Intelligent decision-making method and device for hidden danger disposal of power transmission line, and storage medium

Abstract

The invention relates to an intelligent decision-making method and device for hidden danger disposal of a power transmission line, and a storage medium. The method comprises the following steps: S1, obtaining the type, position and standardized risk assessment value of each hidden danger obtained through identification; s2, acquiring coarse-grained meteorological time sequence data during the duration of the wind disaster, and obtaining fine-grained meteorological time sequence data at each hidden danger position; s3, obtaining the topographic features of the positions of the hidden dangers; s4, inputting the type of each hidden danger into the trained hidden danger prediction model to obtain a standardized risk assessment value at the next moment; s5, repeating the step S4 to obtain a standardized risk assessment value of each hidden danger at each moment in the wind disaster duration, and further obtaining a risk rating of each hidden danger in the wind disaster duration; and S6, selecting a hidden danger disposal scheme based on the risk rating of each hidden danger in the wind disaster duration. Compared with the prior art, the method has the advantages of improving the prediction accuracy of the hidden danger development degree under the wind disaster and the like.

Description

Technical Field

[0001] The present invention relates to the field of wind disaster prevention and control of power transmission lines, and in particular to an intelligent decision-making method, device and storage medium for handling hidden dangers of power transmission lines. Background Art

[0002] Hidden danger identification of transmission lines helps to find and repair hidden dangers at an early stage, thus improving the safety of the power system.

[0003] In some existing technologies, an intelligent decision-making platform is established to aggregate the inspection data and meteorological data of the transmission lines to maintain the transmission line equipment. For example, Chinese patent CN 113162232A discloses a transmission line equipment risk assessment and defense decision-making system and method. The system includes an active early warning and defense decision-making application platform for transmission lines, an enterprise middle platform, an external network business system, and an internal network business system. By displaying the overall operation status of the transmission line, it supports operation and maintenance personnel to grasp the operation status of the power grid in a timely manner; access to meteorological environment data can view the temperature, humidity, wind speed, wind direction and other meteorological information of the specific line; an intelligent risk assessment model is constructed to timely warn of abnormal and hidden danger information of transmission equipment, so as to facilitate operation and inspection professionals to analyze the line operation status, formulate defensive operation and maintenance strategies in advance, reduce equipment failure rate, and realize the "active prevention and control" operation and maintenance mode.

[0004] However, the above prior art has the following defects: 1. The gas phase data used is macro-meteorological data, and the risk warning is relatively rough. It mainly targets risks directly related to the gas phase, such as tower tilt and icing, and lacks the ability to assess risks such as wire breakage; 2. The evolution of hidden dangers under the influence of severe weather is not taken into account, and the assessed risks are divided into risk levels based on only a single factor of risk category, which lacks rationality in command and dispatch. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent decision-making method, device and storage medium for handling hidden dangers of transmission lines. Based on the standardized risk assessment value of the current hidden danger, combined with coarse-grained meteorological data and fine-grained meteorological data, the standardized risk assessment value at the next moment is determined by iterative updating. A more accurate evolution of the hidden danger under the influence of wind disasters can be obtained, thereby providing more accurate guidance for emergency command in wind disaster environments.

[0006] The purpose of the present invention can be achieved by the following technical solutions: An intelligent decision-making method for handling hidden dangers of power transmission lines, comprising: Step S1: Obtain the type, location and standardized risk assessment value of each identified hidden danger; Step S2: obtaining coarse-grained meteorological time series data during the duration of the wind disaster, and obtaining fine-grained meteorological time series data at each potential hazard location based on the coarse-grained meteorological data; Step S3: based on the location of each hidden danger, obtaining the terrain characteristics of the location of each hidden danger; Step S4: Input the type of each hidden danger, the terrain characteristics of the location, the coarse-grained meteorological data, the fine-grained meteorological data and the standardized risk assessment value at the current moment into the trained hidden danger prediction model to obtain the standardized risk assessment value at the next moment; Step S5: Repeat step S4 to obtain the standardized risk assessment value of each hidden danger at each moment during the duration of the wind disaster, and further obtain the risk rating of each hidden danger during the duration of the wind disaster; Step S6: Select a hidden danger disposal plan based on the risk rating of each hidden danger during the duration of the wind disaster.

[0007] The step S2 comprises: Step S2-1: obtaining coarse-grained meteorological time series data during the duration of the wind disaster, wherein the coarse-grained meteorological time series data is composed of meteorological time series data of multiple original reference positions; Step 2-2: Calculate the distance vectors between the hidden danger position and each reference position respectively; Step S2-3: filtering the original reference positions based on the distance vectors between the hidden danger position and each original reference position, and obtaining a plurality of first reference positions by screening; Step S2-4: performing normalization processing based on the modulus of the distance vectors between the hidden danger position and each first reference position to obtain a normalized distance between the hidden danger position and each first reference position; Step S2-5: The normalized distance between the hidden danger location and each first reference location is used as the weight of each first reference location, and based on the weight of each first reference location and its meteorological time series data, weighted summation is performed to obtain the particle size meteorological time series data at the hidden danger location.

[0008] The step S2-3 comprises: Step S2-3-1: based on the modulus of the distance vectors between the hidden danger position and each original reference position, sort all the original reference positions from small to large, and select the first set number of original reference positions as potential reference positions; Step S2-3-2: Initialize the second set quantity to 2, and initialize the first set to an empty set; Step S2-3-3: Select a second set number of potential reference positions as a combination, and add all different combinations to the first set; Step S2-3-4: Determine whether the second set number is equal to the first set number. If yes, execute step S2-3-5. Otherwise, add 1 to the second set number and return to step S2-3-3. Step S2-3-5: for all combinations in the first set, respectively calculate the modulus of the sum of the distance vectors between each potential reference position and the hidden danger position in each combination as the characteristic value of the combination; Step S2-3-6: Select the potential reference position in the combination with the smallest eigenvalue as the first reference position.

[0009] The meteorological time series data includes wind speed, wind direction, precipitation, air pressure, humidity and temperature.

[0010] The terrain characteristics include slope, aspect, altitude, surface roughness and terrain undulation.

[0011] The S3 specifically includes: Step S3-1: obtaining the longitude and latitude information of the hidden danger location based on the location of the hidden danger; Step S3-2: Based on the latitude and longitude information of the hidden danger location, combined with a high-precision geographic information system, determine the slope, slope direction, altitude, surface roughness and terrain undulation of the hidden danger location.

[0012] The hidden danger prediction model adopts a Bayesian probability model to determine the standardized risk assessment value at the next moment.

[0013] The risk rating and corresponding hidden danger disposal plan include: Low risk: regular inspections, no emergency intervention required; Medium risk: arrange drone inspections to monitor the development of hidden dangers; High risk: dispatch a repair team for emergency response.

[0014] A transmission line hidden danger handling intelligent decision-making device comprises a memory, a processor, and a program stored in the memory, wherein the processor implements the above-mentioned method when executing the program.

[0015] A storage medium stores a program, which implements the above method when executed.

[0016] Compared with the prior art, the present invention has the following beneficial effects: 1. Based on the standardized risk assessment value of the current hidden danger, combined with coarse-grained meteorological data and fine-grained meteorological data, the standardized risk assessment value at the next moment is determined by iterative updating. This can obtain a more accurate evolution of the hidden danger under the influence of the wind disaster, thereby providing more accurate guidance for emergency command in the wind disaster environment.

[0017] 2. Utilize coarse-grained meteorological time series data, combine the vectors from each reference position to the hidden danger position, and adopt the weighted summation method to obtain fine-grained meteorological time series data. Compared with the method of arranging various sensors on the tower, it can obtain fine-grained meteorological time series data at a relatively low cost while ensuring a certain accuracy.

[0018] 3. Based on the principle of minimum modulus of the sum of distance vectors, the first reference position is determined, so as to avoid the problem of excessive deviation of the fine-particle meteorological time series data from the actual value due to the uneven orientation of the first reference position, thereby improving the accuracy of the fine-particle meteorological time series data.

[0019] 4. Meteorological time series data include wind speed, wind direction, precipitation, air pressure, humidity and temperature. Topographic features include slope, aspect, altitude, surface roughness and terrain undulation, which can improve the accuracy of the model under small samples.

[0020] 5. The Bayesian probability model is used to determine the standardized risk assessment value at the next moment. The Bayesian reasoning method is used to calculate the dynamic evolution probability of different hidden dangers in wind disasters. By combining historical data and real-time monitoring data, the probability of hidden danger occurrence is updated and the posterior probability of risk level is calculated, which can provide more reliable risk assessment results. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a schematic flow chart of the main steps of the method of the present invention; Figure 2 Schematic diagram of updating the standardized risk assessment value in an embodiment of the present invention. DETAILED DESCRIPTION

[0022] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. This embodiment is implemented based on the technical solution of the present invention, and provides a detailed implementation method and specific operation process, but the protection scope of the present invention is not limited to the following embodiments.

[0023] Example 1

[0024] An intelligent decision-making method for handling hidden dangers of power transmission lines, such as Figure 1 As shown, including: Step S1: Obtain the type, location and standardized risk assessment value of each identified hidden danger; Among them, in most embodiments, the type, location and standardized risk assessment value of the hidden danger are stored in a related database. Specifically, the type and location of the hidden danger stored in the database are obtained by inspection by the inspection platform, and the standardized risk assessment value is given manually or by an assessment system. Specifically, the standardized risk assessment value is a normalized value in an interval. For example, taking the broken wire strands of a certain type of wire as an example, the normalized interval is 0-5M, that is, when the number of broken wire strands is 0, the standardized risk assessment value is 0, when the number of broken wire strands is M, the standardized risk assessment value is 0.2, when the number of broken wire strands is 2M, the standardized risk assessment value is 0.4, and so on, until the number of broken wire strands is ≥5M, the standardized risk assessment value is 1, and M can be determined manually by experts.

[0025] Step S2: Obtain the coarse-grained meteorological time series data during the duration of the wind disaster, and obtain the fine-grained meteorological time series data at each potential hazard location based on the coarse-grained meteorological data, specifically including: Step S2-1: obtaining coarse-grained meteorological time series data during the duration of the wind disaster, wherein the coarse-grained meteorological time series data is composed of meteorological time series data of multiple original reference positions; Step 2-2: Calculate the distance vectors between the hidden danger position and each reference position respectively; Step S2-3: filtering the original reference positions based on the distance vectors between the hidden danger position and each original reference position, and obtaining a plurality of first reference positions by screening; Step S2-4: performing normalization processing based on the modulus of the distance vectors between the hidden danger position and each first reference position to obtain a normalized distance between the hidden danger position and each first reference position; Step S2-5: The normalized distance between the hidden danger location and each first reference location is used as the weight of each first reference location, and based on the weight of each first reference location and its meteorological time series data, weighted summation is performed to obtain the particle size meteorological time series data at the hidden danger location.

[0026] By using coarse-grained meteorological time series data and combining the vectors from each reference position to the hidden danger position, a weighted summation method is adopted to obtain fine-grained meteorological time series data. Compared with the method of arranging various sensors on the tower, it is possible to obtain fine-grained meteorological time series data at a relatively low cost while ensuring a certain accuracy rate.

[0027] In this embodiment, the above step S2-3 includes: Step S2-3-1: based on the modulus of the distance vectors between the hidden danger position and each original reference position, sort all the original reference positions from small to large, and select the first set number of original reference positions as potential reference positions; Step S2-3-2: Initialize the second set quantity to 2, and initialize the first set to an empty set; Step S2-3-3: Select a second set number of potential reference positions as a combination, and add all different combinations to the first set; Step S2-3-4: Determine whether the second set number is equal to the first set number. If yes, execute step S2-3-5. Otherwise, add 1 to the second set number and return to step S2-3-3. Step S2-3-5: for all combinations in the first set, respectively calculate the modulus of the sum of the distance vectors between each potential reference position and the hidden danger position in each combination as the characteristic value of the combination; Step S2-3-6: Select the potential reference position in the combination with the smallest eigenvalue as the first reference position.

[0028] Therefore, based on the principle of minimum modulus of the sum of distance vectors, the range of the first reference position is determined, so as to avoid the problem of excessive deviation of the fine-particle meteorological time series data from the actual value due to the imbalance of the orientation of the first reference position relative to the hidden danger position, thereby improving the accuracy of the fine-particle meteorological time series data.

[0029] It should be pointed out that in the present embodiment, in the above calculations, the reference position and the hidden danger position are both horizontal plane coordinates. In addition, in other embodiments, in order to simplify program design and improve efficiency, other methods may be selected for filtering.

[0030] In addition, the first set number can be set based on experience. In this embodiment, it is set to 10.

[0031] Step S3: Based on the location of each hidden danger, the terrain characteristics of the location of each hidden danger are obtained. In this embodiment, the meteorological time series data includes wind speed, wind direction, precipitation, air pressure, humidity and temperature, and the terrain characteristics include slope, slope direction, altitude, surface roughness and terrain undulation, thereby improving the accuracy of the model under small samples.

[0032] Step S3 specifically includes: Step S3-1: obtaining the longitude and latitude information of the hidden danger location based on the location of the hidden danger; Step S3-2: Based on the latitude and longitude information of the hidden danger location, combined with a high-precision geographic information system, determine the slope, slope direction, altitude, surface roughness and terrain undulation of the hidden danger location.

[0033] In addition, in this embodiment, the meteorological time series data includes wind speed, wind direction, precipitation, air pressure, humidity and temperature, and the terrain characteristics include slope, aspect, altitude, surface roughness and terrain undulation; Step S4: Input the type of each hidden danger, the terrain characteristics of the location, the coarse-grained meteorological data, the fine-grained meteorological data and the standardized risk assessment value at the current moment into the trained hidden danger prediction model to obtain the standardized risk assessment value at the next moment; Step S5: Repeat step S4 to obtain the standardized risk assessment value of each hidden danger at each moment during the duration of the wind disaster, and further obtain the risk rating of each hidden danger during the duration of the wind disaster; In some embodiments, the hidden danger prediction model uses a Bayesian probability model to determine the standardized risk assessment value at the next moment, uses a Bayesian probability model to determine the standardized risk assessment value at the next moment, uses a Bayesian reasoning method to calculate the dynamic evolution probability of different hidden dangers in wind disasters, combines historical data and real-time monitoring data, updates the probability of hidden danger occurrence, and calculates the posterior probability of risk level, which can provide more reliable risk assessment results. Figure 2 As shown in the figure, when the data at a new moment is introduced, the prediction results are updated again.

[0034] Step S6: Select a hidden danger disposal plan based on the risk rating of each hidden danger during the duration of the wind disaster.

[0035] Among them, risk rating and corresponding hidden danger disposal plan include: Low risk: Regular inspections, no need for emergency intervention. Specifically, when it is assessed to be low risk, it means that the hidden dangers currently faced by the UHV transmission lines are in a relatively controllable state, and the possibility of having a major impact on normal operation is low. Low risk usually means that the hidden dangers are minor and will not cause failures or accidents in a short period of time, or even if they occur, the scope and extent of their impact are relatively limited.

[0036] Medium risk: Arrange drone inspections to monitor the development of hidden dangers. Specifically, medium risk indicates that there are certain hidden dangers in the UHV transmission lines, which have posed a potential threat to the performance, stability or safety of the facilities. Although the hidden dangers have not yet reached the level of causing serious problems immediately, if they are not paid attention to and monitored, they may develop further over time, leading to escalated risks.

[0037] High risk: dispatch a repair team for emergency treatment. High risk means that the UHV transmission line is facing serious hidden dangers, which may cause failures and accidents at any time. Once they occur, they will cause significant losses and adverse effects on personnel safety, production operations, the environment, etc. High-risk hidden dangers are usually urgent and serious, and immediate action must be taken to deal with them.

[0038] Example 2

[0039] This embodiment is substantially the same as the first embodiment, and only the differences are described. The difference between this embodiment and the first embodiment is that a different method of screening to obtain the first reference position is adopted in this embodiment. Specifically, in this embodiment, step S2-3 includes: Based on the modulus of the distance vector between the hidden danger position and each original reference position, all original reference positions are sorted from small to large; Select the first two original reference positions to add to the second set; Determining step: determining whether the vector sum of the distance vectors of all the original reference positions in the current second set is less than a preconfigured threshold value, if so, taking all the original reference positions in the second set as the first reference positions, otherwise, determining whether the original reference positions in the second set reach the preconfigured threshold number, if so, taking all the original reference positions in the second set as the first reference positions, otherwise, executing the selecting step; Selection step: among all remaining unselected original reference positions, select the original reference position whose distance vector has the smallest angle with the vector sum of the distance vectors of all original reference positions in the current second set, add it to the second set, and then execute the judgment step.

[0040] The above preconfigured thresholds can be set based on experience. In this embodiment, they are set to 1 kilometer. Similarly, the above threshold numbers are set based on experience. In this embodiment, they are set to 10.

[0041] Example 3

[0042] This embodiment is generally the same as Embodiment 2, and only the differences are described. The difference between this embodiment and Embodiment 2 is that the preconfigured threshold in the judgment step of this embodiment is set to 500 meters, and the rest is the same as Embodiment 2. The number of thresholds in this embodiment is also set to 10.

[0043] However, this method has high requirements for providing the original reference position of the coarse-grained gas phase time series data, which can easily lead to the vector sum of the distance vectors of all the first reference positions of sufficient thickness being too large, resulting in inaccurate fine-grained gas phase time series data.

[0044] The following sample set is used to test the solution of this application. The sample set is obtained by annotating the data of the hidden danger of wire strand breakage under wind disasters of level 7 or above in Shanghai. There are 1000 groups in total, and the length of each group is greater than 50 time units. It is a small-scale sample set. 80% of it is divided into training samples and 20% as test samples. In addition, in addition to the means of obtaining coarse-grained meteorological time series data, the present application also helps improve the classification accuracy of the model by selecting more appropriate meteorological time series data and terrain features. In order to verify this, in the present application, a comparative example is set with reference to Example 1. All comparative examples are substantially the same as Example 1, and differ only in the specific selection of meteorological time series data and terrain features, as follows: Comparative Example 1: Meteorological time series data include wind speed, wind direction, humidity and temperature, and terrain features include slope, aspect and altitude; Comparative Example 2: Meteorological time series data include wind speed, air pressure, humidity and temperature, and terrain features include altitude, surface roughness and terrain undulation; Comparative Example 3: Meteorological time series data include wind speed, wind direction, precipitation, air pressure, humidity and temperature, and terrain features include slope and altitude; After testing, the accuracy, calculation speed and variance were evaluated. The accuracy is as follows: The accuracy of the test samples of Example 1 is 87.5%, the accuracy of Comparative Example 1 is 12.5%, the accuracy of Comparative Example 2 is 9%, the accuracy of Comparative Example 3 is 36%, and the accuracy of Example 2 is 45.5%. Since Example 3 has not completed convergence, it is not discussed. Example 1 has the best effect. Although Example 2 uses the same types of meteorological time series data and terrain features as Example 1, due to the different specific means of obtaining its fine-grained meteorological time series data, there is still a gap with Example 1. The accuracy of Comparative Examples 1 and 2 is obviously low. It can be seen that the specific selection of meteorological time series data and terrain features is the key to improving classification accuracy.

[0045] In addition, the evaluation results of the calculation speed are as follows: The calculation time for the accuracy of the test sample of Example 1 is 5.104 seconds, the calculation time of Example 2 is 3.165 seconds, and Example 3 is not discussed because it has not completed convergence. The calculation time of Comparative Example 1 is 5.785 seconds, Comparative Example 2 is 4.985 seconds, and Comparative Example 3 is 5.215 seconds. The results of Example 1 and all comparative examples are similar, while Example 2 is slightly superior, but the advantage is not obvious. It can be seen that the specific acquisition of particle size meteorological time series data is the key to affecting the overall calculation speed.

[0046] Finally, in terms of variance, Example 1 is also the best. Example 3 is not discussed because it has not completed convergence. The second is Example 2. The variances of Comparative Examples 1, 2 and 3 are relatively large. It can be seen that the present application can greatly improve the performance under small samples, and Example 1, which has two major improvement methods, is the best embodiment.

[0047] This application aims to solve the problems of the difficulty in integrating intelligent identification, emergency response and overall command of UHV transmission lines in traditional wind disaster scenarios, and the single perspective of hidden danger assessment models. It is the first to create an intelligent decision-making method for transmission line hidden danger treatment driven by the physical evolution mechanism of hidden dangers combined with the characterization of tower-level fine-scale meteorological data. By coupling the real-time rating evolution of the danger level of transmission line hidden dangers in wind disaster environments with the trend of tower-level wind disaster fine-scale meteorological changes, it realizes the intelligent matching of dynamic classification of hidden dangers and treatment of transmission line hidden dangers, and generates intelligent electronic emergency plans: including dynamic planning of inspections by different types of drones (reconnaissance drones, load-carrying drones); an electronic hidden danger treatment plan that integrates hidden danger evolution mechanism, acquisition of tower-level fine-scale meteorological time series data, and wind disaster hidden danger expert knowledge graph information. Compared with traditional manual hidden danger treatment plans, the dynamic evolution of hidden dangers and real-time feedback mechanism improve the accuracy of the closed loop of treatment. The average response time is shortened and the accuracy rate is improved.

[0048] Another aspect of the present application provides an intelligent decision-making device for handling hidden dangers of power transmission lines, including a memory, a processor, and a program stored in the memory, and the processor implements the above-mentioned method when executing the program.

[0049] In addition, the electronic device of the present application includes a central processing unit (CPU), which can perform various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) or computer program instructions loaded from a storage unit into a random access memory (RAM). In RAM, various programs and data required for device operation can also be stored. CPU, ROM and RAM are connected to each other via a bus. Input / output (I / O) interfaces are also connected to the bus.

[0050] Multiple components in the device are connected to the I / O interface, including: input units, such as keyboards, mice, etc.; output units, such as various types of displays, speakers, etc.; storage units, such as disks, optical disks, etc.; and communication units, such as network cards, modems, wireless communication transceivers, etc. The communication unit allows the device to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunication networks.

[0051] The processing unit performs the various methods and processes described above, such as steps S1 to S6 of the method. For example, in some embodiments, steps S1 to S6 may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit. In some embodiments, part or all of the computer program may be loaded and / or installed on the device via a ROM and / or a communication unit. When the computer program is loaded into the RAM and executed by the CPU, one or more of the steps S1 to S6 described above may be executed. Alternatively, in other embodiments, the CPU may be configured to execute steps S1 to S6 in any other appropriate manner (e.g., by means of firmware).

[0052] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0053] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0054] In the context of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

Claims

1. An intelligent decision-making method for handling hidden dangers of power transmission lines, characterized in that: include: Step S1: Obtain the type, location and standardized risk assessment value of each identified hidden danger; Step S2: obtaining coarse-grained meteorological time series data during the duration of the wind disaster, and obtaining fine-grained meteorological time series data at each potential hazard location based on the coarse-grained meteorological data; Step S3: based on the location of each hidden danger, obtaining the terrain characteristics of the location of each hidden danger; Step S4: Input the type of each hidden danger, the terrain characteristics of the location, the coarse-grained meteorological data, the fine-grained meteorological data and the standardized risk assessment value at the current moment into the trained hidden danger prediction model to obtain the standardized risk assessment value at the next moment; Step S5: Repeat step S4 to obtain the standardized risk assessment value of each hidden danger at each moment during the duration of the wind disaster, and further obtain the risk rating of each hidden danger during the duration of the wind disaster; Step S6: Select a hidden danger disposal plan based on the risk rating of each hidden danger during the duration of the wind disaster.

2. According to claim 1, a method for intelligent decision-making on hidden dangers in power transmission lines is characterized in that: The step S2 comprises: Step S2-1: obtaining coarse-grained meteorological time series data during the duration of the wind disaster, wherein the coarse-grained meteorological time series data is composed of meteorological time series data of multiple original reference positions; Step 2-2: Calculate the distance vectors between the hidden danger position and each reference position respectively; Step S2-3: filtering the original reference positions based on the distance vectors between the hidden danger position and each original reference position, and obtaining a plurality of first reference positions by screening; Step S2-4: performing normalization processing based on the modulus of the distance vectors between the hidden danger position and each first reference position to obtain a normalized distance between the hidden danger position and each first reference position; Step S2-5: The normalized distance between the hidden danger location and each first reference location is used as the weight of each first reference location, and based on the weight of each first reference location and its meteorological time series data, weighted summation is performed to obtain the particle size meteorological time series data at the hidden danger location.

3. The intelligent decision-making method for handling hidden dangers of power transmission lines according to claim 2 is characterized in that: The step S2-3 comprises: Step S2-3-1: based on the modulus of the distance vectors between the hidden danger position and each original reference position, sort all the original reference positions from small to large, and select the first set number of original reference positions as potential reference positions; Step S2-3-2: Initialize the second set quantity to 2, and initialize the first set to an empty set; Step S2-3-3: Select a second set number of potential reference positions as a combination, and add all different combinations to the first set; Step S2-3-4: Determine whether the second set number is equal to the first set number. If yes, execute step S2-3-5. Otherwise, add 1 to the second set number and return to step S2-3-3. Step S2-3-5: for all combinations in the first set, respectively calculate the modulus of the sum of the distance vectors between each potential reference position and the hidden danger position in each combination as the characteristic value of the combination; Step S2-3-6: Select the potential reference position in the combination with the smallest eigenvalue as the first reference position.

4. The intelligent decision-making method for handling hidden dangers of power transmission lines according to claim 2 is characterized in that: The meteorological time series data includes wind speed, wind direction, precipitation, air pressure, humidity and temperature.

5. The intelligent decision-making method for handling hidden dangers of power transmission lines according to claim 1 is characterized in that: The terrain characteristics include slope, aspect, altitude, surface roughness and terrain undulation.

6. The intelligent decision-making method for handling hidden dangers of power transmission lines according to claim 5 is characterized in that: The S3 specifically includes: Step S3-1: obtaining the longitude and latitude information of the hidden danger location based on the location of the hidden danger; Step S3-2: Based on the latitude and longitude information of the hidden danger location, combined with a high-precision geographic information system, determine the slope, slope direction, altitude, surface roughness and terrain undulation of the hidden danger location.

7. The intelligent decision-making method for handling hidden dangers of power transmission lines according to claim 1 is characterized in that: The hidden danger prediction model adopts a Bayesian probability model to determine the standardized risk assessment value at the next moment.

8. The intelligent decision-making method for handling hidden dangers of power transmission lines according to claim 1 is characterized in that: The risk rating and corresponding hidden danger disposal plan include: Low risk: regular inspections, no emergency intervention required; Medium risk: arrange drone inspections to monitor the development of hidden dangers; High risk: dispatch a repair team for emergency response.

9. An intelligent decision-making device for handling hidden dangers of power transmission lines, comprising a memory, a processor, and a program stored in the memory, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 8 is implemented.

10. A storage medium having a program stored thereon, characterized in that: When the program is executed, the method according to any one of claims 1 to 8 is implemented.

Images