Power transmission line monitoring method based on meteorological disaster early warning

Abstract

The invention relates to the technical field of electric power engineering, in particular to a power transmission line monitoring method based on meteorological disaster early warning, which comprises the steps of risk assessment model establishment, potential risk area division, risk level division, real-time monitoring and remote monitoring and management. The data acquisition center carries out decoding, coding and primary processing on data and regularly checks the working state of a sensor by supporting multiple transmission protocols, and can access monitoring equipment under different communication protocols, so that on one hand, the redundancy and repetition of the equipment can be avoided, and on the other hand, the monitoring efficiency is improved; on the other hand, the building and laying cost of the monitoring system is reduced, comprehensive receiving, efficient transmission, safe storage and accurate analysis of meteorological data are effectively ensured, and a solid technical guarantee is provided for stable operation and efficient management of the real-time monitoring system of the power transmission line.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power engineering, and in particular to a method for monitoring a power transmission line based on meteorological disaster early warning. Background Art

[0002] Meteorological disasters, such as strong winds, heavy rains, lightning, extreme temperatures, etc., pose a serious threat to the stable operation of transmission lines. These meteorological conditions may not only cause physical damage to the lines, but may also cause power failures such as short circuits and tripping, thereby affecting the overall stability of the power system and the reliability of power supply.

[0003] Traditional transmission line monitoring methods often rely on manual inspections or limited fixed monitoring points. This approach is not only inefficient but also difficult to fully cover all potential risk areas. In addition, due to the complexity and diversity of meteorological data, as well as the wide distribution of transmission lines and the changing environment, real-time data collection, transmission, processing and analysis become an extremely challenging task.

[0004] Therefore, in the background technology, there is an urgent need for a method that can efficiently and accurately monitor the meteorological disaster risks of transmission lines in order to achieve early warning and timely response to meteorological disasters. The present invention is proposed to solve this problem. By constructing a transmission line monitoring system based on meteorological disaster warning, real-time monitoring and intelligent analysis of the meteorological parameters of the environment where the transmission lines are located can be achieved, thereby effectively improving the safe operation level of the transmission lines. Summary of the invention

[0005] In order to overcome the problems raised in the above background technology, the present invention provides a transmission line monitoring method based on meteorological disaster early warning.

[0006] The technical solution of the present invention is: a transmission line monitoring method based on meteorological disaster early warning, comprising the following steps:

[0007] S11: Establishing a risk assessment model, firstly collecting historical meteorological data of the area where the transmission line is located and characteristic data of the transmission line, and using the collected data to build a risk assessment model for assessing the meteorological disaster risk of the transmission line;

[0008] S12: Division of potential risk areas: First, conduct meteorological data analysis, analyze the meteorological data in depth, identify meteorological conditions that may cause damage to the transmission line, and then conduct geographical environmental factors analysis. Combined with geographical environmental factors, the area through which the transmission line passes is divided into potential risk areas;

[0009] S13: Risk level classification: Use the risk assessment model to evaluate potential risk areas, determine the risk level of each area, and provide the risk level classification results to power system decision makers so that they can take corresponding prevention and response measures;

[0010] S14: Real-time monitoring: high-precision meteorological sensors and data collection centers are installed along the transmission lines. The key meteorological parameters of the environment where the transmission lines are located are collected in real time using the installed high-precision meteorological sensors and data collection centers. The monitoring data collected by the high-precision meteorological sensors are transmitted to the monitoring center using the Internet of Things technology. The monitoring center then processes and analyzes the data intelligently.

[0011] S15: Remote monitoring and management: Through the monitoring center, the monitoring data can be viewed to achieve unified management across regions and time periods. When abnormal data is detected, emergency response measures can be taken to ensure the safe operation of the transmission line.

[0012] Preferably, when collecting historical meteorological data of the area where the transmission line is located and characteristic data of the transmission line, and using the collected data to construct a risk assessment model for assessing the meteorological disaster risk of the transmission line, the following steps are included:

[0013] S21: Determine data requirements. First, it is necessary to clarify the data types required by the risk assessment model, including historical meteorological data and characteristic data of transmission lines. The historical meteorological data includes wind speed, rainfall, temperature, humidity and air pressure, and the characteristic data of transmission lines includes line material, installation method and maintenance history.

[0014] S22: Data collection channels. The data collection channels are determined according to data requirements. The channels for collecting historical meteorological data include meteorological departments, scientific research institutions and third-party data providers. The channels for collecting characteristic data of transmission lines include power companies and line maintenance departments.

[0015] S23: Data collection: collecting the required data according to the determined data requirements and the determined data collection methods;

[0016] S24: Data preprocessing: cleaning and organizing the collected raw data to remove duplicate, erroneous and invalid data to ensure the accuracy and consistency of the data;

[0017] S25: Model construction: According to the type of data collected and the needs of risk assessment, select the appropriate modeling method, perform feature selection and processing on the collected data, use the processed data to train the model, and evaluate the performance of the model through cross-validation method.

[0018] Preferably, when cleaning and organizing the collected raw data to remove duplicate, erroneous and invalid data and ensure the accuracy and consistency of the data, the data processing methods used include:

[0019] A11: Data standardization includes converting data into dimensionless form to ensure the accuracy and consistency of subsequent analysis. The principle formula of standardization is:

[0020]

[0021] Among them, X , Represents the value of data point X after normalization;

[0022] A12: Identify and process missing values ​​by deleting records with missing values ​​and using specific values ​​to fill missing values, identify and delete duplicate records by comparing records in the data set, and identify and process outliers by statistical methods. The specific values ​​used in the method of using specific values ​​to fill missing values ​​include mean, median and mode. When identifying outliers, the principle formula of the statistical method used is:

[0023]

[0024] Where X is the data point, μ is the mean, and σ is the standard deviation. When identifying outliers, when the size of Z calculated from data point X is greater than the set threshold, the data point X is marked as an outlier.

[0025] A13: Format conversion: converting data into a format suitable for subsequent analysis and modeling, including data type conversion and data encoding;

[0026] A14: Data normalization processing, where the principle formula of normalization processing is:

[0027]

[0028] Among them, X ‘’ Represents the normalized value of data point X, X min represents the minimum value in the data set, X max Represents the maximum value in the data set.

[0029] Preferably, when selecting a suitable modeling method according to the type of data collected and the requirements of risk assessment, and performing feature selection and processing on the collected data, and then using the processed data to train the model, and evaluating the performance of the model through the cross-validation method, the selectable model types include:

[0030] A21: Linear regression model is used to describe the linear relationship between independent variables and dependent variables;

[0031] A22: Logistic regression model, used for binary classification problems;

[0032] A23: Support vector machine decision function model, which performs classification by finding the optimal hyperplane that can separate samples of different categories.

[0033] As a preference, the principle formula of the linear regression model is:

[0034] Y=β0+β1X1+β2X2+...+βnXn+ε;

[0035] Where Y is the risk level of the power line, X1, X2, ..., Xn are independent variables, β0 is the intercept term, β1, β2, ..., βn are regression coefficients, and ε is the error term.

[0036] As a preferred method, the principle formula of the logistic regression model is:

[0037] P(Y=1|X)=1 / (1+e ^ (β0+β1X1+β2X2+...+βnXn)));

[0038] Where P(Y=1|X) is the probability that the dependent variable Y=1 given the independent variable X, and β0, β1, β2, ..., βn are regression coefficients.

[0039] As a preferred embodiment, the principle formula of the support vector machine decision function model is:

[0040] f(x)=sign(∑αiyiK(xi,x)+b);

[0041] Among them, αi is the Lagrange multiplier, yi is the sample label, K(xi,x) is the kernel function, and b is the bias term.

[0042] As a preferred method, when conducting meteorological data analysis, in-depth analysis of meteorological data is performed to identify meteorological conditions that may cause damage to the transmission line, and then geographical environmental factors are analyzed. In combination with geographical environmental factors, the area through which the transmission line passes is divided into potential risk areas. When conducting risk assessment, the calculation principle formula of the risk size is:

[0043] For risk assessment of individual risk factors:

[0044] Risk = Probability × Impact;

[0045] Among them, Risk is the risk value, Probability is the probability of an event occurring, and Impact is the degree of impact after the event occurs;

[0046] For risk assessment with multiple risk factors:

[0047] Total_Risk=∑(Risk_i×Weight_i)

[0048] Among them, Total_Risk is the total risk value, Risk_i is the risk value of the i-th risk factor, and Weight_i is the weight of the i-th risk factor.

[0049] As a preferred method, high-precision meteorological sensors and data collection centers are installed along the transmission lines. The installed high-precision meteorological sensors and data collection centers are used to collect key meteorological parameters of the environment where the transmission lines are located in real time, and the monitoring data collected by the high-precision meteorological sensors are transmitted to the monitoring center using the Internet of Things technology. When the monitoring center performs intelligent processing and analysis on the data, the functions of the data collection center include:

[0050] A31: Provides multiple transmission protocol formats and receives data in different transmission protocol formats;

[0051] A32: decode and re-encode received data;

[0052] A33: performing preliminary processing on the received sensor data, wherein the preliminary processing method adopted includes data encryption and data compression;

[0053] A34: Perform periodic inspections on the working status of high-precision meteorological sensors.

[0054] As a preferred method, high-precision meteorological sensors and data collection centers are installed along the transmission lines, and the key meteorological parameters of the environment where the transmission lines are located are collected in real time by using the installed high-precision meteorological sensors and data collection centers. The monitoring data collected by the high-precision meteorological sensors are transmitted to the monitoring center by using the Internet of Things technology. When the monitoring center performs intelligent processing and analysis on the data, the following steps are included:

[0055] S31: Data preprocessing, including missing value processing, outlier detection and processing, data standardization, data normalization and feature extraction;

[0056] S32: Hazard identification: input the pre-processed data into the constructed model, use the model to process and analyze the data, and identify abnormal meteorological conditions and set hazardous data;

[0057] S33: generating a warning signal, based on the result of abnormality detection and in combination with preset warning rules, generating a warning signal, and issuing the generated warning signal to relevant personnel through a set channel.

[0058] Beneficial effects of the present invention:

[0059] 1. The data acquisition center of the present invention supports multiple transmission protocols, decodes and encodes data, performs preliminary processing, and regularly checks the working status of sensors. It can also access existing monitoring equipment under different communication protocols. On the one hand, it can avoid redundancy and duplication of equipment, and on the other hand, it can reduce the construction and laying costs of the monitoring system, effectively ensuring the comprehensive reception, efficient transmission, safe storage and accurate analysis of meteorological data, and providing a solid technical guarantee for the stable operation and efficient management of the real-time monitoring system of the transmission line;

[0060] 2. By flexibly selecting multiple models such as linear regression, logistic regression and support vector machine decision functions, combining the characteristics of the data and risk assessment requirements for feature selection and processing, and using cross-validation methods to evaluate model performance, not only the applicability and accuracy of the model are improved, but also it is ensured that the model can accurately predict the risk level of the transmission line, providing strong technical support for the safe operation of the power system;

[0061] 3. By building a risk assessment model, dividing potential risk areas and risk levels, combining high-precision meteorological sensors and Internet of Things technology to achieve real-time monitoring, and realizing unified management and emergency response through remote monitoring and management, the early warning capability of transmission lines for meteorological disasters has been effectively improved, providing a scientific basis for power system decision makers and ensuring the safe and stable operation of transmission lines. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 It is a flow chart of a method for monitoring a power transmission line based on meteorological disaster warning according to the present invention;

[0063] Figure 2 It is a schematic diagram of the process of establishing a risk assessment model in the transmission line monitoring method based on meteorological disaster warning of the present invention. DETAILED DESCRIPTION

[0064] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0065] See also Figure 1-2 The present invention provides an embodiment: a transmission line monitoring method based on meteorological disaster warning, comprising the following steps:

[0066] S11: Establishing a risk assessment model, firstly collecting historical meteorological data of the area where the transmission line is located and characteristic data of the transmission line, and using the collected data to build a risk assessment model for assessing the meteorological disaster risk of the transmission line;

[0067] S12: Division of potential risk areas: First, conduct meteorological data analysis, analyze the meteorological data in depth, identify meteorological conditions that may cause damage to the transmission line, and then conduct geographical environmental factors analysis. Combined with geographical environmental factors, the area through which the transmission line passes is divided into potential risk areas;

[0068] S13: Risk level classification: Use the risk assessment model to evaluate potential risk areas, determine the risk level of each area, and provide the risk level classification results to power system decision makers so that they can take corresponding prevention and response measures;

[0069] S14: Real-time monitoring: high-precision meteorological sensors and data collection centers are installed along the transmission lines. The key meteorological parameters of the environment where the transmission lines are located are collected in real time using the installed high-precision meteorological sensors and data collection centers. The monitoring data collected by the high-precision meteorological sensors are transmitted to the monitoring center using the Internet of Things technology. The monitoring center then processes and analyzes the data intelligently.

[0070] S15: Remote monitoring and management: Through the monitoring center, the monitoring data can be viewed to achieve unified management across regions and time periods. When abnormal data is detected, emergency response measures can be taken to ensure the safe operation of the transmission line.

[0071] As described above, the present invention constructs a risk assessment model, divides potential risk areas and risk levels, combines high-precision meteorological sensors and Internet of Things technology to achieve real-time monitoring, and achieves unified management and emergency response through remote monitoring and management, thereby effectively improving the early warning capability of transmission lines for meteorological disasters, providing a scientific basis for power system decision makers, and ensuring the safe and stable operation of transmission lines.

[0072] Preferably, when collecting historical meteorological data of the area where the transmission line is located and characteristic data of the transmission line, and using the collected data to construct a risk assessment model for assessing the meteorological disaster risk of the transmission line, the following steps are included:

[0073] S21: Determine data requirements. First, it is necessary to clarify the data types required by the risk assessment model, including historical meteorological data and characteristic data of transmission lines. The historical meteorological data includes wind speed, rainfall, temperature, humidity and air pressure, and the characteristic data of transmission lines includes line material, installation method and maintenance history.

[0074] S22: Data collection channels. The data collection channels are determined according to data requirements. The channels for collecting historical meteorological data include meteorological departments, scientific research institutions and third-party data providers. The channels for collecting characteristic data of transmission lines include power companies and line maintenance departments.

[0075] S23: Data collection: collecting the required data according to the determined data requirements and the determined data collection methods;

[0076] S24: Data preprocessing: cleaning and organizing the collected raw data to remove duplicate, erroneous and invalid data to ensure the accuracy and consistency of the data;

[0077] S25: Model construction: According to the type of data collected and the needs of risk assessment, select the appropriate modeling method, perform feature selection and processing on the collected data, use the processed data to train the model, and evaluate the performance of the model through cross-validation method.

[0078] As described above, the present invention effectively integrates historical meteorological data and transmission line characteristic data by clarifying data requirements, determining diversified data collection methods, implementing accurate data collection and preprocessing, and adopting scientific model construction and evaluation methods, and constructs an accurate risk assessment model, which provides reliable data support and decision-making basis for meteorological disaster risk assessment of transmission lines, and significantly improves the accuracy and practicality of risk assessment.

[0079] Preferably, when cleaning and organizing the collected raw data to remove duplicate, erroneous and invalid data and ensure the accuracy and consistency of the data, the data processing methods used include:

[0080] A11: Data standardization includes converting data into dimensionless form to ensure the accuracy and consistency of subsequent analysis. The principle formula of standardization is:

[0081]

[0082] Among them, X , Represents the value of data point X after normalization;

[0083] A12: Identify and process missing values ​​by deleting records with missing values ​​and using specific values ​​to fill missing values, identify and delete duplicate records by comparing records in the data set, and identify and process outliers by statistical methods. The specific values ​​used in the method of using specific values ​​to fill missing values ​​include mean, median and mode. When identifying outliers, the principle formula of the statistical method used is:

[0084]

[0085] Where X is the data point, μ is the mean, and σ is the standard deviation. When identifying outliers, when the size of Z calculated from data point X is greater than the set threshold, the data point X is marked as an outlier.

[0086] A13: Format conversion: converting data into a format suitable for subsequent analysis and modeling, including data type conversion and data encoding;

[0087] A14: Data normalization processing, where the principle formula of normalization processing is:

[0088]

[0089] Among them, X ‘’ Represents the normalized value of data point X, X min represents the minimum value in the data set, X max Represents the maximum value in the data set.

[0090] As described above, the present invention ensures the consistency and comparability of data by implementing data standardization and normalization processing; effectively improves the integrity and accuracy of data by means of deletion, filling missing values, deleting duplicate records and using statistical methods to identify and process outliers; and through format conversion, makes the data more suitable for subsequent analysis and modeling, which significantly optimizes the data quality as a whole and lays a solid foundation for the subsequent risk assessment model construction.

[0091] Preferably, when selecting a suitable modeling method according to the type of data collected and the requirements of risk assessment, and performing feature selection and processing on the collected data, and then using the processed data to train the model, and evaluating the performance of the model through the cross-validation method, the selectable model types include:

[0092] A21: Linear regression model is used to describe the linear relationship between independent variables and dependent variables;

[0093] A22: Logistic regression model, used for binary classification problems;

[0094] A23: Support vector machine decision function model, which performs classification by finding the optimal hyperplane that can separate samples of different categories.

[0095] As a preference, the principle formula of the linear regression model is:

[0096] Y=β0+β1X1+β2X2+...+βnXn+ε;

[0097] Where Y is the risk level of the power line, X1, X2, ..., Xn are independent variables, β0 is the intercept term, β1, β2, ..., βn are regression coefficients, and ε is the error term.

[0098] As a preferred method, the principle formula of the logistic regression model is:

[0099] P(Y=1|X)=1 / (1+e ^ (β0+β1X1+β2X2+...+βnXn)));

[0100] Where P(Y=1|X) is the probability that the dependent variable Y=1 given the independent variable X, and β0, β1, β2, ..., βn are regression coefficients.

[0101] As a preferred embodiment, the principle formula of the support vector machine decision function model is:

[0102] f(x)=sign(∑αiyiK(xi,x)+b);

[0103] Among them, αi is the Lagrange multiplier, yi is the sample label, K(xi,x) is the kernel function, and b is the bias term.

[0104] As described above, the present invention flexibly selects multiple models such as linear regression, logistic regression and support vector machine decision function, performs feature selection and processing in combination with the characteristics of the data and risk assessment requirements, and uses cross-validation methods to evaluate model performance. This not only improves the applicability and accuracy of the model, but also ensures that the model can accurately predict the risk level of the transmission line, providing strong technical support for the safe operation of the power system.

[0105] As a preferred method, when conducting meteorological data analysis, in-depth analysis of meteorological data is performed to identify meteorological conditions that may cause damage to the transmission line, and then geographical environmental factors are analyzed. In combination with geographical environmental factors, the area through which the transmission line passes is divided into potential risk areas. When conducting risk assessment, the calculation principle formula of the risk size is:

[0106] For risk assessment of individual risk factors:

[0107] Risk = Probability × Impact;

[0108] Among them, Risk is the risk value, Probability is the probability of an event occurring, and Impact is the degree of impact after the event occurs;

[0109] For risk assessment with multiple risk factors:

[0110] Total_Risk=∑(Risk_i×Weight_i)

[0111] Among them, Total_Risk is the total risk value, Risk_i is the risk value of the i-th risk factor, and Weight_i is the weight of the i-th risk factor.

[0112] As described above, the present invention comprehensively considers meteorological conditions and geographical environmental factors, and adopts a scientific risk assessment formula to calculate the risk size. It not only accurately assesses the potential threat of a single risk factor to the transmission line, but also comprehensively considers the comprehensive impact of multiple risk factors by weighted summation, providing an accurate and quantitative basis for the division of potential risk areas of the transmission line, which helps the power system to take preventive measures in advance and reduce disaster risks.

[0113] As a preferred method, high-precision meteorological sensors and data collection centers are installed along the transmission lines. The installed high-precision meteorological sensors and data collection centers are used to collect key meteorological parameters of the environment where the transmission lines are located in real time, and the monitoring data collected by the high-precision meteorological sensors are transmitted to the monitoring center using the Internet of Things technology. When the monitoring center performs intelligent processing and analysis on the data, the functions of the data collection center include:

[0114] A31: Provides multiple transmission protocol formats and receives data in different transmission protocol formats;

[0115] A32: decode and re-encode received data;

[0116] A33: performing preliminary processing on the received sensor data, wherein the preliminary processing method adopted includes data encryption and data compression;

[0117] A34: Perform periodic inspections on the working status of high-precision meteorological sensors.

[0118] As described above, the data acquisition center in the present invention supports multiple transmission protocols, decodes and encodes data, performs preliminary processing, and regularly checks the working status of sensors. It can also access existing monitoring equipment under different communication protocols. On the one hand, it can avoid redundancy and duplication of equipment, and on the other hand, it reduces the cost of building and laying the monitoring system, effectively ensuring the comprehensive reception, efficient transmission, safe storage and accurate analysis of meteorological data, and providing a solid technical guarantee for the stable operation and efficient management of the real-time monitoring system of the transmission line.

[0119] As a preferred method, high-precision meteorological sensors and data collection centers are installed along the transmission lines, and the key meteorological parameters of the environment where the transmission lines are located are collected in real time by using the installed high-precision meteorological sensors and data collection centers. The monitoring data collected by the high-precision meteorological sensors are transmitted to the monitoring center by using the Internet of Things technology. When the monitoring center performs intelligent processing and analysis on the data, the following steps are included:

[0120] S31: Data preprocessing, including missing value processing, outlier detection and processing, data standardization, data normalization and feature extraction;

[0121] S32: Hazard identification: input the pre-processed data into the constructed model, use the model to process and analyze the data, and identify abnormal meteorological conditions and set hazardous data;

[0122] S33: generating a warning signal, based on the result of abnormality detection and in combination with preset warning rules, generating a warning signal, and issuing the generated warning signal to relevant personnel through a set channel.

[0123] As described above, the present invention ensures the accuracy and availability of data through data preprocessing, uses the constructed model to identify hazards, timely captures abnormal meteorological conditions, and generates and issues warning signals according to preset rules, effectively improving the monitoring and early warning capabilities of meteorological disasters on transmission lines, and providing strong technical support and decision-making basis for the safe operation of the power system.

[0124] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge scope of those skilled in the art without departing from the spirit of the present invention.

Claims

1. A transmission line monitoring method based on meteorological disaster early warning; characterized in that: The following steps are included: S11: Establishing a risk assessment model, firstly collecting historical meteorological data of the area where the transmission line is located and characteristic data of the transmission line, and using the collected data to build a risk assessment model for assessing the meteorological disaster risk of the transmission line; S12: Division of potential risk areas: First, conduct meteorological data analysis, analyze the meteorological data in depth, identify meteorological conditions that may cause damage to the transmission line, and then conduct geographical environmental factors analysis. Combined with geographical environmental factors, the area through which the transmission line passes is divided into potential risk areas; S13: Risk level classification: Use the risk assessment model to evaluate potential risk areas, determine the risk level of each area, and provide the risk level classification results to power system decision makers so that they can take corresponding prevention and response measures; S14: Real-time monitoring: high-precision meteorological sensors and data collection centers are installed along the transmission lines. The key meteorological parameters of the environment where the transmission lines are located are collected in real time using the installed high-precision meteorological sensors and data collection centers. The monitoring data collected by the high-precision meteorological sensors are transmitted to the monitoring center using the Internet of Things technology. The monitoring center then processes and analyzes the data intelligently. S15: Remote monitoring and management: Through the monitoring center, the monitoring data can be viewed to achieve unified management across regions and time periods. When abnormal data is detected, emergency response measures can be taken to ensure the safe operation of the transmission line.

2. The transmission line monitoring method based on meteorological disaster early warning according to claim 1 is characterized in that: When collecting historical meteorological data of the area where the transmission line is located and characteristic data of the transmission line, and using the collected data to build a risk assessment model for assessing the meteorological disaster risk of the transmission line, the following steps are included: S21: Determine data requirements. First, it is necessary to clarify the data types required by the risk assessment model, including historical meteorological data and characteristic data of transmission lines. The historical meteorological data includes wind speed, rainfall, temperature, humidity and air pressure, and the characteristic data of transmission lines includes line material, installation method and maintenance history. S22: Data collection channels. The data collection channels are determined according to data requirements. The channels for collecting historical meteorological data include meteorological departments, scientific research institutions and third-party data providers. The channels for collecting characteristic data of transmission lines include power companies and line maintenance departments. S23: Data collection: collecting the required data according to the determined data requirements and the determined data collection methods; S24: Data preprocessing: cleaning and organizing the collected raw data to remove duplicate, erroneous and invalid data to ensure the accuracy and consistency of the data; S25: Model construction: According to the type of data collected and the needs of risk assessment, select the appropriate modeling method, perform feature selection and processing on the collected data, use the processed data to train the model, and evaluate the performance of the model through cross-validation method.

3. The transmission line monitoring method based on meteorological disaster early warning according to claim 2 is characterized in that: When cleaning and organizing the collected raw data to remove duplicate, erroneous and invalid data and ensure the accuracy and consistency of the data, the data processing methods used include: A11: Data standardization includes converting data into dimensionless form to ensure the accuracy and consistency of subsequent analysis. The principle formula of standardization is: Among them, X , Represents the value of data point X after normalization; A12: Identify and process missing values ​​by deleting records with missing values ​​and using specific values ​​to fill missing values, identify and delete duplicate records by comparing records in the data set, and identify and process outliers by statistical methods. The specific values ​​used in the method of using specific values ​​to fill missing values ​​include mean, median and mode. When identifying outliers, the principle formula of the statistical method used is: Where X is the data point, μ is the mean, and σ is the standard deviation. When identifying outliers, when the size of Z calculated from data point X is greater than the set threshold, the data point X is marked as an outlier. A13: Format conversion: converting data into a format suitable for subsequent analysis and modeling, including data type conversion and data encoding; A14: Data normalization processing, where the principle formula of normalization processing is: Among them, X ‘’ Represents the normalized value of data point X, X min represents the minimum value in the data set, X max Represents the maximum value in the data set.

4. The transmission line monitoring method based on meteorological disaster early warning according to claim 3 is characterized in that: When selecting an appropriate modeling method based on the type of data collected and the needs of risk assessment, and performing feature selection and processing on the collected data, the model is trained using the processed data, and the performance of the model is evaluated through cross-validation methods, the available model types include: A21: Linear regression model is used to describe the linear relationship between independent variables and dependent variables; A22: Logistic regression model, used for binary classification problems; A23: Support vector machine decision function model, which performs classification by finding the optimal hyperplane that can separate samples of different categories.

5. The transmission line monitoring method based on meteorological disaster early warning according to claim 4 is characterized in that: The principle formula of the linear regression model is: Y=β0+β1X1+β2X2+...+βnXn+ε; Where Y is the risk level of the power line, X1, X2, ..., Xn are independent variables, β0 is the intercept term, β1, β2, ..., βn are regression coefficients, and ε is the error term.

6. The method for monitoring power transmission lines based on meteorological disaster warning according to claim 5, characterized in that: The principle formula of the logistic regression model is: P(Y=1|X)=1 / (1+e ^ (β0+β1X1+β2X2+...+βnXn))); Where P(Y=1|X) is the probability that the dependent variable Y=1 given the independent variable X, and β0, β1, β2, ..., βn are regression coefficients.

7. The method for monitoring power transmission lines based on meteorological disaster warning according to claim 6, characterized in that: The principle formula of the support vector machine decision function model is: f(x)=sign(∑αiyiK(xi,x)+b); Among them, αi is the Lagrange multiplier, yi is the sample label, K(xi,x) is the kernel function, and b is the bias term.

8. The method for monitoring power transmission lines based on meteorological disaster warning according to claim 7, characterized in that: When conducting meteorological data analysis, we deeply analyze meteorological data, identify meteorological conditions that may cause damage to transmission lines, and then analyze geographical environmental factors. In combination with geographical environmental factors, we divide the areas through which transmission lines pass into potential risk areas. When conducting risk assessment, the calculation principle formula for the size of the risk is: For risk assessment of individual risk factors: Risk = Probability × Impact; Among them, Risk is the risk value, Probability is the probability of an event occurring, and Impact is the degree of impact after the event occurs; For risk assessment with multiple risk factors: Total_Risk=∑(Risk_i×Weight_i) Among them, Total_Risk is the total risk value, Risk_i is the risk value of the i-th risk factor, and Weight_i is the weight of the i-th risk factor.

9. The transmission line monitoring method based on meteorological disaster early warning according to claim 8 is characterized in that: High-precision meteorological sensors and data collection centers are installed along the transmission lines. The key meteorological parameters of the environment where the transmission lines are located are collected in real time using the installed high-precision meteorological sensors and data collection centers. The monitoring data collected by the high-precision meteorological sensors are transmitted to the monitoring center using the Internet of Things technology. When the monitoring center processes and analyzes the data intelligently, the functions of the data collection center include: A31: Provides multiple transmission protocol formats and receives data in different transmission protocol formats; A32: decode and re-encode received data; A33: performing preliminary processing on the received sensor data, wherein the preliminary processing method adopted includes data encryption and data compression; A34: Perform periodic inspections on the working status of high-precision meteorological sensors.

10. The transmission line monitoring method based on meteorological disaster early warning according to claim 9, characterized in that: High-precision meteorological sensors and data collection centers are installed along the transmission lines. The key meteorological parameters of the environment where the transmission lines are located are collected in real time using the installed high-precision meteorological sensors and data collection centers. The monitoring data collected by the high-precision meteorological sensors are transmitted to the monitoring center using the Internet of Things technology. The monitoring center performs intelligent processing and analysis of the data, including the following steps: S31: Data preprocessing, including missing value processing, outlier detection and processing, data standardization, data normalization and feature extraction; S32: Hazard identification: input the pre-processed data into the constructed model, use the model to process and analyze the data, and identify abnormal meteorological conditions and set hazardous data; S33: generating a warning signal, based on the result of abnormality detection and in combination with preset warning rules, generating a warning signal, and issuing the generated warning signal to relevant personnel through a set channel.

Images