Method and system for identifying and tracking shear line of high-impact weather event for power grid

Abstract

A method and system for identifying and tracking a shear line of a high-impact weather event for a power grid. The method comprises: acquiring high-impact weather event data, screening for weather event data containing shear line features, and manually labeling the position of a shear line; extracting initial meteorological variables, and constructing a shear line identification model by designing an autoencoder and an adversarial network; and training the model, and analyzing and evaluating the performance of the model to optimize the model. In the present invention, the spatial position and intensity change features of the shear line in the whole process of the high-impact weather event are systematically analyzed, thereby optimizing the early warning and coping strategy of the power grid, and improving the stability and risk resistance of the power grid.

Description

A method and system for identifying and tracking shear lines during high-impact weather events on power grids Technical Field

[0001] This invention relates to the field of power grid technology, and in particular to a method and system for identifying and tracking shear lines during high-impact weather events on power grids. Background Technology

[0002] High-impact weather events (such as heavy rainfall, strong winds, and thunderstorms) pose a significant threat to the stable operation of power systems. These events can not only cause mechanical damage to transmission lines but also trigger substation equipment failures and even lead to widespread power outages. For example, Hurricane Harvey in the United States in 2017 caused widespread power outages and severely damaged the power grid system. Shear lines, as a typical small-scale weather system, play a crucial role in these high-impact weather events. A shear line is a region where wind speed and direction change significantly in the horizontal direction. It is usually accompanied by intense convective activity and significant weather phenomena such as thunderstorms, heavy rain, and strong winds. The rapid formation and movement of shear lines make them important triggering factors for high-impact weather events.

[0003] The formation of shear lines is closely related to atmospheric dynamics and thermodynamic processes, which often occur under conditions of frontal systems, low-pressure troughs, and severe convective weather. Intense convective activity and significant wind shear within shear lines lead to extreme weather phenomena such as heavy precipitation, thunderstorms, and strong winds. These weather phenomena have a direct and profound impact on the physical structure and operating status of power systems. For example, heavy precipitation may cause instability in transmission line foundations, thunderstorms may directly damage power equipment, and strong winds may break cables or damage towers.

[0004] Traditional weather forecasting models have significant shortcomings in identifying and tracking shear lines. First, existing forecasting systems have technical limitations in capturing small-scale weather systems, especially under complex terrain and variable climate conditions, making them prone to missed or false alarms. Second, the rapid generation and movement of shear lines make it difficult for existing forecasting models to track their changes in real time. This insufficient timeliness of forecasting systems leads to delayed early warning information, failing to provide timely and accurate warnings and severely impacting the emergency response capabilities of power systems.

[0005] High-impact weather events often require comprehensive analysis of multi-source data, but existing forecasting technologies have limitations in data fusion. Different data sources (such as radar, satellite, and ground observations) have different data formats and temporal resolutions, making comprehensive analysis difficult and affecting the accuracy of shear line identification and tracking. Furthermore, power systems lack response strategies based on the characteristics of small-scale weather systems when facing high-impact weather events. Existing power grid management systems rely heavily on historical experience and statistical models, lacking dynamic response mechanisms for real-time weather systems, and are unable to effectively mitigate risks during extreme weather events.

[0006] Studying the spatial location, intensity, and other characteristics of shear lines during high-impact weather events, and developing corresponding identification and tracking technologies, not only has significant scientific value but can also significantly improve the early warning and response capabilities of power systems, with broad practical application prospects. Summary of the Invention

[0007] The purpose of this section is to outline some aspects of embodiments of the present invention and to briefly describe some preferred embodiments. Simplifications or omissions may be made in this section, as well as in the abstract and title of this application, to avoid obscuring the purpose of these documents; however, such simplifications or omissions should not be construed as limiting the scope of the invention.

[0008] In view of the aforementioned existing problems, this invention is proposed. Therefore, this invention provides a method for identifying and tracking shear lines during high-impact weather events in power grids to solve the above-mentioned problems.

[0009] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0010] In a first aspect, the present invention provides a method for identifying and tracking shear lines of high-impact weather events in power grids, comprising: acquiring high-impact weather event data, filtering weather event data containing shear line features, and manually marking the shear line positions;

[0011] Based on the high-impact weather event data, initial meteorological variables are extracted, and a shear line recognition model is constructed by designing an autoencoder and an adversarial network.

[0012] The shear line identification model is trained, and its performance is analyzed and evaluated. Based on the evaluation results, the model is optimized.

[0013] As a preferred embodiment of the power grid high-impact weather event shear line identification and tracking method described in this invention, the initial meteorological variables include the temperature, humidity, wind speed, wind direction, altitude field, and air pressure of the ground and preset pressure surface, and vorticity, divergence, geopotential temperature, and temperature horizontal gradient are calculated as modeling features.

[0014] As a preferred embodiment of the power grid high-impact weather event shear line identification and tracking method described in this invention, the shear line identification model includes:

[0015] Through an autoencoder architecture design, initial meteorological variable features are extracted from the high-impact weather event data. The autoencoder includes an encoder and a decoder.

[0016] By designing an adversarial network architecture, the initial meteorological variable features are used as input to the adversarial network to generate weather data samples and identify shear lines.

[0017] As a preferred embodiment of the power grid high-impact weather event shear line identification and tracking method described in this invention, the self-encoder includes:

[0018] The encoder compresses high-dimensional input data into a low-dimensional feature space, gradually reducing the dimensionality of the input data to obtain a low-dimensional feature representation.

[0019] The decoder restores low-dimensional features to high-dimensional input data. The decoder structure is symmetrical with the encoder and gradually increases the dimension to reconstruct high-dimensional data from low-dimensional features.

[0020] As a preferred embodiment of the power grid high-impact weather event shear line identification and tracking method described in this invention, the adversarial network includes:

[0021] Samples of real weather data are generated from features extracted by an autoencoder using a generator that progressively transforms low-dimensional noise or features into high-dimensional data.

[0022] The discriminator distinguishes between real data and generated data, classifies the input data, and outputs the position information of the shear line.

[0023] As a preferred embodiment of the power grid high-impact weather event shear line identification and tracking method described in this invention, the model training includes:

[0024] Autoencoder training uses mean squared error to calculate the difference between high-dimensional input data and reconstructed high-dimensional data, updates the autoencoder parameters, and minimizes the reconstruction error.

[0025] Adversarial network training involves training the generator and discriminator adversarially using adversarial loss, identifying shear lines using classification loss, and regressing the shear line positions using regression loss. During training, the generator and discriminator are updated alternately.

[0026] As a preferred embodiment of the power grid high-impact weather event shear line identification and tracking method described in this invention, the optimization of the model includes:

[0027] The performance of the shear line recognition model is evaluated using a validation set, and the model evaluation results are obtained by selecting evaluation metrics.

[0028] Based on the model evaluation results, adjust the parameters and architecture of the shear line identification model.

[0029] Secondly, the present invention provides a power grid high-impact weather event shear line identification and tracking system, comprising:

[0030] The annotation module is used to acquire high-impact weather event data, filter weather event data containing shear line features, and manually annotate the shear line locations.

[0031] The module is used to extract initial meteorological variables based on the high-impact weather event data, and to build a shear line recognition model by designing an autoencoder and an adversarial network.

[0032] The evaluation and optimization module is used to train the shear line recognition model, analyze and evaluate the model's performance, and optimize the model based on the evaluation results.

[0033] Thirdly, the present invention provides an electronic device, comprising:

[0034] Memory and processor;

[0035] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the method for identifying and tracking shear lines of high-impact weather events in the power grid are implemented.

[0036] Fourthly, the present invention provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the method for identifying and tracking shear lines during high-impact weather events in the power grid.

[0037] Compared with the prior art, the beneficial effects of the present invention are as follows: By systematically analyzing the spatial location and intensity change characteristics of shear lines throughout the entire process of high-impact weather events, the present invention optimizes the early warning and response strategies of the power grid, thereby improving the stability and risk resistance of the power grid. Attached Figure Description

[0038] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 is a schematic flowchart of the power grid high-impact weather event shear line identification and tracking method according to an embodiment of the present invention;

[0040] Figure 2 is a schematic diagram of an autoencoder for a power grid high-impact weather event shear line identification and tracking method according to an embodiment of the present invention;

[0041] Figure 3 is a schematic diagram of the GAN architecture of the power grid high-impact weather event shear line identification and tracking method according to an embodiment of the present invention;

[0042] Figure 4 is a schematic diagram of shear line tracking in the power grid high-impact weather event shear line identification and tracking method according to an embodiment of the present invention. Detailed Implementation

[0043] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0044] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0045] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0046] This invention is described in detail with reference to the schematic diagrams. When detailing the embodiments of this invention, for ease of explanation, the cross-sectional views illustrating the device structure may be partially enlarged, not adhering to the usual scale. Furthermore, the schematic diagrams are merely examples and should not be construed as limiting the scope of protection of this invention. In actual fabrication, the three-dimensional spatial dimensions of length, width, and depth should be included.

[0047] Furthermore, in the description of this invention, it should be noted that the terms "upper," "lower," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are used solely for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. In addition, the terms "first," "second," or "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0048] Unless otherwise explicitly specified and limited, the terms "installation," "connection," and "joining" in this invention should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; similarly, they can refer to mechanical connections, electrical connections, or direct connections, or indirect connections through an intermediate medium, or internal connections between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0049] Example 1

[0050] Referring to Figures 1-3, an embodiment of the present invention provides a method for identifying and tracking shear lines during high-impact weather events in power grids, as shown in Figure 1, including:

[0051] S101: Obtain high-impact weather event data, filter weather event data containing shear line characteristics, and manually label the shear line positions;

[0052] S102, based on high-impact weather event data, extracts initial meteorological variables and constructs a shear line recognition model by designing an autoencoder and an adversarial network;

[0053] S103, train the shear line recognition model, analyze and evaluate the model's performance, and optimize the model based on the evaluation results.

[0054] Specifically, in step S101, firstly, weather event instances containing obvious shear line characteristics are selected from the high-impact weather event data. This selection process focuses on events with complex meteorological conditions and obvious shear line characteristics to ensure the representativeness and diversity of the data. Then, experienced meteorological experts manually annotate the data using professional meteorological analysis tools, such as Geographic Information System (GIS) software. During this process, experts will visually mark the precise location of the shear line on the weather image, ensuring that each mark accurately reflects the actual location of the shear line.

[0055] It should be noted that in the development of the shear line recognition model, this step involves a precise manual annotation process. This is to build an effective training dataset, which will serve as the basis for subsequent machine learning model training and is a key initial step in establishing an efficient recognition system.

[0056] Preferably, in step S102, the initial meteorological variables include the temperature, humidity, wind speed, wind direction, height field, and air pressure of the ground and the preset pressure surface, and the vorticity, divergence, geopotential temperature, and temperature horizontal gradient are calculated as modeling features. The preset pressure surface is preferably a pressure surface of 1000hPa-500hPa.

[0057] It should be noted that feature selection is a key step in the development of shear line identification models. By selecting the most relevant features, the performance and efficiency of the model can be improved. The main purpose of feature selection is to select those variables that are most useful for shear line identification and tracking from a large number of meteorological variables. This process can be carried out using various methods, including statistical analysis, correlation analysis and machine learning algorithms.

[0058] Preferably, constructing a shear line recognition model includes:

[0059] Through the design of an autoencoder architecture, initial meteorological variable features are extracted from high-impact weather event data. The autoencoder includes an encoder and a decoder.

[0060] By designing an adversarial network architecture, the initial meteorological variable characteristics are used as input to the adversarial network to generate weather data samples and identify shear lines.

[0061] Preferably, as shown in Figure 2, the self-encoder includes:

[0062] The encoder compresses high-dimensional input data into a low-dimensional feature space, gradually reducing the dimensionality of the input data to obtain a low-dimensional feature representation.

[0063] The decoder restores low-dimensional features to high-dimensional input data. The decoder structure is symmetrical with the encoder, and the dimensions are gradually increased to reconstruct high-dimensional data from low-dimensional features.

[0064] Specifically, an autoencoder is used to extract effective features from the data. The encoder compresses high-dimensional input data into a low-dimensional feature space. Through several layers of neural networks (such as linear layers and activation functions), the dimensionality of the input data is gradually reduced, finally obtaining a compact feature representation, as shown in the following formula: h = f(x) = ReLU(Wx + b).

[0065] Where x represents the input data, W represents the weight matrix, b represents the bias vector, and h represents the low-dimensional feature representation.

[0066] The decoder restores low-dimensional features to high-dimensional input data. The decoder's structure is symmetrical to the encoder. It gradually increases the dimensionality through several layers of neural networks, reconstructing low-dimensional features into high-dimensional data similar to the input data, represented as: x'=g(h)=ReLU(W'h+b')

[0067] Where h represents the low-dimensional feature representation, W' represents the weight matrix, x' represents the reconstructed high-dimensional data, b' represents the bias vector, and ReLU (Rectified Linear Unit) is a non-linear transformation function that enables the neural network to approximate complex functions.

[0068] Preferably, as shown in Figure 3, the adversarial network includes:

[0069] Samples of real weather data are generated by a generator from features extracted by an autoencoder. The generator gradually transforms low-dimensional noise or features into high-dimensional data.

[0070] The discriminator distinguishes between real data and generated data, classifies the input data, and outputs the position information of the shear line.

[0071] Specifically, Generative Adversarial Networks (GANs) use features extracted by autoencoders as input to generate realistic weather data samples and identify shear lines.

[0072] A generator is responsible for producing samples that resemble real weather data from random noise or features extracted by an autoencoder. The generator's structure typically includes several layers of neural networks that progressively transform low-dimensional noise or features into high-dimensional data.

[0073] The discriminator is responsible for distinguishing between real data and generated data. In a semi-supervised setting, it also needs to classify the input data (identify whether it contains shear lines) and output the location information of the shear lines.

[0074] The structure of adversarial networks includes:

[0075] Feature extraction layer: Extracts features from input data through several layers of neural networks;

[0076] Adversarial layer: Outputs the true / false judgment result, usually using a single neuron output (activated by Sigmoid);

[0077] Classification layer: Outputs whether the result includes a shear line;

[0078] Regression layer: Outputs the position of the shear line, such as coordinate information.

[0079] Preferably, in step S103, model training includes:

[0080] Autoencoder training uses mean squared error to calculate the difference between high-dimensional input data and reconstructed high-dimensional data, updates the autoencoder parameters, and minimizes the reconstruction error.

[0081] Adversarial network training involves training the generator and discriminator against each other using adversarial loss, identifying shear lines using classification loss, and regressing the shear line positions using regression loss. During training, the generator and discriminator are updated alternately.

[0082] Specifically, in autoencoder training, the autoencoder is trained with unlabeled data so that it can effectively compress and reconstruct the input data. During the training process, the parameters of the autoencoder are repeatedly updated to reduce the difference between the input and output.

[0083] GAN training employs an alternating training method. During training, the generator and discriminator are updated alternately. The discriminator is trained using both real and generated data to distinguish between real and fake data, while simultaneously classifying and predicting the location of shear lines. The discriminator parameters are then updated to minimize classification and regression errors. Conversely, the generator is trained by using data generated by the generator to deceive the discriminator, making it difficult for the discriminator to distinguish between real and fake data. The generator parameters are then updated to maximize the adversarial loss while ensuring that the generated data reasonably contains shear line features.

[0084] Preferably, model optimization includes:

[0085] The performance of the shear line recognition model is evaluated using a validation set, and the model evaluation results are obtained by selecting evaluation metrics.

[0086] Based on the model evaluation results, adjust the parameters and architecture of the shear line identification model.

[0087] Specifically, the model evaluation process includes: evaluating the model's performance using a validation set, particularly the accuracy of shear line identification and the precision of location prediction. Metrics such as precision, recall, F1 score, and mean squared error (MSE) can be used to evaluate the model's performance.

[0088] The process of optimizing the model includes adjusting the model parameters and architecture based on the evaluation results, such as adjusting the number of network layers, the number of neurons, and the learning rate. Different activation functions and regularization techniques can also be used to improve the model's generalization ability and robustness.

[0089] It should be noted that this semi-supervised learning method, which combines autoencoders and GANs, can make full use of a large amount of unlabeled data to extract effective features, and with the assistance of a small amount of labeled data, can achieve accurate identification and location prediction of shear lines.

[0090] The present invention provides a method for identifying and tracking shear lines during high-impact weather events in power grids. By systematically analyzing the spatial location and intensity variation characteristics of shear lines throughout the entire process of high-impact weather events, this method optimizes the early warning and response strategies of power grids, thereby improving the stability and resilience of power grids.

[0091] The above is an illustrative scheme of a method for identifying and tracking shear lines during high-impact weather events in power grids, according to this embodiment. It should be noted that the technical solution of this high-impact weather event shear line identification and tracking system belongs to the same concept as the technical solution of the aforementioned high-impact weather event shear line identification and tracking method. Details not described in detail in this embodiment can be found in the description of the aforementioned high-impact weather event shear line identification and tracking method.

[0092] The power grid high-impact weather event shear line identification and tracking system in this embodiment includes:

[0093] The annotation module is used to acquire high-impact weather event data, filter weather event data containing shear line features, and manually annotate the shear line locations.

[0094] The module is used to extract initial meteorological variables based on high-impact weather event data and build a shear line recognition model by designing an autoencoder and an adversarial network.

[0095] The evaluation and optimization module is used to train the shear line recognition model, analyze and evaluate the model's performance, and optimize the model based on the evaluation results.

[0096] This embodiment also provides an electronic device suitable for identifying and tracking shear lines during high-impact weather events on power grids, including:

[0097] The system includes a memory and a processor. The memory stores computer-executable instructions, and the processor executes these instructions to implement the method for identifying and tracking shear lines during high-impact weather events in the power grid, as proposed in the above embodiments.

[0098] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, it implements the method for identifying and tracking shear lines of high-impact weather events in power grids as proposed in the above embodiments.

[0099] The storage medium proposed in this embodiment and the method for identifying and tracking shear lines of high-impact weather events in power grids proposed in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0100] Based on the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0101] Example 2

[0102] Referring to Figure 4, an embodiment of the present invention provides a method for identifying and tracking shear lines during high-impact weather events in power grids. To verify its beneficial effects, scientific demonstration is conducted through economic benefit calculations and simulation experiments.

[0103] During a high-impact weather event, a shear line passed through a certain area, accompanied by severe convective weather and thunderstorms. We will use the established model to identify and track the shear line and analyze its potential impact on the power grid.

[0104] The specific implementation steps are as follows:

[0105] Step 1: Data Preparation

[0106] Meteorological data for the event were extracted from the database of high-impact weather events, including temperature, humidity, wind speed, wind direction, and air pressure at the ground and upper atmosphere (1000hPa-500hPa). The time span covered the entire process of the shear line passing through the area, with data intervals of 1 hour.

[0107] Step 2: Feature Extraction

[0108] By using an autoencoder to extract effective features, the input high-dimensional meteorological data is compressed into a low-dimensional feature space through a trained autoencoder. These low-dimensional features include key meteorological variables such as vorticity, divergence, and temperature gradient.

[0109] Step 3: Shear line identification

[0110] Shear line identification is performed using a trained GAN model. The generator produces realistic meteorological data samples, including potential shear line features. The discriminator classifies the input data, identifies whether it contains shear lines, and outputs the location information of the shear lines.

[0111] Step 4: Track the shear line

[0112] The identified shear lines are tracked, and the positional changes of the shear lines are predicted using models based on time series data; the movement path and intensity changes of the shear lines are recorded.

[0113] Step 5: Results Analysis

[0114] Analyze the identification and tracking results: Evaluate the model's identification accuracy and location prediction precision using real-world data. Analyze the spatial location and intensity variation characteristics of the shear line.

[0115] The example results are as follows:

[0116] Suppose that during a shear line crossing in June 2024, our model successfully identified and tracked the shear line, with the following results:

[0117] Recognition results:

[0118] At 08:00 on June 1, 2024, the model identified a shear line located at 35 degrees north latitude and 120 degrees east longitude, with an altitude of 500 hPa.

[0119] The shear line is prominent, with a vorticity as high as 12×10^-5s^-1 and a horizontal temperature gradient of 5℃ / 100km.

[0120] Tracking results:

[0121] From 08:00 on June 1, 2024 to 20:00 on June 1, 2024, the model continuously tracks the position of the shear line;

[0122] The shear line moves from 35°N, 120°E to 34°N, 125°E, at a speed of approximately 30 km / h.

[0123] The intensity gradually weakens, the vorticity drops to 8×10^-5s^-1, and the horizontal temperature gradient drops to 3℃ / 100km.

[0124] Impact analysis on power grid:

[0125] During the passage of the shear line, strong convection and thunderstorms pose a potential threat to the stability of the power grid. Based on the shear line path predicted by the model, the power grid monitoring and emergency measures in the affected areas were strengthened in advance, which effectively reduced the risks caused by weather changes.

[0126] The model performance evaluation results are as follows:

[0127] Accuracy: 90%

[0128] Recall rate: 85%

[0129] F1 score: 0.875

[0130] Mean Square Error (MSE): 0.05° (position prediction accuracy)

[0131] Experimental results verified the effectiveness and practicality of the shear line identification and tracking technology in this invention. The model can accurately identify and track the spatial location and intensity changes of the shear line, and provide important reference for power grid early warning and response strategies, thereby improving the stability and risk resistance of the power grid.

[0132] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for identifying and tracking shear lines during high-impact weather events on power grids, characterized in that, include: Acquire data on high-impact weather events, filter weather event data containing shear line characteristics, and manually label the shear line locations; Based on the high-impact weather event data, initial meteorological variables are extracted, and a shear line recognition model is constructed by designing an autoencoder and an adversarial network. The shear line identification model is trained, and its performance is analyzed and evaluated. Based on the evaluation results, the model is optimized.

2. The method for identifying and tracking shear lines during high-impact weather events in power grids as described in claim 1, characterized in that, The initial meteorological variables include the temperature, humidity, wind speed, wind direction, altitude field, and air pressure of the ground and the preset pressure surface, and vorticity, divergence, geopotential temperature, and temperature horizontal gradient are calculated as modeling features.

3. The method for identifying and tracking shear lines during high-impact weather events in power grids as described in claim 1, characterized in that, The construction of the shear line recognition model includes: Through an autoencoder architecture design, initial meteorological variable features are extracted from the high-impact weather event data. The autoencoder includes an encoder and a decoder. By designing an adversarial network architecture, the initial meteorological variable features are used as input to the adversarial network to generate weather data samples and identify shear lines.

4. The method for identifying and tracking shear lines during high-impact weather events in power grids as described in claim 3, characterized in that, The self-encoder includes: The encoder compresses high-dimensional input data into a low-dimensional feature space, gradually reducing the dimensionality of the input data to obtain a low-dimensional feature representation. The decoder restores low-dimensional features to high-dimensional input data. The decoder structure is symmetrical with the encoder and gradually increases the dimension to reconstruct high-dimensional data from low-dimensional features.

5. The method for identifying and tracking shear lines during high-impact weather events in power grids as described in claim 3, characterized in that, The adversarial network includes: Samples of real weather data are generated from features extracted by an autoencoder using a generator that progressively transforms low-dimensional noise or features into high-dimensional data. The discriminator distinguishes between real data and generated data, classifies the input data, and outputs the position information of the shear line.

6. The method for identifying and tracking shear lines during high-impact weather events in power grids as described in claim 5, characterized in that, The model training includes: Autoencoder training uses mean squared error to calculate the difference between the high-dimensional input data and the reconstructed high-dimensional data, updates the autoencoder parameters, and minimizes the reconstruction error. Adversarial network training involves training the generator and discriminator adversarially using adversarial loss, identifying shear lines using classification loss, and regressing the shear line positions using regression loss. During training, the generator and discriminator are updated alternately.

7. The method for identifying and tracking power grid shear lines during high-impact weather events as described in any one of claims 3-6, characterized in that, The optimization of the model includes: The performance of the shear line recognition model is evaluated using a validation set, and the model evaluation results are obtained by selecting evaluation metrics. Based on the model evaluation results, adjust the parameters and architecture of the shear line identification model.

8. A power grid shear line identification and tracking system for high-impact weather events, characterized in that, include, The annotation module is used to acquire high-impact weather event data, filter weather event data containing shear line features, and manually annotate the shear line locations. The module is used to extract initial meteorological variables based on the high-impact weather event data, and to build a shear line recognition model by designing an autoencoder and an adversarial network. The evaluation and optimization module is used to train the shear line recognition model, analyze and evaluate the model's performance, and optimize the model based on the evaluation results.

9. An electronic device, characterized in that, include: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, they implement the steps of the power grid high-impact weather event shear line identification and tracking method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It stores computer-executable instructions, which, when executed by a processor, implement the steps of the power grid high-impact weather event shear line identification and tracking method according to any one of claims 1 to 7.

Images