Method, device and equipment for evaluating bearing capacity change condition of tower line system and medium

Abstract

The invention belongs to the technical field of power transmission lines, and particularly relates to a tower line system bearing capacity change condition evaluation method and device, equipment and a medium. The method is realized based on a deep residual neural network, the deep residual neural network is utilized to carry out deep mining on wind speed and wind direction data, and iron tower vibration response, wire vibration response and insulator wind deflection of a tower line system under the wind load effect can be accurately predicted. Moreover, wind speed and wind direction data are acquired from multiple heights and multiple structure parts, so that the stress state of the tower line system is comprehensively reflected, and the evaluation accuracy is improved. The evaluation result obtained through the method can provide a scientific basis for maintenance and management of a tower line system. Operation and maintenance personnel can take corresponding maintenance measures in time according to the evaluation result, and stable and safe operation of the tower line system is ensured.

Description

Technical Field

[0001] The present invention belongs to the technical field of power transmission lines, and in particular relates to a method, device, equipment and medium for evaluating changes in the bearing capacity of a tower-line system. Background Art

[0002] In the power system, the tower-line system is a key structure for transmitting electric energy, and the stability of its carrying capacity is directly related to the normal operation of the power grid. The tower-line system is often exposed to complex natural environments, especially significantly affected by wind loads.

[0003] Traditional tower-line system bearing capacity assessment methods mostly rely on static mechanical analysis and empirical formulas. These methods often ignore the dynamic characteristics of wind loads and the nonlinear characteristics of the tower-line system structure, resulting in inaccurate assessment results. Summary of the invention

[0004] The purpose of the present invention is to provide a method, device, equipment and medium for evaluating the change of the bearing capacity of a tower line system, so as to solve the problem in the prior art that traditional methods for evaluating the bearing capacity of a tower line system mostly rely on static mechanical analysis and empirical formulas, resulting in inaccurate evaluation results.

[0005] In order to achieve the above object, the present invention adopts the following technical solution: In a first aspect, the present invention provides a method for evaluating changes in the bearing capacity of a tower line system, comprising the following specific steps: Obtain wind speed data and wind direction data of the tower-line system; wherein the wind speed data and wind direction data are data collected from different heights and different structures of the tower-line system based on different collection equipment; The wind speed data and wind direction data are input into a pre-trained evaluation model, and the evaluation model outputs the tower vibration response, conductor vibration response and insulator wind deflection data corresponding to the tower-line system; wherein the evaluation model is a deep residual neural network; Based on the tower vibration response, conductor vibration response and insulator windage data, the change in the bearing capacity of the tower-line system is determined.

[0006] In a further solution, the wind speed data and wind direction data are data collected from different heights and structures of the tower line system based on different collection equipment, including: The tower line system is preset with actual measurement points; wherein the actual measurement points include wind speed and direction measurement points set at different heights on the tower body; each wind speed and direction measurement point is respectively installed with a mechanical anemometer, an ultrasonic anemometer and a full-factor meteorological station; According to the mechanical anemometer, ultrasonic anemometer and full-element meteorological station, wind speed data and wind direction data at corresponding measured points are collected respectively.

[0007] In a further solution, the wind speed data and wind direction data are input into a pre-trained evaluation model, and the evaluation model outputs the tower vibration response, conductor vibration response and insulator wind deviation data corresponding to the tower-line system; wherein the evaluation model is trained in the following manner: Constructing a deep residual neural network; wherein the deep residual neural network includes a plurality of residual blocks, and the deep residual neural network is constructed by stacking a plurality of residual blocks; Initialize the model parameters of the deep residual neural network and set the weight threshold; Acquire a training data set for deep residual neural network training; wherein the data in the training data set include historical wind speed data and historical wind direction data of the tower-line system, and tower vibration acceleration data, insulator wind deflection angle data, and conductor vibration acceleration data corresponding to the historical wind speed data and historical wind direction data; Based on the training data set and the set weight threshold, the forward propagation algorithm is used to train the deep residual neural network. After the preset conditions are met, the model training is completed.

[0008] In a further solution, historical wind speed data and historical wind direction data, tower vibration acceleration data, insulator wind deflection angle data and conductor vibration acceleration data corresponding to the historical wind speed data and historical wind direction data are obtained by the following method: In the tower-line system, actual measurement points are set, and data collection equipment is installed at the actual measurement points; wherein the actual measurement points include wind speed and wind direction measurement points and tower vibration acceleration measurement points set at different heights on the tower body, wind deflection angle measurement points set on the first-stage conductor insulator, and conductor vibration acceleration measurement points set on the conductor; the data collection equipment includes a mechanical anemometer, an ultrasonic anemometer and a full-element meteorological station respectively installed at each wind speed and wind direction measurement point, a vibration acceleration sensor installed at the tower vibration acceleration measurement point, a wind deflection angle sensor installed at the wind deflection angle measurement point, and a vibration acceleration sensor installed at the conductor vibration acceleration measurement point; The data in the training data set are collected using the collection equipment installed at each measuring point.

[0009] A further solution is to determine the input layer of the deep residual neural network according to the input dimensions of wind speed and wind direction data in the step of constructing the deep residual neural network; and determine the output layer of the deep residual neural network according to the output dimensions of the tower vibration response, the conductor vibration response and the insulator wind deviation data.

[0010] In a second aspect, the present invention provides a device for evaluating changes in the bearing capacity of a tower-line system, comprising: A data acquisition module is used to acquire wind speed data and wind direction data of the tower-line system; wherein the wind speed data and wind direction data are data collected from different heights and different structures of the tower-line system based on different acquisition equipment; A prediction module, used for inputting the wind speed data and wind direction data into a pre-trained evaluation model, wherein the evaluation model outputs the tower vibration response, conductor vibration response and insulator wind deflection data corresponding to the tower-line system; wherein the evaluation model is a deep residual neural network; The evaluation module is used to determine the change in the bearing capacity of the tower-line system based on the vibration response of the tower, the vibration response of the conductor and the wind deflection data of the insulator.

[0011] In a further solution, in the data acquisition module, the wind speed data and wind direction data are data collected from different heights and structures of the tower line system based on different collection devices, including: The tower line system is preset with actual measurement points; wherein the actual measurement points include wind speed and direction measurement points set at different heights on the tower body; each wind speed and direction measurement point is respectively installed with a mechanical anemometer, an ultrasonic anemometer and a full-factor meteorological station; According to the mechanical anemometer, ultrasonic anemometer and full-element meteorological station, wind speed data and wind direction data at corresponding measured points are collected respectively.

[0012] In a further solution, in the prediction module, the wind speed data and wind direction data are input into a pre-trained evaluation model, and the evaluation model outputs the tower vibration response, conductor vibration response and insulator wind deviation data corresponding to the tower-line system; wherein the evaluation model is trained in the following manner: Constructing a deep residual neural network; wherein the deep residual neural network includes a plurality of residual blocks, and the deep residual neural network is constructed by stacking a plurality of residual blocks; Initialize the model parameters of the deep residual neural network and set the weight threshold; Acquire a training data set for deep residual neural network training; wherein the data in the training data set include historical wind speed data and historical wind direction data of the tower-line system, and tower vibration acceleration data, insulator wind deflection angle data, and conductor vibration acceleration data corresponding to the historical wind speed data and historical wind direction data; Based on the training data set and the set weight threshold, the forward propagation algorithm is used to train the deep residual neural network. After the preset conditions are met, the model training is completed.

[0013] According to a third aspect of the present invention, there is provided an electronic device, comprising a processor and a memory, wherein the processor is configured to execute a computer program stored in the memory to implement the above-mentioned method for evaluating changes in the bearing capacity of a tower-line system.

[0014] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, the method for evaluating changes in the bearing capacity of a tower-line system as described above is implemented.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: The method for evaluating the change in the bearing capacity of the tower-line system proposed in this scheme is based on a deep residual neural network. The method uses a deep residual neural network to deeply mine wind speed and wind direction data, and can accurately predict the vibration response of the tower, the vibration response of the conductor, and the wind deflection of the insulator of the tower-line system under wind load. In addition, by collecting wind speed and wind direction data from multiple heights and multiple structural parts, the stress state of the tower-line system is fully reflected, and the accuracy of the evaluation is improved. The evaluation results obtained by this method can provide a scientific basis for the maintenance and management of the tower-line system. Operation and maintenance personnel can take corresponding maintenance measures in a timely manner according to the evaluation results to ensure the stability and safe operation of the tower-line system. A device for evaluating the change in the bearing capacity of a tower-line system, an electronic device, and a computer-readable storage medium provided by the present invention also solve the problems raised in the background technology section.

[0016] This solution realizes the intelligent evaluation of the load-bearing capacity of the tower-line system by constructing an evaluation model based on a deep residual neural network. The evaluation model can automatically learn the characteristics of the data and make predictions and evaluations based on the learned characteristics, reducing the impact of manual intervention and subjective judgment.

[0017] This method can process wind speed and direction data from different acquisition equipment, different heights and structural parts, and support the processing and analysis of multi-source heterogeneous data. This makes the evaluation method more flexible and universal, and can adapt to the evaluation needs of tower and line systems under different environments and conditions.

[0018] In summary, the method for evaluating changes in the carrying capacity of a tower-line system proposed in the present invention has the effects of improving evaluation accuracy, enhancing evaluation real-time performance, improving the level of evaluation intelligence, supporting multi-source heterogeneous data processing, and guiding tower-line system maintenance and management. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings constituting a part of the present application are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings: Figure 1 This is a flow chart of a method for evaluating changes in the bearing capacity of a tower line system according to an embodiment of the present invention; Figure 2 It is a schematic diagram of actual measurement of input and output samples of a power transmission line based on multi-point multi-sensing in an embodiment of the present invention; Figure 3 A schematic diagram of establishing a single neuron in an embodiment of the present invention; Figure 4 These are several commonly used activation function curve types in the embodiments of the present invention; Figure 5 It is a topological diagram of the evaluation model in the embodiment of the present invention; Figure 6 It is a structural block diagram of a device for evaluating changes in the bearing capacity of a tower-line system in an embodiment of the present invention; Figure 7 The present invention is a structural block diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0021] The following detailed description is an exemplary description, which is intended to provide further detailed description of the present invention. Unless otherwise specified, all technical terms used in the present invention have the same meaning as those generally understood by those skilled in the art to which the present application belongs. The terms used in the present invention are only for describing specific embodiments, and are not intended to limit exemplary embodiments according to the present invention.

[0022] Example 1 In the field of power transmission lines, the research and application of deep residual neural networks (ResNet) for structural bearing capacity assessment is gradually increasing. These studies combine measured data and use deep learning models to predict and evaluate the response of power transmission lines under different wind speeds and wind directions. For example, some studies use deep learning technology to detect transmission line defects and improve detection accuracy through the improved YOLOV5 algorithm. In addition, some studies have explored the transmission line fault prediction method based on deep learning, which improves the accuracy and robustness of prediction by combining the MobileNet architecture and the Transformer attention mechanism.

[0023] There are some urgent problems to be solved in the application of deep learning technology in the field of power transmission lines. First, data collection and processing are difficult, especially in the field environment, it is a challenge to obtain high-quality, large-scale labeled data. Secondly, the complexity of the model and the length of training time are also issues that need attention. Complex models may lead to a large consumption of computing resources, while long training time affects the feasibility of real-time monitoring and evaluation. In addition, problems such as sensor failure, data loss and noise need to be solved to achieve accurate prediction of the status of transmission lines.

[0024] The research and application prospects of deep residual neural networks in the field of transmission line structure bearing capacity assessment are broad, but there are also many challenges to overcome, including data quality, model complexity, training efficiency, and model interpretability.

[0025] This scheme uses a deep residual neural network to collect various types of online monitoring data of transmission lines (including wind speed, wind direction, conductor vibration response, insulator wind deviation, and tower vibration response) as training data. Even for the same type of data, different responses (mapping relationship between input and output) will be stimulated due to differences in measurement height and measurement structure, thus reflecting the complexity of the correlation between this load and the structure, without having to establish clear physical laws between multiple inputs and multiple outputs from a theoretical perspective, greatly simplifying the difficulty of research work. This scheme establishes the relationship between multiple variable parameter inputs and the multi-point response and overall bearing capacity of the structure (ratio to the maximum allowable stress ratio, ratio to the maximum allowable deflection) through the transformation and mapping of multi-layer neural networks, so that the residual bearing capacity of the tower can be evaluated directly through environmental monitoring data and vibration response data.

[0026] By constructing an evaluation model based on a deep residual neural network, we can deeply mine wind speed and direction data, accurately predict the tower vibration response, conductor vibration response and insulator wind deflection of the tower-line system under wind load, and thus achieve an accurate evaluation of the bearing capacity of the tower-line system.

[0027] In summary, in order to solve the shortcomings of the traditional tower-line system bearing capacity assessment method and improve the accuracy and real-time performance of the assessment, the present invention proposes a tower-line system bearing capacity change assessment method based on a deep residual neural network.

[0028] like Figure 1 As shown, a method for evaluating the change of the bearing capacity of a tower line system includes the following specific steps: S1. Obtain wind speed data and wind direction data of the tower-line system; wherein the wind speed data and wind direction data are data collected from different heights and different structures of the tower-line system based on different collection equipment.

[0029] A further solution is that the wind speed data and wind direction data are data collected from different heights and structures of the tower line system based on different collection equipment, including: measured measurement points are preset in the tower line system; wherein the measured measurement points include wind speed and direction measurement points arranged at different heights on the tower body; mechanical anemometers, ultrasonic anemometers and full-element meteorological stations are respectively installed at each wind speed and direction measurement point; according to the mechanical anemometers, ultrasonic anemometers and full-element meteorological stations, the wind speed data and wind direction data at the corresponding measured measurement points are respectively collected.

[0030] Specifically, conduct wind field measurements at multiple points on the transmission line tower system to obtain input parameters of wind speed and wind direction at multiple different heights. Conduct vibration and displacement response output measurements at multiple different locations such as tower body vibration, conductor windage and insulators to obtain acceleration and windage displacement data at these points.

[0031] For example, according to Figure 2 The on-site measurement point distribution is shown in the figure, and the transmission line environmental input parameters and tower line vibration response are measured.

[0032] Three mechanical anemometers, one ultrasonic anemometer, and one full-element meteorological station are installed at five different heights along the tower. These five sensors collect wind speed sample data sequences at five different heights. , , , , , and the wind direction sample data sequences at 5 different heights , , , , ; Install three vibration acceleration sensors on the tower to collect acceleration data sequences at different positions of the tower. , , ; Install four wind deflection angle sensors on the four insulators of a conductor and collect the wind deflection angle data series of the four insulators. , , , ; Install two vibration acceleration sensors on the conductor to collect acceleration data sequences at different positions of the conductor. , .

[0033] S2. Input the wind speed data and wind direction data into a pre-trained evaluation model, and the evaluation model outputs the tower vibration response, conductor vibration response and insulator wind deviation data corresponding to the tower-line system; wherein the evaluation model is a deep residual neural network.

[0034] In a further scheme, the evaluation model is trained in the following manner: a deep residual neural network is constructed; wherein the deep residual neural network includes a plurality of residual blocks, and the deep residual neural network is constructed by stacking a plurality of residual blocks; the model parameters of the deep residual neural network are initialized, and a weight threshold is set; a training data set for training the deep residual neural network is obtained; wherein each item of data in the training data set includes historical wind speed data and historical wind direction data of the tower-line system, and tower vibration acceleration data, insulator wind deflection angle data, and conductor vibration acceleration data corresponding to the historical wind speed data and historical wind direction data; based on the training data set and the set weight threshold, a forward propagation algorithm is used to train the deep residual neural network, and the model training is completed after the preset conditions are met.

[0035] It should be noted that in this solution, residual blocks are used as the basic building blocks of the network. Each residual block contains several convolutional layers, batch normalization layers, and ReLU activation functions. A deep network is constructed by stacking multiple residual blocks. ResNet architectures of different depths (ResNet-18, ResNet-34, ResNet-50, etc.) can be selected as needed. The first few residual blocks of the network can be used to extract low-level features of the input data, while the deep residual blocks are used to extract more advanced feature representations.

[0036] A further solution is that during model training, historical wind speed data and historical wind direction data, tower vibration acceleration data, insulator wind deflection angle data and conductor vibration acceleration data corresponding to the historical wind speed data and historical wind direction data are obtained in the following manner: actual measurement points are set in the tower-line system, and collection equipment is installed at the actual measurement points; wherein the actual measurement points include wind speed and wind direction measurement points and tower vibration acceleration measurement points set at different heights on the tower body, wind deflection angle measurement points set on the insulator of a first-stage conductor, and conductor vibration acceleration measurement points set on the conductor; the collection equipment includes a mechanical anemometer, an ultrasonic anemometer and a full-factor meteorological station respectively installed at each wind speed and wind direction measurement point, a vibration acceleration sensor installed at the tower vibration acceleration measurement point, a wind deflection angle sensor installed at the wind deflection angle measurement point, and a vibration acceleration sensor installed at the conductor vibration acceleration measurement point; and the collection equipment installed at each actual measurement point is used to collect each data in the training data set.

[0037] A further solution is to determine the input layer of the deep residual neural network according to the input dimensions of wind speed and wind direction data in the step of constructing the deep residual neural network; and determine the output layer of the deep residual neural network according to the output dimensions of the tower vibration response, the conductor vibration response and the insulator wind deviation data.

[0038] In an optional embodiment, when training the model, a suitable loss function (such as mean square error loss) and an optimizer (such as Adam or SGD) are selected to train the network. The network weights are adjusted by minimizing the loss function so that the network can accurately predict the output data. The network is trained and verified using historical data sets, and the quality of the model training results is evaluated by dividing the data set into a training set, a verification set, and a test set, and deciding whether to continue data supplementation and continuous training.

[0039] In an optional embodiment, the output layer is implemented using a fully connected layer, and the output data is denormalized to obtain the actual physical quantity.

[0040] In an optional embodiment, when training the model, the input data such as wind speed and wind direction are normalized to adapt to the input requirements of the neural network. At the same time, the output data such as the vibration response of the tower, the vibration response of the conductor and the wind deflection of the insulator are also normalized accordingly. The input layer receives the normalized wind speed and wind direction data, which can be real-time monitoring data or historical data sets.

[0041] It should be noted that when constructing a neural network, the underlying neurons are constructed first, and then the underlying neurons are expanded to obtain a deep residual neural network.

[0042] Step 1: A neuron consists of several input units and one output unit. Each input unit is connected by weights ω Weighted ω Used to represent the strength of connections between neurons. z represents the activity value of the neuron, b For bias, such as Figure 3 shown.

[0043] Step 2: Using activation function f(z) Perform classification operations to obtain output units y The input and output of a neuron can be expressed as formula (1).

[0044] (1) Among them, the activation function of the neuron f (z) As shown in formula (2).

[0045] (2) Weight of each input node ω and bias b It can be learned through a large number of samples, and the learning process is as follows: Step 3: Set the connection weight of each input node ω and bias bThe initial value of .

[0046] Step 4: Continuously update connection weights through samples ω and bias b For the k Learning samples ( , ), the update process is as follows: Step 4-1: Calculate the output of the neuron using equation (1) ; Step 4-2: Calculate the error : (3) (4) Step 4-3: Correct weights and biases: (5) (6) (7) (8) Among them, α and β are learning rates, , for this example, i =1, 2, 3, 4, 5, corresponding to the wind speed input, i =6, 7, 8, 9, 10, the corresponding is the wind direction input. Figure 5 As shown in the figure, the input layer of the deep residual neural network constructed by this scheme has 10 nodes corresponding to the wind speed and direction input, and the output layer has 9 nodes. The output layer nodes correspond to 9 groups of prediction data corresponding to the positions of 3 vibration acceleration sensors on the tower, 4 wind deflection angle sensors on 4 insulators, and 2 vibration acceleration sensors on the conductor.

[0047] Step 5: Repeat step 4 until the error Approaches 0 or is less than the set upper error limit.

[0048] Optionally, when expanding on the basis of the underlying neurons, you can add hidden layers to enhance the expressive power of the neural network; establish a mapping relationship from one input neuron to multiple output neurons, so that the network topology is more flexible; you can choose sigmoid, tanh, ReLU, softplus, softmax, unit step and linear as activation functions. Common activation function curve types are as follows Figure 4 As shown, a) sigmoid: ; b) tanh: ; c) ReLU ; d) softplus: .

[0049] In the above formula (1), various weights and biases are involved, and the weights and biases in formula (1) are defined. For example, the weights from the 4th neuron in the 2nd layer to the 2nd neuron in the 3rd layer are defined as , the bias of the second neuron in the third layer is , the output value of the first neuron in the third layer is Preferably, Greater than or equal to 0.66.

[0050] After that, the iterative calculation of the mapping relationship of each layer is continued, that is, the output of each neuron in the second layer is expressed by formula (9):

[0051]

[0052]

[0053] (9) Assume l- Layer 1 contains m neurons, then l Tier j The output of a neuron can be expressed by formula (10): (10) Further, l The output of each neuron in the layer can be obtained through matrix operation, as shown in formula (11): (11) In the formula, let l- Layer 1 has m neurons. l The layer has n neurons, a l For the l The n×1 dimensional vector composed of neurons in each layer; a l-1 For the l- The m×1 dimensional vector composed of neurons in layer 1; W l For the l- 1st floor and l The connection weights between layer neurons are n×m dimensional matrices; b l For the l The bias of each neuron in the layer is an n×1 dimensional vector.

[0054] By repeating this process multiple times, a deep neural network can be established.

[0055] In an optional embodiment, , , , , Wind speed samples together with , , , , , , , , , , , , , The measured variables are normalized to 0-1. Half of the input samples (wind speed, wind direction) and output samples (tower vibration response, conductor vibration response, insulator wind deflection angle) are used as DNN training samples, and the DNN is trained using the mini-batch gradient descent algorithm. The activation function of the hidden layer uses the ReLU function, while the activation function of the output layer uses the Sigmoid function to ensure that the output node variable is between 0-1.

[0056] The mean square error is used as the loss function, as shown in formula (12).

[0057] (12) Where n is the number of neurons in the output layer; is the calculated value of the jth neuron in the output layer, which can be obtained by formula (11); is the true value of the j-th neuron training sample.

[0058] In an optional embodiment, a Dropout mechanism is added to the last few hidden layers of the evaluation model according to actual conditions. After DNN training, when the loss function satisfies the preset residual tolerance value, the training ends.

[0059] S3. Determine the change in the bearing capacity of the tower-line system based on the tower vibration response, conductor vibration response and insulator windage data.

[0060] Specifically, based on the tower vibration response, conductor vibration response and insulator windage data output by the network, combined with the knowledge of material mechanics and structural mechanics, the changes in the bearing capacity of the tower-line system are evaluated.

[0061] In the above-mentioned embodiment, the method of the present invention is based on the monitoring data of load parameters such as wind speed and wind direction, and is combined with the vibration response of the iron tower, the vibration response of the conductor and the wind deflection response data of the insulator string. Through the training of the deep residual neural network, a neural network mapping relationship that can reflect the current bearing capacity state of the structure is obtained, and the various structures (towers, wires, insulators) of the tower-line system can be well matched. Under such a model mapping relationship, a structural response that comprehensively considers the mutual influence between the tower, wire and insulator can be obtained. By only monitoring the wind speed and wind direction, based on the observation data of environmental parameters such as wind speed and wind direction with the lowest cost and the most common implementation, a more accurate tower, wire and insulator response is obtained, thereby ultimately providing data support for the safety assessment of the transmission tower-line system structure.

[0062] Example 2 like Figure 6 As shown, based on the same inventive concept as the above embodiment, the present invention also provides a device for evaluating changes in the bearing capacity of a tower-line system, comprising: A data acquisition module is used to acquire wind speed data and wind direction data of the tower-line system; wherein the wind speed data and wind direction data are data collected from different heights and different structures of the tower-line system based on different acquisition equipment; A prediction module, used for inputting the wind speed data and wind direction data into a pre-trained evaluation model, wherein the evaluation model outputs the tower vibration response, conductor vibration response and insulator wind deflection data corresponding to the tower-line system; wherein the evaluation model is a deep residual neural network; The evaluation module is used to determine the change in the bearing capacity of the tower-line system based on the vibration response of the tower, the vibration response of the conductor and the wind deflection data of the insulator.

[0063] In a further solution, in the data acquisition module, the wind speed data and wind direction data are data collected from different heights and structures of the tower line system based on different collection devices, including: The tower line system is preset with actual measurement points; wherein the actual measurement points include wind speed and direction measurement points set at different heights on the tower body; each wind speed and direction measurement point is respectively installed with a mechanical anemometer, an ultrasonic anemometer and a full-factor meteorological station; According to the mechanical anemometer, ultrasonic anemometer and full-element meteorological station, wind speed data and wind direction data at corresponding measured points are collected respectively.

[0064] In a further solution, in the prediction module, the wind speed data and wind direction data are input into a pre-trained evaluation model, and the evaluation model outputs the tower vibration response, conductor vibration response and insulator wind deviation data corresponding to the tower-line system; wherein the evaluation model is trained in the following manner: Constructing a deep residual neural network; wherein the deep residual neural network includes a plurality of residual blocks, and the deep residual neural network is constructed by stacking a plurality of residual blocks; Initialize the model parameters of the deep residual neural network and set the weight threshold; Acquire a training data set for deep residual neural network training; wherein the data in the training data set include historical wind speed data and historical wind direction data of the tower-line system, and tower vibration acceleration data, insulator wind deflection angle data, and conductor vibration acceleration data corresponding to the historical wind speed data and historical wind direction data; Based on the training data set and the set weight threshold, the forward propagation algorithm is used to train the deep residual neural network. After the preset conditions are met, the model training is completed.

[0065] Example 3 like Figure 7 As shown, the present invention also provides an electronic device 100 for implementing a method for evaluating changes in the load-bearing capacity of a tower-line system; The electronic device 100 includes a memory 101 , at least one processor 102 , a computer program 103 stored in the memory 101 and executable on the at least one processor 102 , and at least one communication bus 104 .

[0066] The memory 101 can be used to store a computer program 103. The processor 102 implements the steps of a tower line system bearing capacity change assessment method in Example 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101.

[0067] The memory 101 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data (such as audio data) created according to the use of the electronic device 100, etc. In addition, the memory 101 may include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices.

[0068] At least one processor 102 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 102 may be a microprocessor or any conventional processor, etc. The processor 102 is the control center of the electronic device 100, and uses various interfaces and lines to connect various parts of the entire electronic device 100.

[0069] The memory 101 in the electronic device 100 stores a plurality of instructions to implement a method for evaluating changes in the carrying capacity of a tower line system, and the processor 102 can execute the plurality of instructions to implement: Obtain wind speed data and wind direction data of the tower-line system; wherein the wind speed data and wind direction data are data collected from different heights and different structures of the tower-line system based on different collection equipment; The wind speed data and wind direction data are input into a pre-trained evaluation model, and the evaluation model outputs the tower vibration response, conductor vibration response and insulator wind deflection data corresponding to the tower-line system; wherein the evaluation model is a deep residual neural network; Based on the tower vibration response, conductor vibration response and insulator windage data, the change in the bearing capacity of the tower-line system is determined.

[0070] Example 4 If the module / unit integrated in the electronic device 100 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. Computer-readable media may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory and read-only memory (ROM, Read-Only Memory).

[0071] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0072] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0073] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0074] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0075] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0076] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for evaluating changes in the bearing capacity of a tower-line system, characterized in that: The specific steps include: Obtain wind speed data and wind direction data of the tower-line system; wherein the wind speed data and wind direction data are data collected from different heights and different structures of the tower-line system based on different collection equipment; The wind speed data and wind direction data are input into a pre-trained evaluation model, and the evaluation model outputs the tower vibration response, conductor vibration response and insulator wind deflection data corresponding to the tower-line system; wherein the evaluation model is a deep residual neural network; Based on the tower vibration response, conductor vibration response and insulator windage data, the change in the bearing capacity of the tower-line system is determined.

2. The method for evaluating changes in the bearing capacity of a tower line system according to claim 1, characterized in that: The wind speed data and wind direction data are data collected from different heights and structures of the tower line system based on different collection equipment, including: The tower line system is preset with actual measurement points; wherein the actual measurement points include wind speed and direction measurement points set at different heights on the tower body; each wind speed and direction measurement point is respectively installed with a mechanical anemometer, an ultrasonic anemometer and a full-factor meteorological station; According to the mechanical anemometer, ultrasonic anemometer and full-element meteorological station, wind speed data and wind direction data at corresponding measured points are collected respectively.

3. The method for evaluating changes in the bearing capacity of a tower line system according to claim 1, characterized in that: The wind speed data and wind direction data are input into a pre-trained evaluation model, and the evaluation model outputs the tower vibration response, conductor vibration response and insulator wind deviation data corresponding to the tower-line system; wherein the evaluation model is trained in the following manner: Constructing a deep residual neural network; wherein the deep residual neural network includes a plurality of residual blocks, and the deep residual neural network is constructed by stacking a plurality of residual blocks; Initialize the model parameters of the deep residual neural network and set the weight threshold; Acquire a training data set for deep residual neural network training; wherein the data in the training data set include historical wind speed data and historical wind direction data of the tower-line system, and tower vibration acceleration data, insulator wind deflection angle data, and conductor vibration acceleration data corresponding to the historical wind speed data and historical wind direction data; Based on the training data set and the set weight threshold, the forward propagation algorithm is used to train the deep residual neural network. After the preset conditions are met, the model training is completed.

4. The method for evaluating changes in the bearing capacity of a tower line system according to claim 3, characterized in that: The historical wind speed data and the historical wind direction data, the tower vibration acceleration data, the insulator wind deflection angle data and the conductor vibration acceleration data corresponding to the historical wind speed data and the historical wind direction data are obtained by the following method: In the tower-line system, actual measurement points are set, and data collection equipment is installed at the actual measurement points; wherein the actual measurement points include wind speed and wind direction measurement points and tower vibration acceleration measurement points set at different heights on the tower body, wind deflection angle measurement points set on the first-stage conductor insulator, and conductor vibration acceleration measurement points set on the conductor; the data collection equipment includes a mechanical anemometer, an ultrasonic anemometer and a full-element meteorological station respectively installed at each wind speed and wind direction measurement point, a vibration acceleration sensor installed at the tower vibration acceleration measurement point, a wind deflection angle sensor installed at the wind deflection angle measurement point, and a vibration acceleration sensor installed at the conductor vibration acceleration measurement point; The data in the training data set are collected using the collection equipment installed at each measuring point.

5. The method for evaluating changes in the bearing capacity of a tower line system according to claim 3, characterized in that: In the step of constructing a deep residual neural network, the input layer of the deep residual neural network is determined according to the input dimensions of wind speed and wind direction data; the output layer of the deep residual neural network is determined according to the output dimensions of tower vibration response, conductor vibration response and insulator wind deviation data.

6. A device for evaluating changes in the bearing capacity of a tower line system, characterized in that: include: A data acquisition module is used to acquire wind speed data and wind direction data of the tower-line system; wherein the wind speed data and wind direction data are data collected from different heights and different structures of the tower-line system based on different acquisition equipment; A prediction module, used for inputting the wind speed data and wind direction data into a pre-trained evaluation model, wherein the evaluation model outputs the tower vibration response, conductor vibration response and insulator wind deflection data corresponding to the tower-line system; wherein the evaluation model is a deep residual neural network; The evaluation module is used to determine the change in the bearing capacity of the tower-line system based on the vibration response of the tower, the vibration response of the conductor and the wind deflection data of the insulator.

7. The device for evaluating changes in the load-bearing capacity of a tower-line system according to claim 6, characterized in that: In the data acquisition module, the wind speed data and wind direction data are data collected from different heights and structures of the tower line system based on different collection equipment, including: The tower line system is preset with actual measurement points; wherein the actual measurement points include wind speed and direction measurement points set at different heights on the tower body; each wind speed and direction measurement point is respectively installed with a mechanical anemometer, an ultrasonic anemometer and a full-factor meteorological station; According to the mechanical anemometer, ultrasonic anemometer and full-element meteorological station, wind speed data and wind direction data at corresponding measured points are collected respectively.

8. The device for evaluating changes in the load-bearing capacity of a tower-line system according to claim 6, characterized in that: In the prediction module, the wind speed data and wind direction data are input into a pre-trained evaluation model, and the evaluation model outputs the tower vibration response, conductor vibration response and insulator wind deviation data corresponding to the tower-line system; wherein the evaluation model is trained in the following manner: Constructing a deep residual neural network; wherein the deep residual neural network includes a plurality of residual blocks, and the deep residual neural network is constructed by stacking a plurality of residual blocks; Initialize the model parameters of the deep residual neural network and set the weight threshold; Acquire a training data set for deep residual neural network training; wherein the data in the training data set include historical wind speed data and historical wind direction data of the tower-line system, and tower vibration acceleration data, insulator wind deflection angle data, and conductor vibration acceleration data corresponding to the historical wind speed data and historical wind direction data; Based on the training data set and the set weight threshold, the forward propagation algorithm is used to train the deep residual neural network. After the preset conditions are met, the model training is completed.

9. An electronic device, characterized in that: It comprises a processor and a memory, wherein the processor is used to execute a computer program stored in the memory to implement the method for evaluating changes in the bearing capacity of a tower-line system as claimed in any one of claims 1 to 5.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by the processor, the method for evaluating changes in the bearing capacity of a tower-line system according to any one of claims 1 to 5 is implemented.

Images