Method, device, computer equipment, readable storage medium and program product for predicting the grading ring hanging angle of a transmission line

Abstract

The present application relates to a method, device, computer equipment, readable storage medium and program product for predicting the grading ring hanging angle of a transmission line. The method obtains and inputs the target tower type and the insulation gap and grading ring size corresponding to the target tower type into a preset hanging angle prediction model, thereby obtaining the predicted grading ring hanging angle of the target transmission line tower corresponding to the target tower type under the target gap and grading ring size, wherein the predicted grading ring hanging angle is the acute angle between the outer ring of the grading ring and the normal of the transmission line. When the actual grading ring hanging angle of the target transmission line tower corresponding to the target tower type is set to the above-mentioned predicted grading ring hanging angle, it is possible to reduce noise pollution, flashover, electromagnetic interference and other phenomena generated by the target transmission line tower, and maintain the balance of the electric field around the target transmission line tower.

Description

Technical Field

[0001] The present application relates to the technical field of the hanging angle of a grading ring of a transmission line, and in particular to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for predicting the hanging angle of a grading ring of a transmission line. Background Art

[0002] Insulators are crucial components in transmission lines, carrying conductors and providing good electrical insulation. Multiple insulators are connected to form an insulator string. High voltage transmission lines place high demands on insulation, and this can be improved by increasing the number of insulators. However, the voltage distribution within an insulator string typically exhibits a U-shaped curve, with the insulators at the ends of the string bearing higher voltages and the insulators in the middle bearing lower voltages, making partial discharge more likely to occur.

[0003] The existing technology generally adopts the method of adding a grading ring to solve this problem. However, when the local field strength exceeds the corona starting field strength of the grading ring, corona discharge will be formed on the surface of the grading ring or in the surrounding air, resulting in an imbalance in the electric field distribution. Summary of the Invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for predicting the grading ring hanging angle of a transmission line that can maintain the balance of electric field distribution in order to address the above technical problems.

[0005] In a first aspect, the present application provides a method for predicting the grading ring mounting angle of a transmission line, comprising:

[0006] Obtain the target tower type and the insulation gap and grading ring size corresponding to the target tower type; wherein the insulation gap is the gap distance between the tower cross arm and the grading ring of the target tower type;

[0007] The target tower type and the insulation gap and grading ring size corresponding to the target tower type are input into the preset hanging angle prediction model to obtain the predicted grading ring hanging angle; wherein the predicted grading ring hanging angle is the acute angle between the outer ring of the grading ring and the normal of the transmission line; the preset hanging angle prediction model is a model trained based on multiple sample tower types, multiple sample insulation gaps, multiple sample grading ring sizes and multiple sample grading ring hanging angles.

[0008] In one embodiment, the step of determining the hanging angle of the sample pressure equalizing ring includes:

[0009] Construct multiple sample transmission tower models based on various sample tower types, multiple sample insulation gaps, and multiple sample grading ring sizes;

[0010] Under the condition of maintaining the sample insulation gap of each sample transmission tower model unchanged, adjusting the hanging angle of the grading ring of each sample transmission tower model;

[0011] According to the hanging angle of each grading ring and based on Maxwell's equations, the electric field amplitude on the surface of the grading ring corresponding to each hanging angle of the grading ring is determined;

[0012] The grading ring hanging angle corresponding to the minimum grading ring surface electric field amplitude in each sample transmission tower model is determined as the sample grading ring hanging angle.

[0013] In one embodiment, while maintaining the sample insulation gap of each sample transmission tower model unchanged, the step of adjusting the grading ring hanging angle of each sample transmission tower model includes:

[0014] Mark the hanging position of the pressure equalizing ring;

[0015] The hanging position of the grading ring is kept unchanged, and the length of the insulator corresponding to the target tower type is adjusted to adjust the hanging angle of the grading ring of each sample transmission tower model.

[0016] In one embodiment, the step of determining the electric field amplitude on the surface of the grading ring corresponding to each grading ring hanging angle according to the grading ring hanging angle and based on Maxwell's equations includes:

[0017] According to Maxwell's equations, the governing equations of the electroquasistatic field are determined; wherein the Maxwell's equations are target Maxwell's equations corresponding to the electroquasistatic field;

[0018] The electric field amplitude on the surface of the grading ring is determined according to the hanging angle of the grading ring and the control equation.

[0019] In one embodiment, the step of determining the preset docking angle prediction model includes:

[0020] Obtain a sample training set; wherein the sample training set includes multiple sample tower types, multiple sample insulation gaps, multiple sample grading ring sizes, and multiple sample grading ring hanging angles;

[0021] The sample training set is input into the machine learning algorithm for training to obtain a preset docking angle prediction model.

[0022] In one embodiment, the step of inputting the sample training set into a machine learning algorithm for training to obtain a preset docking angle prediction model includes:

[0023] Obtain a sample test set; wherein the sample test set includes multiple sample tower types, multiple sample insulation gaps, multiple sample grading ring sizes, and multiple sample grading ring hanging angles;

[0024] Input the test data in the sample test set into the preset anchor angle prediction model to obtain the prediction results;

[0025] Get the real results corresponding to the test data;

[0026] Determine the loss value between the predicted result and the actual result based on the preset loss function;

[0027] The gradient descent method is used to iteratively optimize the preset anchoring angle prediction model according to the loss value until the end condition is reached to obtain the preset anchoring angle prediction model.

[0028] In a second aspect, the present application further provides a device for predicting the angle of a grading ring of a transmission line, comprising:

[0029] A data acquisition module is used to obtain the target tower type and the insulation gap and grading ring size corresponding to the target tower type; wherein the insulation gap is the gap distance between the tower cross arm and the grading ring of the target tower type;

[0030] The prediction module is used to input the target tower type and the insulation gap and grading ring size corresponding to the target tower type into a preset hanging angle prediction model to obtain the predicted grading ring hanging angle; wherein the predicted grading ring hanging angle is the acute angle between the outer ring of the grading ring and the normal of the transmission line; the preset hanging angle prediction model is a model trained based on multiple sample tower types, multiple sample insulation gaps, multiple sample grading ring sizes and multiple sample grading ring hanging angles.

[0031] In a third aspect, the present application also provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements any step in the above-mentioned method for predicting the angle of the grading ring of the transmission line.

[0032] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any step in the above-mentioned method for predicting the grading ring hanging angle of a transmission line.

[0033] In a fifth aspect, the present application also provides a computer program product, comprising a computer program, which, when executed by a processor, implements any step in the above-mentioned method for predicting the grading ring hanging angle of a transmission line.

[0034] The above-mentioned transmission line grading ring hanging angle prediction method, apparatus, computer equipment, computer-readable storage medium, and computer program product obtain and input the target tower type and the insulation gap and grading ring size corresponding to the target tower type into a preset hanging angle prediction model to obtain the predicted grading ring hanging angle of the target transmission line tower corresponding to the target tower type under the target gap and grading ring size. The predicted grading ring hanging angle is the acute angle between the outer ring of the grading ring and the normal of the transmission line. Because the transmission line grading ring hanging angle prediction method incorporates the specific parameters of the target transmission line tower, the predicted grading ring hanging angle is output while taking into account the electric field distribution that may affect the target transmission line tower, and is highly reliable. When the actual grading ring hanging angle of the target transmission line tower corresponding to the target tower type is set to the above-mentioned predicted grading ring hanging angle, it can reduce noise pollution, flashover, electromagnetic interference, and other phenomena generated by the target transmission line tower, and maintain the balance of the electric field around the target transmission line tower. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments of the present application or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying any creative work.

[0036] Figure 1 This is a diagram showing an application environment of a method for predicting the hanging angle of a grading ring of a transmission line in one embodiment;

[0037] Figure 2 1 is a flow chart of a method for predicting the angle of a grading ring of a transmission line in one embodiment;

[0038] Figure 3 This is a flow chart of one step of determining the hanging angle of the sample pressure equalizing ring in one embodiment;

[0039] Figure 4 A schematic structural diagram of a sample transmission tower model in one embodiment;

[0040] Figure 5 This is a second flow chart of the step of determining the hanging angle of the sample pressure equalizing ring in one embodiment;

[0041] Figure 6 This is a third flow chart of the step of determining the hanging angle of the sample pressure equalizing ring in one embodiment;

[0042] Figure 7 FIG1 is a flow chart of a step of determining a preset docking angle prediction model in one embodiment;

[0043] Figure 8 This is a second flow chart of the steps of determining a preset docking angle prediction model in one embodiment;

[0044] Figure 9 1. It is a structural block diagram of a device for predicting the hanging angle of a grading ring of a transmission line in one embodiment;

[0045] Figure 10 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0047] The method for predicting the angle of the grading ring of a transmission line provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. The terminal 102 communicates with the server 104 via a network. The data storage system can store the relevant data of the target tower type that the server 104 needs to process, as well as the insulation gap and grading ring size corresponding to the target tower type. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The server 104 obtains and inputs the relevant data of the target tower type and the insulation gap and grading ring size corresponding to the target tower type into a preset hanging angle prediction model to obtain the predicted grading ring hanging angle of the target tower type. The preset hanging angle prediction model is a prediction model determined by a model trained based on multiple sample tower types, multiple sample insulation gaps, multiple sample grading ring sizes and multiple sample grading ring hanging angles. The terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, projection equipment, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The head-mounted device may be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. The server 104 may be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0048] In an exemplary embodiment, Figure 2 As shown in the figure, a method for predicting the angle of the grading ring of a transmission line is provided. Figure 1The server 104 in FIG. 1 is used as an example to illustrate the present invention, including:

[0049] S202, obtaining the target tower type and the insulation gap and grading ring size corresponding to the target tower type; wherein the insulation gap is the gap distance between the tower cross arm and the grading ring of the target tower type. The insulation gap can be found in Figure 4 The distance d is indicated in the figure.

[0050] The target tower type includes the tower head model of the target transmission line tower, wherein the tower head includes the tower body and the tower body cross arm.

[0051] Graduating rings are devices that evenly distribute high voltage around an object, ensuring no potential difference between different parts of the ring, thus achieving a voltage equalization effect. When applied to transmission line towers, grading rings can evenly distribute the electric field on the insulators on the tower, thereby reducing the range of electric field variation on the insulators and preventing insulator breakdown due to excessive electric fields. Graduating rings are typically installed on transmission line towers with large creepage distances and high voltage insulators. Creepage distance refers to the safe distance required for current to leak to the ground or surrounding objects due to insulation failure or other reasons. Generally, higher levels of contamination reduce the creepage distance and result in more uneven electric field distribution on the insulator surface.

[0052] The size of the equalizing ring is related to the equalizing effect. A larger diameter ring increases its effective area, providing better electric field uniformity. Increasing the thickness of the ring can enhance its electric field dispersion. Therefore, the size of the equalizing ring can include both its outer diameter and its inner diameter.

[0053] The grading ring includes open grading ring and closed grading ring. Among them, the open grading ring can be installed in the middle or end of the insulator, while the closed grading ring can be installed on the insulator head.

[0054] S204, input the target tower type and the insulation gap and grading ring size corresponding to the target tower type into the preset hanging angle prediction model to obtain the predicted grading ring hanging angle; wherein, the predicted grading ring hanging angle is the acute angle between the outer ring of the grading ring and the normal of the transmission line; the preset hanging angle prediction model is a model trained based on multiple sample tower types, multiple sample insulation gaps, multiple sample grading ring sizes and multiple sample grading ring hanging angles.

[0055] By pairing different sample tower types, different sample insulation gaps, and different sample grading ring sizes, we can obtain corresponding sample grading ring mounting angles. Model training based on multiple sample tower types, multiple sample insulation gaps, multiple sample grading ring sizes, and multiple sample grading ring mounting angles can produce a preset mounting angle prediction model that can output a predicted grading ring mounting angle. This allows us to obtain a predicted grading ring mounting angle based on the target tower type and its corresponding insulation gap and grading ring size.

[0056] The above-mentioned method for predicting the grading ring hanging angle of the transmission line can obtain the predicted grading ring hanging angle of the target transmission line tower corresponding to the target tower type under the target gap and grading ring size by obtaining and inputting the target tower type and the insulation gap and grading ring size corresponding to the target tower type into a preset hanging angle prediction model, wherein the predicted grading ring hanging angle is the acute angle between the outer ring of the grading ring and the normal of the transmission line. Since the transmission line grading ring hanging angle prediction method combines the specific parameters of the target transmission line tower, the predicted grading ring hanging angle is output under the consideration of the electric field distribution that can affect the target transmission line tower, and has high reliability. When the actual grading ring hanging angle of the target transmission line tower corresponding to the target tower type is set to the above-mentioned predicted grading ring hanging angle, the noise pollution, flashover, electromagnetic interference and other phenomena generated by the target transmission line tower can be reduced, and the balance of the electric field around the target transmission line tower can be maintained.

[0057] In an exemplary embodiment, Figure 3 As shown, the steps for determining the hanging angle of the sample pressure equalizing ring include:

[0058] S302: Construct multiple sample transmission tower models based on multiple sample tower types, multiple sample insulation gaps, and multiple sample grading ring sizes.

[0059] Based on different sample tower types, different sample insulation gaps, and different sample grading ring sizes, a one-to-one corresponding sample transmission tower model can be constructed. Figure 4 The structure diagram of the sample transmission tower model is shown, wherein the tower head 402 includes a tower body 4022 and a tower cross arm 4024; the transmission line 404 includes a split conductor 4042, a grading ring 4044 and an insulator 4046.

[0060] In one embodiment, the sample transmission tower model can be implemented using model building software, such as CAD (Computer-Aided Design).

[0061] S304: While maintaining the sample insulation gap of each sample transmission tower model unchanged, adjust the hanging angle of the grading ring of each sample transmission tower model.

[0062] S306 , determining the electric field amplitude on the surface of the grading ring corresponding to each grading ring hanging angle according to the grading ring hanging angle and based on Maxwell's equations.

[0063] S308: Determine the grading ring hanging angle corresponding to the minimum grading ring surface electric field amplitude in each sample transmission tower model as the sample grading ring hanging angle.

[0064] Since the larger the electric field amplitude on the surface of the grading ring is, the greater the probability and harm of corona discharge will be. Therefore, the minimum value of the electric field amplitude on the surface of the grading ring is selected as the optimal value, that is, the grading ring hanging angle corresponding to the minimum surface electric field amplitude is the optimal sample grading ring hanging angle.

[0065] Because the physical field corresponding to transmission line towers is a steady-state electrostatic field, electric field analysis of the sample transmission tower model can be performed based on the simulated physics provided by the simulation platform. For example, the AC / DC module provided by COMSOL (COMSOL Multiphysics) is suitable for static, steady-state, time-varying, transient electromagnetic, and multi-physics coupling analysis, thus meeting the requirements for simulation analysis of the sample transmission tower model.

[0066] In one embodiment, determining the electric field amplitude on the surface of the grading ring includes the following steps:

[0067] The sample transmission tower model built using the model building software is input into the simulation platform.

[0068] The model materials in the sample transmission tower model can be selected based on the materials of actual transmission line towers. Specifically, the tower body, tower crossarms, and split conductors of the sample transmission tower model can be made of stainless steel, which is used in actual application scenarios. The grading ring of the sample transmission tower model can be made of aluminum alloy, which is used in actual application scenarios. The insulators of the sample transmission tower model can be made of rubber, which is used in actual application scenarios. The parameter settings of the surrounding environment of the sample transmission tower model, such as air quality, can also be based on the environmental settings in actual application scenarios. This can achieve the same or similar conductivity and relative dielectric constant as those of actual transmission line towers.

[0069] Exemplarily, the format of the sample transmission tower model input into the simulation platform may be in .dxf (Drawing Exchange Format) format.

[0070] Set up boundary conditions for the sample transmission tower model.

[0071] Among them, the parameters involved in the boundary conditions include the charge conservation of the sample transmission tower model, the low-voltage end of the sample transmission tower model (the tower body and the hardware connected to the tower body), and the high-voltage end of the sample transmission tower model (the split conductor, the grading ring, and the hardware in contact with the split conductor).

[0072] Select and mesh the sample transmission tower model based on the mesh type and mesh size.

[0073] The mesh defines the shape and structure of the sample transmission tower model. This allows for precise definition of both the exterior and internal structure of the sample tower model, enabling modeling of complex shapes and intricate details. The size of the mesh also influences the appearance and internal structure of the sample tower model. Generally, smaller mesh sizes result in more accurate sample tower models.

[0074] Specifically, when the sample transmission tower model is a two-dimensional model, the mesh type may be free triangle, the minimum unit size may be 3 mm, the maximum unit size may be 6360 mm, and the maximum unit growth rate may be 1.3.

[0075] Set up the solver.

[0076] The electric field amplitude on the surface of the grading ring at the current grading ring hanging angle is calculated based on the solver and Maxwell's equations.

[0077] Since the physical field corresponding to the transmission line tower is a steady-state electrostatic field, the solver can be a steady-state solver to ensure rapid model convergence. Specifically, the solver's initial damping coefficient can be set to 1, the minimum damping coefficient can be set to 1E-4, the termination technique can be set to iteration end or tolerance satisfaction, the number of iterations can be set to 25, and the tolerance factor can be set to 1.

[0078] Post-process the electric field amplitude on the surface of the grading ring.

[0079] Among them, post-processing of the electric field amplitude on the surface of the grading ring can analyze the electric field distribution and specific values ​​of the sample transmission tower model.

[0080] In an exemplary embodiment, Figure 5 As shown, while maintaining the sample insulation gap of each sample transmission tower model unchanged, the steps of adjusting the grading ring hanging angle of each sample transmission tower model include:

[0081] S502, marking the hanging position of the pressure equalizing ring.

[0082] S504: Keep the hanging position of the grading ring unchanged, and adjust the length of the insulator corresponding to the target tower type to adjust the hanging angle of the grading ring of each sample transmission tower model.

[0083] The marking position can be determined by establishing a vertical line between the equalizing ring and the tower cross arm. In this case, when the projection of the equalizing ring on the plane where the tower cross arm and the tower body are located is kept at the marking position determined by the above vertical line, the hanging position of the equalizing ring can be kept unchanged.

[0084] In one embodiment, the insulator can be rotated with the end closest to the split conductor as the axis of rotation to adjust the grading ring's mounting angle. During rotation, the insulator's end no longer rests on the tower crossarm, and the grading ring's mounting position changes. Therefore, the insulator's length needs to be adjusted so that the insulator's end rests on the tower crossarm again and the grading ring's mounting position returns to the marked position.

[0085] In one embodiment, the insulator can be rotated with the marked position as the rotation axis to adjust the grading ring hanging angle. During the rotation process, the length of the insulator needs to be adjusted so that one end of the insulator is connected to the split conductor and the other end is hung on the tower crossarm.

[0086] In an exemplary embodiment, Figure 6 As shown, according to the hanging angle of each grading ring and based on Maxwell's equations, the steps of determining the electric field amplitude on the surface of the grading ring corresponding to each hanging angle of the grading ring include:

[0087] S602 : Determine the control equations of the electroquasistatic field according to Maxwell's equations; wherein the Maxwell's equations are target Maxwell's equations corresponding to the electroquasistatic field.

[0088] S604: Determine the electric field amplitude on the surface of the grading ring according to the grading ring hanging angle and the control equation.

[0089] Since the transmission line is a bushing structure, the sample transmission tower model constructed based on the actual transmission line tower can be studied according to the characteristics of the bushing structure. Generally, the bushing structure can be considered to be in an electro-quasi-static field.

[0090] Therefore, calculations can be performed based on Maxwell's equations for the electroquasistatic field, which can be expressed as:

[0091]

[0092] in, is an operator that can act on scalar fields or vector fields; represents the electric displacement vector; represents the volume charge density; B is the magnetic flux density; Indicates the electric field strength; Indicates time; Indicates the magnetic field strength; represents the conduction current density.

[0093] According to the constitutive relationship of the medium and the relationship between the electric field and the electric potential, the following governing equations can be determined:

[0094]

[0095] in, represents electric potential; Indicates the coordinates corresponding to the pressure equalizing ring; Representation field function The rate of change in the r direction; represents the diffusion of the field function in the z direction. A polar coordinate system is established with the end of the insulator closest to the split conductor as the rotation axis and a line parallel to the normal of the transmission line and passing through the rotation axis as the polar axis.

[0096] The constitutive relation of the medium can be expressed as:

[0097]

[0098] in, Represents the relative dielectric constant of the medium.

[0099] The relationship between electric field and electric potential can be expressed as:

[0100]

[0101] in, Indicates conductivity.

[0102] According to the above control equation, the potential distribution at the grading ring hanging angle can be determined, and based on the relationship between the electric field and the electric potential, the electric field amplitude on the surface of the grading ring in the electrostatic field can be determined.

[0103] In an exemplary embodiment, Figure 7 As shown, the steps for determining the preset docking angle prediction model include:

[0104] S702, obtaining a sample training set; wherein the sample training set includes a plurality of sample tower types, a plurality of sample insulation gaps, a plurality of sample grading ring sizes, and a plurality of sample grading ring hanging angles.

[0105] The sample tower type, sample insulation gap and sample grading ring size in the sample training set can be determined based on field measurements, reference to the transmission line tower manual corresponding to the sample transmission tower model, etc.; the sample grading ring hanging angle can be determined according to the above-mentioned steps for determining the sample grading ring hanging angle, which will not be repeated here.

[0106] S704: Input the sample training set into a machine learning algorithm for training to obtain a preset docking angle prediction model.

[0107] The machine learning algorithm can be a neural network algorithm, which consists of an input layer, hidden layers, and an output layer. The input layer is the first layer of the neural network algorithm and is primarily responsible for receiving the sample training set. The number of neurons in the input layer corresponds to the number of features in the input sample training set. The input layer can perform data preprocessing, such as normalization or standardization, on the input sample training set to improve the performance of the preset anchor angle prediction model.

[0108] The hidden layer, located between the input and output layers, is primarily responsible for nonlinear transformation and feature extraction. The neurons in the hidden layer perform nonlinear transformations on the input signal using activation functions, extracting key features from the sample training set. The number and structure of hidden layers can be adjusted based on the amount of data in the sample training set. These activation functions can include Sigmoid (standard logistic function), Tanh (hyperbolic tangent function), ReLU (rectified linear unit), and others. These activation functions can improve the performance of the pre-set docking angle prediction model.

[0109] The output layer is the last layer of the neural network algorithm and is responsible for generating the final prediction results. The output layer can convert the output of the hidden layer into a specific prediction result.

[0110] In an exemplary embodiment, Figure 8 As shown, the steps of inputting the sample training set into the machine learning algorithm for training to obtain the preset anchoring angle prediction model include:

[0111] S802, obtaining a sample test set; wherein the sample test set includes a plurality of sample tower types, a plurality of sample insulation gaps, a plurality of sample grading ring sizes, and a plurality of sample grading ring hanging angles.

[0112] Among them, the data in the sample test set does not overlap with the data in the sample training set.

[0113] S804: Input the test data in the sample test set into a preset anchoring angle prediction model to obtain a prediction result.

[0114] S806: Obtain the actual result corresponding to the test data.

[0115] Based on the test data of a sample transmission line tower in the sample test set, a prediction result can be determined; the sample transmission line tower has an actual real result in actual application, and the real result is the real result corresponding to the test data.

[0116] S808: Determine the loss value between the predicted result and the actual result based on a preset loss function.

[0117] The loss value can be determined based on a loss function, which can be a cross entropy loss function, a multi-label classification loss function, etc., which is not limited here.

[0118] S810, using the gradient descent method, iteratively optimize the preset anchoring angle prediction model according to the loss value until the end condition is reached, thereby obtaining the preset anchoring angle prediction model.

[0119] Optimization refers to guiding the update direction of the various parameters of the loss function during the backpropagation process of a machine learning model (especially a neural network algorithm) so that the updated parameters can bring the loss value close to the global minimum. By optimizing parameters such as weights, biases, and learning rates in the preset anchor angle prediction model, the optimized preset anchor angle prediction model can be obtained when the training reaches the number of iterations or the loss value reaches the loss threshold, etc.

[0120] In one embodiment, an adaptive gradient algorithm, a root mean square propagation algorithm, an adaptive moment estimation algorithm, etc. may also be used for iterative optimization.

[0121] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0122] Based on the same inventive concept, an embodiment of the present application further provides a device for predicting the attachment angle of a grading ring of a transmission line for implementing the aforementioned method for predicting the attachment angle of a grading ring of a transmission line. The solution provided by the device for solving the problem is similar to the solution described in the aforementioned method. Therefore, the specific limitations in the embodiments of the device for predicting the attachment angle of a grading ring of a transmission line provided below can be found in the limitations of the method for predicting the attachment angle of a grading ring of a transmission line described above, and will not be repeated here.

[0123] In an exemplary embodiment, Figure 9 As shown, a device 900 for predicting the grading ring hanging angle of a transmission line is provided, comprising: a data acquisition module 902 and a prediction module 904, wherein:

[0124] The data acquisition module 902 is used to obtain the target tower type and the insulation gap and grading ring size corresponding to the target tower type; wherein the insulation gap is the gap distance between the tower cross arm and the grading ring of the target tower type.

[0125] The prediction module 904 is used to input the target tower type and the insulation gap and grading ring size corresponding to the target tower type into the preset hanging angle prediction model to obtain the predicted grading ring hanging angle; wherein, the predicted grading ring hanging angle is the acute angle between the outer ring of the grading ring and the normal of the transmission line; the preset hanging angle prediction model is a model trained based on multiple sample tower types, multiple sample insulation gaps, multiple sample grading ring sizes and multiple sample grading ring hanging angles.

[0126] In an exemplary embodiment, the above-mentioned device 900 for predicting the grading ring hanging angle of a transmission line further includes: a model building module, an adjustment module, a calculation module, and a determination module.

[0127] The model building module is used to build multiple sample transmission tower models based on various sample tower types, multiple sample insulation gaps, and multiple sample grading ring sizes.

[0128] The adjustment module is used to adjust the hanging angle of the grading ring of each sample transmission tower model while maintaining the sample insulation gap of each sample transmission tower model unchanged.

[0129] The calculation module is used to determine the electric field amplitude on the surface of the grading ring corresponding to each grading ring hanging angle according to the grading ring hanging angle and based on Maxwell's equations.

[0130] The determination module is used to determine the grading ring hanging angle corresponding to the minimum grading ring surface electric field amplitude in each sample transmission tower model as the sample grading ring hanging angle.

[0131] In an exemplary embodiment, the adjustment module includes: a marking module and an adjustment submodule.

[0132] The marking module is used to mark the hanging position of the pressure equalizing ring.

[0133] The adjustment submodule is used to keep the hanging position of the grading ring unchanged and adjust the length of the insulator corresponding to the target tower type to adjust the hanging angle of the grading ring of each sample transmission tower model.

[0134] In an exemplary embodiment, the calculation module includes: a control equation determination module and a calculation submodule.

[0135] The control equation determination module is used to determine the control equation of the electroquasistatic field based on Maxwell's equations; wherein the Maxwell's equations are target Maxwell's equations corresponding to the electroquasistatic field.

[0136] The calculation submodule is used to determine the electric field amplitude on the surface of the grading ring according to the grading ring hanging angle and the control equation.

[0137] In an exemplary embodiment, the step of determining the preset docking angle prediction model includes:

[0138] Obtain a sample training set; wherein the sample training set includes multiple sample tower types, multiple sample insulation gaps, multiple sample grading ring sizes, and multiple sample grading ring hanging angles;

[0139] The sample training set is input into the machine learning algorithm for training to obtain a preset docking angle prediction model.

[0140] In an exemplary embodiment, the above-mentioned device 900 for predicting the grading ring hanging angle of a transmission line further includes: a sample test set acquisition module, a prediction result determination module, a real result acquisition module, a loss value determination module and an optimization module.

[0141] The sample test set acquisition module is used to acquire a sample test set; wherein the sample test set includes a plurality of sample tower types, a plurality of sample insulation gaps, a plurality of sample grading ring sizes and a plurality of sample grading ring hanging angles.

[0142] The prediction result determination module is used to input the test data in the sample test set into the preset anchoring angle prediction model to obtain the prediction result.

[0143] The real result acquisition module is used to obtain the real results corresponding to the test data.

[0144] The loss value determination module is used to determine the loss value between the predicted result and the actual result based on a preset loss function.

[0145] The optimization module is used to iteratively optimize the preset anchoring angle prediction model using the gradient descent method according to the loss value until the end condition is reached to obtain the preset anchoring angle prediction model.

[0146] Each module in the aforementioned transmission line grading ring attachment angle prediction device can be implemented in whole or in part via software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0147] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 10As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store relevant data of the target tower type to be processed and the insulation gap and grading ring size corresponding to the target tower type. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for predicting the grading ring hanging angle of a transmission line is implemented.

[0148] Those skilled in the art will understand that Figure 10 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0149] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor executes the steps of any one of the above-mentioned methods for predicting the grading ring hanging angle of a transmission line.

[0150] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any method of the above-mentioned method for predicting the hanging angle of the grading ring of the transmission line are implemented.

[0151] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the steps of any one of the above-mentioned methods for predicting the hanging angle of a grading ring of a transmission line.

[0152] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), quantum computing-based data processing logic devices, artificial intelligence (AI) processors, and the like.

[0153] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0154] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for predicting the angle of a grading ring of a transmission line, characterized in that: The method comprises: Obtaining a target tower type and the insulation gap and grading ring size corresponding to the target tower type; wherein the insulation gap is the gap distance between the tower cross arm and the grading ring of the target tower type; The target tower type and the insulation gap and grading ring size corresponding to the target tower type are input into a preset hanging angle prediction model to obtain a predicted grading ring hanging angle; wherein, the predicted grading ring hanging angle is the acute angle between the outer ring of the grading ring and the normal of the transmission line; the preset hanging angle prediction model is a model trained based on multiple sample tower types, multiple sample insulation gaps, multiple sample grading ring sizes and multiple sample grading ring hanging angles.

2. The method according to claim 1, characterized in that The step of determining the hanging angle of the sample pressure equalizing ring includes: Constructing a plurality of sample transmission tower models according to the plurality of sample tower types, the plurality of sample insulation gaps, and the plurality of sample grading ring sizes; Under the condition of maintaining the sample insulation gap of each of the sample transmission tower models unchanged, adjusting the hanging angle of the grading ring of each of the sample transmission tower models; According to the hanging angles of the grading rings and based on Maxwell's equations, the electric field amplitudes on the surfaces of the grading rings corresponding to the hanging angles of the grading rings are determined; The grading ring hanging angle corresponding to the minimum grading ring surface electric field amplitude in each of the sample transmission tower models is determined as the sample grading ring hanging angle.

3. The method according to claim 2, characterized in that The step of adjusting the hanging angle of the grading ring of each of the sample transmission tower models while maintaining the sample insulation gap of each of the sample transmission tower models unchanged comprises: Mark the hanging position of the pressure equalizing ring; The hanging position of the grading ring is kept unchanged, and the length of the insulator corresponding to the target tower type is adjusted to adjust the hanging angle of the grading ring of each sample transmission tower model.

4. The method according to claim 2, characterized in that The step of determining the electric field amplitude on the surface of the grading ring corresponding to each grading ring hanging angle according to each grading ring hanging angle and based on Maxwell's equations includes: Determining the control equations of the electroquasistatic field according to the Maxwell equations; wherein the Maxwell equations are target Maxwell equations corresponding to the electroquasistatic field; The electric field amplitude on the surface of the grading ring is determined according to the grading ring hanging angle and the control equation.

5. The method according to claim 1, wherein The step of determining the preset docking angle prediction model includes: Obtaining a sample training set; wherein the sample training set includes the multiple sample tower types, the multiple sample insulation gaps, the multiple sample grading ring sizes, and the multiple sample grading ring hanging angles; The sample training set is input into a machine learning algorithm for training to obtain the preset docking angle prediction model.

6. The method according to claim 5, characterized in that The step of inputting the sample training set into a machine learning algorithm for training to obtain the preset docking angle prediction model includes: Obtaining a sample test set; wherein the sample test set includes the multiple sample tower types, the multiple sample insulation gaps, the multiple sample grading ring sizes, and the multiple sample grading ring hanging angles; Inputting the test data in the sample test set into the preset anchor angle prediction model to obtain a prediction result; Obtaining the actual result corresponding to the test data; Determine the loss value between the predicted result and the actual result based on a preset loss function; The preset docking angle prediction model is iteratively optimized according to the loss value using a gradient descent method until an end condition is reached, thereby obtaining the preset docking angle prediction model.

7. A device for predicting the angle of a grading ring of a transmission line, characterized in that: The device comprises: A data acquisition module is used to obtain a target tower type and the insulation gap and grading ring size corresponding to the target tower type; wherein the insulation gap is the gap distance between the tower cross arm and the grading ring of the target tower type; A prediction module is used to input the target tower type and the insulation gap and grading ring size corresponding to the target tower type into a preset hanging angle prediction model to obtain a predicted grading ring hanging angle; wherein the predicted grading ring hanging angle is the acute angle between the outer ring of the grading ring and the normal of the transmission line; the preset hanging angle prediction model is a model trained based on multiple sample tower types, multiple sample insulation gaps, multiple sample grading ring sizes and multiple sample grading ring hanging angles.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images