Intelligent studying, judging and early warning system and method for external risk of power grid transmission line

Abstract

The invention discloses an intelligent studying, judging and early warning system and method for external risks of a power grid transmission line, and relates to the technical field of power grid risk early warning. Compared with a previous power transmission line external risk monitoring and management mode, the power transmission line external risk monitoring and management method solves the problems of low efficiency, low accuracy and untimely early warning due to the fact that a traditional mode mainly depends on manual inspection and experience judgment; multi-source information is integrated, various risk factors can be comprehensively considered, and the limitation of a single data source is avoided, so that the accuracy of risk research and judgment is greatly improved; a risk deduction prediction algorithm is adopted to train and learn a large amount of historical data, and risk features and rules are automatically extracted to perform risk deduction prediction; performing real-time early warning on the risk, and performing dynamic adjustment and updating according to the risk change condition to ensure that the early warning information is always matched with the actual risk condition; and auxiliary decision-making suggestions are further provided for the operation and maintenance personnel, the operation and maintenance personnel are helped to quickly formulate reasonable countermeasures, and the working efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid risk early warning, and in particular to a power grid transmission line external risk intelligent assessment and early warning system and method. Background Art

[0002] With the rapid development of social economy and the continuous growth of electricity demand, the scale of power grid is constantly expanding, and the safe and stable operation of transmission lines has become crucial. However, power grid transmission lines are often exposed to complex natural and social environments and face the threat of multiple external risk factors.

[0003] On the one hand, natural disasters such as strong winds, heavy rains, lightning, blizzards, earthquakes, etc. often damage transmission lines. Strong winds may cause conductors to flutter, towers to tilt or even collapse; floods and mudslides caused by heavy rains may destroy the foundations of towers; lightning directly hitting transmission lines may cause equipment damage and line tripping; heavy snow and freezing may cause conductors to break due to excessive ice, or cause insulator flashover. These natural disasters are sudden and unpredictable, posing huge challenges to the safe operation of transmission lines.

[0004] On the other hand, human factors also pose a serious threat to transmission lines. Construction activities carried out near transmission lines may accidentally touch the lines and damage the towers; theft by lawless elements may cause the loss of line equipment and affect normal power supply; in addition, deliberate sabotage and misoperation may also cause transmission line failures.

[0005] Traditional external risk monitoring and management of transmission lines mainly rely on manual inspections and experience-based judgments, which have problems such as low efficiency, low accuracy, and untimely early warning.

[0006] In order to solve the above problems, the present invention proposes a system and method for intelligent assessment and early warning of external risks of power grid transmission lines. Summary of the invention

[0007] The purpose of the present invention is to propose an intelligent assessment and early warning system and method for external risks of power transmission lines in a power grid to solve the problems raised in the background technology: Traditional external risk monitoring and management of transmission lines mainly rely on manual inspections and experience-based judgments, which have problems such as low efficiency, low accuracy, and untimely early warning.

[0008] In order to achieve the above object, the present invention adopts the following technical solutions: An intelligent assessment and early warning system and method for external risks of power transmission lines of a power grid, comprising: Data acquisition module: used to collect data related to external risks of transmission lines through multiple sensors and monitoring equipment; Data transmission module: used to adapt to different power transmission line environments and data transmission requirements through a combination of wired communication and wireless communication; Risk assessment module: It is used to use big data analysis technology to conduct in-depth mining and fusion analysis of the collected external risk-related data, and to conduct real-time intelligent assessment of the external risks of the transmission line through the risk assessment indicator system; Risk warning module: Based on the risk assessment results, when the risk level reaches or exceeds the preset threshold, the system will immediately activate the warning mechanism; Decision-making support module: Provide decision-making support suggestions for operation and maintenance personnel based on risk assessment results and historical data; Visual display module: provides users with an intuitive and convenient operation interface and visual display function; The risk assessment module includes a risk analysis unit and an intelligent assessment unit. The risk analysis unit is used to perform in-depth mining and fusion analysis on the collected multi-source data using big data analysis technology and intelligent algorithm models. The intelligent analysis unit is used to establish a risk assessment index system, comprehensively consider the impact degree and mutual relationship of various risk factors, and conduct real-time intelligent analysis of external risks of transmission lines.

[0009] Preferably, the sensors and data acquisition devices of the data acquisition module include quantum sensors, multifunctional sensors, lidars, and composite drones, which are combined with edge computing modules to realize local preprocessing and analysis of data.

[0010] Preferably, the external risks of the transmission lines include natural disaster factors, geological disaster factors, environmental factors, human factors, social factors and other factors, among which human factors include construction damage, theft damage and deliberate damage; the social factors include policies and regulations, social economy, technological development and international situation factors; the other factors include animal activities and the impact of cross-crossing objects.

[0011] Preferably, the risk analysis unit performs situation deduction on the external risk of the power transmission line of the power grid based on a risk deduction prediction algorithm; the risk deduction prediction algorithm is specifically as follows: Based on the collected data on factors related to different external risks, the association model and its expansion mode are set as follows:

[0012]

[0013] in, Represents the input factor data feature value matrix; Taking values ​​for the output external risk factor characteristics; is the weight coefficient of each input feature; and is a random variable; is a unit vector; is the number of cases or data samples used for feature selection; For one of the cases or samples; is the original input feature number; Indicates one of the characteristics; Set the characteristic coefficient vector In The elements are divided into R independent groups. , , Ø, express The number of elements contained; express The sub-feature coefficient vector of as follows:

[0014]

[0015] in, is the adjustment coefficient; is the transpose of a vector; ; is the identity matrix; Output the feature values ​​of external risk factors based on feature selection, and use them to establish a dynamic Bayesian network for external risk situation transformation ,consider time segments, where the edges are directed, Indicates a time segment; and Time segments The node set and directed edge set of the dynamic Bayesian network are as follows:

[0016] in, and Separately and A vector of For time segments; The external risk situation transformation network conforms to the independence of the dynamic Bayesian network, and the following formula is obtained:

[0017] Let the dynamic Bayesian network ,get:

[0018] in, and They are the node set and directed edge set of the dynamic Bayesian network respectively; , ; represents the Cartesian product;

[0019] in, Post-conversion scenario elements Features The value state, conversion probability p o That is Probability of occurrence; Will p o The value is compared with a preset threshold, and a risk prediction is performed based on an artificial intelligence network for situations exceeding the preset threshold. The artificial intelligence network performs risk identification based on a CNN network and a BiLSTM network. The CNN network performs feature fusion based on a one-dimensional convolutional network, a two-dimensional convolutional network, and a three-dimensional convolutional network and then inputs the feature into the BiLSTM network for risk prediction. The one-dimensional convolutional network performs convolution processing based on the residual structure and the convolution kernel, respectively, for the convolution layer with the convolution kernel size of 1*1; The two-dimensional convolutional network performs convolution processing based on convolutional layers whose convolution kernel sizes are 3*3, 5*5, and 7*7 respectively; The three-dimensional convolutional network performs convolution processing based on three convolutional layers with a convolution kernel size of 3*3; The outputs of the one-dimensional convolutional network, the two-dimensional convolutional network, and the three-dimensional convolutional network are cross-fused based on the residual fusion layer, and then the output of the feature fusion layer is input into the BiLSTM network for risk prediction; The residual fusion layer includes a residual module and a feature fusion module; The residual module includes a residual unit and a connection unit, wherein the residual unit is composed of a convolutional layer, a BN layer and a ReLu activation function, and the connection layer connects the input and output of the residual unit respectively; The feature fusion module incorporates the channel attention mechanism and the spatial attention mechanism to perform feature fusion.

[0020] Preferably, the risk analysis unit establishes a risk assessment index system, comprehensively considers the impact degree and mutual relationship of various risk factors, and conducts real-time intelligent analysis and judgment on the external risks of the transmission line.

[0021] Preferably, in the warning mechanism of the risk warning module, a protection mechanism is activated while performing message notification warning.

[0022] Preferably, the auxiliary decision-making module implements personalized early warning information customization and push services according to user responsibilities, focus and receiving habits.

[0023] Preferably, the auxiliary decision-making module also links with the historical case library to provide users with several solutions and decision-making suggestions, and performs simulation analysis and evaluation through the risk deduction and prediction algorithm of the risk analysis unit to predict the implementation effects and real-time risks of different solutions.

[0024] Preferably, the visualization display module also combines VR and AR technologies to present the real-time operating status, risk distribution and warning information of the transmission line to the user in the form of a three-dimensional virtual scene, while providing an interactive operation interface and tools.

[0025] A method for intelligent assessment and early warning of external risks of power transmission lines of a power grid, comprising the following steps: S1: Collecting data related to external risks of transmission lines through several sensors and monitoring equipment; S2: Adapt to different power transmission line environments and data transmission requirements by combining wired and wireless communications; S3: Use big data analysis technology to conduct in-depth mining and fusion analysis of the collected external risk-related data, and conduct real-time intelligent analysis of the external risks of transmission lines through the risk assessment indicator system; S4: Based on the risk assessment results, when the risk level reaches or exceeds the preset threshold, the system will immediately activate the early warning mechanism; S5: Provide auxiliary decision-making suggestions to operation and maintenance personnel based on risk assessment results and historical data; S6: Provide users with an intuitive and convenient operation interface and visual display function.

[0026] Compared with the prior art, the present invention provides a system and method for intelligent assessment and early warning of external risks of power transmission lines of power grids, which has the following beneficial effects: The present invention integrates multi-source information such as meteorological data, geographic information data, and line operation data, and can comprehensively consider various risk factors, avoiding the limitations of a single data source, thereby greatly improving the accuracy of risk assessment; it also adopts a risk deduction and prediction algorithm to train and learn a large amount of historical data, and automatically extracts risk characteristics and laws for risk deduction and prediction; it provides real-time early warning of risks, dynamically adjusts and updates according to changes in risks, and ensures that early warning information always matches the actual risk situation; it further provides auxiliary decision-making suggestions for operation and maintenance personnel, helping them to quickly formulate reasonable response measures and improve work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 This is a system block diagram mentioned in Embodiment 1 of the present invention; Figure 2 This is a flow chart of the method mentioned in Example 1 of the present invention; Figure 3 This is a schematic diagram of the artificial intelligence network architecture mentioned in Example 1 of the present invention. DETAILED DESCRIPTION

[0028] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0029] The present invention integrates multi-source information such as meteorological data, geographic information data, and line operation data, and can comprehensively consider various risk factors, avoiding the limitations of a single data source, thereby greatly improving the accuracy of risk assessment; it also uses a risk deduction and prediction algorithm to train and learn a large amount of historical data, automatically extract risk characteristics and laws for risk deduction and prediction; it provides real-time early warning of risks, dynamically adjusts and updates according to risk changes, and ensures that early warning information always matches the actual risk situation; it further provides auxiliary decision-making suggestions for operation and maintenance personnel, helping them to quickly formulate reasonable response measures and improve work efficiency. Specifically, it includes the following contents.

[0030] Embodiment 1: See also Figure 1-3 The present invention provides an intelligent assessment and early warning system and method for external risks of power transmission lines of a power grid, comprising: The data acquisition module 100 collects real-time meteorological data (such as wind speed, rainfall, temperature, etc.) around the line, geographic information data (topography and landforms around the line, etc.), line operation data (current, voltage, power, etc.), environmental data such as real-time monitoring image data, and external event information that may affect line safety by installing various sensors on the transmission line, such as meteorological sensors, image monitoring equipment, vibration sensors, quantum sensors, multifunctional sensors, laser radars, composite drones, etc. The transmission line has a variety of sensors installed on the transmission line, such as meteorological sensors, image monitoring equipment, vibration sensors, quantum sensors, multifunctional sensors, laser radars, composite drones, etc. The data acquisition module 100 collects real-time meteorological data (such as wind speed, rainfall, temperature, etc.), geographic information data (topography and landforms around the line, etc.), line operation data (current, voltage, power, etc.), environmental data such as real-time monitoring image data, and external event information that may affect line safety. The external risks of the transmission line include natural disaster factors, geological disaster factors, environmental factors, human factors, social factors, and other factors. Among them, natural disaster factors include strong winds, heavy rains, lightning, heavy snow, and earthquakes; geological disaster factors include landslides and ground subsidence; environmental factors include environmental pollution, foreign body invasion, and tree growth; human factors include construction damage, theft damage, and deliberate damage; social factors include policies and regulations, social economy, technological development, and international situation factors; other factors include animal activities and the impact of cross-crossing objects.

[0031] Data transmission module 200: uses advanced communication technology to ensure that the collected data can be safely, stably and quickly transmitted to the back-end processing center. This includes a combination of wired communication (such as optical fiber) and wireless communication (such as 4G / 5G, ZigBee, etc.) to adapt to different power transmission line environments and data transmission requirements.

[0032] The risk assessment module 300 is the core part of the system, including the risk analysis unit 310 and the intelligent assessment unit 320. The risk analysis unit 310 uses big data analysis technology and intelligent algorithm models to conduct in-depth mining and fusion analysis of the collected multi-source data.

[0033] The risk analysis unit 310 performs a situational analysis on the external risks of the power transmission line based on the risk analysis prediction algorithm. In the early stage of the generation of the external risks of the power transmission line, it is impossible to comprehensively evaluate and predict the risks by relying on a single data. Through situational analysis, the relationship between different data can be clarified, and the external risks of the power transmission line can be accurately evaluated and predicted. The risk analysis prediction algorithm is as follows: The risk analysis unit 310 sets the correlation model and its expansion mode as follows based on the collected factor data related to different external risks:

[0034]

[0035] in, Represents the input factor data feature value matrix; Taking values ​​for the output external risk factor characteristics; is the weight coefficient of each input feature; and is a random variable; is a unit vector; is the number of cases or data samples used for feature selection; For one of the cases or samples; is the original input feature number; Indicates one of the characteristics; Set the characteristic coefficient vector In The elements are divided into R independent groups. , , Ø, express The number of elements contained; express The sub-feature coefficient vector of as follows:

[0036]

[0037] in, is the adjustment coefficient; is the transpose of a vector; ; is the identity matrix; After the above feature selection steps, the key variables in the external risk transformation process can be determined. These key variables are essential for accurately assessing and predicting the external risks of power transmission lines. A dynamic Bayesian network for external risk situation transformation is established based on key variables. ,consider time segments, where the edges are directed, Indicates a time segment; and Time segments The node set and directed edge set of the dynamic Bayesian network are as follows:

[0038] in, and Separately and A vector of For time segments; The external risk situation transformation network conforms to the independence of the dynamic Bayesian network, and the following formula is obtained:

[0039] Let the dynamic Bayesian network ,get:

[0040] in, and They are the node set and directed edge set of the dynamic Bayesian network respectively; , ; represents the Cartesian product;

[0041] in, Post-conversion scenario elements Features The value state, conversion probability p o That is Probability of occurrence; Based on the above dynamic Bayesian probability, we can calculate the probability of failure due to risk in the current risk environment. By continuously updating the risk probability, we can more accurately grasp the external risk status faced by the transmission line.

[0042] Will p o The value is compared with the preset threshold, and the risk prediction is performed based on the artificial intelligence network for situations exceeding the preset threshold. The artificial intelligence network performs risk identification based on the CNN network and the BiLSTM network. Figure 3 ,The CNN network performs feature fusion based on one-dimensional convolutional network, two-dimensional convolutional network and three-dimensional convolutional network and then inputs it into the BiLSTM network for risk prediction; The one-dimensional convolutional network performs convolution processing based on the residual structure and the convolution kernel, respectively, with a convolution kernel size of 1*1; the two-dimensional convolutional network performs convolution processing based on the convolution kernel, respectively, with a convolution kernel size of 3*3, 5*5, and 7*7; the three-dimensional convolutional network performs convolution processing based on three convolution kernels with a size of 3*3. The outputs of the one-dimensional convolutional network, the two-dimensional convolutional network, and the three-dimensional convolutional network are cross-fused based on the residual fusion layer, and then the output of the feature fusion layer is input into the BiLSTM network for risk prediction; The residual fusion layer includes a residual module and a feature fusion module; The residual module includes a residual unit and a connection unit. The residual unit is composed of a convolutional layer, a BN layer, and a ReLu activation function. The connection layer connects the input and output of the residual unit respectively. The feature fusion module integrates the channel attention mechanism and the spatial attention mechanism to perform feature fusion.

[0043] Risk prediction based on three-dimensional CNN convolutional network and BiLSTM network can reuse the diversity and complementarity of input risk features, enhance the effective representation of risk features, and improve the accuracy of risk prediction.

[0044] The input features of the single-channel CNN convolutional network, the dual-channel CNN convolutional network, and the triple-channel CNN convolutional network are compared. The specific results can be found in Table 1: Table 1 Input comparison of single-channel CNN convolutional network, dual-channel CNN convolutional network and triple-channel CNN convolutional network

[0045] It can be seen from the table that only inputting single-channel input features or dual-channel input features cannot take into account all information and obtain effective risk feature representation; compared with single-channel input features and dual-channel input features, this embodiment inputs three-channel multi-dimensional and multi-scale features, and can simultaneously obtain one-dimensional network features, two-dimensional network features and three-dimensional network features, integrate the important information of the three-channel multi-dimensional and multi-scale features, increase feature diversity and complementarity, and significantly improve the accuracy and precision of risk identification. On the RAVDESS dataset, the classification accuracy reached 91.18%, which was 10.34% and 3.23% higher than the single-path input feature and the dual-path input feature, respectively; the classification precision reached 91.22%, which was 8.46% and 2.5% higher than the single-path input feature and the dual-path input feature, respectively; on the SEWA dataset, the classification accuracy reached 90.20%, which was 10.07% and 2.62% higher than the single-path input feature and the dual-path input feature, respectively; the classification accuracy reached 92.03%, which was 10.08% and 2.94% higher than the single-path input feature and the dual-path input feature, respectively. The above results all show that the three-way multi-dimensional and multi-scale feature extraction model has significant progress.

[0046] The intelligent analysis unit 320 establishes a risk assessment index system, comprehensively considers the impact degree and mutual relationship of various risk factors, conducts real-time intelligent analysis of the external risks of the transmission line, and accurately assesses the risk level and development trend.

[0047] The intelligent analysis unit 320 establishes a risk assessment indicator system, which can be constructed according to the following standards: I. Natural disaster risk indicators (1) Meteorological disaster indicators Wind speed level: reflects the impact of strong winds on transmission lines. The risk level can be divided according to different wind speed ranges.

[0048] Rainfall: To assess the degree of damage to pole tower foundations and lines caused by heavy rains, floods, etc., the damage can be classified according to the amount of rainfall.

[0049] Lightning activity frequency and intensity: A measure of the likelihood of lightning striking a transmission line and the extent of damage it may cause.

[0050] Snowfall and snow thickness: This indicator is important for areas where ice may cover conductors and stress may be placed on towers.

[0051] (2) Geological disaster indicators Landslide risk factor: Combine factors such as terrain, soil type, and precipitation to assess the threat of landslides to the line.

[0052] Degree of ground subsidence: reflects the impact of uneven ground subsidence on the stability of towers.

[0053] Earthquake intensity: Assess the extent of damage to power transmission lines that may be caused by an earthquake.

[0054] II. Environmental Risk Indicators (1) Pollution degree index Concentration of atmospheric pollutants: such as the corrosive effects of sulfur dioxide, nitrogen oxides, etc. on line equipment.

[0055] Soil pH and corrosivity: Determine the risk of soil erosion to the tower foundation.

[0056] (2) Foreign matter interference index: Frequency of surrounding construction activities: Construction may cause damage to the line, such as digging up cables, colliding with poles and towers, etc.

[0057] Probability of foreign objects such as kites and balloons: Assess the risk of foreign objects getting caught on the line.

[0058] Frequency of bird activities: Bird nesting and roosting may cause line short circuits.

[0059] 3. Human risk indicators (1) Possibility of deliberate sabotage Regional security situation: reflects the potential risk of deliberate human damage to transmission lines.

[0060] Protection level of important facilities: such as whether the line is located in a key protection area.

[0061] (2) Risk of incorrect operation Awareness of nearby residents and operators about power facilities: Low awareness may increase the risk of misoperation.

[0062] Line marking clarity and warning: Unclear marking may lead to accidental damage to the line.

[0063] IV. Line risk indicators (1) Equipment aging degree Wire aging index: a comprehensive assessment based on the wire’s age, appearance, electrical performance, etc.

[0064] Insulator aging degree: including assessment of insulation performance degradation, surface damage, etc.

[0065] The degree of tower corrosion: determine the structural stability of the tower.

[0066] (2) Line load index Long-term load rate: reflects the operating pressure of the line. High load may increase the risk of failure.

[0067] Load fluctuation amplitude: Large load fluctuations may affect line stability.

[0068] V. Emergency Response Capability Indicators (1) Fault repair time: Mean time to repair a fault: measures the efficiency of responding to line faults.

[0069] (2) Resource reserves: Adequacy of spare parts: Ensure that there are sufficient supplies to repair when a failure occurs.

[0070] Emergency rescue team response time: Assess how quickly emergency rescue teams arrive at the scene.

[0071] By quantitatively evaluating the above indicators and assigning different weights, the external risk level of the power grid transmission lines can be comprehensively calculated, providing a scientific basis for risk warning and management.

[0072] Risk warning module 400: According to the risk assessment results, when the risk level reaches or exceeds the preset threshold, the system will immediately start the warning mechanism; the warning methods include SMS notification, sound and light alarm, system pop-up window and other forms, to ensure that relevant personnel can obtain risk information in time and take corresponding response measures. At the same time, a protection mechanism is also used to protect the outside of the power grid in time.

[0073] Decision support module 500: Based on the risk assessment results and historical data, it provides decision support suggestions for operation and maintenance personnel, including troubleshooting solutions, maintenance strategies, resource allocation, etc., to help operation and maintenance personnel quickly formulate scientific and reasonable response measures to reduce risk losses. Based on the risk assessment results and historical case library, it provides users with a variety of response plans and decision suggestions, and simulates analysis and evaluation through the risk deduction and prediction algorithm of the risk analysis unit 310 to predict the implementation effects of different plans and the possible risks. At the same time, the system can automatically adjust and optimize the decision plan according to the real-time risk changes to improve the scientificity and timeliness of the decision.

[0074] Visualization display module 600: Provides users with an intuitive and convenient operation interface and visualization display function. Through map visualization, chart analysis and other methods, the operation status, risk distribution and early warning information of the transmission line are displayed in real time, so that managers can clearly understand the overall situation of the power grid transmission line, which is convenient for remote monitoring and management decision-making. Combined with VR / AR technology, the real-time operation status, risk distribution and early warning information of the transmission line are presented to the user in the form of a three-dimensional virtual scene. Users can observe and analyze risk situations immersively through head-mounted display devices or mobile terminals, and improve their perception and understanding of risks. In the VR / AR environment, users are provided with interactive operation interfaces and tools to support users to simulate and rehearse risk scenarios, formulate response plans in advance, and improve emergency response capabilities.

[0075] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. An intelligent assessment and early warning system for external risks of power transmission lines, characterized in that: include: Data collection module (100): used to collect data related to external risks of power transmission lines through a number of sensors and monitoring equipment; Data transmission module (200): used to adapt to different power transmission line environments and data transmission requirements by combining wired communication and wireless communication; Risk assessment module (300): used to use big data analysis technology to conduct in-depth mining and fusion analysis on the collected external risk-related data, and to conduct real-time intelligent assessment of the external risks of the transmission line through a risk assessment indicator system; Risk warning module (400): based on the risk assessment results, when the risk level reaches or exceeds the preset threshold, the system will immediately activate the warning mechanism; Decision support module (500): provides decision support suggestions to operation and maintenance personnel based on risk assessment results and historical data; Visual display module (600): provides users with an intuitive and convenient operation interface and visual display function; The risk assessment module (300) comprises a risk analysis unit (310) and an intelligent assessment unit (320), wherein the risk analysis unit (310) is used to perform in-depth mining and fusion analysis on the collected multi-source data using big data analysis technology and intelligent algorithm models; The intelligent assessment unit (320) is used to establish a risk assessment index system, comprehensively consider the impact degree and mutual relationship of various risk factors, and conduct real-time intelligent assessment of the external risks of the transmission line.

2. According to claim 1, a power grid transmission line external risk intelligent assessment and early warning system is characterized in that: The sensors and data acquisition devices of the data acquisition module (100) include quantum sensors, multifunctional sensors, laser radars, and composite drones, and are combined with an edge computing module to achieve local preprocessing and analysis of data.

3. According to claim 2, a power grid transmission line external risk intelligent analysis and early warning system is characterized in that: The external risks of transmission lines include natural disasters, geological disasters, environmental factors, human factors, social factors and other factors. Among them, human factors include construction damage, theft damage and deliberate damage; the social factors include policies and regulations, social economy, technological development and international situation factors; the other factors include animal activities and the impact of cross-crossing objects.

4. According to claim 1, a power grid transmission line external risk intelligent assessment and early warning system is characterized in that: The risk analysis unit (310) performs situation deduction on the external risk of the power transmission line of the power grid based on a risk deduction prediction algorithm; the risk deduction prediction algorithm is specifically as follows: Based on the collected data on factors related to different external risks, the association model and its expansion mode are set as follows: in, Represents the input factor data feature value matrix; Taking values ​​for the output external risk factor characteristics; is the weight coefficient of each input feature; and is a random variable; is a unit vector; is the number of cases or data samples used for feature selection; For one of the cases or samples; is the original input feature number; Indicates one of the characteristics; Set the characteristic coefficient vector In The elements are divided into R independent groups. , , Ø, express The number of elements contained; express The sub-feature coefficient vector of as follows: in, is the adjustment coefficient; T is the transpose of a vector; ; is the identity matrix; Output the feature values ​​of external risk factors based on feature selection, and use them to establish a dynamic Bayesian network for external risk situation transformation ,consider time segments, where the edges are directed, t Indicates a time segment; A t and B t Time segments t The node set and directed edge set of the dynamic Bayesian network are as follows: in, a and b Separately A t-1 and A t A vector of For time segments; The external risk situation transformation network conforms to the independence of the dynamic Bayesian network, and the following formula is obtained: Let the dynamic Bayesian network ,get: in, and They are the node set and directed edge set of the dynamic Bayesian network respectively; , ; represents the Cartesian product; in, Post-conversion scenario elements f Features The value state, conversion probability p o That is Probability of occurrence; Will p o The value is compared with a preset threshold, and a risk prediction is performed based on an artificial intelligence network for situations exceeding the preset threshold. The artificial intelligence network performs risk identification based on a CNN network and a BiLSTM network. The CNN network performs feature fusion based on a one-dimensional convolutional network, a two-dimensional convolutional network, and a three-dimensional convolutional network and then inputs the feature into the BiLSTM network for risk prediction. The one-dimensional convolutional network performs convolution processing based on the residual structure and the convolution kernel, respectively, for the convolution layer with the convolution kernel size of 1*1; The two-dimensional convolutional network performs convolution processing based on convolutional layers whose convolution kernel sizes are 3*3, 5*5, and 7*7 respectively; The three-dimensional convolutional network performs convolution processing based on three convolutional layers with a convolution kernel size of 3*3; The outputs of the one-dimensional convolutional network, the two-dimensional convolutional network, and the three-dimensional convolutional network are cross-fused based on the residual fusion layer, and then the output of the feature fusion layer is input into the BiLSTM network for risk prediction; The residual fusion layer includes a residual module and a feature fusion module; The residual module includes a residual unit and a connection unit, wherein the residual unit is composed of a convolutional layer, a BN layer and a ReLu activation function, and the connection layer connects the input and output of the residual unit respectively; The feature fusion module incorporates the channel attention mechanism and the spatial attention mechanism to perform feature fusion.

5. According to claim 4, a power grid transmission line external risk intelligent assessment and early warning system is characterized in that: The risk analysis unit (310) establishes a risk assessment index system, comprehensively considers the impact degree and mutual relationship of various risk factors, and conducts real-time intelligent analysis and judgment on the external risks of the transmission line.

6. According to claim 1, the intelligent assessment and early warning system for external risks of power transmission lines of a power grid is characterized in that: In the warning mechanism of the risk warning module (400), a protection mechanism is activated while performing a message notification warning.

7. According to claim 5, a power grid transmission line external risk intelligent assessment and early warning system is characterized in that: The auxiliary decision-making module (500) implements personalized early warning information customization and push services according to user responsibilities, focus and receiving habits.

8. The intelligent assessment and early warning system for external risks of power transmission lines according to claim 7 is characterized in that: The auxiliary decision module (500) also links with the historical case library to provide the user with several solutions and decision suggestions, and performs simulation analysis and evaluation through the risk deduction and prediction algorithm of the risk analysis unit (310) to predict the implementation effects and real-time risks of different solutions.

9. The intelligent assessment and early warning system for external risks of power transmission lines according to claim 1 is characterized in that: The visualization display module (600) also combines VR and AR technologies to present the real-time operation status, risk distribution and warning information of the transmission line to the user in the form of a three-dimensional virtual scene, while providing an interactive operation interface and tools.

10. A method for an intelligent assessment and early warning system for external risks of power transmission lines according to any one of claims 1 to 9, characterized in that: The steps include: S1: Collecting data related to external risks of transmission lines through multiple sensors and monitoring equipment; S2: Adapt to different power transmission line environments and data transmission requirements by combining wired and wireless communications; S3: Use big data analysis technology to conduct in-depth mining and fusion analysis of the collected external risk-related data, and conduct real-time intelligent analysis of the external risks of transmission lines through the risk assessment indicator system; S4: Based on the risk assessment results, when the risk level reaches or exceeds the preset threshold, the system will immediately activate the early warning mechanism; S5: Provide auxiliary decision-making suggestions to operation and maintenance personnel based on risk assessment results and historical data; S6: Provide users with an intuitive and convenient operation interface and visual display function.

Images