A mechanical calculation method and system based on transmission tower conductors

Abstract

This invention provides a method and system for mechanical calculation of transmission tower conductors. It collects multi-source meteorological data and fuses similar data from these sources using the entropy weight method to obtain fused meteorological parameter values. Based on the fused meteorological parameter values ​​and the conductor's mechanical property gradient, adaptive segmentation of the conductor is performed. For each segment, a simulation calculation model integrating the meteorological-mechanical coupling relationship is constructed. AI-optimized boundary conditions are combined, and the finite element method is used to solve the simulation calculation model for each segment, yielding the mechanical calculation results for each segment. An attention mechanism is used to assign differentiated weights to the mechanical calculation results of different segments, and a weighted fusion strategy is employed to obtain the global mechanical calculation results. Specifically, the accuracy of the simulation calculation is improved by precisely adapting meteorological data to the segmentation.

Description

Technical Field

[0001] This invention belongs to the field of power transmission line engineering technology, and specifically relates to a mechanical calculation method and system based on power transmission tower conductors. Background Technology

[0002] As the core carrier of power transmission, the mechanical properties (such as stress, strain, and sag) of transmission lines directly determine their safe and stable operation. Complex meteorological conditions (such as strong winds, icing, and sudden temperature changes) can significantly alter the physical properties and external loads of conductors, leading to faults such as conductor fatigue fracture, galloping, and icing collapse. Therefore, accurate conductor mechanical simulation is of great significance for ensuring the safety of transmission lines.

[0003] Existing mechanical calculation methods for transmission lines mostly use a single, fixed meteorological parameter to be substituted into the simulation model, without considering the spatiotemporal dynamic changes of meteorological parameters and the complementarity of multi-source data. This results in insufficient accuracy of the basic data for simulation calculations. In addition, the simulation model usually directly outputs the mechanical simulation calculation parameters of the conductor between two transmission towers. However, for conductors with longer distances, they are more susceptible to interference from the external environment, so the mechanical parameters calculated are not accurate. Summary of the Invention

[0004] Based on this, the present invention provides a mechanical calculation method and system based on transmission tower conductors, aiming to improve the accuracy and reliability of simulation calculations through AI-meteorological fusion segmented mechanical simulation calculations based on transmission tower conductors.

[0005] A first aspect of this invention provides a mechanical calculation method based on the conductor of a power transmission tower, the method comprising:

[0006] Collect multi-source meteorological data, and fuse similar types of data from the multi-source meteorological data according to the entropy weight method to obtain fused meteorological parameter values;

[0007] Based on the fused meteorological parameter values ​​and the gradient of the conductor's mechanical properties, adaptive segmentation of the conductor is performed;

[0008] For each segment, a simulation calculation model integrating meteorological-mechanical coupling is constructed. The boundary conditions are optimized by AI, and the finite element method is used to solve the simulation calculation model of each segment to obtain the mechanical calculation results of each segment.

[0009] By assigning differentiated weights to the mechanical calculation results of different segments through an attention mechanism, and by adopting a weighted fusion strategy, the global mechanical calculation results are obtained.

[0010] Furthermore, the multi-source meteorological data includes fixed monitoring data, mobile sensing data, and numerical forecast data;

[0011] The fixed monitoring data is collected in real time by miniature weather stations deployed at the top of the transmission tower, the conductor suspension point and the middle section to collect wind speed, wind direction, ambient temperature, relative humidity and icing thickness.

[0012] The mobile sensing data is collected by a drone equipped with sensors cruising along the guide path to collect data on the surface temperature of the guide and the local wind speed gradient.

[0013] The numerical forecast data is obtained by accessing short-term numerical forecast data from regional meteorological departments to obtain the spatiotemporal variation trends of meteorological parameters.

[0014] Furthermore, in the step of collecting multi-source meteorological data and fusing similar data from the multi-source meteorological data according to the entropy weight method to obtain fused meteorological parameter values, the weights are determined by calculating the information entropy of the multi-source meteorological data, and then the similar data are weighted and summed to obtain the fusion result. The weight calculation and fusion formula are as follows:

[0015] ;

[0016] ;

[0017] Among them, w j Let e ​​be the weight of the j-th data source. j Let p be the information entropy of the j-th data source. ij Let z be the normalized probability of the i-th data point in the j-th data source. j Let z be the meteorological parameter value of the j-th data source, m be the total number of data sources participating in the fusion, n be the number of data samples contained in the j-th data source, and z be the value of the meteorological parameter of the j-th data source. 融合 These are the merged meteorological parameter values.

[0018] Furthermore, the step of adaptively segmenting the conductor based on the fused meteorological parameter values ​​and the conductor's mechanical property gradient includes:

[0019] Based on the fused meteorological parameter values, meteorological features are extracted. At the same time, based on the classical catenary equation, initial mechanical features are determined. Based on the meteorological features and the initial mechanical features, a piecewise feature vector is constructed. The meteorological features include wind speed gradient, temperature gradient, and icing thickness gradient. The initial mechanical features include the initial stress and sag of the conductor.

[0020] Based on the segmented feature vectors, the improved K-means algorithm is used to determine the optimal number of segments through the elbow rule, and the cluster centers are iteratively optimized with the goal of minimizing the feature variance within segments and maximizing the variance between segments to obtain the initial segments;

[0021] Based on the conductor suspension point constraints and the insulator string swing characteristics, the initial segmentation is adjusted to obtain the final segmentation result.

[0022] Furthermore, in the step of constructing a simulation calculation model integrating the meteorological-mechanical coupling relationship for each segment, combining AI-optimized boundary conditions, and solving the simulation calculation model for each segment using the finite element method to obtain the mechanical calculation results for each segment, the simulation calculation model is represented as follows:

[0023] ;

[0024] ;

[0025] ;

[0026] Where Δγ is the weight increase per unit length of the conductor caused by icing, and γ is the weight per unit length of the conductor itself, Δγ=πδ(2r+δ)γ 冰 r is the radius of the conductor, γ 冰 Let ρ be the density of the ice, δ be the thickness of the ice cover, and q be the density of the ice. w (x) represents the wind load distribution per unit length of the conductor at position x, C d ρ is the wind resistance coefficient, D is the air density, v(x) is the equivalent diameter of the conductor, σ(x) is the actual wind speed at position x, α is the axial stress of the conductor at position x, T0 is the reference temperature, T is the actual ambient temperature, σ0 is the initial axial stress of the conductor at the reference temperature, A is the cross-sectional area of ​​the conductor, and E is the elastic modulus of the conductor material.

[0027] Furthermore, in the step of constructing a simulation calculation model that integrates meteorological-mechanical coupling for each segment, combining AI-optimized boundary conditions, and solving the simulation calculation model of each segment using the finite element method to obtain the mechanical calculation results of each segment, a BP neural network is used to optimize the boundary conditions. The input layer of the BP neural network includes the meteorological characteristics of the segment, the initial mechanical characteristics, and the segment length.

[0028] The output layer of the BP neural network consists of optimized boundary conditions at both ends of the segment, including horizontal displacement, vertical displacement, axial force, and bending moment.

[0029] The model is trained using historical measured data as labels to train a backpropagation neural network, and the network parameters are optimized using gradient descent.

[0030] Furthermore, the step of assigning differentiated weights to the mechanical calculation results of different segments through an attention mechanism and adopting a weighted fusion strategy to obtain the global mechanical calculation results includes:

[0031] The simulation credibility features of each segment are extracted, including local error features, boundary continuity features, and meteorological matching features.

[0032] Based on the simulation credibility features and the constructed multilayer perceptron, calculate the attention weight for each segment;

[0033] Based on the mechanical calculation results and attention weights of each segment, a weighted fusion is performed to obtain the global mechanical calculation result.

[0034] A second aspect of this invention provides a mechanical calculation system based on transmission tower conductors, used to implement the mechanical calculation method based on transmission tower conductors described in the first aspect, the system comprising:

[0035] The first fusion module is used to collect multi-source meteorological data and fuse similar data from the multi-source meteorological data according to the entropy weight method to obtain fused meteorological parameter values.

[0036] The segmentation module is used to adaptively segment the conductor based on the fused meteorological parameter values ​​and the conductor's mechanical property gradient.

[0037] The module is used to build a simulation calculation model that integrates the meteorological-mechanical coupling relationship for each segment, combine AI-optimized boundary conditions, and use the finite element method to solve the simulation calculation model of each segment to obtain the mechanical calculation results of each segment.

[0038] The second fusion module is used to assign differentiated weights to the mechanical calculation results of different segments through an attention mechanism, and to obtain the global mechanical calculation results by adopting a weighted fusion strategy.

[0039] A third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the mechanical calculation method based on transmission tower conductors provided in the first aspect.

[0040] A fourth aspect of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the mechanical calculation method based on transmission tower conductors provided in the first aspect.

[0041] This invention provides a method and system for mechanical calculation of transmission tower conductors. It collects multi-source meteorological data and fuses similar data from these sources using the entropy weight method to obtain fused meteorological parameter values. Based on the fused meteorological parameter values ​​and the conductor's mechanical property gradient, the conductor is adaptively segmented. For each segment, a simulation calculation model integrating the meteorological-mechanical coupling relationship is constructed. AI-optimized boundary conditions are combined, and the finite element method is used to solve the simulation calculation model for each segment, yielding the mechanical calculation results for each segment. An attention mechanism is used to assign differentiated weights to the mechanical calculation results of different segments, and a weighted fusion strategy is employed to obtain the global mechanical calculation results. Specifically, the accuracy of the simulation calculation is improved by precisely adapting meteorological data to the segmentation. Attached Figure Description

[0042] Figure 1 This is a flowchart illustrating the implementation of a mechanical calculation method based on transmission tower conductors provided in Embodiment 1 of the present invention.

[0043] Figure 2 This is a structural block diagram of a mechanical calculation system based on a power transmission tower conductor provided in Embodiment 2 of the present invention;

[0044] Figure 3 This is a structural block diagram of an electronic device provided in Embodiment 3 of the present invention. Detailed Implementation

[0045] To facilitate understanding of the present invention, a more complete description will be given below with reference to the accompanying drawings. Several embodiments of the invention are illustrated in the drawings. However, the invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.

[0046] It should be noted that when a component is said to be "fixed to" another component, it can be directly on the other component or there may be an intervening component. When a component is said to be "connected to" another component, it can be directly connected to the other component or there may be an intervening component. The terms "vertical," "horizontal," "left," "right," and similar expressions used in this document are for illustrative purposes only.

[0047] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0048] Example 1

[0049] According to an embodiment of the present invention, a mechanical calculation method based on the conductor of a power transmission tower is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0050] This first embodiment provides a mechanical calculation method based on the conductors of power transmission towers, which can be used in electronic devices, such as computers. Please refer to... Figure 1 , Figure 1 The flowchart of the implementation of a mechanical calculation method based on the conductor of a power transmission tower provided in Embodiment 1 of the present invention is shown, specifically including steps S01 to S04.

[0051] Step S01: Collect multi-source meteorological data, and according to the entropy weight method, fuse the same type of data in the multi-source meteorological data to obtain the fused meteorological parameter values.

[0052] Specifically, the multi-source meteorological data includes fixed monitoring data, mobile sensing data, and numerical weather prediction data;

[0053] The fixed monitoring data is collected in real time by miniature weather stations deployed at the top of the transmission tower, the conductor suspension point and the middle section to collect wind speed, wind direction, ambient temperature, relative humidity and icing thickness.

[0054] The mobile sensing data is collected by a drone equipped with sensors cruising along the guide path to collect surface temperature and local wind speed gradient of the guide, thus making up for the spatial blind spots of fixed monitoring.

[0055] The numerical forecast data is obtained by accessing short-term numerical forecast data from regional meteorological departments to obtain the spatiotemporal variation trends of meteorological parameters.

[0056] It should be noted that the collected multi-source meteorological data needs to be preprocessed. First, based on the Grubbs' test, outlier data that exceeds the confidence interval (95% confidence level) is removed. Then, using the timestamp of the fixed monitoring data as a benchmark, the UAV mobile sensing data and numerical forecast data are aligned to the same time dimension through linear interpolation. Finally, a time series prediction model based on LSTM is used to complete the missing data. The input is the historical meteorological sequence, and the output is the predicted value of the meteorological parameters at the missing time.

[0057] In this embodiment of the invention, the weights are determined by calculating the information entropy of multi-source meteorological data, and then the data of the same type are weighted and summed to obtain the fusion result. The weight calculation and fusion formula are as follows:

[0058] ;

[0059] ;

[0060] Among them, w j Let e ​​be the weight of the j-th data source. j Let p be the information entropy of the j-th data source. ij Let z be the normalized probability of the i-th data point in the j-th data source. j Let z be the meteorological parameter value of the j-th data source, m be the total number of data sources participating in the fusion, n be the number of data samples contained in the j-th data source, and z be the value of the meteorological parameter of the j-th data source. 融合 These are the fused meteorological parameter values. It's understandable that information entropy reflects the degree of data dispersion; the smaller the entropy value, the greater the weight. Then, the aligned meteorological parameters (such as wind speed) are weighted and summed to obtain the fused meteorological parameter values.

[0061] Step S02: Based on the fused meteorological parameter values ​​and the gradient of the conductor's mechanical properties, perform adaptive segmentation of the conductor.

[0062] Specifically, meteorological features are extracted based on the fused meteorological parameter values. At the same time, initial mechanical features are determined based on the classical catenary equation. Based on the meteorological features and the initial mechanical features, a piecewise feature vector is constructed. The meteorological features include wind speed gradient, temperature gradient, and icing thickness gradient. The initial mechanical features include the initial stress and sag of the conductor.

[0063] It should be noted that the classical catenary equation is expressed as:

[0064] ;

[0065] Where σ0 is the initial axial stress of the conductor at the reference temperature, A is the cross-sectional area of ​​the conductor, E is the elastic modulus of the conductor material, γ is the weight per unit length of the conductor itself, L is the distance between the two transmission towers, and f0 is the initial sag.

[0066] Based on the segmented feature vectors, the improved K-means algorithm is used to determine the optimal number of segments through the elbow rule, and the cluster centers are iteratively optimized with the goal of minimizing the feature variance within segments and maximizing the variance between segments to obtain the initial segments;

[0067] Based on the conductor suspension point constraints (fixed at both ends) and the swing characteristics of the insulator string, the initial segmentation is adjusted to ensure that the boundary points do not exceed the actual range of the conductor and avoid stress concentration areas, thus obtaining the final segmentation result.

[0068] Step S03: For each segment, construct a simulation calculation model that integrates the meteorological-mechanical coupling relationship, combine the boundary conditions optimized by AI, and use the finite element method to solve the simulation calculation model of each segment to obtain the mechanical calculation results of each segment.

[0069] In this embodiment of the invention, the simulation calculation model that integrates the meteorological-mechanical coupling relationship is represented as follows:

[0070] ;

[0071] ;

[0072] ;

[0073] Where Δγ is the weight increase per unit length of the conductor caused by icing, and γ is the weight per unit length of the conductor itself, Δγ=πδ(2r+δ)γ 冰 r is the radius of the conductor, γ 冰 Let ρ be the density of the ice, δ be the thickness of the ice cover, and q be the density of the ice. w (x) represents the wind load distribution per unit length of the conductor at position x, C d ρ is the wind resistance coefficient, D is the air density, v(x) is the equivalent diameter of the conductor, σ(x) is the actual wind speed at position x, α is the axial stress of the conductor at position x, T0 is the reference temperature, T is the actual ambient temperature, σ0 is the initial axial stress of the conductor at the reference temperature, A is the cross-sectional area of ​​the conductor, and E is the elastic modulus of the conductor material.

[0074] Furthermore, a BP neural network is used to optimize the boundary conditions, wherein the input layer of the BP neural network includes segmented meteorological features, initial mechanical features, and segment lengths;

[0075] The output layer of the BP neural network consists of optimized boundary conditions at both ends of the segment, including horizontal displacement, vertical displacement, axial force, and bending moment.

[0076] The model was trained using historical measured data (conductor stress sensor data, GPS displacement monitoring data) as labels to train a BP neural network, and the network parameters were optimized using gradient descent (learning rate 0.01, number of iterations 1000).

[0077] Furthermore, the finite element method is used to solve the mechanical model of each segment. Specifically, each segment is first divided into tetrahedral meshes, and the mesh density is adaptively adjusted according to the mechanical gradient (the mesh is finer in areas with large gradients).

[0078] The Newton-Raphson iterative method is then used to solve the simulation model for each segment. The convergence condition is that the residual is less than 10. The stress distribution, strain distribution, sag, and displacement field of each segment are output.

[0079] Step S04: Differentiated weights are assigned to the mechanical calculation results of different segments through an attention mechanism, and a weighted fusion strategy is adopted to obtain the global mechanical calculation results.

[0080] Specifically, simulation credibility features are extracted for each segment. These features include local error features, boundary continuity features, and meteorological matching features. The local error feature calculates the relative error e by comparing the simulated and measured values ​​of monitoring points within the segment. The boundary continuity feature reflects the degree of boundary connection by calculating the stress difference Δσ at the boundary of adjacent segments. The meteorological matching feature calculates the deviation d between the meteorological parameters used in the segment simulation and the measured meteorological parameters; the smaller the deviation, the higher the matching degree.

[0081] Based on the simulation credibility features and the constructed multilayer perceptron, the attention weight of each segment is calculated, as follows:

[0082] ;

[0083] in, The attention weight for the k-th segment. The local relative error of the k-th segment is... Let be the boundary stress difference between the k-th segment and its adjacent segments. The meteorological parameter deviation for the k-th segment is represented by MLP, which stands for Multilayer Perceptron, and the Softmax function is used to normalize the weights.

[0084] Based on the mechanical calculation results and attention weights of each segment, a weighted fusion is performed to obtain the global mechanical calculation result. Understandably, the stress and sag of each segment are weighted and fused, and then Gaussian filtering is used to smooth the fused curve to eliminate local fluctuations.

[0085] In summary, the mechanical calculation method based on transmission tower conductors in the above embodiments of the present invention collects multi-source meteorological data and fuses similar data from the multi-source meteorological data according to the entropy weight method to obtain fused meteorological parameter values; adaptively segments the conductor according to the fused meteorological parameter values ​​and the mechanical property gradient of the conductor; for each segment, a simulation calculation model integrating the meteorological-mechanical coupling relationship is constructed, and the simulation calculation model of each segment is solved by combining AI-optimized boundary conditions and using the finite element method to obtain the mechanical calculation results of each segment; different weights are assigned to the mechanical calculation results of different segments through an attention mechanism, and a weighted fusion strategy is adopted to obtain the global mechanical calculation results. Specifically, the simulation calculation accuracy is improved by accurately adapting meteorological data to the segmentation.

[0086] Example 2

[0087] Please see Figure 2 , Figure 2 This is a structural block diagram of a mechanical calculation system based on transmission tower conductors according to Embodiment 2 of the present invention. This mechanical calculation system 200 is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0088] Specifically, the mechanical calculation system 200 based on transmission tower conductors includes: a first fusion module 21, a segmentation module 22, a construction module 23, and a second fusion module 24, wherein:

[0089] The first fusion module 21 is used to collect multi-source meteorological data and fuse the same type of data in the multi-source meteorological data according to the entropy weight method to obtain the fused meteorological parameter values. The multi-source meteorological data includes fixed monitoring data, mobile sensing data and numerical forecast data.

[0090] The fixed monitoring data is collected in real time by miniature weather stations deployed at the top of the transmission tower, the conductor suspension point and the middle section to collect wind speed, wind direction, ambient temperature, relative humidity and icing thickness.

[0091] The mobile sensing data is collected by a drone equipped with sensors cruising along the guide path to collect data on the surface temperature of the guide and the local wind speed gradient.

[0092] The numerical forecast data is obtained by accessing short-term numerical forecast data from regional meteorological departments to obtain the spatiotemporal variation trends of meteorological parameters;

[0093] The weights are determined by calculating the information entropy of multi-source meteorological data, and then the data of the same type are weighted and summed to obtain the fusion result. The weight calculation and fusion formula are as follows:

[0094] ;

[0095] ;

[0096] Among them, w j Let e ​​be the weight of the j-th data source. j Let p be the information entropy of the j-th data source. ij Let z be the normalized probability of the i-th data point in the j-th data source. j Let z be the meteorological parameter value of the j-th data source, m be the total number of data sources participating in the fusion, n be the number of data samples contained in the j-th data source, and z be the value of the meteorological parameter of the j-th data source. 融合 The merged meteorological parameter values

[0097] Segmentation module 22 is used to adaptively segment the conductor based on the fused meteorological parameter values ​​and the conductor mechanical property gradient.

[0098] Module 23 is used to construct a simulation calculation model that integrates the meteorological-mechanical coupling relationship for each segment. Combined with AI-optimized boundary conditions, the simulation calculation model for each segment is solved using the finite element method to obtain the mechanical calculation results for each segment. The simulation calculation model is represented as follows:

[0099] ;

[0100] ;

[0101] ;

[0102] Where Δγ is the weight increase per unit length of the conductor caused by icing, and γ is the weight per unit length of the conductor itself, Δγ=πδ(2r+δ)γ 冰 r is the radius of the conductor, γ 冰 Let ρ be the density of the ice, δ be the thickness of the ice cover, and q be the density of the ice. w (x) represents the wind load distribution per unit length of the conductor at position x, C d ρ is the drag coefficient, D is the equivalent diameter of the conductor, v(x) is the actual wind speed at position x, σ(x) is the axial stress of the conductor at position x, α is the thermal expansion coefficient of the conductor, T0 is the reference temperature, T is the actual ambient temperature, σ0 is the initial axial stress of the conductor at the reference temperature, A is the cross-sectional area of ​​the conductor, and E is the elastic modulus of the conductor material.

[0103] A backpropagation (BP) neural network is used to optimize the boundary conditions. The input layer of the BP neural network includes segmented meteorological features, initial mechanical features, and segment lengths.

[0104] The output layer of the BP neural network consists of optimized boundary conditions at both ends of the segment, including horizontal displacement, vertical displacement, axial force, and bending moment.

[0105] The model is trained using historical measured data as labels to train a backpropagation (BP) neural network, and the network parameters are optimized using gradient descent.

[0106] The second fusion module 24 is used to assign differentiated weights to the mechanical calculation results of different segments through an attention mechanism, and to obtain the global mechanical calculation results by adopting a weighted fusion strategy.

[0107] Furthermore, in some optional embodiments of the present invention, the segmentation module 22 includes:

[0108] The first extraction unit is used to extract meteorological features based on the fused meteorological parameter values. At the same time, based on the classical catenary equation, it determines the initial mechanical features and constructs a piecewise feature vector based on the meteorological features and the initial mechanical features. The meteorological features include wind speed gradient, temperature gradient, and icing thickness gradient, and the initial mechanical features include the initial stress and sag of the conductor.

[0109] The clustering unit is used to determine the optimal number of segments based on the segmented feature vectors using the improved K-means algorithm and the elbow rule, and to iteratively optimize the clustering centers with the goal of minimizing the feature variance within segments and maximizing the variance between segments, so as to obtain the initial segments.

[0110] The adjustment unit is used to adjust the initial segmentation according to the conductor suspension point constraint and the swing characteristics of the insulator string to obtain the final segmentation result.

[0111] Furthermore, in some optional embodiments of the present invention, the second fusion module 24 includes:

[0112] The second extraction unit is used to extract the simulation credibility features of each segment, which include local error features, boundary continuity features, and meteorological matching features.

[0113] The computing unit is used to calculate the attention weight of each segment based on the simulation credibility features and the constructed multilayer perceptron.

[0114] The weighted fusion unit is used to perform weighted fusion based on the mechanical calculation results and attention weights of each segment to obtain the global mechanical calculation results.

[0115] Example 3

[0116] In another aspect, the present invention also proposes an electronic device, please refer to [link to relevant documentation]. Figure 3 The image shows an electronic device according to Embodiment 3 of the present invention, including a memory 20, a processor 10, and a computer program 30 stored in the memory and executable on the processor. When the processor 10 executes the computer program 30, it implements the mechanical calculation method based on the transmission tower conductor as described above.

[0117] In some embodiments, the processor 10 may be a central processing unit (CPU), controller, microcontroller, microprocessor or other data processing chip, used to run program code stored in memory 20 or process data, such as executing access restriction programs.

[0118] The memory 20 includes at least one type of readable storage medium, such as flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 20 can be an internal storage unit of an electronic device, such as the hard disk of the electronic device. In other embodiments, the memory 20 can also be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. Furthermore, the memory 20 can include both internal and external storage units of the electronic device. The memory 20 can be used not only to store application software and various types of data of the electronic device, but also to temporarily store data that has been output or will be output.

[0119] It should be pointed out that, Figure 3 The structure shown does not constitute a limitation on the electronic device. In other embodiments, the electronic device may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0120] This invention also proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described mechanical calculation method based on transmission tower conductors.

[0121] Those skilled in the art will understand that the logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can mean any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0122] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0123] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0124] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0125] The above embodiments merely illustrate several implementation methods of the present invention, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this patent should be determined by the appended claims.

Claims

1. A mechanical calculation method based on the conductor of a power transmission tower, characterized in that, The method includes: Collect multi-source meteorological data, and fuse similar types of data from the multi-source meteorological data according to the entropy weight method to obtain fused meteorological parameter values; Based on the fused meteorological parameter values ​​and the gradient of the conductor's mechanical properties, adaptive segmentation of the conductor is performed; For each segment, a simulation calculation model integrating meteorological-mechanical coupling is constructed. The boundary conditions are optimized by AI, and the finite element method is used to solve the simulation calculation model of each segment to obtain the mechanical calculation results of each segment. By assigning differentiated weights to the mechanical calculation results of different segments through an attention mechanism, and by adopting a weighted fusion strategy, the global mechanical calculation results are obtained. The step of adaptively segmenting the conductor based on the fused meteorological parameter values ​​and the conductor's mechanical property gradient includes: Based on the fused meteorological parameter values, meteorological features are extracted. At the same time, based on the classical catenary equation, initial mechanical features are determined. Based on the meteorological features and the initial mechanical features, a piecewise feature vector is constructed. The meteorological features include wind speed gradient, temperature gradient, and icing thickness gradient. The initial mechanical features include the initial stress and sag of the conductor. Based on the segmented feature vectors, the improved K-means algorithm is used to determine the optimal number of segments through the elbow rule, and the cluster centers are iteratively optimized with the goal of minimizing the feature variance within segments and maximizing the variance between segments to obtain the initial segments; Based on the conductor suspension point constraints and the insulator string swing characteristics, the initial segmentation is adjusted to obtain the final segmentation result; In the step of constructing a simulation calculation model integrating the meteorological-mechanical coupling relationship for each segment, combining AI-optimized boundary conditions, and solving the simulation calculation model for each segment using the finite element method to obtain the mechanical calculation results for each segment, the simulation calculation model is represented as follows: ； ； ； Where Δγ is the weight increase per unit length of the conductor caused by icing, and γ is the weight per unit length of the conductor itself, Δγ=πδ(2r+δ)γ 冰 r is the radius of the conductor, γ 冰 Let ρ be the density of the ice, δ be the thickness of the ice cover, and q be the density of the ice. w (x) represents the wind load distribution per unit length of the conductor at position x, C d ρ is the wind resistance coefficient, D is the air density, v(x) is the equivalent diameter of the conductor, σ(x) is the actual wind speed at position x, α is the axial stress of the conductor at position x, T0 is the reference temperature, T is the actual ambient temperature, σ0 is the initial axial stress of the conductor at the reference temperature, A is the cross-sectional area of ​​the conductor, and E is the elastic modulus of the conductor material.

2. The mechanical calculation method based on transmission tower conductors according to claim 1, characterized in that, The multi-source meteorological data includes fixed monitoring data, mobile sensing data, and numerical weather prediction data; The fixed monitoring data is collected in real time by miniature weather stations deployed at the top of the transmission tower, the conductor suspension point and the middle section to collect wind speed, wind direction, ambient temperature, relative humidity and icing thickness. The mobile sensing data is collected by a drone equipped with sensors cruising along the guide path to collect data on the surface temperature of the guide and the local wind speed gradient. The numerical forecast data is obtained by accessing short-term numerical forecast data from regional meteorological departments to obtain the spatiotemporal variation trends of meteorological parameters.

3. The mechanical calculation method based on transmission tower conductors according to claim 2, characterized in that, In the step of collecting multi-source meteorological data and fusing similar data from the multi-source meteorological data according to the entropy weight method to obtain fused meteorological parameter values, the weights are determined by calculating the information entropy of the multi-source meteorological data, and then the fused results are obtained by weighted summation of similar data. The weight calculation and fusion formula are as follows: ； ； Among them, w j Let e ​​be the weight of the j-th data source. j Let p be the information entropy of the j-th data source. ij Let z be the normalized probability of the i-th data point in the j-th data source. j Let z be the meteorological parameter value of the j-th data source, m be the total number of data sources participating in the fusion, n be the number of data samples contained in the j-th data source, and z be the value of the meteorological parameter of the j-th data source. 融合 These are the merged meteorological parameter values.

4. The mechanical calculation method based on transmission tower conductors according to claim 3, characterized in that, In the step of constructing a simulation calculation model that integrates meteorological-mechanical coupling for each segment, combining AI-optimized boundary conditions, and solving the simulation calculation model of each segment using the finite element method to obtain the mechanical calculation results of each segment, a BP neural network is used to optimize the boundary conditions. The input layer of the BP neural network includes the meteorological characteristics of the segment, the initial mechanical characteristics, and the segment length. The output layer of the BP neural network consists of optimized boundary conditions at both ends of the segment, including horizontal displacement, vertical displacement, axial force, and bending moment. The model is trained using historical measured data as labels to train a backpropagation neural network, and the network parameters are optimized using gradient descent.

5. The mechanical calculation method based on transmission tower conductors according to claim 4, characterized in that, The steps of assigning differentiated weights to the mechanical calculation results of different segments through an attention mechanism and obtaining the global mechanical calculation results by adopting a weighted fusion strategy include: The simulation credibility features of each segment are extracted, including local error features, boundary continuity features, and meteorological matching features. Based on the simulation credibility features and the constructed multilayer perceptron, calculate the attention weight for each segment; Based on the mechanical calculation results and attention weights of each segment, a weighted fusion is performed to obtain the global mechanical calculation result.

6. A mechanical calculation system based on transmission tower conductors, characterized in that, The system is used to implement the mechanical calculation method based on transmission tower conductors as described in any one of claims 1-5, the system comprising: The first fusion module is used to collect multi-source meteorological data and fuse similar data from the multi-source meteorological data according to the entropy weight method to obtain fused meteorological parameter values. The segmentation module is used to adaptively segment the conductor based on the fused meteorological parameter values ​​and the conductor's mechanical property gradient. The module is used to build a simulation calculation model that integrates the meteorological-mechanical coupling relationship for each segment, combine AI-optimized boundary conditions, and use the finite element method to solve the simulation calculation model of each segment to obtain the mechanical calculation results of each segment. The second fusion module is used to assign differentiated weights to the mechanical calculation results of different segments through an attention mechanism, and to obtain the global mechanical calculation results by adopting a weighted fusion strategy.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the mechanical calculation method based on the conductor of the transmission tower as described in any one of claims 1-5.

8. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the program to implement the mechanical calculation method based on the conductor of the transmission tower as described in any one of claims 1-5.

Images