Power transmission line mountain fire disaster risk assessment method and system based on space-time event driving

Abstract

The invention provides a power transmission line mountain fire disaster risk assessment method and system based on space-time event driving, and the method comprises the steps: obtaining mountain fire monitoring data of a to-be-assessed region, and generating a space-time event according to the mountain fire monitoring data; according to an event association rule, the space-time event is associated with a power transmission line tower through a directional edge, and then a power transmission line mountain fire disaster hidden danger map is constructed; performing similarity matching on the time-space events generated in real time and the time-space events in the power transmission line mountain fire disaster hidden danger map, and searching the corresponding time-space events in the power transmission line mountain fire disaster hidden danger map by adopting a map traversal algorithm; and for the searched towers influenced by the space-time events, quantitatively calculating the risk score of each tower based on the data values of the real-time space-time events, and dividing the risk grades according to the risk scores. According to the method, the association precision of power transmission line risk assessment and the precision and efficiency of power transmission line forest fire prevention and control can be improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of power system transmission line safety protection, and specifically relates to a transmission line wildfire disaster risk assessment method and system based on spatiotemporal event driving. Background Art

[0002] As a core component of the power system, transmission lines' operational status directly determines the safe and reliable operation of the entire system. They shoulder the crucial task of efficiently transmitting electricity generated by power plants to substations and load centers. They are also crucial for achieving the optimal allocation of power resources across regions and the rational layout of energy structures.

[0003] However, wildfires pose numerous threats to the safety of power transmission lines. High-temperature flames can directly damage conductors, insulators, or towers, causing structural collapse. High temperatures reduce the insulation strength of air, and carbon particles and smoke from flames can easily cause line flashovers, short circuits, or tripping. Smoke and ash from wildfires adhere to insulator surfaces, potentially causing flashover failures. Heat-induced conductor sagging or breakage can trigger arcing. Furthermore, the fire scene can hinder repair efforts, prolong power outages, and even further expand the fire's reach through transmission equipment failures, creating a vicious cycle. These threats severely impact the stable operation of the power grid, potentially leading to widespread blackouts and significant socioeconomic losses.

[0004] Currently, the industry primarily relies on satellite fire monitoring to predict transmission line wildfire risk. This method uses infrared sensors to identify high-temperature areas, but suffers from low resolution (1-5 kilometers), making it difficult to accurately correlate transmission lines. Furthermore, triggering alarms based on fixed temperature thresholds (e.g., >60°C) ignores the dynamic spread of fires. Furthermore, the system relies on manual judgment of the fire's impact on transmission lines, resulting in inefficient response. Summary of the Invention

[0005] In view of this, the present invention aims to provide a transmission line wildfire disaster risk assessment method and system based on spatiotemporal event-driven, aiming to reduce human intervention, achieve accurate prediction of transmission line wildfire disaster risks, reduce the accident risk of transmission lines affected by wildfire disasters, and ensure the safe and stable operation of the power grid.

[0006] In order to achieve the above object, the technical solution provided by the present invention is as follows:

[0007] In a first aspect, the present invention provides a method for assessing transmission line wildfire disaster risk based on spatiotemporal event-driven methods, comprising the following steps:

[0008] Obtain wildfire monitoring data for the area to be assessed, and generate spatiotemporal events based on the wildfire monitoring data; the spatiotemporal events include at least the data value of the generated event and the geographic coordinates and time corresponding to the data value;

[0009] According to the event association rules, spatiotemporal events are associated with transmission line towers through directed edges to construct a transmission line wildfire disaster hazard map. The event association rules stipulate the rules for describing the influence relationship between spatiotemporal events and corresponding towers through directed edges under preset time and space conditions.

[0010] The real-time generated spatiotemporal events are matched with the spatiotemporal events in the transmission line wildfire hazard map for similarity, and the corresponding spatiotemporal events are found in the transmission line wildfire hazard map using a graph traversal algorithm.

[0011] For the pole towers affected by the found spatiotemporal events, the risk score of each pole tower is quantitatively calculated based on the data value of the real-time spatiotemporal events, and the risk level is divided according to the risk score, thereby realizing the transmission line wildfire disaster risk assessment of the assessment area.

[0012] Furthermore, spatiotemporal events are generated based on wildfire monitoring data, including:

[0013] Divide the transmission corridor into several grids sequentially and assign a unique identifier to each grid;

[0014] Based on the vegetation status in each grid, mark the vegetation flammability level for each grid;

[0015] Extract data exceeding a preset threshold from wildfire monitoring data, determine the event type based on the size and collection location of the data, and match all extracted data to the grid;

[0016] Generates spatiotemporal events based on the grid's unique identifier, vegetation flammability rating, matching data values, event type, geographic coordinates, and time.

[0017] Furthermore, event association rules include time association rules and space association rules. According to the event association rules, the spatiotemporal events are associated with the transmission line towers through directional edges to construct a transmission line wildfire disaster hazard map, including

[0018] According to the time association rule, the towers associated with the spatiotemporal event are determined. The time association rule stipulates that within a spatial grid, the grids that meet the preset time requirements of the event duration and the data values ​​of wind speed and temperature in the event are in the fire spread period. At this time, the corresponding spatiotemporal event and the towers in the grid have a time association.

[0019] According to the spatial association rules, the towers associated with spatiotemporal events are determined. The spatial association rules stipulate that within a preset range, grids where the vegetation flammability level meets the set requirements are grids in the direct threat area. Spatiotemporal events in the direct threat area are spatially associated with the towers.

[0020] Determine the nodes in the graph according to the predefined graph node types; the graph node types include at least entity nodes and relationship nodes; entity nodes include at least event nodes and transmission tower nodes, and relationship nodes are used to describe the relationship between entity nodes;

[0021] Determine the directed edges between entity nodes and relationship nodes based on predefined graph edge types;

[0022] Starting from the event node, through directed edges, the corresponding relationship nodes and transmission tower nodes are connected in sequence according to the association relationship to form a transmission line wildfire disaster hazard map containing the spatiotemporal event propagation path.

[0023] Furthermore, the entity nodes include:

[0024] Fire event node, which records the temperature, area, occurrence time and geographical location of the fire point;

[0025] Transmission tower node, including tower ID and longitude and latitude coordinates;

[0026] Wind speed node, which records real-time wind speed and wind direction data;

[0027] Vegetation dryness node, which records the normalized vegetation index;

[0028] Terrain slope node, which records the surface inclination angle data;

[0029] Relationship nodes include:

[0030] Acceleration nodes, influence nodes, and association nodes;

[0031] Graph edge types include:

[0032] The acceleration edge is used to represent the promoting relationship of wind speed on fire spread;

[0033] The influence edge is used to describe the effect of vegetation dryness on the fire spread rate;

[0034] Correlation edges are used to reflect the statistical correlation between terrain slope and fire direction.

[0035] Furthermore, the real-time generated spatiotemporal events are matched with the spatiotemporal events in the transmission line wildfire disaster hazard map for similarity, including:

[0036] For the spatiotemporal events generated in real time and the spatiotemporal events in the transmission line wildfire hazard map, the similarity of the same type of parameters and the similarity of different dimensions between the events are calculated using the similarity calculation formula. The similarity calculation formula is as follows:

[0037]

[0038]

[0039] Where, For parameters The similarity of and They are the parameters of the spatiotemporal events generated in real time and the spatiotemporal events in the transmission line wildfire disaster hazard map. The value of and The parameters are The maximum and minimum values ​​of ; For parameters The similarity of the dimension, For parameters The number of parameters in the dimension, is the quantity index, is the weight of the kth parameter, is the similarity of the kth parameter;

[0040] The similarities of different dimensions are fused and calculated according to the weight method to obtain the comprehensive similarity;

[0041] Two events whose comprehensive similarity is greater than a set threshold are regarded as matching events.

[0042] Furthermore, for the towers affected by the found spatiotemporal events, the risk score of each tower is quantitatively calculated based on the data value of the real-time spatiotemporal events, including:

[0043] For the towers affected by the found spatiotemporal events, the data of each node is extracted from the spatiotemporal event propagation path and normalized;

[0044] The data of each node are fused and calculated according to the weight method to obtain the risk score of the corresponding tower.

[0045] Furthermore, wildfire monitoring data includes:

[0046] Satellite remote sensing monitoring data, including heat source temperature and fire area;

[0047] Ground sensor monitoring data, including surface temperature;

[0048] Weather station data, including wind speed, wind direction, and air humidity;

[0049] Vegetation status monitoring data, including the Normalized Difference Vegetation Index.

[0050] In a second aspect, the present invention provides a transmission line wildfire disaster risk assessment system based on spatiotemporal event driving, comprising:

[0051] A spatiotemporal event generation module is used to obtain wildfire monitoring data of the area to be evaluated and generate spatiotemporal events based on the wildfire monitoring data; the spatiotemporal event includes at least the data value of the generated event and the geographical coordinates and time corresponding to the data value;

[0052] The graph construction module is used to construct a transmission line wildfire hazard map by associating spatiotemporal events with transmission line towers through directed edges based on event association rules. Event association rules specify the rules for describing the relationship between spatiotemporal events and corresponding towers through directed edges under preset time and space conditions.

[0053] The event matching module is used to perform similarity matching between the spatiotemporal events generated in real time and the spatiotemporal events in the transmission line wildfire hazard hazard map, and use the graph traversal algorithm to find the corresponding spatiotemporal events in the transmission line wildfire hazard hazard map;

[0054] The risk assessment module is used to quantitatively calculate the risk score of each tower affected by the found spatiotemporal events based on the data value of the real-time spatiotemporal events, and divide the risk level according to the risk score, thereby realizing the transmission line wildfire disaster risk assessment in the assessment area.

[0055] In a third aspect, the present invention provides a computer device, comprising a processor and a memory:

[0056] The memory is used to store computer programs and send instructions of the computer programs to the processor;

[0057] The processor executes the transmission line wildfire disaster risk assessment method based on spatiotemporal event driving as described in the first aspect according to the instructions of the computer program.

[0058] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, a method for assessing the risk of wildfire disasters on transmission lines driven by spatiotemporal events as in the first aspect is implemented.

[0059] In summary, the present invention provides a method for assessing the risk of wildfire disasters on transmission lines driven by spatiotemporal events, including obtaining wildfire monitoring data of an area to be assessed, and generating spatiotemporal events based on the wildfire monitoring data; the spatiotemporal events at least include the data value of the generated event and the geographical coordinates and time corresponding to the data value; according to the event association rules, the spatiotemporal events are associated with the transmission line towers through directional edges to construct a transmission line wildfire disaster hazard map; the event association rules stipulate the rules for describing the influence relationship between spatiotemporal events and corresponding towers through directional edges under preset time and space conditions; the real-time generated spatiotemporal events are matched with the spatiotemporal events in the transmission line wildfire disaster hazard map for similarity, and a graph traversal algorithm is used to search for corresponding spatiotemporal events in the transmission line wildfire disaster hazard map; for the towers affected by the found spatiotemporal events, the risk score of each tower is quantitatively calculated based on the data value of the real-time spatiotemporal events, and the risk level is divided according to the risk score, thereby realizing the assessment of the risk of wildfire disasters on the transmission line in the area to be assessed. The present invention quantitatively assesses wildfire disaster risks by combining multi-source data with dynamic graph correlation to multiple factors, solving the problems of low transmission line correlation accuracy and neglect of dynamic characteristics in existing methods. It also replaces manual judgment with an automated similarity matching and risk scoring mechanism to achieve second-level early warning response, thereby improving the accuracy and efficiency of transmission line wildfire prevention and control.

[0060] The present invention also provides a transmission line wildfire disaster risk assessment system, computer equipment and computer-readable storage medium driven by spatiotemporal events, which have similar effects to the above-mentioned method when implemented and will not be described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. 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 paying any creative work.

[0062] Figure 1 A flow chart of a method for assessing transmission line wildfire disaster risk based on spatiotemporal event-driven methods provided by an embodiment of the present invention;

[0063] Figure 2 A diagram illustrating the implementation process of a method for assessing transmission line wildfire disaster risk based on spatiotemporal event-driven methods provided by an embodiment of the present invention;

[0064] Figure 3 A flowchart of wildfire event monitoring provided by an embodiment of the present invention;

[0065] Figure 4A flowchart for constructing a map of hidden dangers of wildfire disasters on power transmission lines provided by an embodiment of the present invention;

[0066] Figure 5 A flowchart for quickly searching for wildfire disaster risk factors for power transmission lines provided by an embodiment of the present invention;

[0067] Figure 6 A flow chart of the transmission line wildfire disaster risk assessment provided by an embodiment of the present invention;

[0068] Figure 7 A block diagram of a transmission line wildfire disaster risk assessment system driven by spatiotemporal events provided by an embodiment of the present invention;

[0069] Figure 8 A block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0070] In order to make the purposes, features, and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0071] See also Figure 1 The embodiment of the present invention provides a method for assessing the risk of wildfire disasters on power transmission lines based on spatiotemporal event driving, comprising the following steps:

[0072] S11: Obtain wildfire monitoring data of the area to be evaluated, and generate spatiotemporal events based on the wildfire monitoring data; the spatiotemporal events at least include the data value of the generated event and the geographic coordinates and time corresponding to the data value.

[0073] It should be noted that wildfire monitoring data refers to information such as the temperature, location, and spread speed of wildfires in the area to be assessed, collected through satellite remote sensing, ground sensors and other equipment; spatiotemporal events are data structures formed after integrating and processing wildfire monitoring data, which include three key elements: wildfire data values, geographic coordinates, and time, and are used to characterize the spatiotemporal characteristics and status information of wildfires.

[0074] This step uses a variety of monitoring methods to obtain wildfire-related data in the area to be evaluated. These scattered, multi-source heterogeneous data are then processed according to unified rules and formats to extract specific data indicators of wildfire occurrence, corresponding geographic coordinates, and occurrence time, ultimately generating a spatiotemporal event that can fully describe the wildfire event.

[0075] S12: According to the event association rules, spatiotemporal events are associated with transmission line towers through directed edges to construct a transmission line wildfire disaster hazard map; the event association rules stipulate the rules for describing the influence relationship between spatiotemporal events and corresponding towers through directed edges under preset time and space conditions.

[0076] It should be noted that event association rules are a series of pre-set conditions used to determine whether there is an influence relationship between spatiotemporal events and transmission line towers; directed edges in the graph represent the direction of influence, such as from wildfire spatiotemporal events to affected towers; the transmission line wildfire disaster hazard map is a graph structure constructed with towers as nodes and the influence relationship between spatiotemporal events that meet the association rules and towers as directed edges, which is used to intuitively display the potential risk connection between wildfires and transmission lines.

[0077] This step uses pre-defined event association rules to determine the spatial and temporal matching between generated spatiotemporal events and transmission line towers. If a spatiotemporal event falls within a preset timeframe and meets the rules, such as its distance from the tower, a directed edge is established between the event and the tower. This continues by integrating all qualifying relationships, ultimately creating a map of transmission line wildfire hazards and achieving a structured representation of wildfire risk information.

[0078] S13: Perform similarity matching between the spatiotemporal events generated in real time and the spatiotemporal events in the transmission line wildfire hazard hazard map, and use a graph traversal algorithm to search for corresponding spatiotemporal events in the transmission line wildfire hazard hazard map.

[0079] It should be noted that similarity matching is the calculation of the similarity between the real-time generated spatiotemporal events and the existing spatiotemporal events in the graph in different dimensions through a specific algorithm; the graph traversal algorithm is an algorithm used to find specific spatiotemporal events in the constructed transmission line wildfire hazard map according to certain paths and strategies, such as breadth-first search or depth-first search algorithm.

[0080] This step extracts features from multiple dimensions and quantitatively compares them with historical spatiotemporal events in the transmission line wildfire hazard map. Similarity calculation methods are then used to determine the degree of similarity between the two. A graph traversal algorithm is then applied to the map to search for events with high similarity to the real-time spatiotemporal events. This determines the location and association of the real-time wildfire events within the map, facilitating subsequent risk assessment.

[0081] S14: For the pole towers affected by the found spatiotemporal events, the risk score of each pole tower is quantitatively calculated based on the data value of the real-time spatiotemporal events, and the risk level is divided according to the risk score, thereby realizing the transmission line wildfire disaster risk assessment of the assessment area.

[0082] It should be noted that the risk score is a quantitative value obtained through a specific calculation model that comprehensively considers the data values ​​of real-time spatiotemporal events and the characteristics of the tower itself, and is used to measure the risk of the tower being affected by wildfires; the risk level classification is to divide the continuous risk score into different risk levels according to certain threshold standards, such as low risk, medium risk, and high risk, so as to facilitate intuitive management and response to risks.

[0083] This step calculates a risk score for each tower associated with a real-time spatiotemporal event found in the atlas. Based on the data values ​​of the real-time spatiotemporal event, such as temperature and wind speed, and the tower's inherent properties, such as its material and protection capabilities, these values ​​are then incorporated into a pre-established risk assessment model. The calculated risk score is then assigned to the corresponding risk level based on the established risk level threshold, completing a comprehensive assessment of the wildfire risk of transmission lines in the area being assessed.

[0084] This embodiment provides a method for assessing transmission line wildfire risk based on spatiotemporal events. This method first utilizes multi-source monitoring to acquire wildfire data and converts it into spatiotemporal events. Next, event association rules are used to construct a transmission line wildfire hazard map, enabling structured storage and representation of wildfire risk. Similarity matching and search are then performed between real-time spatiotemporal events and the map to rapidly locate relevant risk nodes. Finally, tower risk scores are calculated and categorized based on the real-time event data. This entire process, driven by spatiotemporal events and combining graph structure and data computation, enables dynamic and quantitative assessment of transmission line wildfire risk. This embodiment introduces a spatiotemporal event-driven mechanism, breaking away from the traditional static assessment model and enabling dynamic tracking of wildfire risk. Knowledge graph technology is used to construct a hazard map, visually presenting the complex relationship between wildfires and transmission lines. Multi-source data fusion generates spatiotemporal events, enhancing the comprehensiveness of assessment data. Simultaneously, similarity matching and graph traversal algorithms are employed to rapidly locate and quantitatively assess risks, improving the real-time and accuracy of transmission line wildfire risk assessment.

[0085] See also Figure 2 , Figure 2This article illustrates the implementation of a spatiotemporal event-driven transmission line wildfire risk assessment method based on the methods proposed in the preceding embodiments. This method includes wildfire event monitoring, construction of a transmission line wildfire hazard map, rapid search for transmission line wildfire risk factors, and transmission line wildfire risk assessment. The following further describes this method in conjunction with other embodiments of the present invention.

[0086] See also Figure 3 , Figure 3 The following diagram illustrates the wildfire event monitoring process. Wildfire event monitoring begins with multi-source data collection. Satellite remote sensing monitoring obtains information such as heat source temperature and fire area. Meteorological stations collect parameters such as wind speed, wind direction, and air humidity. Ground sensors are deployed at key nodes along the transmission corridor to monitor surface temperature. Vegetation status monitoring uses satellite remote sensing to obtain the Normalized Difference Vegetation Index (NDVI). This is followed by spatiotemporal event generation, with precise timestamps recorded. The transmission corridor is spatially gridded into a 1 km x 1 km square grid, and vegetation flammability levels are annotated. Finally, the collected data is standardized into a unified event format that includes a unique identifier, event type, geographic location, and event parameters.

[0087] based on Figure 3 In the wildfire event monitoring process shown, in one embodiment, the wildfire monitoring data includes:

[0088] Satellite remote sensing monitoring data, accessed through high-resolution satellites (such as the Himawari-8), provides heat source temperature and fire area. Heat source temperature is the real-time temperature at the center of the fire, measured in degrees Celsius. Fire area is the fire's coverage area, measured in square kilometers (km²).

[0089] Ground sensors monitor data, and infrared thermal imagers are deployed at key nodes along the transmission corridor to monitor surface temperature.

[0090] Weather station data: The weather station collects wind speed (unit: meters per second), wind direction (such as "northwest"), and air humidity data (unit: percentage) every minute.

[0091] Vegetation status monitoring data uses satellite remote sensing technology to obtain the Normalized Difference Vegetation Index (NDVI). NDVI values ​​range from 0 to 1, with lower values ​​indicating drier vegetation (for example, a value of 0.3 indicates extremely dry vegetation).

[0092] Please refer again Figure 3 In one embodiment, generating spatiotemporal events based on wildfire monitoring data includes:

[0093] S21: Divide the transmission corridor into several grids in sequence and assign a unique identifier to each grid.

[0094] It should be noted that the grid is the basic unit for spatial division of the transmission corridor.

[0095] The transmission corridor is divided into regular grids (such as 1 km × 1 km square grids) in a certain order, and each grid is assigned a unique number (such as "GX-1023").

[0096] S22: Based on the vegetation status in each grid, mark the vegetation flammability level for each grid.

[0097] It should be noted that the "vegetation flammability level" is a classification of vegetation flammability based on factors such as vegetation type and dryness.

[0098] This step assigns a flammability rating of 1 to 5 (5 being the most flammable) to the vegetation within each grid cell, based on its type (e.g., dry pine forest, high-density shrubs) and dryness (measured using indicators such as the Normalized Difference Vegetation Index (NDVI)). This vegetation flammability rating provides a visual representation of the potential for vegetation within each grid cell to cause or contribute to wildfire spread and is a crucial factor in assessing wildfire risk.

[0099] S23: Extracting data exceeding a preset threshold from the wildfire monitoring data, and determining the event type based on the size and collection location of the data, and matching all the extracted data with the grid.

[0100] It should be noted that the preset threshold is a pre-set standard value for filtering data; the event type is the classification of wildfire events based on the characteristics of wildfire data.

[0101] This step filters wildfire monitoring data from multiple sources (satellite remote sensing, ground sensors, meteorological stations, etc.) to identify data exceeding a pre-defined threshold (e.g., heat source temperature exceeding 300°C). Based on the specific values ​​(e.g., temperature, wind speed) and the collection location, the nature of the wildfire event is determined, identifying the event type (e.g., "High Intensity Fire"). The extracted data is then matched to the previously defined grid to identify the specific grid area to which the data corresponds, achieving precise spatial localization.

[0102] S24: Generate spatiotemporal events based on the grid's unique identifier, vegetation flammability level, matching data value, event type, geographic coordinates, and time.

[0103] It should be noted that spatiotemporal events are structured data units that integrate space, time, and wildfire-related data information.

[0104] This step combines the unique grid identifier, vegetation flammability level, matching data values ​​(such as heat source temperature 650.5°C and fire spread speed 1.2 km / h), and event type (such as high-intensity wildfire) obtained in the previous step with the precise geographic coordinates (latitude and longitude) and time (accurate to seconds) corresponding to the collected data to generate spatiotemporal events in a unified standardized format.

[0105] In specific implementations, the standardized event format may include the following:

[0106] (1) Event ID: Starts with "F" and is followed by the time the event occurred (year, month, day, hour, minute, and second). For example: "F20250401143045".

[0107] (2) Event Type:

[0108] 1) Event type classification: For example, "HighIntensityFire" indicates a high-intensity wildfire event.

[0109] 2) Geographic location (Location): Contains the grid ID (GridID), which identifies the 1 km × 1 km grid where the event is located, for example: "GX-1023"; and the longitude and latitude coordinates, which are accurate to six decimal places, for example: longitude 113.521127°, latitude 22.201803°.

[0110] (3) Event parameters:

[0111] 1) Heat source temperature (Temperature): The temperature at the center of the fire point, the example value is 650.5℃.

[0112] 2) Spread Speed: The rate at which wildfire spreads, with an example value of 1.2 km / h.

[0113] 3) Wind Speed: Real-time wind speed, with an example value of 8.5 m / s.

[0114] 4) Vegetation Dryness: NDVI normalized value, with an example value of 0.3 (dry state).

[0115] A record of a wildfire incident is as follows:

[0116] Event ID: F20250401143045;

[0117] Event type: High Intensity Fire;

[0118] Time of occurrence: 2025-04-01 14:30:45;

[0119] Location: Located at grid GX-1023, longitude 113.521127°, latitude 22.201803°;

[0120] Parameters: heat source temperature 650.5℃, fire spread speed 1.2 km / h, wind speed 8.5 m / s, vegetation dryness 0.3.

[0121] See also Figure 4 , Figure 4 This article illustrates the process for constructing a wildfire hazard map for power transmission lines. This process first establishes event association rules, encompassing both temporal association rules (such as the duration of specific wind speeds and temperatures marking periods of high fire spread risk) and spatial association rules (the distance between the fire point and the transmission line and the flammability level of vegetation determine the direct threat area). Next, the hazard map is constructed, defining entity nodes (such as fire events and transmission towers), relationship nodes (such as acceleration and impact), and graph edges (such as the relationship between wind speed and fire spread acceleration). The map is then stored and queried, selecting a graph database (such as Neo4j) to determine the storage structure and set complex query logic. Finally, new data is injected and automatically associated through real-time events, and rule thresholds are optimized through historical pattern learning to achieve dynamic map updates.

[0122] based on Figure 4 The process for constructing a transmission line wildfire hazard map is shown. In one embodiment, event association rules include temporal association rules and spatial association rules. According to the event association rules, spatiotemporal events are associated with transmission line towers via directional edges to construct a transmission line wildfire hazard map, including:

[0123] S31: Determine the pole tower associated with the spatiotemporal event according to the time association rule; the time association rule stipulates that within a spatial grid, the grid that meets the preset time requirement of the event duration and the data value requirements of the wind speed and temperature in the event is in the fire spread period. At this time, the corresponding spatiotemporal event and the pole tower in the grid have a time association.

[0124] It should be noted that within the same spatial grid, a conditional judgment of the time dimension is performed on spatiotemporal events. When the duration of the event reaches the preset time length, and the data values ​​of wind speed and temperature meet the pre-set requirements, the grid is deemed to be in the fire spread period. For example, when the wind speed in the same spatial grid exceeds 6 meters per second for three consecutive hours, and the heat source temperature is continuously higher than 300°C, the system automatically marks this period as a "high-risk period for fire spread." This rule takes into account scenarios where strong winds and high temperatures may cause the fire to spread rapidly, requiring early warning.

[0125] S32: Determine the pole tower associated with the spatiotemporal event based on the spatial association rule. The spatial association rule stipulates that within a preset range, grids whose vegetation flammability levels meet the set requirements are grids in the direct threat area, and spatiotemporal events in the direct threat area are spatially associated with the pole tower.

[0126] It should be noted that, starting from the spatial dimension, the spatial relationship between the grid where the spatiotemporal event is located and the transmission line tower is judged. When the distance between the grid where the fire point is located and the tower is within the preset range, and the flammability level of the vegetation in the grid meets the set requirements (such as ≥ level 4), the grid is identified as a direct threat area. There is a spatial correlation between the spatiotemporal event and the tower in the direct threat area, that is, from the spatial position, the spatiotemporal event poses a direct threat to the tower, thereby determining the tower associated with the spatiotemporal event. For example, if the straight-line distance between the center of the fire point and the transmission line is less than 500 meters, and the flammability level of the vegetation in the grid is ≥ level 4 (such as dry pine forests, high-density shrubs), the area is marked as a "direct threat area." This rule takes into account the scenario where an emergency response needs to be initiated immediately when the fire point is adjacent to transmission facilities and the vegetation is flammable.

[0127] S33: Determine the nodes in the graph according to predefined graph node types; graph node types include at least entity nodes and relationship nodes; entity nodes include at least event nodes and transmission tower nodes, and relationship nodes are used to describe the relationship between entity nodes.

[0128] It is important to note that when constructing a transmission line wildfire hazard map, specific nodes within the map are determined according to predefined map node types. A clear distinction is made between entity nodes (e.g., event nodes that record specific information about wildfire events, transmission tower nodes that record relevant parameters of transmission towers) and relationship nodes (nodes used to describe the relationships between different entity nodes). This lays the foundation for the subsequent construction of the map's structural framework.

[0129] S34: Determine directed edges between entity nodes and relationship nodes according to predefined graph edge types.

[0130] It's important to note that directional edges are established between identified entity nodes and relationship nodes based on predefined graph edge types. Different edge types represent relationships of varying nature. For example, an "acceleration" edge represents the effect of wind speed on fire spread. Edges are directional, clarifying the direction of the relationship and thus establishing connections between nodes.

[0131] S35: Starting from the event node, corresponding relationship nodes and transmission tower nodes are connected in sequence according to the association relationship through directed edges to form a transmission line wildfire disaster hazard map containing the spatiotemporal event propagation path.

[0132] It should be noted that, starting with the event node, directed edges are used to sequentially connect the corresponding relationship nodes and transmission tower nodes based on the previously determined associations. This connection method constructs a transmission line wildfire hazard map that reflects the spatiotemporal event propagation path. This intuitively displays the impact paths and associations of wildfire spatiotemporal events on transmission line towers, providing a visual graph structure foundation for subsequent risk assessment and analysis.

[0133] This example uses temporal and spatial association rules to determine the relationship between spatiotemporal events and towers, then defines graph node and edge types to construct a transmission line wildfire hazard map that includes the spatiotemporal event propagation paths. The core of this approach is to formalize the complex relationships between wildfire spatiotemporal events and transmission towers through a graph structure, integrating multi-dimensional association information into the map. This facilitates subsequent graph-based risk factor search and risk assessment, enabling systematic analysis and management of transmission line wildfire hazard risks.

[0134] In a further embodiment, the graph nodes are defined as follows:

[0135] (1) Entity node:

[0136] Fire Event: records the fire point temperature, area, time and location.

[0137] Power Tower: Contains tower ID, longitude and latitude, voltage level, and maintenance status.

[0138] WindSpeed: Real-time wind speed and direction data.

[0139] Vegetation Dryness: NDVI index or vegetation moisture content measured by sensors.

[0140] Terrain Slope: The slope of the ground (unit: degrees).

[0141] (2) Relationship nodes:

[0142] ACCELERATES: Indicates the effect of wind speed on the spread of fire.

[0143] IMPACTS: Indicates the effect of vegetation dryness on the rate of fire spread.

[0144] Correlation (CORRELATES_WITH): Indicates the statistical correlation between terrain slope and fire direction.

[0145] The graph edge is defined as follows:

[0146] Edge type 1: Wind speed > 8 m / s - [Acceleration] -> Fire spread. That is, when the wind speed exceeds 8 m / s, the fire spread speed increases significantly. For example, for every 1 m / s increase in wind speed, the fire spread rate increases by 0.2 km / h.

[0147] Edge type 2: Vegetation dryness < 0.4 - [Influence] -> Fire spread rate. That is, when vegetation dryness is lower than 0.4 (NDVI index), the fire spread rate is negatively correlated with dryness (the lower the dryness, the faster the spread).

[0148] Edge Type 3: Terrain Slope > 15° - [Association] -> Fire Direction Shift. This means that in areas with a slope greater than 15 degrees, the fire may shift along ridgelines or valleys. Therefore, the risk prediction model needs to be adjusted based on the terrain.

[0149] Furthermore, the transmission line wildfire hazard map is stored in the Neo4j graph database, which offers the advantage of efficiently managing nodes, edges, and their attribute relationships. For example, a fire event node stores information such as temperature (e.g., 650.5°C), spread speed (1.2 km / h), and timestamp, while a wind speed node records wind speed (8.5 m / s) and wind direction (northwest). Complex queries are implemented through label matching and relationship traversal. For example, when searching for wildfire events with temperatures greater than 500°C and spread speeds greater than 1.5 km / h, the fire event nodes are first filtered, and then the wind speed data is linked using the "ACCELERATES" relationship. Finally, the nodes and edges that meet the criteria are returned, enabling rapid identification of multi-dimensional risk factors.

[0150] The graph is dynamically optimized through real-time event injection and historical pattern learning. Real-time data ingestion involves the real-time injection of satellite fire data, ground sensor streams, and meteorological API data. New fire events are automatically linked to nearby towers and real-time wind speed data within 500 meters, and relationship weights (such as the wind speed's acceleration factor on fire) are updated. Historical data-driven optimization involves training a fire spread model based on wildfire incidents from the past five years using machine learning algorithms like random forests, and dynamically adjusting rule thresholds. For example, the wind speed warning threshold was lowered from 8 meters per second to 7.5 meters per second to reduce the risk of missed reports and improve model adaptability.

[0151] For example, when monitoring a wildfire (temperature 650°C, spread rate 1.8 km / h, wind speed 9 m / s, vegetation dryness 0.3, slope 20°), the atlas triggers the "ACCELERATES" relationship (wind speed > 8 m / s) through rule matching. Combined with the terrain slope node, it predicts the fire will shift northwest. The system automatically generates a high-risk alert, dispatches a drone to the fire coordinates to spray flame retardant, and simultaneously disconnects power to the affected lines through the power grid interface. This automated "monitor-analyze-respond" emergency process shortens risk response time.

[0152] See also Figure 5 , Figure 5 The following figure illustrates a process for quickly identifying wildfire risk factors associated with power transmission lines. This process first performs multi-dimensional similarity calculations, calculating fire characteristic similarity (weighted by temperature, spread rate, and fire point area similarity), environmental similarity (wind speed, vegetation dryness, terrain slope), and spatiotemporal similarity (season and geographic location). A comprehensive similarity is then calculated using a formula. A graph traversal algorithm (depth-first search (DFS)) is then used to search for event elements within the graph. Associated nodes are traversed, and associated paths and weights are recorded. Nodes are then filtered and processed. Finally, the results are optimized using association strength calculations and filtering rules, retaining high-weighted association paths.

[0153] based on Figure 5 The rapid search process for transmission line wildfire disaster risk factors shown in the figure, in one embodiment, performs similarity matching between the spatiotemporal events generated in real time and the spatiotemporal events in the transmission line wildfire disaster hazard map, including:

[0154] S41: For the spatiotemporal events generated in real time and the spatiotemporal events in the transmission line wildfire hazard map, the similarity of the same type of parameters and the similarity of different dimensions between the events are calculated using the similarity calculation formula. The similarity calculation formula is as follows:

[0155]

[0156]

[0157] Where, For parameters The similarity of and They are the parameters of the spatiotemporal events generated in real time and the spatiotemporal events in the transmission line wildfire disaster hazard map. The value of and The parameters are The maximum and minimum values ​​of ; For parameters The similarity of the dimension, For parameters The number of parameters in the dimension, is the quantity index, is the weight of the kth parameter, is the similarity of the kth parameter.

[0158] The above similarity calculation process is introduced using the three dimensions of fire characteristic similarity (Fire_Sim), environment similarity (Env_Sim) and spatiotemporal similarity (SpatioTemp_Sim) as examples.

[0159] (1) Fire characteristic similarity (Fire_Sim):

[0160] The similarity of fire characteristics is calculated by weighting the similarity of three parameters: temperature, spread speed, and fire point area. The formula is as follows:

[0161]

[0162] Parameter definition:

[0163]

[0164] Weight distribution:

[0165] .

[0166] (2) Environment similarity (Env_Sim):

[0167] Environmental similarity is composed of the similarity of wind speed, vegetation dryness, and terrain slope:

[0168]

[0169] Parameter definition:

[0170]

[0171] Weight distribution:

[0172] .

[0173] (3) Spatiotemporal similarity (SpatioTemp_Sim)

[0174] Spatiotemporal similarity consists of similarity in season and geographic location:

[0175]

[0176] Parameter definition:

[0177]

[0178] Weight distribution:

[0179] .

[0180] S42: The similarities of different dimensions are fused and calculated according to the weighting method to obtain a comprehensive similarity.

[0181] The comprehensive similarity formula is as follows:

[0182]

[0183] Constraints:

[0184] .

[0185] S43: The two events whose comprehensive similarity is greater than a set threshold are regarded as matching events.

[0186] In a further embodiment, a depth-first search (DFS) algorithm is used to search for associated spatiotemporal events in the transmission line wildfire hazard map, including:

[0187] S51: Initialization and stacking: Taking the target fire event node F as the starting point, create an empty stack and push it in, and mark it as "visited" to avoid repeated processing of the same node.

[0188] S52: Loop Traversal and Node Expansion: After popping node N from the top of the stack, traverse all of its outgoing edges (such as "acceleration," "influence," and "association") to obtain the set of adjacent nodes {Nadj}. For any unvisited adjacent nodes, push them back onto the stack and mark them as visited. Also, record the path between the nodes and the edge weights (for example, the weight of the "wind speed → fire spread" edge is 0.8).

[0189] S53: Optimize termination conditions and results: The search stops when the stack is empty or reaches a preset traversal depth (e.g., 3 layers of association). By calculating path weights (the product of edge weights, e.g., the weight of the path "fire point → wind speed → spread speed" is 0.8 × 0.6 = 0.48), low-intensity paths with a total weight below 0.2 are filtered out, retaining only highly reliable association paths for subsequent analysis.

[0190] The following is an application example to introduce the above process.

[0191] Target event F1 features include a temperature of 700°C, a spread speed of 2 km / h, an area of ​​5 km², a wind speed of 10 m / s, a vegetation dryness of 0.2, and a slope of 20°. It occurs in a mountainous area during summer.

[0192] Similarity calculation and retrieval process:

[0193] Calculation of fire characteristic similarity: Comparing historical event F2 (temperature 680°C, spread speed 1.8 km / h, area 4.5 km²), we first calculated the temperature similarity to be 0.975, the spread speed similarity to be 0.96, and the area similarity to be 0.975. Then, we used the weighted formula: Fire_Sim = 0.4 × 0.975 + 0.4 × 0.96 + 0.2 × 0.975 = 0.969. Assuming that all parameters have been normalized, the similarities of temperature, spread speed, and area are 0.975, 0.96, and 0.975, respectively, resulting in a final fire characteristic similarity of 0.969.

[0194] Comprehensive similarity ranking: Set a similarity threshold (e.g., >0.8) to filter out historical events that are highly similar to F1 and generate a priority list. Combined with the DFS algorithm, the graph is traversed to locate nodes associated with similar events, such as wind speed, vegetation dryness, and terrain slope, and analyze potential risk transmission paths (e.g., "fire point → high wind speed accelerates spread → dry vegetation amplifies fire → tower is threatened").

[0195] See also Figure 6 , Figure 6 The following figure illustrates the process for assessing the risk of wildfire disasters along power transmission lines. This process first assigns weights to risk factors using an expert scoring method combined with historical data and emergency response experience. The weights for risk factors such as temperature, spread rate, wind speed, and vegetation dryness are determined, with the sum total being 1. The raw values ​​of each risk factor are then normalized and mapped to the [0, 1] interval to eliminate dimensional differences. A comprehensive risk value is then calculated using a formula: the sum of the normalized values ​​of each risk factor multiplied by their corresponding weights. Finally, the risk values ​​are classified into low, medium, and high risk levels, and corresponding response strategies are formulated.

[0196] based on Figure 6 The transmission line wildfire disaster risk assessment process shown in the figure, in one embodiment, for towers affected by the found spatiotemporal events, quantitatively calculates the risk score of each tower based on the data value of the real-time spatiotemporal event, including:

[0197] S61: For the towers affected by the found spatiotemporal events, extract the data of each node from the spatiotemporal event propagation path and perform normalization processing.

[0198] It should be noted that the spatiotemporal event propagation path is a directed path in the map starting from the fire point event node, through the relationship nodes (such as wind speed, vegetation dryness) to the transmission tower node, reflecting the transmission chain of wildfire risk (such as "fire point → high wind speed accelerates spread → dry vegetation expands the fire → tower").

[0199] This step extracts key node data affecting the tower from the associated paths traversed by the DFS, including fire event parameters (temperature, spread speed), environmental parameters (wind speed, vegetation dryness, terrain slope), etc. For example, a path contains parameters such as a fire temperature of 650°C, a wind speed of 9m / s, and a vegetation dryness of 0.3.

[0200] The normalization formula is as follows:

[0201] Map the original values ​​of each risk factor to the interval [0,1] to eliminate the dimension difference. The formula is:

[0202]

[0203] Parameter definition:

[0204]

[0205] Examples of normalized ranges for each factor

[0206]

[0207] S62: The data of each node are integrated and calculated according to the weight method to obtain the risk score of the corresponding tower.

[0208] It should be noted that the weighting method assigns weights based on the importance of risk factors to the tower threat, with the sum of the weights equal to 1 (e.g., temperature weight 0.35, wind speed weight 0.20), reflecting the combination of expert experience and historical data. The following is an example of weighting:

[0209] (1) Temperature (W T ):0.35.

[0210] Basis: High temperature directly reflects the intensity of the fire and is the main cause of short circuit and arc discharge in transmission lines.

[0211] (2) Spread speed (W S ):0.25.

[0212] Basis: The fire spread rate determines the emergency response time window; the faster the speed, the higher the risk.

[0213] (3) Wind speed (W W ):0.20.

[0214] Rationale: Wind speed accelerates the spread of fire and may carry sparks that ignite distant vegetation.

[0215] (4) Vegetation dryness (W V ):0.20.

[0216] Rationale: Dry vegetation is highly flammable, significantly increasing the probability of a fire getting out of control.

[0217] Constraints:

[0218] .

[0219] The formula for calculating the comprehensive risk value is as follows:

[0220]

[0221] Variable Description:

[0222]

[0223] The above embodiment is introduced below with reference to a calculation example.

[0224] Assume that the parameters of a wildfire event are as follows:

[0225]

[0226] The comprehensive risk value is:

[0227]

[0228] Then the risk level is divided according to the following criteria:

[0229]

[0230] The risk of wildfire disasters along power transmission lines is categorized into three levels: low, medium, and high, each level determined by the threat posed by the fire to the transmission lines. Low risk means the fire is under control and poses no direct threat to transmission facilities. Medium risk means there is a possibility of the fire spreading to the transmission corridor, necessitating the early deployment of resources and preparedness. High risk indicates that the fire has already or is about to affect the transmission line, requiring immediate power outage to prevent secondary hazards such as short circuits and ensure the safety of the transmission line and surrounding facilities.

[0231] Clear early warning response strategies are developed for different risk levels. When an early warning is triggered, the system automatically dispatches a firefighting drone to the fire's coordinates to spray flame retardant (Action 1). The system precisely plans the drone's target coordinates (e.g., longitude 113.521127°, latitude 22.201803°), action details, and flight altitude (e.g., spray 500 liters of flame retardant at an altitude of 50 meters). Simultaneously, the system disconnects power to the affected transmission line through the power system interface (Action 2). During this operation, the isolated line is recorded (e.g., the transmission line ID "Line-205"), and the time and person who performed the operation are noted (the system automatically marks it as "AI decision") to ensure traceability and compliance.

[0232] During the early warning and response process, a closed-loop, coordinated response process of "risk assessment - automatic execution - status feedback" is adopted. For example, when a wildfire is determined to have reached a high-risk level due to high temperatures (e.g., 650°C) and rapid spread (1.2 km / h), a drone dispatch command is automatically triggered, requiring it to fly to the target area carrying flame retardants and transmit a real-time video stream of the fire scene. Simultaneously, power is cut off to the corresponding section based on the transmission line number, and backup lines are activated to maintain regional power supply. Furthermore, both drone operational parameters and grid isolation strategies support dynamic adjustment. The drone's flight altitude, flame retardant spray concentration, and other parameters can be flexibly adjusted based on the intensity of the fire. Grid isolation also comprehensively considers line voltage levels and load conditions to select the optimal solution, minimizing the impact on users while ensuring safety.

[0233] The present invention provides a method for assessing the risk of wildfire disasters in power transmission lines based on spatiotemporal event-driven methods, which has the following characteristics: First, a dynamic fire spread model that integrates a real-time prediction algorithm based on meteorological, topographic, and vegetation data, combined with a big data hidden danger map, to achieve real-time early warning. Second, a fast risk matching algorithm based on similarity calculation that ensures the efficiency of large-scale map queries through refined calculations. The present invention fully considers historical hidden danger data, uses a spatiotemporal driven model to extract hidden danger features, and then uses machine learning to carry out predictions. This provides a new way to improve prediction accuracy and ensure the safe and stable operation of transmission lines and power grids.

[0234] Based on the same inventive concept, the present application also provides a spatiotemporal event-driven transmission line wildfire disaster risk assessment system for implementing the spatiotemporal event-driven transmission line wildfire disaster risk assessment method mentioned above. The implementation solution provided by this system is similar to the implementation solution described in the above method. Therefore, the specific limitations of the spatiotemporal event-driven transmission line wildfire disaster risk assessment system embodiment provided below can be found in the limitations of the spatiotemporal event-driven transmission line wildfire disaster risk assessment method above, and will not be repeated here.

[0235] See also Figure 7 The embodiment of the present invention further provides a transmission line wildfire disaster risk assessment system based on spatiotemporal event driving, comprising:

[0236] A spatiotemporal event generation module is used to obtain wildfire monitoring data of the area to be evaluated and generate spatiotemporal events based on the wildfire monitoring data; the spatiotemporal event includes at least the data value of the generated event and the geographical coordinates and time corresponding to the data value;

[0237] The graph construction module is used to construct a transmission line wildfire hazard map by associating spatiotemporal events with transmission line towers through directed edges based on event association rules. Event association rules specify the rules for describing the relationship between spatiotemporal events and corresponding towers through directed edges under preset time and space conditions.

[0238] The event matching module is used to perform similarity matching between the spatiotemporal events generated in real time and the spatiotemporal events in the transmission line wildfire hazard hazard map, and use the graph traversal algorithm to find the corresponding spatiotemporal events in the transmission line wildfire hazard hazard map;

[0239] The risk assessment module is used to quantitatively calculate the risk score of each tower affected by the found spatiotemporal events based on the data value of the real-time spatiotemporal events, and divide the risk level according to the risk score, thereby realizing the transmission line wildfire disaster risk assessment in the assessment area.

[0240] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0241] Reference Figure 8 An embodiment of the present invention further provides a computer device, comprising: a memory and a processor and a computer program stored in the memory. When the computer program is executed on the processor, it implements the transmission line wildfire disaster risk assessment method based on spatiotemporal event driving as described in any one of the above methods.

[0242] The computer device may be a desktop computer, notebook computer, PDA, cloud server or other computing device. The computer device may include, but is not limited to, a processor and a memory. It will be understood by those skilled in the art that Figure 8 The computer device is merely an example and does not constitute a limitation on the computer device. The computer device may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the computer device may also include input and output devices, network access devices, etc.

[0243] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0244] In some embodiments, the memory may be an internal storage unit of the computer device, such as a hard disk or memory of the computer device. In other embodiments, the memory may also be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped with the computer device. Furthermore, the memory may include both an internal storage unit of the computer device and an external storage device. The memory is used to store an operating system, application programs, a boot loader, data, and other programs, such as the program code of the computer program. The memory may also be used to temporarily store data that has been output or is about to be output.

[0245] An embodiment of the present invention also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for assessing the risk of wildfire disasters on a transmission line based on spatiotemporal event-driven transmission lines as described in any one of the above methods is implemented.

[0246] In this embodiment, if the integrated unit is implemented as a software functional unit and sold or used as a standalone product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application can implement all or part of the process steps in the above-mentioned method embodiments by using a computer program to instruct the relevant hardware. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a camera / terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signals, telecommunication signals, and software distribution media. Examples include USB flash drives, removable hard drives, magnetic disks, or optical disks. In some jurisdictions, based on legislation and patent practice, computer-readable media cannot be electric carrier signals or telecommunication signals.

[0247] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0248] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0249] In the embodiments disclosed in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are merely schematic. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0250] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for assessing transmission line wildfire disaster risk based on spatiotemporal event-driven, characterized in that: The steps include: Obtaining wildfire monitoring data for the area to be assessed, and generating a spatiotemporal event based on the wildfire monitoring data; the spatiotemporal event includes at least a data value of the generated event and the geographic coordinates and time corresponding to the data value; According to event association rules, the spatiotemporal events are associated with transmission line towers via directed edges to construct a transmission line wildfire disaster hazard map; the event association rules specify rules for describing the influence relationship between the spatiotemporal events and the corresponding towers via directed edges under preset time and space conditions; Performing similarity matching between the spatiotemporal events generated in real time and the spatiotemporal events in the transmission line wildfire hazard hazard map, and using a graph traversal algorithm to search for the corresponding spatiotemporal events in the transmission line wildfire hazard hazard map; For the pole towers affected by the spatiotemporal events found, the risk score of each pole tower is quantitatively calculated based on the data value of the real-time spatiotemporal events, and the risk level is divided according to the risk score, thereby realizing the transmission line wildfire disaster risk assessment of the area to be assessed.

2. The method for assessing transmission line wildfire disaster risk based on spatiotemporal event-driven according to claim 1, characterized in that: Generate spatiotemporal events based on the wildfire monitoring data, including: Divide the transmission corridor into several grids sequentially and assign a unique identifier to each grid; Based on the vegetation status in each grid, mark the vegetation flammability level for each grid; Extracting data exceeding a preset threshold from the wildfire monitoring data, and determining the event type based on the size and collection location of the data, and matching all extracted data with the grid; The spatiotemporal event is generated according to the unique identifier of the grid, the vegetation flammability level, the matching data value, the event type, geographic coordinates and time.

3. The method for assessing transmission line wildfire disaster risk based on spatiotemporal event driving according to claim 1, characterized in that: The event association rules include time association rules and space association rules. According to the event association rules, the spatiotemporal events are associated with the transmission line towers through directional edges to construct a transmission line wildfire disaster hazard map, including Determining the tower associated with the spatiotemporal event according to the temporal association rule; the temporal association rule stipulates that within a spatial grid, a grid that meets a preset duration requirement of the event and data value requirements of wind speed and temperature in the event is in a fire spreading period, and at this time, the corresponding spatiotemporal event and the tower within the grid have a temporal association; Determining the tower associated with the spatiotemporal event according to the spatial association rule; The spatial association rule stipulates that within a preset range, grids whose vegetation flammability levels meet set requirements are grids in direct threat areas, and the spatiotemporal events in the direct threat areas have a spatial association with the towers; Determine the nodes in the graph according to predefined graph node types; the graph node types include at least entity nodes and relationship nodes; the entity nodes include at least event nodes and transmission tower nodes, and the relationship nodes are used to describe the relationship between the entity nodes; Determining a directed edge between the entity node and the relationship node according to a predefined graph edge type; Through the directed edges, starting from the event node, the corresponding relationship nodes and the transmission tower nodes are connected in sequence according to the association relationship to form the transmission line wildfire disaster hazard map containing the spatiotemporal event propagation path.

4. The method for assessing transmission line wildfire disaster risk based on spatiotemporal event-driven according to claim 3, characterized in that: The entity nodes include: Fire event node, which records the temperature, area, occurrence time and geographical location of the fire point; Transmission tower node, including tower ID and longitude and latitude coordinates; Wind speed node, which records real-time wind speed and wind direction data; Vegetation dryness node, which records the normalized vegetation index; Terrain slope node, which records the surface inclination angle data; The relationship nodes include: Acceleration nodes, influence nodes, and association nodes; The graph edge types include: The acceleration edge is used to represent the promoting relationship of wind speed on fire spread; The influence edge is used to describe the effect of vegetation dryness on the fire spread rate; Correlation edges are used to reflect the statistical correlation between terrain slope and fire direction.

5. The method for assessing transmission line wildfire disaster risk based on spatiotemporal event driving according to claim 1, characterized in that: The real-time generated spatiotemporal events are matched with the spatiotemporal events in the transmission line wildfire hazard map for similarity, including: For the spatiotemporal events generated in real time and the spatiotemporal events in the transmission line wildfire hazard map, the similarity of the same type of parameters and the similarity of different dimensions between the events are calculated using a similarity calculation formula. The similarity calculation formula is as follows: Where, For parameters The similarity of and They are respectively the spatiotemporal events generated in real time and the parameters of the spatiotemporal events in the transmission line wildfire disaster hazard map The value of and The parameters are The maximum and minimum values ​​of ; For parameters The similarity of the dimension, For parameters The number of parameters in the dimension, is the quantity index, is the weight of the kth parameter, is the similarity of the kth parameter; The similarities of different dimensions are fused and calculated according to the weight method to obtain the comprehensive similarity; The two events whose comprehensive similarity is greater than a set threshold are regarded as matching events.

6. The method for assessing transmission line wildfire disaster risk based on spatiotemporal event driving according to claim 3, characterized in that: For the towers affected by the spatiotemporal event found, a risk score of each tower is quantitatively calculated based on the data value of the real-time spatiotemporal event, including: For the towers affected by the spatiotemporal event found, extracting data of each node from the spatiotemporal event propagation path and performing normalization processing; The data of each node are fused and calculated according to the weight method to obtain the risk score of the corresponding tower.

7. The method for assessing transmission line wildfire disaster risk based on spatiotemporal event driving according to claim 1, characterized in that: The wildfire monitoring data includes: Satellite remote sensing monitoring data, including heat source temperature and fire area; Ground sensor monitoring data, including surface temperature; Weather station data, including wind speed, wind direction, and air humidity; Vegetation status monitoring data, including the Normalized Difference Vegetation Index.

8. A transmission line wildfire disaster risk assessment system based on spatiotemporal event driving, characterized by: include: A spatiotemporal event generation module, configured to obtain wildfire monitoring data of the area to be assessed and generate spatiotemporal events based on the wildfire monitoring data; The spatiotemporal event includes at least a data value that generates the event and the geographic coordinates and time corresponding to the data value; A graph construction module is configured to construct a transmission line wildfire hazard map by associating the spatiotemporal events with transmission line towers via directed edges according to event association rules; the event association rules specify rules for describing the relationship between the spatiotemporal events and the corresponding towers via directed edges under preset time and space conditions; An event matching module is used to perform similarity matching between the spatiotemporal events generated in real time and the spatiotemporal events in the transmission line wildfire hazard hazard map, and to use a graph traversal algorithm to search for the corresponding spatiotemporal events in the transmission line wildfire hazard hazard map; The risk assessment module is used to quantitatively calculate the risk score of each tower affected by the found spatiotemporal event based on the data value of the real-time spatiotemporal event, and to divide the risk level according to the risk score, thereby realizing the transmission line wildfire disaster risk assessment in the area to be assessed.

9. A computer device, characterized in that: The device includes a processor and a memory: The memory is used to store the computer program and send instructions of the computer program to the processor; The processor executes a transmission line wildfire disaster risk assessment method based on spatiotemporal event driving according to any one of claims 1 to 7 according to the instructions of the computer program.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, implements a method for assessing transmission line wildfire disaster risk based on spatiotemporal event driving according to any one of claims 1 to 7.

Images