transmission line jumpers includes: acquiring and inputting the following parameters (reference height 10m): first wind speed, raindrop diameter, jumper height, jumper height, number of raindrops per unit volume, wind pressure height variation coefficient, rainfall intensity, jumper rain-facing area, and jumper length into a preset jumper rain load calculation formula to obtain the jumper rain load. The preset jumper rain load calculation formula is as follows: ； ； ； In the formula, For the first wind speed, For raindrop diameter, At the height of the jumper, For jumper height, The number of raindrops per unit volume The wind pressure height variation coefficient, Rainfall intensity, The area of the jumper wire exposed to rain. This refers to the jumper length; The finite element modeling module is used to model the power transmission line jumper according to the horizontal wind load in the direction of the vertical conductor, the vertical wind load in the direction of the vertical conductor, and the jumper rain load to obtain an initial finite element model. The model data partitioning module is used to obtain wind deflection angle data under multiple preset working conditions based on the initial finite element model, and to partition the wind deflection angle data into a model training dataset and a model prediction dataset, wherein the preset working conditions include wind speed, wind direction and rainfall intensity. The optimal wind deflection angle calculation model construction module is used to train the BP neural network model based on the model training dataset to obtain an initial wind deflection angle calculation model, and input the model prediction dataset into the initial wind deflection angle calculation model to predict the wind deflection angle to obtain the optimal wind deflection angle calculation model. The wind deflection angle prediction module is used to acquire and input real-time wind speed, real-time wind direction and real-time rainfall intensity into the optimal wind deflection angle calculation model to obtain the wind deflection angle prediction value.
5. The wind deflection angle prediction device for power transmission line jumpers as described in claim 4, characterized in that, The load calculation module is used to obtain the horizontal wind load and the vertical wind load in the direction perpendicular to the conductor of the transmission line jumper, specifically including: The first wind speed at a reference height of 10m, conductor outer diameter, jumper span, wind pressure non-uniformity coefficient, wind pressure height variation coefficient, conductor shape coefficient, wind load adjustment coefficient, and wind load amplification coefficient are obtained and input into the preset horizontal wind load calculation formula in the vertical conductor direction to obtain the horizontal wind load in the vertical conductor direction. The preset horizontal wind load calculation formula in the vertical conductor direction is as follows: = ； In the formula, For the first wind speed, For the outer diameter of the conductor, For jumper spacing, For wind pressure non-uniformity coefficient, The wind pressure height variation coefficient, For the shape factor of the conductor, For wind load adjustment factor, This is the wind load amplification factor; Obtain the wind direction angle at a reference height of 10m. Input the wind direction angle and the horizontal wind load in the vertical traverse direction into the preset vertical wind load calculation formula to obtain the vertical wind load in the vertical traverse direction. The preset vertical wind load calculation formula is as follows: ； In the formula, This is the wind direction angle.
6. The wind deflection angle prediction device for transmission line jumpers as described in claim 4, characterized in that, The optimal wind deflection angle calculation model construction module is used to input the model prediction dataset into the initial wind deflection angle calculation model to predict the wind deflection angle and obtain the optimal wind deflection angle calculation model, specifically including: Input the model prediction dataset into the initial wind deflection angle calculation model to obtain the sample prediction value corresponding to each prediction data sample in the model prediction dataset; The sample prediction values are input into the average relative error calculation formula to obtain the average relative error value; The average relative error value is compared with the preset average relative error threshold. When the average relative error value is less than the preset average relative error threshold, the current initial wind deflection angle calculation model is set as the optimal wind deflection angle calculation model.
7. A terminal device, characterized in that, The method includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the wind deflection prediction method for transmission line jumpers as described in any one of claims 1 to 3.
8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device containing the computer-readable storage medium to perform the wind deflection angle prediction method for transmission line jumpers as described in any one of claims 1 to 3.