Intelligent prediction method and system for line tripping in extreme and turning weather

Abstract

The invention discloses an intelligent prediction method and system for line tripping in extreme and turning weather, and relates to the field of prediction of a tripping fault of a power transmission line, and the method comprises the steps: obtaining first data reflecting at least one of the extreme weather or the turning weather, and second data reflecting the line condition; performing deep learning training based on the first data and the second data to obtain a first prediction model; performing visualization and iterative optimization on the first prediction model to obtain a second prediction model; introducing the tower positioning frame into the second prediction model to obtain a line tripping prediction model; and substituting prediction data later than the acquisition time of the first data and the second data into the line trip prediction model to obtain a trip fault range and a fault level. According to the method, the tower positioning frame is introduced, the fault position can be accurately positioned based on the prediction model, 10kV line tripping prediction under extreme weather is realized, and the fault severity and the risk level are automatically given according to tower division.

Description

Technical Field

[0001] The present invention relates to the field of prediction of transmission line tripping faults, and in particular to an intelligent prediction method and system for line tripping under extreme and transitional weather conditions. Background Art

[0002] Line tripping caused by extreme and transitional weather changes often occurs, such as tripping caused by lightning directly striking insulators, external force damage caused by heavy rain, and branch pressure caused by heavy snow, which may affect the line faults; there are many 10kV distribution lines, a large power supply area, a wide area, and complex terrain. At present, the situation of line tripping is relatively passive. It is handled only after receiving a notification after the tripping occurs, or it is completely dependent on manual experience. Only some preliminary predictions can be made based on a large amount of power grid line information and weather information. At present, only the fault point can be locked and isolated, and the fault point cannot be accurately located, and the fault cannot be prevented or predicted efficiently, which affects the safe and stable operation of the power grid and the reliability of power supply. Therefore, it is urgent to study an intelligent prediction tool for line tripping under extreme and transitional weather, using historical weather, faults, etc. as the basis, and combined with the influence of future weather, to automatically and quickly predict the probability of 10kV line tripping. Existing patents and technologies combine the power grid system's flow data and weather data to output fault prediction information, but are deficient in locating the fault. The present invention combines the longitude and latitude of the line tower to more accurately locate the fault. Summary of the invention

[0003] In view of the above-mentioned problems, the present invention is proposed.

[0004] Therefore, the problem to be solved by the present invention is that the existing patents and technologies combine the power grid system's flow data and weather data to output fault prediction information, but are deficient in locating the fault.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: an intelligent prediction method for line tripping under extreme and transitional weather conditions, comprising: obtaining first data that satisfies at least one of extreme weather or transitional weather conditions, and second data that reflects line conditions; performing deep learning training based on the first data and the second data to obtain a first prediction model; visualizing the first prediction model and iteratively optimizing it to obtain a second prediction model; introducing a pole tower positioning frame into the second prediction model to obtain a line tripping prediction model; substituting the prediction data that is later than the acquisition time of the first data and the second data into the line tripping prediction model to obtain the tripping fault range and fault level.

[0006] As a preferred solution of the intelligent prediction method for line tripping under extreme and transitional weather conditions described in the present invention, wherein: before the first data and the second data are subjected to deep learning training, it is necessary to ensure that the first data and the second data are consistent in time scale and event scale, that is, the time when the first data is acquired and the time when the second data is acquired correspond to each other and are consistent; the calibration event when the first data is acquired and the calibration event when the second data is acquired are the same event; the first time and the second data that are consistent in time scale and event scale are used as a group of data pairs for deep learning training.

[0007] As a preferred solution of the intelligent prediction method for line tripping under extreme and transitional weather conditions described in the present invention, the training content of the first prediction model includes, based on the first data and the second data, training to obtain, under the condition of obtaining the first data, according to the second data, the occurrence status of the second data under different first data conditions, that is, under different weather conditions, the probability of occurrence of the fault, the cause of occurrence, the scope of impact and the degree of impact.

[0008] As a preferred solution of the intelligent prediction method for line tripping under extreme and transitional weather conditions described in the present invention, the visualization requirement of the second prediction model is that the prediction model, prediction process and prediction results are displayed in a visualized graph, and the visualization graph contains the prediction information of the prediction model.

[0009] As a preferred solution of the intelligent prediction method for line tripping under extreme and transitional weather conditions described in the present invention, the introduction of the pole tower locating frame into the second prediction model includes introducing a corresponding pole tower locating frame under the calibration event of the second data; the pole tower locating frame includes the latitude and longitude, height and tower shape of the pole tower in the calibration event of the second data.

[0010] As a preferred solution of the intelligent prediction method for line tripping under extreme and transitional weather conditions described in the present invention, wherein: the substitution of the prediction data later than the acquisition time of the first data and the second data into the line tripping prediction model includes using the first data and the second data acquired at the first time for model training, and substituting the prediction data acquired at the second time later than the first time into the line tripping prediction model for prediction; the prediction data includes the first data and the second data at the second time; the amount of the first data and the second data at the second time is less than the amount of the first data and the second data at the first time.

[0011] As a preferred solution of the intelligent prediction method for line tripping under extreme and transitional weather conditions described in the present invention, the obtaining of the tripping fault range and fault level includes obtaining the tripping fault range according to the impact range in the training content; obtaining the tripping fault level according to the probability of occurrence, cause of occurrence and impact degree of the fault in the training content; and the fault level is divided into at least two levels.

[0012] Another object of the present invention is to provide an intelligent prediction system for line tripping under extreme and transitional weather conditions, which can predict the probability, scope, impact degree and other information of tripping faults based on future weather data and line data.

[0013] To solve the above technical problems, the present invention provides the following technical solutions: a system for an intelligent prediction method for line tripping under extreme and transitional weather conditions, comprising: a data acquisition module, a model training module and a prediction module; the data acquisition module acquires first data that satisfies at least one of extreme weather or transitional weather conditions, and second data that reflects line conditions; the model training module performs deep learning training based on the first data and the second data to obtain a first prediction model, visualizes the first prediction model and iteratively optimizes it to obtain a second prediction model; the prediction module introduces a pole tower positioning frame into the second prediction model to obtain a line tripping prediction model, substitutes the prediction data that is later than the acquisition time of the first data and the second data into the line tripping prediction model, and obtains the tripping fault range and fault level.

[0014] A computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned method for intelligently predicting line tripping under extreme and transitional weather conditions are implemented.

[0015] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for intelligent prediction of line tripping under extreme and transitional weather conditions.

[0016] The beneficial effects of the present invention are as follows: based on historical weather and 10kV line tripping information, a prediction model is formed by using intelligent technologies such as deep learning and visualization, which can support the prediction of line tripping under complex weather conditions.

[0017] In addition, existing patents and technologies combine the power grid system's flow data and weather data to output fault prediction information, but are deficient in locating the fault. The present invention introduces a tower positioning frame, based on a prediction model and combined with visualization capabilities, to accurately locate the fault location, achieve 10kV line tripping prediction under extreme weather conditions, and automatically give fault severity and risk level according to tower divisions, assisting operation and maintenance units to dynamically and quickly predict risks in order to reduce risks or take preventive measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0019] Figure 1 This is a flow chart of an intelligent prediction method for line tripping under extreme and transitional weather conditions in Example 1.

[0020] Figure 2 This is a module structure diagram of an intelligent prediction system for line tripping under extreme and transitional weather conditions in Example 3. DETAILED DESCRIPTION

[0021] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0022] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0023] Example 1, reference Figure 1 , which is the first embodiment of the present invention, and which provides an intelligent prediction method for line tripping under extreme and transitional weather conditions, including: Figure 1 As shown:

[0024] S1. Acquire first data that reflects at least one of extreme weather or transitional weather, and second data that reflects line conditions.

[0025] In this embodiment, the first data may be extreme weather data or transitional weather data, and extreme weather includes weather data such as lightning, strong wind, heavy rain, heavy snow, high temperature, low temperature, etc. Transitional weather may include weather type data such as sudden temperature difference change, sudden humidity change, sudden wind direction change, sudden air pressure change, etc.

[0026] It should be noted that transitional weather is weather in which weather type parameters undergo drastic changes, so extreme weather includes transitional weather.

[0027] To further illustrate, the first data of the present invention is parameter data such as temperature, precipitation, wind level, etc. under extreme weather or transitional weather. Since the difficulty of parameter measurement increases in extreme weather environments, the size of the data is not required.

[0028] The second data in this embodiment may be a combination of basic information in the 10kV line, line GIS information, line tripping information, and line defect information.

[0029] Among them, basic information includes line number, line type, line length, material type, commissioning date, operation and maintenance unit and other information; line GIS information includes spatial location, grounding facilities, line path, topography, environmental conditions and other information; line tripping information includes tripping time, tripping location, tripping cause, tripping type, recovery time, impact range, treatment measures and other information; line defect information includes defect type, defect level, discovery time, defect description, treatment results and other information.

[0030] It should be noted that in order to achieve the purpose of predicting tripping faults of the present invention, the second data must include basic information and line tripping information. If the acquired information lacks any one of the basic information and the line tripping information, the acquired information cannot be used as the second data and will be discarded.

[0031] In an optional embodiment, the first data and the second data can be obtained by using crawler technology. For extreme weather and transitional weather data, they are usually obtained from meteorological department websites, meteorological data open platforms or professional meteorological service websites. For 10kV line information, the data may be stored in the power company's internal database, operation and maintenance management system or public data of relevant government regulatory platforms.

[0032] Before crawling, choose a suitable programming language and crawler framework, such as Python's Scrapy, BeautifulSoup or requests library, and prepare corresponding storage and computing resources, such as cloud servers, databases, etc. Use browser developer tools to analyze the target website structure and determine the location of the data to be crawled. Determine the URLpattern, parameters, page turning logic, etc. of the target data. Write code to implement simulated login (if necessary). Write code to parse the web page content and extract the required data. Process paging and page turning logic to ensure data integrity. Add exception handling, delay, proxy and other mechanisms to avoid being restricted by the website's anti-crawler strategy. Store the crawled data in a database, such as MySQL, MongoDB, etc. Design a reasonable data table structure to ensure data integrity and query efficiency. Clean the crawled data to remove invalid, erroneous or duplicate data. Perform necessary preprocessing on the data, such as format conversion, data validation, etc.

[0033] In an optional embodiment, the acquisition method of the first data and the second data can also be collected by offline import, confirming the data provider and data format, checking the integrity and format of the data file, and performing preliminary cleaning on the data, such as removing irrelevant formats, correcting errors, etc. Design a reasonable database structure according to the data content, including table structure, field type, index, etc. Use database management tools (such as MySQL Workbench, SQL Server Management Studio, etc.) or command line tools (such as mysqlimport, sqlcmd, etc.) to import data files into the database. For CSV or Excel files, it may be necessary to write an import script or use the database import wizard. After the data is imported, perform data verification to ensure the accuracy and integrity of the data. Compare the number of data records before and after the import, and check whether there are missing values ​​or abnormal values ​​in the key fields. If the data comes from different sources, data integration may be required to eliminate duplication, unify the data format, etc. After the data is successfully imported, perform a database backup to prevent data loss.

[0034] S2. Perform deep learning training based on the first data and the second data to obtain a first prediction model.

[0035] Before deep learning training is performed on the first data and the second data, it is necessary to ensure that the first data and the second data are consistent in time scale and event scale, that is, the time when the first data is acquired corresponds to the time when the second data is acquired and remains consistent; the calibration event when the first data is acquired is the same event as the calibration event when the second data is acquired.

[0036] It should be noted that the time for acquiring the first data is the time when the parameter data is collected under extreme weather or transitional weather, and the time for acquiring the second data is the time when the tripping fault occurs, such as xx:00 on xx:00 on xx:00, wherein the time for acquiring the first data corresponds to the time for acquiring the second data and remains consistent, which does not mean that the time for acquiring the first data is exactly the same as the time for acquiring the second data. There may be a time difference, and the threshold of the time difference depends on the specific working conditions, and the maximum cannot exceed 24 hours.

[0037] To further illustrate, the calibration event when the first data is acquired, such as heavy snow at xx:00 on ...

[0038] The first time data and the second data which are consistent in time scale and event scale are used as a set of data pairs for deep learning training.

[0039] The training content of the first prediction model includes, based on the first data and the second data, training to obtain the occurrence of the second data under different first data conditions according to the second data under the first data acquisition conditions, that is: under different weather conditions, the probability of occurrence of the tripping fault, the cause of occurrence, the scope of impact and the degree of impact.

[0040] The deep learning training methods can be multi-layer perceptron (MLP), convolutional neural network (CNN), recurrent neural network (RNN) and its variants, temporal convolutional network (TCN), autoencoder (Autoencoder), generative adversarial network (GAN), attention mechanism (Attention Mechanism) and other training models.

[0041] In an optional embodiment, the first model may be trained by a convolutional neural network (CNN), specifically including data standardization, and the formula is expressed as:

[0042]

[0043] Among them, X norm Represents the standardized data, X represents the original data pair, μ represents the mean of the data, and σ represents the standard deviation of the data.

[0044] Building a CNN model:

[0045] Input layer: receives the standardized data X norm .

[0046] Convolutional layer: Y conv =ReLU(conv(Xnorm , W conv )+b conv )

[0047] Among them, conv represents the convolution operation, W conv Represented as the convolution kernel weight, b conv It is represented as the bias term and ReLU is represented as the activation function.

[0048] Pooling layer: Y Pool =Pool(Y conv )

[0049] Among them, Pool represents the pooling operation.

[0050] Fully connected layer: Y fc =ReLU(W fc Y Pool +b fc )

[0051] Among them, Y fc Represented as the fully connected layer output, W fc Denotes the weight of the fully connected layer, b fc Represented as the bias term of the fully connected layer.

[0052] Output layer:

[0053] in, is represented as the prediction result, ε is represented as the activation function of the output layer, W out Denotes the weight of the output layer, b out Represented as the bias term of the output layer.

[0054] The loss function L is constructed as:

[0055]

[0056] Where N is the number of samples, y i is represented as the true label, Expressed as predicted probability.

[0057] The following steps are repeated until convergence: Forward propagation calculates the predicted value Calculate the loss L and update the weights W of each layer.

[0058] In an optional embodiment, the first model can also be obtained by training a recurrent neural network (RNN), and the data normalization step is the same as the convolutional neural network (CNN) training process.

[0059] Build the RNN model:

[0060] Input layer: receives the normalized data.

[0061] RNN layer: For each time step t, calculate the hidden state h t It is expressed as,

[0062] h t =tanh(W ih X t +W hh h t-1 +b h )

[0063] Among them, X t Denote the input at time step t, W ih Represented as the weight input to the hidden layer, W hh It is represented as the weight from hidden layer to hidden layer, b h It is represented as the bias term of the hidden layer and tanh is represented as the activation function.

[0064] Output layer: Calculates the predicted output for each time step t It is expressed as,

[0065]

[0066] Among them, W ho Represented as the weight from the hidden layer to the output layer, b o Represented as the bias term of the output layer of the RNN model.

[0067] The construction of the loss function is the same as the convolutional neural network (CNN) training process.

[0068] Using, for example, the Adam optimizer to update the weights is expressed as,

[0069]

[0070] Among them, α represents the learning rate, It is expressed as the gradient of the loss function with respect to the weights.

[0071] The following steps are repeated until convergence: Initialize the weights, and for each time step t, forward propagate to calculate h t and Calculate the loss L and back propagate to calculate the gradient Update the weight W.

[0072] S3. Visualize the first prediction model and iteratively optimize it to obtain a second prediction model.

[0073] The visualization requirement of the second prediction model is that the prediction model, prediction process and prediction results are displayed in a visualized graph, and the visualization graph contains the prediction information of the prediction model.

[0074] S4. Introduce the tower positioning frame into the second prediction model to obtain a line tripping prediction model.

[0075] A corresponding tower positioning frame is introduced under the calibration event of the second data.

[0076] The information in the pole tower positioning frame includes the latitude and longitude, height and tower shape of the pole tower in the calibration event corresponding to the second data.

[0077] S5. Substitute the prediction data acquired later than the first data and the second data into the line trip prediction model to obtain the trip fault range and fault level.

[0078] The first data and the second data acquired at the first time are used for model training, and the prediction data acquired at the second time later than the first time is substituted into the line tripping prediction model for prediction.

[0079] The predicted data includes first data and second data at a second time.

[0080] The data amounts of the first data and the second data at the second time are less than the data amounts of the first data and the second data at the first time.

[0081] It should be noted that the first time in this embodiment is the time when the data is acquired, that is, the historical time, and the second time is the time of the current prediction point or the future time. Because the amount of information acquired in the future is less, the amount of data in the second time is generally less than the first time.

[0082] The tripping fault range is estimated based on the impact range obtained by the prediction model.

[0083] The tripping fault level is obtained by comprehensively analyzing the probability of occurrence, cause of occurrence and impact degree of the fault obtained by the prediction model.

[0084] It is further explained that the tripping fault level can be obtained by weighted calculation of the probability of occurrence of the fault, the cause of occurrence and the degree of impact. The specific fault level is obtained by comparing with the preset threshold. The fault level is divided into at least two levels.

[0085] In an optional embodiment, the fault level can be divided into two levels, such as serious and non-serious. If the fault level is serious, a plan is immediately made for repair. If the fault level is non-serious, a specific repair time can be determined based on actual conditions.

[0086] In an optional embodiment, the fault level can be further divided into three levels, such as low, medium and high. If the fault level is low, idle personnel will be sent to check and repair it. If the fault level is medium, the specific repair time can be determined according to the actual situation, and a professional team can be organized to repair it. If the fault level is high, a plan will be made immediately for repair.

[0087] Embodiment 2 is the second embodiment of the present invention, which is different from the first embodiment in that: a method for intelligent prediction of line tripping under extreme and transitional weather conditions also includes visualizing the first prediction model to obtain a second prediction model.

[0088] It should be noted that the visualization method can be knowledge graph visualization, geographic information system (GIS) visualization, interactive data visualization and other methods.

[0089] In an optional embodiment, the second model may be obtained by visualizing the knowledge graph, specifically including defining entities and relationships:

[0090] Entities: such as lines, substations, weather events, tripping events, defect reports, etc.

[0091] Relationship: such as "located in", "cause", "influence", etc.

[0092] Design the ontology structure, define entity types and relationship types, use entity recognition technology to extract entities from the data and link them with entities in the ontology, and finally extract the relationships between entities from the data.

[0093] Knowledge graph storage:

[0094] Select storage medium: You can use graph databases such as Neo4j, OrientDB, etc. to store knowledge graphs and import the constructed knowledge graphs into the graph database.

[0095] Visual design:

[0096] Choose visualization tools: You can use tools such as Neo4j Browser, Cytoscape, Gephi, etc. for visualization. Customize the color, shape, size and other properties of nodes and edges as needed to better express information.

[0097] In an optional embodiment, the second model can also be obtained by visualization of a geographic information system (GIS) (reminder: if this method is adopted, it can generally be performed after the positioning box is introduced in step S4), specifically including ensuring that all data contains geospatial information (such as longitude and latitude) and preparing data formats such as CSV, Shapefile or GeoJSON.

[0098] Choose a GIS software such as ArcGIS, QGIS, or Google Earth Pro.

[0099] Import data into GIS software.

[0100] For QGIS, open QGIS and select Layer > Add Layer > Add Vector Layer to import the Shapefile or GeoJSON file.

[0101] For non-spatial data, you can import a CSV file via "Add DelimitedTextLayer" and specify the geospatial fields.

[0102] Set different symbols and colors for different data types. For example, you can set lines to different colors, trip events to red markers, and defect reports to yellow markers.

[0103] Create different layers, each representing a data type (e.g. lines, trips, defects, weather events).

[0104] Create a new layer via Layer > AddLayer > Create Layer > New Shapefile Layer.

[0105] Use spatial joins or attribute joins to relate data from different layers.

[0106] In QGIS, you can use the "Vector" > "Data Management Tools" > "Join Attributes by Location" function.

[0107] Use the analysis tools of GIS software to perform spatial analysis, such as buffer analysis, overlay analysis, etc.

[0108] View spatial relationships between different layers, such as whether tripping events are concentrated near specific lines or weather events.

[0109] Take advantage of the interactive features of GIS software, such as clicking to view detailed information, filtering data for a specific time period, etc.

[0110] Export visualization results as images or PDF files. If you are using a web GIS platform, you can generate a sharing link or embed it into a web page.

[0111] Example 3, reference Figure 2, which is the third embodiment of the present invention, and is different from the previous two embodiments in that: a system for an intelligent prediction method for line tripping under extreme and transitional weather conditions, comprising a data acquisition module 100, a model training module 200 and a prediction module 300; the data acquisition module 100 acquires first data that satisfies at least one of extreme weather or transitional weather, and second data that reflects line conditions; the model training module 200 performs deep learning training based on the first data and the second data to obtain a first prediction model, visualizes the first prediction model and iteratively optimizes it to obtain a second prediction model; the prediction module 300 introduces a tower positioning frame into the second prediction model to obtain a line tripping prediction model, substitutes the prediction data that is later than the first data and the second data acquisition time into the line tripping prediction model, and obtains the tripping fault range and fault level.

[0112] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0113] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0114] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0115] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0116] 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 preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An intelligent prediction method for line tripping under extreme and transitional weather conditions, characterized by: include, Acquire first data that satisfies at least one of extreme weather or transitional weather, and second data that reflects line conditions; Performing deep learning training based on the first data and the second data to obtain a first prediction model; Visualizing the first prediction model and iteratively optimizing it to obtain a second prediction model; The tower positioning frame is introduced into the second prediction model to obtain a line tripping prediction model; The prediction data acquired later than the first data and the second data are substituted into the line trip prediction model to obtain the trip fault range and fault level.

2. The intelligent prediction method for line tripping under extreme and transitional weather conditions according to claim 1, characterized in that: Before deep learning training is performed on the first data and the second data, it is necessary to ensure that the first data and the second data are consistent in time scale and event scale, that is: The time of acquiring the first data corresponds to the time of acquiring the second data and remains consistent with each other; The calibration event during the first data acquisition and the calibration event during the second data acquisition are the same event; The first time data and the second data which are consistent in time scale and event scale are used as a set of data pairs for deep learning training.

3. The intelligent prediction method for line tripping under extreme and transitional weather conditions as claimed in claim 2, characterized in that: The training content of the first prediction model includes, based on the first data and the second data, training to obtain, under the condition of obtaining the first data, according to the second data, the occurrence of the second data under different first data conditions, namely: The probability, cause, scope and degree of impact of failures under different weather conditions.

4. The intelligent prediction method for line tripping under extreme and transitional weather conditions as claimed in claim 3, characterized in that: The visualization requirement of the second prediction model is that the prediction model, prediction process and prediction results are displayed in a visualized graph, and the visualization graph contains the prediction information of the prediction model.

5. The intelligent prediction method for line tripping under extreme and transitional weather conditions according to claim 4, characterized in that: The introducing the pole tower positioning frame into the second prediction model comprises introducing a corresponding pole tower positioning frame under a calibration event of the second data; The pole tower positioning frame includes the latitude and longitude, height and tower shape of the pole tower in the calibration event of the second data.

6. The intelligent prediction method for line tripping under extreme and transitional weather conditions according to claim 5, characterized in that: Substituting the prediction data acquired later than the first data and the second data into the line tripping prediction model comprises: using the first data and the second data acquired at the first time for model training, and substituting the prediction data acquired at the second time later than the first time into the line tripping prediction model for prediction; The predicted data includes first data and second data at a second time; The data amounts of the first data and the second data at the second time are less than the data amounts of the first data and the second data at the first time.

7. The intelligent prediction method for line tripping under extreme and transitional weather conditions according to claim 6, characterized in that: The obtaining of the tripping fault range and fault level includes obtaining the tripping fault range according to the impact range in the training content; A tripping fault level is obtained based on the probability of occurrence, cause of occurrence and impact degree of the fault in the training content; The fault level is divided into at least two levels.

8. A system using the intelligent prediction method for line tripping under extreme and transitional weather conditions as claimed in any one of claims 1 to 7, characterized in that: It includes a data collection module (100), a model training module (200) and a prediction module (300); The data collection module (100) acquires first data that reflects at least one of extreme weather or transitional weather, and second data that reflects line conditions; The model training module (200) performs deep learning training based on the first data and the second data to obtain a first prediction model, and visualizes and iteratively optimizes the first prediction model to obtain a second prediction model; The prediction module (300) introduces the pole tower positioning frame into the second prediction model to obtain a line trip prediction model, substitutes the prediction data acquired later than the first data and the second data into the line trip prediction model to obtain the trip fault range and fault level.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the intelligent prediction method for line tripping under extreme and transitional weather conditions described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a method for intelligently predicting line tripping under extreme and transitional weather conditions described in any one of claims 1 to 7 are implemented.

Images