A Wildfire Early Warning System and Method for Transmission Lines Based on 3D LiDAR

Abstract

This invention relates to the field of early warning data management technology, specifically disclosing a power transmission line wildfire early warning system and method based on three-dimensional lidar. This system accurately collects and evaluates meteorological parameters of the target area, intelligently initializes data acquisition process parameters to ensure data accuracy and timeliness. After acquiring data collection results from the target area, it can accurately locate various abnormal environmental areas and deeply collect and analyze their dynamic fire risk parameters, thereby flexibly adjusting data acquisition process parameters to achieve precise monitoring of fire risk. Furthermore, it intelligently matches the abnormal risk level of each abnormal environmental area, promptly determining whether a wildfire early warning needs to be issued, effectively improving the accuracy and timeliness of the early warning. Simultaneously, it utilizes three-dimensional lidar technology to accurately locate abnormal power transmission line sections and evaluate their operational anomaly index within the third cycle, providing a scientific basis for power transmission line protection and early warning.

Description

Technical Field

[0001] This invention relates to the field of early warning data management technology, specifically to a power transmission line wildfire early warning system and method based on three-dimensional lidar. Background Technology

[0002] In the field of power grid safety operation and maintenance, transmission line wildfires have become a core risk threatening the stable operation of the power system due to their strong destructiveness, rapid evolution, and complex disaster-causing mechanisms. Therefore, intelligent analysis is needed to achieve accurate fire perception, quantitative threat assessment, and proactive early warning, providing a new generation of technical support for power grid disaster prevention and mitigation.

[0003] For example, the invention patent with publication number CN104268655A discloses a method for early warning of wildfires on power transmission lines. Based on historical satellite monitoring data of fire points, precipitation data, and industrial and agricultural fire habits in the target area, the method calculates the current early warning level of wildfires on power transmission lines and creates an early warning table based on the early warning level.

[0004] For example, the invention patent with publication number CN118822247A discloses a method for early warning of wildfire disasters in transmission lines that considers the physical processes of wildfire disasters. This method constructs a physical process model of wildfire disasters in transmission lines based on this model. Based on this model, it constructs wildfire risk assessment indicators, including: combustible material risk level, wildfire meteorological risk level, ignition source risk level, and wildfire spread risk level. The warning area is divided into multiple grids of a fixed size, and each grid is assessed using the wildfire risk assessment indicators to obtain the wildfire risk assessment indicator value for each grid. The method then comprehensively assesses the wildfire risk level of each tower within a fixed range of all grids in the transmission line, and finally assesses the wildfire risk level of the entire transmission line based on the wildfire risk levels of all towers.

[0005] However, in the process of implementing the embodiments of this application, it was found that the above-mentioned technology has at least the following technical problems: In the process of early warning of wildfires on power transmission lines, the core logic of the existing technology is still anchored to a passive response to the current state. It can only identify the fire signs that have appeared or trigger alarms based on preset rules, but cannot achieve proactive early warning by forward-looking deduction of the environmental risk chain. It lacks dynamic perception of the cumulative effect of environmental risks over time, often misses the best intervention window for suppressing the spread of disasters, and significantly reduces the timeliness of early warning and the initiative of prevention and control. Summary of the Invention

[0006] To address the shortcomings of existing technologies, this invention provides a power transmission line wildfire early warning system and method based on three-dimensional lidar, which can effectively solve the problems mentioned in the background technology.

[0007] To achieve the above objectives, the present invention provides the following technical solution: The first aspect of the present invention provides a power transmission line wildfire early warning system based on three-dimensional lidar, comprising: an environmental analysis module, used to collect and evaluate meteorological parameters of a target area, thereby initializing the data acquisition process parameters of the target area, obtaining the data acquisition results of the target area, and locating each abnormal environmental area; a wildfire early warning module, used to collect and analyze the dynamic fire risk parameters of each abnormal environmental area, thereby adjusting the data acquisition process parameters of each abnormal environmental area, matching the abnormal risk level of each abnormal environmental area, and determining whether to issue a wildfire early warning for each abnormal environmental area; and a line early warning module, used to locate each abnormal power transmission line segment based on three-dimensional lidar, evaluate the operational anomaly index of each abnormal power transmission line segment within the third cycle, and determine whether to issue a protection early warning for each abnormal power transmission line segment.

[0008] As a further solution, the initialization process of the data acquisition parameters of the target area is as follows: the parameter set of each data acquisition device corresponding to each environmental anomaly influence coefficient interval is stored in the early warning database. The environmental anomaly influence coefficient of the target area in the first period is compared with the environmental anomaly influence coefficient intervals stored in the early warning database. If the environmental anomaly influence coefficient of the target area in the first period belongs to a certain environmental anomaly influence coefficient interval stored in the early warning database, the parameter set of each data acquisition device corresponding to that environmental anomaly influence coefficient interval stored in the early warning database is initialized and set to the parameter set of each data acquisition device belonging to the target area, thereby completing the initialization of the data acquisition process parameters of the target area.

[0009] As a further solution, the data acquisition process parameters for each abnormal environmental area are adjusted. The specific adjustment process is as follows: by analyzing the dynamic fire risk parameters of each abnormal environmental area, the abnormal risk factors of each abnormal environmental area in the second cycle are obtained; the parameter sets of each data acquisition device belonging to each abnormal environmental area are obtained; based on the abnormal risk factors of each abnormal environmental area in the second cycle, the parameter adjustment sets of each data acquisition device belonging to each abnormal environmental area are matched from the early warning database, thereby updating the parameter sets of each data acquisition device belonging to each abnormal environmental area, and completing the adjustment of the data acquisition process parameters for each abnormal environmental area.

[0010] As a further solution, the specific process for determining whether to issue wildfire warnings for each abnormal environmental area is as follows: Based on the abnormal risk factors of each abnormal environmental area in the second period, the abnormality level of each abnormal environmental area in the second period is matched. If the abnormality level of an abnormal environmental area in the second period belongs to the abnormal warning level, then it is determined that a wildfire warning should be issued for that abnormal environmental area; if the abnormality level of an abnormal environmental area in the second period does not belong to the abnormal warning level, then it is determined that a wildfire warning should not be issued for that abnormal environmental area. At the same time, each abnormal environmental area whose abnormality level does not belong to the abnormal warning level is marked as an abnormal monitoring environmental area, and the abnormal risk factors of each abnormal monitoring environmental area in the second period are obtained; the target area is then obtained. The environmental anomaly impact coefficient within the prediction period is compared with the environmental anomaly impact coefficient of the target area within the second period. The result is marked as the environmental anomaly impact deviation coefficient of the target area. Anomaly risk factor correction values ​​are matched from the early warning database to correct the anomaly risk factors of each anomaly monitoring environmental area within the second period. This allows for the rematching of the anomaly level of each anomaly monitoring environmental area within the second period. If the anomaly level of an anomaly monitoring environmental area within the second period is at the anomaly warning level, then a wildfire prediction and warning is issued for that anomaly monitoring environmental area. If the anomaly level of an anomaly monitoring environmental area within the second period is not at the anomaly warning level, then a wildfire prediction and warning is not issued for that anomaly monitoring environmental area.

[0011] As a further solution, the specific protection process for determining whether to provide protection warnings for each abnormal transmission line segment is as follows: Based on the operational anomaly index of each abnormal transmission line segment within the third cycle, the protection scheme for each abnormal transmission line segment is matched from the warning database. Simultaneously, the operational anomaly index corresponding to the protection scheme for each abnormal transmission line segment is obtained and marked as the reference operational anomaly index for each abnormal transmission line segment. This reference operational anomaly index is then compared with the operational anomaly index of each abnormal transmission line segment within the third cycle, and the result is marked as the operational anomaly index deviation value for each abnormal transmission line segment. If the operational anomaly index deviation value of a certain abnormal transmission line segment is less than or equal to the reference operational anomaly index deviation value, then the abnormal transmission line segment is protected. The protection scheme for abnormal transmission lines is adjusted by increasing the protection level. If the deviation value of the abnormal operation index of a certain abnormal transmission line is greater than the deviation value of the reference abnormal operation index, the protection scheme for that abnormal transmission line is adjusted by decreasing the protection level. The abnormal operation threshold of each abnormal transmission line is obtained and compared with the abnormal operation index of the corresponding abnormal transmission line in the third cycle. If the abnormal operation index of a certain abnormal transmission line in the third cycle is less than or equal to the corresponding abnormal operation threshold, it is determined that no warning will be issued for that abnormal transmission line. If the abnormal operation index of a certain abnormal transmission line in the third cycle is greater than the corresponding abnormal operation threshold, it is determined that a warning will be issued for that abnormal transmission line.

[0012] The second aspect of this invention provides a method for early warning of wildfires on power transmission lines based on three-dimensional lidar, comprising: Step 1, collecting and evaluating meteorological parameters of the target area to initialize the data acquisition process parameters of the target area, obtaining the data acquisition results of the target area, and locating each abnormal environmental area; Step 2, collecting and analyzing the dynamic fire risk parameters of each abnormal environmental area to adjust the data acquisition process parameters of each abnormal environmental area, matching the abnormal risk level of each abnormal environmental area, and determining whether to issue a wildfire warning for each abnormal environmental area; Step 3, locating each abnormal power transmission line segment based on three-dimensional lidar, evaluating the operational anomaly index of each abnormal power transmission line segment in the third cycle, and determining whether to issue a protection warning for each abnormal power transmission line segment.

[0013] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects:

[0014] (1) This invention provides a transmission line wildfire early warning system and method based on three-dimensional lidar. By accurately collecting and evaluating meteorological parameters of the target area, intelligently initializing data acquisition process parameters, ensuring the accuracy and timeliness of data, after obtaining the data acquisition results of the target area, it can accurately locate each abnormal environmental area and deeply collect and analyze its fire risk dynamic parameters, thereby flexibly adjusting the data acquisition process parameters to achieve fine monitoring of fire risk. In addition, it can intelligently match the abnormal risk level of each abnormal environmental area and promptly determine whether a wildfire early warning needs to be issued, effectively improving the accuracy and timeliness of the early warning. At the same time, it uses three-dimensional lidar technology to accurately locate each abnormal transmission line segment and evaluate its abnormal operation index in the third cycle, providing a scientific basis for the protection and early warning of transmission lines.

[0015] (2) This invention calculates the difference in environmental anomaly impact coefficient between the prediction period and the second period for the target area, obtains the environmental anomaly impact deviation coefficient, and uses the anomaly risk factor correction value in the early warning database to accurately correct the anomaly risk factor in the second period and rematch the anomaly level, thereby significantly improving the accuracy and pertinence of wildfire prediction and early warning, effectively avoiding false alarms and missed alarms, and timely issuing early warnings for abnormal monitoring environmental areas that truly have wildfire risks, providing more scientific and reliable decision support for wildfire prevention and control.

[0016] (3) By quantifying the degree of operational anomalies, this invention enables precise protection and early warning for each abnormal transmission line segment. This not only improves the accuracy and timeliness of the early warning, but also allows for timely measures to avoid line faults and ensure the stable operation of the power system. In addition, quantitative early warning can provide a scientific basis for line maintenance, optimize the allocation of maintenance resources, and improve the overall safety and reliability of the transmission line. Attached Figure Description

[0017] The present invention will be further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present invention. For those skilled in the art, other drawings can be obtained based on the following drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of the system module connections of the present invention.

[0019] Figure 2 This is a schematic diagram of the method steps of the present invention. Detailed Implementation

[0020] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0021] Reference Figure 1 As shown, the first aspect of the present invention provides a power transmission line wildfire early warning system based on three-dimensional lidar, including: an environmental analysis module, a wildfire early warning module, a line early warning module, and an early warning database.

[0022] The early warning database is used to store parameters involved in the power transmission line wildfire early warning system based on three-dimensional lidar.

[0023] The environmental analysis module is connected to the wildfire early warning module, which in turn is connected to the line early warning module. All three modules are connected to the early warning database.

[0024] The environmental analysis module is used to collect and evaluate meteorological parameters of the target area, thereby initializing the data acquisition process parameters of the target area, obtaining the data acquisition results of the target area, and locating each abnormal environmental area.

[0025] The aforementioned location of abnormal environmental areas refers to the use of 3D LiDAR scanning technology to rapidly scan power transmission lines in forest areas, simultaneously collecting infrared and visible image data from the site. A 3D modeling technique (such as geographic information spatial analysis and integration) is then used to construct a model of the power transmission lines in the forest area. This model represents the data collection results for the target area. Environmental areas in the model with temperatures exceeding a preset temperature threshold are automatically marked as abnormal environmental areas. These abnormal environmental areas are then located based on pre-defined regional classification criteria set by data analysts. The aforementioned temperature threshold represents the maximum permissible temperature, extracted from the early warning database.

[0026] Specifically, the collection and evaluation of meteorological parameters in the target area involves the following evaluation process: The meteorological parameters of the target area include the average air pressure, total rainfall, and solar radiation accumulation in the target area during the first period. The first period refers to the time period for analyzing meteorological data, the specific duration of which is determined by the meteorological data analysts. The average air pressure represents the average atmospheric pressure in the target area during the first period. The total rainfall represents the total amount of precipitation in the target area during the first period, usually expressed in millimeters, indicating the depth of precipitation accumulation on the horizontal surface. The solar radiation accumulation represents the total amount of solar radiation energy received by the target area during the first period, reflecting the energy input of solar radiation to the target area. The average air pressure, total rainfall, and solar radiation accumulation can all be obtained from the meteorological stations in the target area.

[0027] By introducing influence coefficients to quantify the impact of the ratio between the average air pressure deviation and the defined average air pressure deviation, the ratio between total rainfall and the defined total rainfall, and the ratio between accumulated solar radiation and the defined accumulated solar radiation on the environmental anomaly impact coefficient, these influence coefficients are coupled to derive the environmental anomaly impact coefficient for the target area in the first period. This environmental anomaly impact coefficient for the target area in the first period characterizes the increased risk of wildfires due to abnormal environmental conditions in the target area during the first period, and its specific expression is as follows:

[0028] ;

[0029] ;

[0030] In the formula, The environmental anomaly impact coefficient of the target area during the first period. The average air pressure deviation value of the target area during the first cycle. The total rainfall in the target area during the first cycle. This represents the amount of solar radiation accumulated in the target area during the first cycle. The predefined average air pressure deviation value in the early warning database. The total rainfall is defined as a preset threshold in the early warning database. The pre-defined limit for accumulated solar radiation in the early warning database. The average air pressure in the target area during the first cycle. The preset reference average air pressure in the early warning database, The influence coefficient corresponding to the preset average air pressure deviation value in the early warning database. The impact coefficient corresponding to the preset total rainfall in the early warning database. This refers to the influence coefficient corresponding to the pre-set solar radiation accumulation in the early warning database.

[0031] The above-defined average pressure deviation value represents the maximum allowable value of the average pressure deviation value; the above-defined total rainfall represents the minimum allowable value of the total rainfall; the above-defined solar radiation accumulation represents the maximum allowable value of solar radiation accumulation; the above-defined reference average pressure represents the reference value of the average pressure; and the above-defined average pressure deviation value represents the degree of deviation between the average pressure and the reference average pressure.

[0032] The influence coefficients corresponding to the aforementioned average air pressure deviation values ​​represent the degree of influence of the unit value of the average air pressure deviation value on the environmental anomaly influence coefficient; the influence coefficients corresponding to the aforementioned total rainfall represent the degree of influence of the unit value of the total rainfall on the environmental anomaly influence coefficient; the influence coefficients corresponding to the aforementioned solar radiation accumulation represent the degree of influence of the unit value of the solar radiation accumulation on the environmental anomaly influence coefficient; the early warning database stores the correspondence between the average air pressure deviation value, total rainfall, and solar radiation accumulation and their corresponding influence coefficients. For example, by inputting the average air pressure deviation value, total rainfall, and solar radiation accumulation into the early warning database, the database can match the influence coefficients corresponding to the average air pressure deviation value, the total rainfall, and the solar radiation accumulation, all of which have values ​​between 0 and 1.

[0033] It should be explained that a large deviation in average air pressure means that the ambient air pressure in the target area is in a significantly abnormal state. This change is often closely related to the adjustment of atmospheric circulation and changes in airflow. Specifically, the prevalence of high-pressure areas is often accompanied by descending air currents and relatively dry air. These meteorological conditions are unfavorable for cloud formation and maintenance, thus inhibiting rainfall and leading to reduced total rainfall and a drier environment. Simultaneously, high-pressure areas are usually accompanied by clear weather, thin clouds, and increased atmospheric transparency, allowing solar radiation to reach the surface more directly and efficiently, thus promoting an increase in solar radiation accumulation. This change not only intensifies the surface heating process but also further reduces surface moisture evaporation, further drying the environment. The interaction of these meteorological parameters reveals an abnormal state of the target area's environment. This anomaly is not only reflected in significant changes in air pressure, rainfall, and solar radiation but may also indicate an increased risk of wildfires. The dry environment, reduced rainfall, and enhanced solar radiation all provide favorable conditions for wildfires. Therefore, continuous monitoring and analysis of these meteorological parameters, especially utilizing the comprehensive indicator of the environmental anomaly impact coefficient, can more accurately assess the degree of environmental anomaly in the target area. This can then guide the adjustment and optimization of data acquisition equipment, ensuring the accuracy and timeliness of monitoring data and providing a scientific basis for wildfire early warning and emergency response.

[0034] Furthermore, the initialization process of the data acquisition parameters for the target area is as follows: The early warning database stores the parameter sets of each data acquisition device corresponding to each environmental anomaly influence coefficient interval. The environmental anomaly influence coefficient of the target area in the first period is compared with the environmental anomaly influence coefficient intervals stored in the early warning database. If the environmental anomaly influence coefficient of the target area in the first period belongs to a certain environmental anomaly influence coefficient interval stored in the early warning database, then the parameter sets of each data acquisition device corresponding to that environmental anomaly influence coefficient interval stored in the early warning database are initialized and set to the parameter sets of each data acquisition device belonging to the target area, thereby completing the initialization of the data acquisition process parameters for the target area. It should be explained that each data acquisition device includes, but is not limited to, 3D LiDAR scanning equipment, infrared thermal imagers, and visible light cameras. The parameter sets of the aforementioned data acquisition devices refer to a set of parameter configurations necessary to ensure that each data acquisition device can accurately and efficiently collect relevant information of the target area. These parameter sets specify in detail the specific technical specifications, measurement range, sampling frequency, resolution, accuracy requirements, and data transmission format that each device must follow when performing the task. Together, they constitute the basic framework of the data acquisition task, ensuring that the data collected from the target area has high accuracy, completeness, and timeliness.

[0035] The wildfire early warning module is used to collect and analyze the dynamic parameters of fire risk in various abnormal environmental areas, thereby adjusting the data collection process parameters of each abnormal environmental area, matching the abnormal risk level of each abnormal environmental area, and determining whether to issue a wildfire early warning for each abnormal environmental area.

[0036] Specifically, the data collection process parameters for each abnormal environmental area are adjusted. The adjustment process is as follows: by analyzing the dynamic fire risk parameters of each abnormal environmental area, the abnormal risk factors of each abnormal environmental area in the second period are obtained. The aforementioned second period refers to the time period set for in-depth data analysis of the identified abnormal environmental areas. The second period not only covers the previous first period, but also extends in terms of time span. The specific duration of the second period is determined by the data analysts.

[0037] The parameter sets of each data acquisition device belonging to each abnormal environment area are obtained. Based on the abnormal risk factors of each abnormal environment area in the second period, the parameter adjustment sets of each data acquisition device belonging to each abnormal environment area are matched from the early warning database, thereby updating the parameter sets of each data acquisition device belonging to each abnormal environment area and completing the adjustment of the data acquisition process parameters of each abnormal environment area. It should be explained that before adjusting the data acquisition process parameters of each abnormal environment area, the parameter sets of each data acquisition device belonging to each abnormal environment area are consistent with the parameter sets of each data acquisition device deployed in the target area. In other words, since each abnormal environment area is essentially part of the target area, the parameter sets of the data acquisition devices used by them are the corresponding device parameter sets adopted by the target area as a whole. The specific matching process of the parameter adjustment sets of each data acquisition device belonging to each abnormal environment area is as follows: the early warning database stores the corresponding intervals of each abnormal risk factor. The parameter adjustment set for each data acquisition device compares the abnormal risk factors of each abnormal environmental area in the second period with the abnormal risk factor intervals stored in the early warning database. If the abnormal risk factors of an abnormal environmental area in the second period belong to a certain abnormal risk factor interval stored in the early warning database, then the parameter adjustment set of each data acquisition device corresponding to that abnormal risk factor interval stored in the early warning database is set as the parameter adjustment set of each data acquisition device belonging to that abnormal environmental area. The parameter adjustment set of each data acquisition device represents the set of adjustments to the parameter set of each data acquisition device, covering all parameter modifications required for each data acquisition device, including but not limited to key parameters such as the adjusted sampling frequency, updated measurement accuracy, revised data transmission protocol, and optimized device working mode. These adjustments aim to enable the data acquisition devices to more accurately adapt to and meet the urgent needs of monitoring specific abnormal environmental areas.

[0038] Specifically, the analysis process for the abnormal risk factors of each abnormal environmental area in the second cycle is as follows: the dynamic fire risk parameters of each abnormal environmental area include the vegetation water loss factor, the thermal radiation field-average thermal radiation intensity relationship factor, and the duration of thermal anomalies in each abnormal environmental area during the second cycle. The vegetation water loss factor represents the degree of vegetation water loss. The temperature difference in each abnormal environmental area during the second cycle is obtained by acquiring the canopy temperature and air temperature in the abnormal environmental area from the forest power transmission line model and calculating the difference between them. This temperature difference can be obtained by querying the early warning database for each abnormal environmental area during the second cycle. The vegetation water loss factor corresponding to the temperature difference value is obtained; the above-mentioned thermal radiation field-average thermal radiation intensity relationship factor represents the weighted summation relationship between the rate of change of thermal radiation field and the rate of change of average thermal radiation intensity in the abnormal environmental area. It not only considers the overall intensity and distribution of thermal radiation field, but also the trend of these parameters over time, thus reflecting the fire risk status of the abnormal environmental area more comprehensively; the above-mentioned thermal anomaly duration refers to the duration during which the thermal radiation intensity in the abnormal environmental area is continuously higher than the average thermal radiation intensity threshold within the second cycle, which can be extracted from the infrared data in the forest area transmission line model. The average thermal radiation intensity threshold represents the maximum allowable value of thermal radiation intensity, which is extracted from the early warning database.

[0039] It's important to explain that a large rate of change in the thermal radiation field indicates a significant change in the thermal radiation field within the anomalous environment area over a short period. This change could be due to the presence of high-temperature objects, the initial stages of a fire, or the influence of other heat sources. An increased thermal radiation field increases the likelihood of a fire because high-temperature objects or flames can rapidly heat the surrounding air and combustibles, thus igniting a fire. An increase in the rate of change of the average thermal radiation intensity indicates an increase in the average thermal radiation intensity across the entire anomalous environment area. This could be due to rising ambient temperature, accumulation of combustibles, or the combined effect of other factors. An increase in the average thermal radiation intensity means that combustibles within the entire area are more easily ignited. Ignition increases the risk of fire. The larger the thermal radiation field-average thermal radiation intensity relationship factor, the stronger the interaction and mutual influence between the thermal radiation field and the average thermal radiation intensity. This enhanced combined effect leads to a significant increase in fire risk because the enhancement of the thermal radiation field and the increase in the average thermal radiation intensity promote each other, forming a vicious cycle that makes fires easier to occur and spread. Therefore, the larger the thermal radiation field-average thermal radiation intensity relationship factor, the higher the fire risk in abnormal environmental areas. This indicator provides an important reference for fire early warning and risk assessment, helping relevant departments to take timely preventive measures to reduce the probability and severity of fires.

[0040] The environmental anomaly impact coefficient of the target area in the second period is obtained. By coupling the vegetation water loss factor, thermal anomaly duration, and thermal radiation field-average thermal radiation intensity relationship factors of each anomalous environmental area in the second period, and introducing the degree of influence of the environmental anomaly impact coefficient of the target area in the second period on the anomaly risk factor, the anomaly risk factor of each anomalous environmental area in the second period is obtained. The environmental anomaly impact coefficient of the target area in the second period is obtained in the same way and with the same meaning as the environmental anomaly impact coefficient of the target area in the first period, with only the time difference.

[0041] The abnormal risk factors for each abnormal environmental region during the second period characterize the degree of abnormal risk for each abnormal environmental region during the second period, and are specifically expressed as follows:

[0042] ;

[0043] ;

[0044] ;

[0045] ;

[0046] ;

[0047] In the formula, For the a-th anomalous environmental region, the abnormal risk factor during the second period is... The environmental anomaly impact coefficient for the target area during the second period. The vegetation water loss factor influence component of the a-th anomalous environmental region during the second period. This represents the influence component of the thermal radiation field-average thermal radiation intensity relationship factor for the a-th anomalous environmental region during the second period. The factor representing the relationship between the thermal radiation field and the average thermal radiation intensity of the a-th anomalous environmental region during the second period. The duration of thermal anomalies in the a-th anomalous environmental region during the second period is the influence component. The pre-defined factor in the early warning database defines the relationship between the thermal radiation field and the average thermal radiation intensity. The impact value corresponding to the preset environmental anomaly impact coefficient in the early warning database. These are the influencing factors corresponding to the pre-set vegetation water loss factors in the early warning database. The influencing factors corresponding to the preset thermal radiation field-average thermal radiation intensity relationship factors in the early warning database. The influencing factors corresponding to the duration of thermal anomalies are preset in the early warning database. The vegetation water loss factor in the a-th anomalous environmental region during the second cycle. The pre-defined vegetation water loss factors in the early warning database Let be the rate of change of the thermal radiation field in the a-th anomalous environmental region during the second period. Let a be the rate of change of the average thermal radiation intensity of the a-th anomalous environmental region during the second period. Let be the duration of the thermal anomaly in the a-th ... The duration of thermal anomalies is predefined in the early warning database. This refers to the influencing factors corresponding to the preset rate of change of thermal radiation field in the early warning database. The influencing factor corresponding to the average rate of change of thermal radiation intensity preset in the early warning database, where 'a' is the number of each abnormal environmental region. b is the total number of abnormal regions.

[0048] The aforementioned rate of change of thermal radiation field refers to the rate at which the intensity of the thermal radiation field in the anomalous environmental region changes with time within the second period. This is achieved by continuously monitoring the anomalous environmental region using thermal imagers or other relevant equipment to obtain time-series data of the thermal radiation field. Data processing software (such as a matrix laboratory) is then used to process the monitored thermal radiation field data, calculating the thermal radiation field intensity at each time point. The rate of change of the thermal radiation field is then calculated using thermal radiation field data from adjacent time points. Similarly, the aforementioned rate of change of average thermal radiation intensity refers to the rate at which the average thermal radiation intensity in the anomalous environmental region changes with time within the second period. This is also achieved by continuously monitoring the anomalous environmental region using thermal imagers to obtain time-series data of the thermal radiation field. At each time point, the average thermal radiation intensity of the entire region is calculated. This typically involves spatial averaging of the thermal radiation field data, and the rate of change of the average thermal radiation intensity is calculated using average thermal radiation intensity data from adjacent time points.

[0049] Among them, thermal radiation field intensity focuses on the thermal radiation situation in the entire region or space. This intensity is spatially distributed. Average thermal radiation intensity focuses more on the thermal radiation energy received at a specific point or area. This intensity is accumulated over time, so it is usually expressed as the thermal radiation energy received per unit area per unit time.

[0050] The above-defined vegetation water loss factor represents the maximum permissible value of the vegetation water loss factor; the above-defined thermal radiation field-average thermal radiation intensity relationship factor represents the maximum permissible value of the thermal radiation field-average thermal radiation intensity relationship factor; the above-defined duration of thermal anomalies represents the maximum permissible duration of thermal anomalies; the above-defined vegetation water loss factor influence component represents the degree of influence of the vegetation water loss factor on the anomaly risk factor; the above-defined thermal radiation field-average thermal radiation intensity relationship factor influence component represents the degree of influence of the thermal radiation field-average thermal radiation intensity relationship factor on the anomaly risk factor; the above-defined duration of thermal anomalies influence component represents the degree of influence of the duration of thermal anomalies on the anomaly risk factor.

[0051] The influence values ​​corresponding to the environmental anomaly impact coefficients mentioned above represent the degree of influence of the de-unitized unit value of the environmental anomaly impact coefficients on the anomaly risk factor; the influence factor corresponding to the vegetation water loss factor mentioned above represents the degree of influence of the unit value of the vegetation water loss factor on the anomaly risk factor; the influence factor corresponding to the thermal radiation field-average thermal radiation intensity relationship factor mentioned above represents the degree of influence of the unit value of the thermal radiation field-average thermal radiation intensity relationship factor on the anomaly risk factor; the influence factor corresponding to the duration of thermal anomalies mentioned above represents the degree of influence of the duration of thermal anomalies on the anomaly risk factor; the influence factor corresponding to the rate of change of thermal radiation field mentioned above represents the degree of influence of the de-unitized unit value of the rate of change of thermal radiation field on the thermal radiation field-average thermal radiation intensity relationship factor; the influence factor corresponding to the rate of change of average thermal radiation intensity mentioned above represents the degree of influence of the de-unitized unit value of the rate of change of average thermal radiation intensity on the thermal anomaly risk factor. The influence degree of the radiation field-average thermal radiation intensity relationship factor; the early warning database stores the correspondence between the environmental anomaly influence coefficient, vegetation water loss factor, thermal radiation field-average thermal radiation intensity relationship factor, thermal anomaly duration, thermal radiation field change rate, and average thermal radiation intensity change rate and their corresponding influence factors. For example, by inputting the environmental anomaly influence coefficient, vegetation water loss factor, thermal radiation field-average thermal radiation intensity relationship factor, thermal anomaly duration, thermal radiation field change rate, and average thermal radiation intensity change rate into the early warning database, the early warning database can match the influence value corresponding to the environmental anomaly influence coefficient, the influence factor corresponding to the vegetation water loss factor, the influence factor corresponding to the thermal radiation field-average thermal radiation intensity relationship factor, the influence factor corresponding to the thermal anomaly duration, the influence factor corresponding to the thermal radiation field change rate, and the influence factor corresponding to the average thermal radiation intensity change rate, all with values ​​ranging from 0 to 1.

[0052] It needs to be explained that a larger thermal radiation field-average thermal radiation intensity relationship factor indicates a stronger interaction between the thermal radiation field and average thermal radiation intensity within the abnormal environmental area, thus increasing the risk of abnormal events such as fires. The environmental anomaly impact coefficient considers the degree of influence of meteorological factors on the abnormal environmental area; its changes directly lead to fluctuations in the thermal radiation field and average thermal radiation intensity, thereby affecting the value of the thermal radiation field-average thermal radiation intensity relationship factor. A prolonged duration of thermal anomalies increases the likelihood of abnormal events such as fires because prolonged high temperatures accelerate the drying and combustion processes of combustibles. Simultaneously, the duration of thermal anomalies also indirectly affects vegetation growth and moisture conditions, leading to... Changes in vegetation water loss factors are significant. A higher vegetation water loss factor indicates lower vegetation moisture content and higher flammability. Changes in vegetation water loss factors are not only affected by the duration of thermal anomalies but are also closely related to the environmental anomaly influence coefficient and the thermal radiation field-average thermal radiation intensity relationship factor. For example, an increase in the environmental anomaly influence coefficient may lead to extreme climate conditions such as drought, thereby exacerbating the vegetation water loss process. Conversely, an increase in the thermal radiation field-average thermal radiation intensity relationship factor will accelerate heat accumulation and water evaporation on the vegetation surface, leading to a further increase in the vegetation water loss factor. Changes in these parameters directly affect the degree of anomaly risk in the abnormal environmental area during the second cycle, thereby increasing the risk of abnormal events such as fires.

[0053] Furthermore, the specific process for determining whether to issue a wildfire warning for each abnormal environmental area is as follows: Based on the abnormal risk factors of each abnormal environmental area in the second period, the abnormality level of each abnormal environmental area in the second period is matched. If the abnormality level of an abnormal environmental area in the second period belongs to the abnormal warning level, then it is determined that a wildfire warning should be issued for that abnormal environmental area. The specific matching process for matching the abnormality level of each abnormal environmental area in the second period is as follows: The warning database stores the abnormality levels corresponding to each abnormal risk factor interval. The abnormal risk factor interval to which the abnormal risk factor of each abnormal environmental area belongs in the warning database in the second period is queried. The abnormality level corresponding to the abnormal risk factor interval is the abnormality level of each abnormal environmental area in the second period. The above-mentioned abnormal warning level refers to the highest level among the abnormal levels, which indicates that the abnormal environmental area has developed to a critical stage where the warning mechanism must be activated. The occurrence of this level indicates that the environmental anomaly in the area has reached a point where it cannot be ignored, and corresponding measures are urgently needed to prevent potential risks or hazards. In an example embodiment, the specific warning content for this abnormal environmental area is as follows: Specific latitude and longitude range: XX°XX'XX''E to XX°XX'XX''E, XX°XX'XX''N to XX°XX'XX''N. The current anomaly level of this area is determined to be the highest level (anomaly warning level), signifying an extremely high risk of wildfires. The vegetation drought stress index is significantly increased, and the temperature difference between the canopy and the air exceeds 5°C, indicating weakened vegetation transpiration, severe water loss, a thermal inertia ratio below 0.6, low vegetation moisture content, and increased flammability. Recent dry weather conditions, strong winds, and low relative humidity are conducive to the rapid spread of fire. Relevant departments should immediately notify emergency response units at all levels and activate the wildfire emergency plan.

[0054] If the abnormality level of a certain abnormal environmental area does not belong to the abnormal warning level in the second cycle, it is determined that no wildfire warning will be issued for the abnormal environmental area. At the same time, each abnormal environmental area whose abnormality level does not belong to the abnormal warning level is marked as an abnormal monitoring environmental area, and the abnormal risk factor of each abnormal monitoring environmental area in the second cycle is obtained.

[0055] The environmental anomaly impact coefficient of the target area within the forecast period is obtained and compared with the environmental anomaly impact coefficient of the target area in the second period. The result is marked as the environmental anomaly impact deviation coefficient of the target area. Anomaly risk factor correction values ​​are then matched from the early warning database to correct the anomaly risk factors of each anomaly monitored environmental area in the second period, thereby re-matching the anomaly level of each anomaly monitored environmental area in the second period. If the anomaly level of an anomaly monitored environmental area in the second period is at the anomaly warning level, then a wildfire prediction and warning is issued for that anomaly monitored environmental area; otherwise, a wildfire prediction and warning is not issued for that anomaly monitored environmental area. The aforementioned forecast period refers to the time period for predicting and analyzing the target area, and the specific duration is determined by the meteorological data analyst. The environmental anomaly impact coefficient of the target area within the forecast period and the environmental anomaly impact coefficient of the target area in the first period are compared. The acquisition method and meaning are consistent, differing only in time; the aforementioned environmental anomaly impact deviation coefficient of the target area refers to the difference between the environmental anomaly impact coefficient of the target area within the prediction period and the environmental anomaly impact coefficient of the target area within the second period; the aforementioned anomaly risk factor correction value represents the numerical value of the degree of correction for the anomaly risk factor. The specific matching process is as follows: the early warning database stores the anomaly risk factor correction values ​​corresponding to each environmental anomaly impact deviation coefficient interval; the early warning database stores the environmental anomaly impact deviation coefficient interval to which the environmental anomaly impact deviation coefficient of the target area belongs; the anomaly risk factor correction value corresponding to this environmental anomaly impact deviation coefficient interval is the matched anomaly risk factor correction value; the aforementioned correction of the anomaly risk factors of each anomaly monitored environmental area within the second period refers to multiplying the anomaly risk factor correction value by the anomaly risk factor of each anomaly monitored environmental area within the second period, thereby updating the anomaly risk factors of each anomaly monitored environmental area within the second period.

[0056] It should be explained that if the deviation coefficient of the environmental anomaly impact of the target area is greater than or equal to 0, the correction value of the anomaly risk factor is a value greater than 1; if the deviation coefficient of the environmental anomaly impact of the target area is less than 0, the correction value of the anomaly risk factor is a value less than 1.

[0057] The aforementioned wildfire prediction and early warning refers to determining, based on a comprehensive consideration and analysis of future environmental factors, whether an abnormal monitoring area is about to reach a level requiring the activation of an early warning mechanism, and taking predictive and early warning measures accordingly. This process aims to provide relevant departments and residents with sufficient preparation time through scientific prediction and timely warning, enabling them to take effective prevention and response measures, thereby reducing the likelihood of wildfires or mitigating their potential harm. In one example embodiment, wildfire prediction and early warning includes specific geographical locations (e.g., latitude and longitude range, administrative divisions, etc.), the expected time period for wildfires, and a detailed description of the abnormal environmental conditions within the warning area, including... The changes in key indicators such as vegetation drought stress index, canopy temperature to air temperature difference, thermal inertia ratio, and vegetation moisture content reflect the degree of drought and flammability of vegetation, and are important bases for judging wildfire risk. The weather conditions during the warning period are described, including temperature, humidity, wind speed, and wind direction. These meteorological factors directly affect the occurrence and spread of wildfires, so they must be closely monitored and corresponding countermeasures must be taken. At the same time, based on the warning level and abnormal environmental conditions, specific prevention and response measures are given, including restricting fire source activities, strengthening monitoring and patrols, establishing temporary firebreaks, strengthening meteorological monitoring and early warning, organizing emergency drills, and preparing emergency supplies and equipment.

[0058] In one specific embodiment, the present invention calculates the difference in environmental anomaly impact coefficient between the target area in the prediction period and the second period to obtain the environmental anomaly impact deviation coefficient. Then, by using the anomaly risk factor correction value in the early warning database, the anomaly risk factor in the second period is accurately corrected and the anomaly level is rematched. This significantly improves the accuracy and pertinence of wildfire prediction and early warning, effectively avoids false alarms and missed alarms, and provides timely early warning for anomaly monitoring environmental areas that truly pose a wildfire risk, thus providing more scientific and reliable decision support for wildfire prevention and control.

[0059] The line early warning module is used to locate each abnormal transmission line segment based on three-dimensional lidar, evaluate the operational anomaly index of each abnormal transmission line segment in the third cycle, and determine whether to provide protection and early warning for each abnormal transmission line segment.

[0060] In one specific embodiment, the present invention achieves precise protection and early warning for abnormal transmission lines by quantifying the degree of operational anomalies. This not only improves the accuracy and timeliness of early warnings, but also enables timely measures to avoid line faults and ensure the stable operation of the power system. At the same time, quantitative early warning can also provide a scientific basis for line maintenance, optimize the allocation of maintenance resources, and improve the overall safety and reliability of transmission lines.

[0061] Specifically, the process for locating abnormal transmission line segments involves the following steps: First, identifying the abnormal environmental regions within the risk unit of each transmission line segment. Second, obtaining the corresponding abnormal risk factors for each abnormal environmental region within the third period and accumulating them. The accumulated result is marked as the accumulated abnormal risk factor value for each transmission line segment within the third period. The third period refers to the time frame for analyzing the abnormal transmission lines. The third period not only covers the previous second period but also extends in time span. The specific duration of the third period is determined by the data analysts. Each transmission line segment refers to an independent part obtained by dividing the entire transmission network according to a specific division method, such as using the two transmission towers at both ends as boundaries to define each segment, i.e., from one transmission tower to the adjacent tower. The portion of the transmission line between each transmission tower is considered a segment. The risk unit to which each segment of the transmission line belongs refers to a specific geographical area delineated based on each segment. The environmental conditions within this area may affect the safe and stable operation of the transmission line. For example, for an overhead transmission line, the area within two parallel planes formed by extending horizontally a certain distance outward from its edge and perpendicular to the ground, such as 10 meters on each side for a 110 kV line and 15 meters on each side for a 220 kV line (the extension distance varies for different voltage levels), can be considered as a risk unit as a whole. The abnormal environmental areas included within the risk units to which each segment of the transmission line belongs refer to the abnormal environmental areas that are within the risk unit delineated based on each segment of the transmission line or that intersect with the risk unit.

[0062] The cumulative values ​​of abnormal risk factors for each transmission line segment during the third cycle are weighted and summed with the operational anomaly factors for each segment during the third cycle to assess the operational anomaly index for each segment during the third cycle; that is... .

[0063] The abnormal operation index of each transmission line segment in the third cycle is compared with the abnormal operation threshold. If the abnormal operation index of a certain transmission line segment in the third cycle is less than or equal to the abnormal operation threshold, the transmission line segment is not marked as an abnormal transmission line. If the abnormal operation index of a certain transmission line segment in the third cycle is greater than the abnormal operation threshold, the transmission line segment is marked as an abnormal transmission line, thereby locating each abnormal transmission line segment. The aforementioned abnormal operation threshold represents the maximum value of the reasonable range of the abnormal operation index, which is extracted from the early warning database.

[0064] Specifically, the determination of whether to provide protection warnings for each abnormal transmission line segment involves the following protection process: Based on the operational anomaly index of each abnormal transmission line segment within the third cycle, the protection scheme for each abnormal transmission line segment is matched from the warning database. Simultaneously, the operational anomaly index corresponding to the protection scheme for each abnormal transmission line segment is obtained and marked as the reference operational anomaly index for each segment. This reference index is then compared with the operational anomaly index of each abnormal transmission line segment within the third cycle, and the result is marked as the operational anomaly index deviation value for each abnormal transmission line segment. If the operational anomaly index deviation value of a certain abnormal transmission line segment is small... If the deviation value of the operational anomaly index for a certain abnormal transmission line is equal to or greater than the reference operational anomaly index deviation value, the protection scheme for that abnormal transmission line segment will be increased. If the deviation value of the operational anomaly index for a certain abnormal transmission line segment is greater than the reference operational anomaly index deviation value, the protection scheme for that abnormal transmission line segment will be decreased. The protection schemes for the aforementioned abnormal transmission lines refer to a series of protection measures designed to ensure the continued normal operation of the transmission line when an anomaly or fault occurs, such as current protection. The specific matching process for the operational anomaly index of a certain abnormal transmission line segment in the third cycle is as follows: the early warning database stores the protection schemes corresponding to each operational anomaly index. The abnormal operation index of the abnormal transmission line in the third cycle is compared with the various abnormal operation indices stored in the early warning database. The minimum value of the difference is then retrieved. The protection scheme corresponding to the abnormal operation index stored in the early warning database corresponding to the minimum value is the protection scheme for the abnormal transmission line. The aforementioned reference abnormal operation index deviation value represents the reference value of the abnormal operation index deviation value, which is extracted from the early warning database. If the abnormal operation index deviation value is large, greater than the reference abnormal operation index deviation value, it indicates that the actual operation is better than the situation corresponding to the matched protection scheme. If the protection scheme is not adjusted, it may lead to oversensitivity of the protection, causing frequent operation in some cases that are not real faults or serious anomalies, resulting in unnecessary power outages or equipment malfunctions, affecting the normal operation of the transmission line. By reducing the adjustment of the protection scheme, the protection action threshold can be made more in line with the actual operation, avoiding overprotection. In one example embodiment, reducing the adjustment can be done by extending the delay time of the overcurrent protection to twice the existing data, so that the protection device operates only after the current has continuously exceeded the set value for a period of time, avoiding protection malfunctions caused by instantaneous current fluctuations. Similarly, increasing the adjustment can also make the protection action threshold more in line with the actual operation.

[0065] The abnormal operation threshold of each abnormal transmission line segment is obtained and compared with the corresponding abnormal operation index of each abnormal transmission line segment in the third cycle. If the abnormal operation index of an abnormal transmission line segment in the third cycle is less than or equal to the corresponding abnormal operation threshold, it is determined that no warning will be issued for that abnormal transmission line segment. If the abnormal operation index of an abnormal transmission line segment in the third cycle is greater than the corresponding abnormal operation threshold, it is determined that a warning will be issued for that abnormal transmission line segment. The aforementioned abnormal operation threshold of each abnormal transmission line segment represents the maximum allowable value of the abnormal operation index of each abnormal transmission line segment in the third cycle, and is extracted from the warning database. In one example embodiment, the aforementioned abnormal operation threshold of each abnormal transmission line segment is compared with the corresponding abnormal operation index of each abnormal transmission line segment in the third cycle. The power line will issue an early warning. Specifically, an audible and visual alarm will be sent to the monitoring platform of the power operation and maintenance center immediately. At the same time, the line number and location information of the abnormal transmission line will be marked in a conspicuous flashing red on the monitoring interface. For example, if the transmission line numbered L005 is located between a substation in the suburbs of a city and an industrial park, and its abnormal operation index is detected to be 85% in the third cycle (the corresponding abnormal operation threshold is 70%), and it exceeds the threshold, the line location will be accurately located on the electronic map and flashed in red. At the same time, a text message containing detailed information such as the line number, location and abnormal index will be sent to the mobile phones of the operation and maintenance personnel responsible for the area, reminding them to go to the site as soon as possible to investigate potential faults.

[0066] Furthermore, the assessment of the operational anomaly index of each transmission line segment during the third cycle is specifically carried out as follows: the average thermal radiation intensity and the hot spot area of ​​each transmission line segment during the third cycle are obtained; the average thermal radiation intensity, the thermal radiation energy received per unit area per unit time, can be extracted from the infrared data in the forest area transmission line model; the hot spot area refers to the maximum area occupied by hot spots (usually local overheating phenomena caused by current overload, poor contact, line aging, etc.) found and recorded on each line segment during the third cycle when thermal imaging monitoring of the transmission line is carried out, which can be extracted from the thermal imaging data in the forest area transmission line model, and the hot spot temperature range is determined by the electrical engineer.

[0067] The environmental anomaly impact coefficient of the target area in the third period is obtained. Influence weights are introduced to quantify the impact of the ratio between the average thermal radiation intensity and the defined average thermal radiation intensity on the operational anomaly factor, and the impact of the ratio between the hot spot area and the defined hot spot area on the operational anomaly factor. At the same time, the impact of the environmental anomaly impact coefficient of the target area in the third period on the operational anomaly factor is summarized to obtain the operational anomaly factor. The cumulative value of the anomaly risk factor is weighted and summarized with the operational anomaly factor to obtain the operational anomaly index. The above-mentioned operational anomaly factor is used to quantify the sum of the impact of the environmental anomaly impact coefficient, the average thermal radiation intensity, and the hot spot area on the degree of operational anomaly. The environmental anomaly impact coefficient of the target area in the third period is obtained in the same way and with the same meaning as the environmental anomaly impact coefficient of the target area in the first period, with only a difference in time.

[0068] The operational anomaly index of each transmission line segment during the third cycle characterizes the degree of operational anomaly during the third cycle, and its specific expression is as follows:

[0069] ;

[0070] ;

[0071] In the formula, This represents the operational anomaly index of the abnormal transmission line in segment c during the third cycle. This represents the cumulative value of abnormal risk factors for transmission line segment c during the third cycle. This refers to the abnormal operation factors of the c-th transmission line during the third cycle. The impact weights corresponding to the pre-set cumulative values ​​of abnormal risk factors in the early warning database. Here, c represents the impact weights corresponding to the pre-set operational anomaly factors in the early warning database, and c is the number of each abnormal transmission line segment. y represents the total number of abnormal transmission line segments. The environmental anomaly impact coefficient of the target area during the third cycle. The average thermal radiation intensity of the c-th transmission line during the third cycle. Let c be the area of ​​the hot spot in the third cycle of the transmission line segment c. The predefined average thermal radiation intensity in the early warning database. The predefined hot spot area in the early warning database, The influence weights corresponding to the preset environmental anomaly influence coefficients in the early warning database. The influence weights corresponding to the preset average thermal radiation intensity in the early warning database are: The influence weights corresponding to the pre-defined hot spot areas in the early warning database.

[0072] The above definition of average thermal radiation intensity represents the maximum allowable value of average thermal radiation intensity; the above definition of hot spot area represents the maximum allowable value of hot spot area.

[0073] The influence weights corresponding to the cumulative values ​​of the aforementioned abnormal risk factors represent the degree of influence of the de-unitized unit values ​​of the cumulative values ​​of abnormal risk factors on the operational anomaly index; the influence weights corresponding to the aforementioned operational anomaly factors represent the degree of influence of the de-unitized unit values ​​of the operational anomaly factors on the operational anomaly index; the influence weights corresponding to the aforementioned environmental anomaly influence coefficients represent the degree of influence of the de-unitized unit values ​​of the environmental anomaly influence coefficients on the operational anomaly factor; the influence weights corresponding to the aforementioned average thermal radiation intensity represent the degree of influence of the unit value of the average thermal radiation intensity on the operational anomaly factor; and the influence weights corresponding to the aforementioned hot spot area represent the degree of influence of the unit value of the hot spot area on the operational anomaly index. The impact of abnormal factors is measured; the early warning database stores the correspondence between the cumulative value of abnormal risk factors, operational abnormal factors, environmental abnormality impact coefficient, average thermal radiation intensity, and hot spot area and their corresponding impact weights. For example, by inputting the cumulative value of abnormal risk factors, operational abnormal factors, environmental abnormality impact coefficient, average thermal radiation intensity, and hot spot area into the early warning database, the early warning database can match the impact weights corresponding to the cumulative value of abnormal risk factors, operational abnormal factors, environmental abnormality impact coefficient, average thermal radiation intensity, and hot spot area, with values ​​ranging from 0 to 1.

[0074] It should be explained that when the anomaly level of the surrounding environment (such as forests) of transmission lines is high, it poses a significant threat to the safe and stable operation of the transmission lines. At the same time, abnormal meteorological factors can exacerbate the physical stress and electrical load of transmission lines, thereby triggering or aggravating abnormal phenomena on the lines. In this environment, transmission lines are more likely to exhibit characteristics of increased hot spot area and increased average thermal radiation intensity. The formation of hot spots is usually due to local overheating of the line, which may be caused by factors such as current overload, poor contact, or line aging. When environmental factors are abnormal, these potential problems are more likely to be triggered or amplified, making the hot spot phenomenon more significant. The increase in hot spot area and the increase in average thermal radiation intensity directly reflect the aggravation of the anomaly level of the transmission lines. These abnormal phenomena may not only damage the insulation performance and mechanical strength of the line itself, but may also pose potential safety risks to the surrounding environment, such as further causing fires. Therefore, continuous monitoring is required for predictive protection and early warning.

[0075] In one specific embodiment, the present invention provides a power transmission line wildfire early warning system and method based on three-dimensional lidar. By accurately collecting and evaluating meteorological parameters of the target area, and intelligently initializing data acquisition process parameters, the system ensures the accuracy and timeliness of the data. After acquiring the data acquisition results of the target area, it can accurately locate each abnormal environmental area and deeply collect and analyze its fire risk dynamic parameters, thereby flexibly adjusting the data acquisition process parameters to achieve precise monitoring of fire risk. In addition, it can intelligently match the abnormal risk level of each abnormal environmental area and promptly determine whether a wildfire early warning needs to be issued, effectively improving the accuracy and timeliness of the early warning. At the same time, it uses three-dimensional lidar technology to accurately locate each abnormal section of the power transmission line and evaluate its operational anomaly index in the third cycle, providing a scientific basis for the protection and early warning of the power transmission line.

[0076] Reference Figure 2 As shown, the second aspect of the present invention provides a method for early warning of wildfires on power transmission lines based on three-dimensional lidar, comprising: Step 1, collecting and evaluating meteorological parameters of the target area to initialize the data acquisition process parameters of the target area, obtaining the data acquisition results of the target area, and locating each abnormal environmental area; Step 2, collecting and analyzing the dynamic fire risk parameters of each abnormal environmental area to adjust the data acquisition process parameters of each abnormal environmental area, matching the abnormal risk level of each abnormal environmental area, and determining whether to issue a wildfire warning for each abnormal environmental area; Step 3, locating each abnormal power transmission line segment based on three-dimensional lidar, evaluating the operational anomaly index of each abnormal power transmission line segment in the third cycle, and determining whether to issue a protection warning for each abnormal power transmission line segment.

[0077] The above description is merely an example and illustration of the structure of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described, or use similar methods to replace them, as long as they do not deviate from the structure of the invention or exceed the scope defined by the present invention, they should all fall within the protection scope of the present invention.

Claims

1. A power transmission line wildfire early warning system based on three-dimensional lidar, characterized in that, include: The environmental analysis module is used to collect and evaluate meteorological parameters of the target area, thereby initializing the data acquisition process parameters of the target area, obtaining the data acquisition results of the target area, and locating various abnormal environmental areas. The wildfire early warning module is used to collect and analyze the dynamic parameters of fire risk in various abnormal environmental areas, thereby adjusting the parameters of the data collection process in each abnormal environmental area, matching the abnormal risk level of each abnormal environmental area, and determining whether to issue a wildfire early warning for each abnormal environmental area. The line early warning module is used to locate abnormal transmission lines based on three-dimensional lidar, evaluate the abnormal operation index of each abnormal transmission line in the third cycle, and determine whether to provide protection and early warning for each abnormal transmission line. The specific analysis process for locating the abnormal transmission line segments is as follows: Obtain the abnormal environment areas contained in the risk unit to which each transmission line belongs, obtain the abnormal risk factors of each abnormal environment area in the third period, and accumulate them. The accumulation result is marked as the accumulated value of abnormal risk factors of each transmission line in the third period. The cumulative value of abnormal risk factors of each transmission line segment in the third cycle is weighted and summarized with the abnormal operation factors of each transmission line segment in the third cycle to evaluate the abnormal operation index of each transmission line segment in the third cycle. The abnormal operation index of each transmission line segment in the third cycle is compared with the abnormal operation threshold. If the abnormal operation index of a certain transmission line segment in the third cycle is less than or equal to the abnormal operation threshold, the transmission line segment is not marked as an abnormal transmission line. If the abnormal operation index of a certain transmission line segment in the third cycle is greater than the abnormal operation threshold, the transmission line segment is marked as an abnormal transmission line, thereby locating each abnormal transmission line segment. The assessment process for determining the operational anomaly index of each transmission line segment during the third cycle is as follows: The average thermal radiation intensity of each transmission line segment during the third cycle and the hot spot area of ​​each transmission line segment during the third cycle were obtained. Influence weights are introduced to quantify the impact of the ratio between the average thermal radiation intensity and the defined average thermal radiation intensity on the operational anomaly factor, as well as the impact of the ratio between the hot spot area and the defined hot spot area on the operational anomaly factor. At the same time, the impact of the environmental anomaly influence coefficient on the operational anomaly factor is summarized. The cumulative value of the anomaly risk factor and the operational anomaly factor are weighted and summarized to obtain the operational anomaly index. The operational anomaly index of each transmission line segment during the third cycle represents the degree of operational anomaly of each transmission line segment during the third cycle.

2. The power transmission line wildfire early warning system based on three-dimensional lidar according to claim 1, characterized in that: The specific evaluation process for collecting and evaluating meteorological parameters in the target area is as follows: The meteorological parameters of the target area include the average air pressure of the target area during the first cycle, the total rainfall of the target area during the first cycle, and the solar radiation accumulation of the target area during the first cycle. By introducing influence coefficients to quantify the influence of the ratio between the average air pressure deviation value and the defined average air pressure deviation value on the environmental anomaly influence coefficient, the influence of the ratio between the total rainfall and the defined total rainfall on the environmental anomaly influence coefficient, and the influence of the ratio between the solar radiation accumulation and the defined solar radiation accumulation on the environmental anomaly influence coefficient, the influence of each influence degree is coupled to obtain the environmental anomaly influence coefficient of the target area in the first period. The environmental anomaly impact coefficient of the target area during the first period is used to characterize the degree to which abnormal environmental conditions in the target area increase the risk of wildfires during the first period.

3. The power transmission line wildfire early warning system based on three-dimensional lidar according to claim 1, characterized in that: The initialization process for the data acquisition parameters of the initialization target area is as follows: The early warning database stores the parameter sets of each data acquisition device corresponding to each environmental anomaly impact coefficient interval. The environmental anomaly impact coefficient of the target area in the first period is compared with the environmental anomaly impact coefficient intervals stored in the early warning database. If the environmental anomaly impact coefficient of the target area in the first period belongs to a certain environmental anomaly impact coefficient interval stored in the early warning database, the parameter sets of each data acquisition device corresponding to that environmental anomaly impact coefficient interval stored in the early warning database are initialized and set to the parameter sets of each data acquisition device belonging to the target area, thereby completing the initialization of the data acquisition process parameters of the target area.

4. The power transmission line wildfire early warning system based on three-dimensional lidar according to claim 1, characterized in that: The parameters for data acquisition in each abnormal environmental area are adjusted, and the specific adjustment process is as follows: By analyzing the dynamic parameters of fire risk in each abnormal environmental area, the abnormal risk factors of each abnormal environmental area in the second cycle are obtained. Obtain the parameter sets of each data acquisition device belonging to each abnormal environment area. Based on the abnormal risk factors of each abnormal environment area in the second cycle, match the parameter adjustment sets of each data acquisition device belonging to each abnormal environment area from the early warning database, thereby updating the parameter sets of each data acquisition device belonging to each abnormal environment area and completing the adjustment of the data acquisition process parameters of each abnormal environment area.

5. The power transmission line wildfire early warning system based on three-dimensional lidar according to claim 1, characterized in that: The specific process for determining whether to issue wildfire warnings for each abnormal environmental area is as follows: Based on the abnormal risk factors of each abnormal environmental area in the second period, the abnormal level of each abnormal environmental area in the second period is matched. If the abnormal level of an abnormal environmental area in the second period is an abnormal warning level, then a wildfire warning is issued for that abnormal environmental area. If the abnormality level of a certain abnormal environmental area does not belong to the abnormal warning level in the second cycle, it is determined that no wildfire warning will be issued for the abnormal environmental area. At the same time, each abnormal environmental area whose abnormality level does not belong to the abnormal warning level is marked as an abnormal monitoring environmental area, and the abnormal risk factor of each abnormal monitoring environmental area in the second cycle is obtained. The environmental anomaly impact coefficient of the target area within the prediction period is obtained, and the difference between the environmental anomaly impact coefficient of the target area in the second period is processed. The processing result is marked as the environmental anomaly impact deviation coefficient of the target area. The anomaly risk factor correction value is matched from the early warning database, and the anomaly risk factor of each anomaly monitoring environmental area in the second period is corrected. Thus, the anomaly level of each anomaly monitoring environmental area in the second period is rematched. If the anomaly level of an anomaly monitoring environmental area in the second period belongs to the anomaly warning level, then it is determined that a wildfire prediction and warning will be issued for that anomaly monitoring environmental area. If the anomaly level of an anomaly monitoring environmental area in the second period does not belong to the anomaly warning level, then it is determined that a wildfire prediction and warning will not be issued for that anomaly monitoring environmental area.

6. The power transmission line wildfire early warning system based on three-dimensional lidar according to claim 5, characterized in that: The specific analysis process for the abnormal risk factors of each abnormal environmental region during the second period is as follows: The fire risk dynamic parameters of each abnormal environmental area include the vegetation water loss factor of each abnormal environmental area in the second period, the thermal radiation field-average thermal radiation intensity relationship factor of each abnormal environmental area in the second period, and the duration of thermal anomaly in each abnormal environmental area in the second period. The environmental anomaly impact coefficient of the target area in the second period is obtained. By coupling the vegetation water loss factor, thermal anomaly duration and thermal radiation field-average thermal radiation intensity relationship factor of each abnormal environmental area in the second period, and introducing the degree of influence of the environmental anomaly impact coefficient of the target area in the second period on the anomaly risk factor, the anomaly risk factor of each abnormal environmental area in the second period is obtained. The abnormal risk factors of each abnormal environmental region in the second period represent the degree of abnormal risk of each abnormal environmental region in the second period.

7. The power transmission line wildfire early warning system based on three-dimensional lidar according to claim 1, characterized in that: The specific protection process for determining whether to provide protection and early warning for each abnormal transmission line segment is as follows: Based on the abnormal operation index of each abnormal transmission line segment during the third cycle, the protection schemes for each abnormal transmission line segment are matched from the early warning database. At the same time, the abnormal operation index corresponding to the protection scheme of each abnormal transmission line segment is obtained and marked as the reference abnormal operation index of each abnormal transmission line segment. The difference between the reference and the reference abnormal operation index of each abnormal transmission line segment during the third cycle is processed, and the processing result is marked as the deviation value of the abnormal operation index of each abnormal transmission line segment. If the deviation value of the abnormal operation index of a certain abnormal transmission line segment is less than or equal to the deviation value of the reference abnormal operation index, the protection scheme of that abnormal transmission line segment is increased. If the deviation value of the abnormal operation index of a certain abnormal transmission line segment is greater than the deviation value of the reference abnormal operation index, the protection scheme of that abnormal transmission line segment is decreased. The abnormal operation threshold of each abnormal transmission line segment is obtained and compared with the abnormal operation index of the corresponding abnormal transmission line segment in the third cycle. If the abnormal operation index of an abnormal transmission line segment in the third cycle is less than or equal to the corresponding abnormal operation threshold, it is determined that no warning will be issued for that abnormal transmission line segment. If the abnormal operation index of an abnormal transmission line segment in the third cycle is greater than the corresponding abnormal operation threshold, it is determined that a warning will be issued for that abnormal transmission line segment.

8. A method for applying the three-dimensional lidar-based power transmission line wildfire early warning system according to any one of claims 1-7, characterized in that: include: Step 1: Collect and evaluate meteorological parameters of the target area to initialize the data acquisition process parameters of the target area, obtain the data acquisition results of the target area, and locate each abnormal environmental area; Step 2: Collect and analyze the dynamic fire risk parameters of each abnormal environmental area, thereby adjusting the data collection process parameters of each abnormal environmental area, matching the abnormal risk level of each abnormal environmental area, and determining whether to issue a wildfire warning for each abnormal environmental area. Step 3: Locate each abnormal transmission line segment using 3D lidar, assess the operational anomaly index of each abnormal transmission line segment during the third cycle, and determine whether to provide protection and early warning for each abnormal transmission line segment.

Images