Intelligent Decision-making Method, Device and Storage Medium for Hidden Danger Disposal of Transmission Lines

Abstract

The present invention relates to an intelligent decision-making method, device and storage medium for dealing with potential hazards in transmission lines. The method includes: Step S1: Obtain the types, locations and standardized risk assessment values of the identified potential hazards; Step S2: Obtain the coarse-grained meteorological time series data during the wind disaster period, and obtain the fine-grained meteorological time series data at the locations of each potential hazard; Step S3: Obtain the topographic features of the locations where each potential hazard is located; Step S4: Input the types, etc. of each potential hazard into the trained potential hazard prediction model to obtain the standardized risk assessment value at the next moment; Step S5: Repeat Step S4 to obtain the standardized risk assessment values of each potential hazard at each moment during the wind disaster period, and further obtain the risk ratings of each potential hazard during the wind disaster period; Step S6: Select a potential hazard disposal plan based on the risk ratings of each potential hazard during the wind disaster period. Compared with the prior art, the present invention has the advantages of improving the prediction accuracy of the development degree of potential hazards under wind disasters, etc.

Description

Technical Field

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

[0002] Identifying potential hazards in transmission lines helps to detect and repair potential hazards at an early stage, thereby improving the safety of the power system.

[0003] In some existing technologies, an intelligent decision-making platform is established to summarize inspection data, meteorological data, etc. of transmission lines for the maintenance of transmission line equipment. For example, Chinese Patent CN 113162232A discloses a risk assessment and defense decision-making system and method for transmission line equipment. 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 comprehensively displaying the operating status of transmission lines, it supports maintenance personnel to timely grasp the operating status of the power grid; accessing meteorological environment data allows viewing meteorological information such as temperature, humidity, wind speed, and wind direction of specific lines; constructing an intelligent risk assessment model to timely give early warning prompts for abnormal and potential hazard information of transmission equipment, facilitating operation and maintenance professionals to analyze the operating conditions of the lines, formulate preventive maintenance strategies in advance, reduce equipment failure rates, and achieve an "active prevention and control" operation and maintenance mode.

[0004] However, the above-mentioned existing technologies have the following defects:

[0005] 1. The gas-phase data it uses is macroscopic meteorological data, and the risk early warning is also relatively rough. It mainly targets risks directly related to the gas phase such as tower inclination and icing, and lacks the ability to evaluate risks of potential hazards such as broken conductor strands.

[0006] 2. It does not consider the evolution of potential hazards under adverse weather conditions, and only divides the risk levels according to a single factor of risk category for the evaluated risks, lacking the rationality of command and dispatch. Summary of the Invention

[0007] The purpose of the present invention is to provide an intelligent decision-making method, device, and storage medium for handling potential hazards in transmission lines. Based on the standardized risk assessment value of the current potential hazard, combined with coarse-grained meteorological data and fine-grained meteorological data, the standardized risk assessment value of the next moment is determined by an iterative update method, and a more accurate evolution situation of the potential hazard under the influence of wind disasters can be obtained, thereby providing more accurate guidance for emergency command in a wind disaster environment.

[0008] The purpose of the present invention can be achieved through the following technical solutions:

[0009] An intelligent decision-making method for handling potential hazards in transmission lines includes:

[0010] Step S1: Obtain the types, locations, and standardized risk assessment values of the identified potential hazards;

[0011] Step S2: Obtain the coarse-grained meteorological time-series data during the wind disaster, and based on the coarse-grained meteorological data, obtain the fine-grained meteorological time-series data at the locations of each potential hazard;

[0012] Step S3: Based on the locations of each potential hazard, obtain the topographic features of the locations where each potential hazard is located;

[0013] Step S4: Input the types of each potential hazard, the topographic features of the location where it is located, and the current coarse-grained meteorological data, fine-grained meteorological data, and standardized risk assessment value into the trained potential hazard prediction model to obtain the standardized risk assessment value at the next moment;

[0014] Step S5: Repeat Step S4 to obtain the standardized risk assessment values of each potential hazard at each moment during the wind disaster, and further obtain the risk ratings of each potential hazard during the wind disaster;

[0015] Step S6: Select a potential hazard disposal plan based on the risk ratings of each potential hazard during the wind disaster.

[0016] The said Step S2 includes:

[0017] Step S2-1: Obtain the coarse-grained meteorological time-series data during the wind disaster, where the coarse-grained meteorological time-series data consists of the meteorological time-series data of multiple original reference locations;

[0018] Step 2-2: Calculate the distance vectors between the potential hazard location and each reference location respectively;

[0019] Step S2-3: Based on the distance vectors between the potential hazard location and each original reference location, filter the original reference locations and screen out multiple first reference locations;

[0020] Step S2-4: Based on the norms of the distance vectors between the potential hazard location and each first reference location, perform normalization processing to obtain the normalized distances between the potential hazard location and each first reference location;

[0021] Step S2-5: Use the normalized distances between the potential hazard location and each first reference location as the weights of each first reference location, and based on the weights of each first reference location and their meteorological time-series data, perform weighted summation to obtain the fine-grained meteorological time-series data at the potential hazard location.

[0022] The said Step S2-3 includes:

[0023] Step S2-3-1: Based on the norms of the distance vectors between the potential hazard location and each original reference location, sort all the original reference locations from small to large, and select the first set number of original reference locations from the front as potential reference locations;

[0024] Step S2-3-2: Initialize the second set number to 2 and initialize the first set to an empty set;

[0025] Step S2-3-3: Select the second set number of potential reference positions as a combination, and add all distinct combinations to the first set;

[0026] Step S2-3-4: Determine whether the second set number is equal to the first set number. If so, execute Step S2-3-5; otherwise, increment the second set number by 1 and return to Step S2-3-3;

[0027] Step S2-3-5: For all combinations in the first set, calculate the modulus of the sum of the distance vectors between each potential reference position in each combination and the hidden danger position as the eigenvalue of the combination;

[0028] Step S2-3-6: Select the potential reference position in the combination with the minimum eigenvalue as the first reference position.

[0029] The meteorological time series data includes wind speed, wind direction, precipitation, air pressure, humidity, and temperature.

[0030] The terrain features include slope, aspect, elevation, surface roughness, and terrain undulation.

[0031] The specific content of S3 includes:

[0032] Step S3-1: Obtain the longitude and latitude information of the hidden danger location based on the location of the hidden danger;

[0033] Step S3-2: Based on the longitude and latitude information of the hidden danger location, combine with a high-precision geographic information system to determine the slope, aspect, elevation, surface roughness, and terrain undulation of the location where the hidden danger is located.

[0034] The hidden danger prediction model uses a Bayesian probability model to determine the standardized risk assessment value at the next moment.

[0035] The risk rating and the corresponding hidden danger disposal plan include:

[0036] Low risk: Conduct regular inspections, no emergency intervention is required;

[0037] Medium risk: Arrange for drone inspections to monitor the development of hidden dangers;

[0038] High risk: Dispatch a repair team for emergency disposal.

[0039] An intelligent decision-making device for hidden danger disposal of transmission lines includes a memory, a processor, and a program stored in the memory. When the processor executes the program, the above-mentioned method is implemented.

[0040] A storage medium stores a program thereon, and when the program is executed, the above-mentioned method is implemented.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] 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 of the next moment is determined by an iterative update method, and a more accurate evolution of the hidden danger under the influence of a wind disaster can be obtained, thereby providing more accurate guidance for emergency command in a wind disaster environment.

[0043] 2. Using the coarse-grained meteorological time series data, combined with the vectors from each reference position to the hidden danger position, the fine-grained meteorological time series data is obtained by weighted summation. Compared with the method of arranging various sensors on the pole towers, while obtaining the fine-grained meteorological time series data at a relatively low cost, a certain accuracy can be guaranteed.

[0044] 3. Based on the principle of the minimum modulus of the sum of distance vectors, the first reference position is determined, thereby avoiding the problem that the fine-grained meteorological time series data deviates too much from the actual value due to the uneven azimuth of the first reference position, and thus improving the accuracy of the fine-grained meteorological time series data.

[0045] 4. The meteorological time series data includes wind speed, wind direction, precipitation, air pressure, humidity and temperature, and the terrain features include slope, aspect, altitude, surface roughness and terrain undulation, thereby improving the accuracy of the model under small samples.

[0046] 5. The Bayesian probability model is used to determine the standardized risk assessment value of the next moment. The Bayesian inference method is used to calculate the dynamic evolution probability of different hidden dangers in a wind disaster. Combining historical data and real-time monitoring data, the occurrence probability of the hidden danger is updated, and the posterior probability of the risk level is calculated, which can give a more reliable risk assessment result. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a schematic diagram of the main step flow of the method of the present invention;

[0048] Figure 2 It is a schematic diagram of the update of the standardized risk assessment value in the embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0049] The present invention will be described in detail below with reference to the drawings and specific embodiments. This embodiment is implemented on the premise of the technical solution of the present invention, and gives the detailed implementation manner and specific operation process, but the protection scope of the present invention is not limited to the following embodiments.

[0050] Embodiment 1

[0051] An intelligent decision-making method for handling potential hazards in transmission lines, as Figure 1 shown, includes:

[0052] Step S1: Obtain the types, locations, and standardized risk assessment values of each identified potential hazard;

[0053] Among them, in most embodiments, the types, locations, and standardized risk assessment values of potential hazards are stored in a relevant database. Specifically, the types and locations of potential hazards stored in the database are obtained through inspections by an inspection platform, and the standardized risk assessment values are given by manual or an assessment system. Specifically, the standardized risk assessment value is a value normalized in an interval. For example, taking the broken strands of a certain type of wire as an example, the normalized interval is 0 - 5M. That is, when the number of broken strands of the wire is 0, the standardized risk assessment value is 0; when the number of broken strands of the wire is M, the standardized risk assessment value is 0.2; when the number of broken strands of the wire is 2M, the standardized risk assessment value is 0.4, and so on. Until when the number of broken strands of the wire ≥ 5M, the standardized risk assessment value is 1, and M can be determined manually by experts.

[0054] Step S2: Obtain the coarse-grained meteorological time-series data during the duration of the wind disaster, and based on the coarse-grained meteorological data, obtain the fine-grained meteorological time-series data at each potential hazard location, specifically including:

[0055] Step S2-1: Obtain the coarse-grained meteorological time-series data during the duration of the wind disaster, where the coarse-grained meteorological time-series data consists of the meteorological time-series data of multiple original reference locations;

[0056] Step 2-2: Calculate the distance vectors between the potential hazard location and each reference location respectively;

[0057] Step S2-3: Based on the distance vectors between the potential hazard location and each original reference location, filter the original reference locations to screen out multiple first reference locations;

[0058] Step S2-4: Based on the norms of the distance vectors between the potential hazard location and each first reference location, perform normalization processing to obtain the normalized distances between the potential hazard location and each first reference location;

[0059] Step S2-5: Use the normalized distances between the potential hazard location and each first reference location as the weights of each first reference location, and based on the weights of each first reference location and their meteorological time-series data, perform weighted summation to obtain the fine-grained meteorological time-series data at the potential hazard location.

[0060] Using coarse-grained meteorological time series data, combining the vectors from each reference position to the hidden danger position, and adopting the method of weighted summation to obtain fine-grained meteorological time series data. Compared with the method of arranging various sensors on the pole tower, it can obtain fine-grained meteorological time series data while maintaining a low cost and ensuring a certain accuracy rate.

[0061] Among them, in this embodiment, the above step S2-3 includes:

[0062] 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;

[0063] Step S2-3-2: Initialize the second set number to 2, and initialize the first set as an empty set;

[0064] Step S2-3-3: Select the second set number of potential reference positions as a combination, and add all the distinct combinations to the first set;

[0065] Step S2-3-4: Determine whether the second set number is equal to the first set number. If it is, execute step S2-3-5; otherwise, increment the second set number by 1 and return to step S2-3-3;

[0066] Step S2-3-5: For all combinations in the first set, calculate the modulus of the sum of the distance vectors between each potential reference position in each combination and the hidden danger position as the eigenvalue of this combination;

[0067] Step S2-3-6: Select the potential reference positions in the combination with the smallest eigenvalue as the first reference position.

[0068] Thus, based on the principle of the minimum modulus of the sum of the distance vectors, the range of the first reference position is determined, which can avoid the problem that the fine-grained meteorological time series data deviates too much from the actual value due to the unbalanced azimuth of the first reference position relative to the hidden danger position, thereby improving the accuracy rate of the fine-grained meteorological time series data.

[0069] It should be noted that in this embodiment, in the above calculation, both the reference position and the hidden danger position are horizontal plane coordinates. In addition, in other embodiments, in order to simplify the program design and improve the efficiency, other filtering methods can also be selected.

[0070] In addition, the above first set number can be set according to experience. In this embodiment, it is set to 10.

[0071] Step S3: Based on the locations of the potential hazards, obtain the topographic features of the locations where the potential hazards are located. In this embodiment, the meteorological time-series data includes wind speed, wind direction, precipitation, air pressure, humidity, and temperature, and the topographic features include slope, aspect, altitude, surface roughness, and terrain undulation, thereby improving the accuracy of the model under small samples.

[0072] Step S3 specifically includes:

[0073] Step S3-1: Obtain the longitude and latitude information of the location of the potential hazard based on the location of the potential hazard;

[0074] Step S3-2: Based on the longitude and latitude information of the location of the potential hazard, combine with a high-precision geographic information system to determine the slope, aspect, altitude, surface roughness, and terrain undulation of the location where the potential hazard is located.

[0075] In addition, in this embodiment, the meteorological time-series data includes wind speed, wind direction, precipitation, air pressure, humidity, and temperature, and the topographic features include slope, aspect, altitude, surface roughness, and terrain undulation;

[0076] Step S4: Input the type of each potential hazard, the topographic features of the location where it is located, the coarse-grained meteorological data, the fine-grained meteorological data, and the standardized risk assessment value at the current moment into the trained potential hazard prediction model to obtain the standardized risk assessment value at the next moment;

[0077] Step S5: Repeat Step S4 to obtain the standardized risk assessment values of each potential hazard at each moment during the duration of the wind disaster, and further obtain the risk ratings of each potential hazard during the duration of the wind disaster;

[0078] In some embodiments, the potential hazard prediction model uses the Bayesian probability model to determine the standardized risk assessment value at the next moment. By using the Bayesian probability model to determine the standardized risk assessment value at the next moment and the Bayesian inference method, calculate the dynamic evolution probability of different potential hazards in the wind disaster, combine historical data and real-time monitoring data, update the occurrence probability of potential hazards, and calculate the posterior probability of the risk level, which can give a more reliable risk assessment result. As Figure 2 shown, when new moment data is introduced, the prediction result is updated again.

[0079] Step S6: Select a potential hazard disposal plan based on the risk ratings of each potential hazard during the duration of the wind disaster.

[0080] Among them, the risk ratings and the corresponding potential hazard disposal plans include:

[0081] Low risk: Regular inspections are carried out, and no emergency intervention is required. Specifically, when it is evaluated as a low risk, it means that the potential hazards faced by the current UHV transmission line are in a relatively controllable state, and the possibility of having a significant impact on normal operation is relatively low. Low risks usually manifest as minor potential hazards that will not cause faults or accidents in a short period of time, or even if they occur, the scope and degree of their impact are relatively limited.

[0082] Medium risk: Arrange for UAV inspections to monitor the development of potential hazards. Specifically, a medium risk indicates that there are certain potential hazards in the UHV transmission line, which have posed potential threats to the performance, stability, or safety of the facilities. Although the potential hazards have not reached the level of immediately causing serious problems, if not paid attention to and monitored, over time, the potential hazards may further develop, leading to an escalation of the risk.

[0083] High risk: Dispatch a repair team for emergency handling. A high risk means that the UHV transmission line is facing serious potential hazards and may trigger faults or accidents at any time. Once they occur, they will cause significant losses and adverse impacts on personnel safety, production operations, the environment, etc. The potential hazards of high risks usually have urgency and severity, and immediate action must be taken for handling.

[0084] Embodiment 2

[0085] This embodiment is generally the same as Embodiment 1, and only the differences are described. The difference between this embodiment and Embodiment 1 is that in this embodiment, a different method is used to screen for the first reference position. Specifically, in this embodiment, step S2-3 includes:

[0086] Based on the magnitude of the distance vectors between the potential hazard position and each original reference position, sort all the original reference positions from smallest to largest;

[0087] Select the first two original reference positions and add them to the second set;

[0088] Judgment step: Judge whether the vector sum of the distance vectors of all the original reference positions in the current second set is less than a pre-configured threshold. If so, use all the original reference positions in the second set as the first reference position. Otherwise, judge whether the number of original reference positions in the second set has reached the pre-configured threshold number. If so, use all the original reference positions in the second set as the first reference position. Otherwise, execute the selection step;

[0089] Selection step: Among all the remaining unselected original reference positions, select the original reference position with the smallest included angle between the direction of its distance vector and the vector sum of the distance vectors of all the original reference positions in the current second set, add it to the second set, and then execute the judgment step.

[0090] The above pre-configured thresholds can be set according to experience. In this embodiment, they are set to 1 kilometer. Similarly, the number of the above thresholds is set according to experience. In this embodiment, it is set to 10.

[0091] Embodiment 3

[0092] This embodiment is generally the same as Embodiment 2. Only the differences are described. The difference between this embodiment and Embodiment 2 is that: the pre-configured 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.

[0093] However, this method has relatively high requirements for the original reference positions that provide coarse-grained gas-phase timing data, and it is easy to cause the modulus of the vector sum of the distance vectors of all the first reference positions with sufficient thickness to be too large, resulting in inaccurate fine-grained gas-phase timing data.

[0094] The following is an experiment on the solution of this application using a certain sample set. The sample set is obtained by data annotation of the hidden danger of conductor strand breakage under wind disasters above level 7 in the Shanghai area. There are 1,000 groups in total, and the length of each group is greater than 50 time units, belonging to a small-scale sample set. 80% of it is divided into training samples, and 20% is used as test samples.

[0095] In addition, in addition to the means of obtaining coarse-grained meteorological timing data, this application also helps to improve the classification accuracy of the model by selecting more appropriate meteorological timing data and terrain features. To verify this, in this application, a comparative example is also set with reference to Embodiment 1. All comparative examples are generally the same as Embodiment 1, only the specific selection of meteorological timing data and terrain features is different, as follows:

[0096] Comparative Example 1: The meteorological timing data includes wind speed, wind direction, humidity, and temperature, and the terrain features include slope, aspect, and altitude;

[0097] Comparative Example 2: The meteorological timing data includes wind speed, air pressure, humidity, and temperature, and the terrain features include altitude, surface roughness, and terrain undulation;

[0098] Comparative Example 3: The meteorological timing data includes wind speed, wind direction, precipitation, air pressure, humidity, and temperature, and the terrain features include slope and altitude;

[0099] After testing, it is evaluated from three aspects: accuracy, calculation speed, and variance. Among them, the accuracy is as follows:

[0100] The accuracy rate of the test samples in Example 1 is 87.5%, that in Comparative Example 1 is 12.5%, that in Comparative Example 2 is 9%, that in Comparative Example 3 is 36%, and that in Example 2 is 45.5%. Since the convergence of Example 3 was not completed, it will not be discussed. The effect of Example 1 is the best. Although Example 2 uses the same types of meteorological time series data and terrain features as Example 1, there is still a gap between Example 2 and Example 1 due to the different specific acquisition methods of its fine-grained meteorological time series data. The accuracies of Comparative Example 1 and Comparative Example 2 are significantly lower. It can be seen that the specific selection of meteorological time series data and terrain features is the key to improving the classification accuracy.

[0101] In addition, the evaluation results for the calculation speed are as follows:

[0102] The calculation time for the accuracy rate of the test samples in Example 1 is 5.104 seconds, that in Example 2 is 3.165 seconds. Since the convergence of Example 3 was not completed, it will not be discussed. The calculation time in Comparative Example 1 is 5.785 seconds, that in Comparative Example 2 is 4.985 seconds, and that in Comparative Example 3 is 5.215 seconds. The results of Example 1 and all comparative examples are similar, and Example 2 is slightly superior, but the advantage is not obvious. It can be seen that the specific acquisition of fine-grained meteorological time series data is the key to affecting the overall calculation speed.

[0103] Finally, in terms of variance, Example 1 is still the best. Since the convergence of Example 3 was not completed, it will not be discussed. Followed by Example 2. The variances of Comparative Example 1, Comparative Example 2, and Comparative Example 3 are relatively large. It can be seen that this application can greatly improve the performance under small samples, and Example 1 with two improvement means is the optimal example.

[0104] This application aims at the problems that the intelligent identification, emergency disposal, and overall command of UHV transmission lines in traditional wind disaster scenarios are difficult to integrate, and the hidden danger assessment model has a single perspective. It first creates an intelligent decision-making method for the disposal of transmission line hidden dangers driven by the combination of the physical evolution mechanism of hidden dangers and the description of tower-level fine-grained meteorological data. Through the coupling of the real-time rating evolution of the danger level of transmission line hidden dangers in a wind disaster environment and the trend of tower-level wind disaster fine-grained meteorological changes, the intelligent matching of the dynamic classification of hidden dangers and the disposal of transmission line hidden dangers is realized, and an intelligent electronic emergency plan is generated, including the dynamic planning of inspections by different types of unmanned aerial vehicles (reconnaissance UAVs, load-carrying UAVs); an electronic hidden danger disposal plan that integrates the hidden danger evolution mechanism, the acquisition of tower-level fine-grained meteorological time series data, and the information of the expert knowledge graph of wind disaster hidden dangers. Compared with the traditional manual hidden danger disposal plan, the hidden danger dynamic evolution and real-time feedback mechanism improve the accuracy of the disposal closed-loop, shorten the average response time, and increase the accuracy rate.

[0105] Another aspect of the present application further provides an intelligent decision-making device for handling potential hazards in transmission lines, including a memory, a processor, and a program stored in the memory. When the processor executes the program, the above-described method is implemented.

[0106] In addition, the electronic device of the present application includes a central processing unit (CPU), which can execute 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 the RAM, various programs and data required for device operation can also be stored. The CPU, ROM, and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.

[0107] Multiple components in the device are connected to the I / O interface, including: an input unit, such as a keyboard, a mouse, etc.; an output unit, such as various types of displays, speakers, etc.; a storage unit, such as a disk, an optical disc, etc.; and a communication unit, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit allows the device to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0108] The processing unit executes 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 can be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device via the ROM and / or the communication unit. When the computer program is loaded into the RAM and executed by the CPU, one or more of the above-described steps S1 to S6 can be executed. Alternatively, in other embodiments, the CPU can be configured to execute steps S1 to S6 by any other suitable means (e.g., by means of firmware).

[0109] The functions described above herein can be at least partially executed by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that can be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), and so on.

[0110] 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, such that when the program codes are executed by the processor or controller, the functions / operations specified in the flowchart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, executed partially on the machine as an independent software package and partially on a remote machine, or executed entirely on a remote machine or server.

[0111] In the context of the present invention, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, 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 disc 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 hidden danger disposal of transmission lines, characterized in that, Including: Step S1: Obtain the types, locations, and standardized risk assessment values of each identified hidden danger; Step S2: Obtain the coarse-grained meteorological time-series data during the wind disaster, and based on the coarse-grained meteorological data, obtain the fine-grained meteorological time-series data at each hidden danger location; Step S3: Based on the locations of each hidden danger, obtain the topographic features of the locations where each hidden danger is located; Step S4: Input the types of each hidden danger, the topographic features of the location where it is located, as well as the coarse-grained meteorological data, fine-grained meteorological data, and 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 values of each hidden danger at each moment during the wind disaster, and further obtain the risk ratings of each hidden danger during the wind disaster; Step S6: Select a hidden danger disposal plan based on the risk ratings of each hidden danger during the wind disaster; The said Step S2 includes: Step S2-1: Obtain the coarse-grained meteorological time-series data during the wind disaster, where the coarse-grained meteorological time-series data consists of the meteorological time-series data of multiple original reference locations; Step S2-2: Calculate the distance vectors between the hidden danger location and each reference location respectively; Step S2-3: Based on the distance vectors between the hidden danger location and each original reference location, filter the original reference locations and screen out multiple first reference locations; Step S2-4: Based on the norms of the distance vectors between the hidden danger location and each first reference location, perform normalization processing to obtain the normalized distances between the hidden danger location and each first reference location; Step S2-5: Use the normalized distances between the hidden danger location and each first reference location as the weights of each first reference location, and based on the weights of each first reference location and their meteorological time-series data, perform weighted summation to obtain the fine-grained meteorological time-series data at the hidden danger location; The said Step S2-3 includes: Step S2-3-1: Based on the norms of the distance vectors between the hidden danger location and each original reference location, sort all the original reference locations from small to large, and select the first set number of original reference locations as potential reference locations; Step S2-3-2: Initialize the second set number to 2, and initialize the first set as an empty set; Step S2-3-3: Select the second set number of potential reference locations as a combination, and add all the different combinations to the first set; Step S2-3-4: Judge whether the second set number is equal to the first set number. If it is, 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, calculate the norms of the sums of the distance vectors between each potential reference location in each combination and the hidden danger location as the eigenvalue of this combination; Step S2-3-6: Select the potential reference locations in the combination with the smallest eigenvalue as the first reference locations.

2. The intelligent decision-making method for hidden danger disposal of a transmission line according to claim 1, wherein The said meteorological time-series data includes wind speed, wind direction, precipitation, air pressure, humidity, and temperature.

3. The intelligent decision-making method for hidden danger disposal of a power transmission line according to claim 1, characterized in that The said topographic features include slope, aspect, altitude, surface roughness, and terrain undulation.

4. The intelligent decision-making method for hidden danger disposal of a transmission line according to claim 3, characterized in that, The said S3 specifically includes: Step S3-1: Obtain the longitude and latitude information of the hidden danger location based on the location of the hidden danger; Step S3-2: Based on the longitude and latitude information of the hidden danger location, combine with a high-precision geographic information system to determine the slope, aspect, altitude, surface roughness, and terrain undulation of the location where the hidden danger is located.

5. The intelligent decision-making method for hidden danger disposal of a transmission line according to claim 1, characterized in that The hidden danger prediction model uses a Bayesian probability model to determine the standardized risk assessment value at the next moment.

6. The intelligent decision-making method for hidden danger disposal of a transmission line according to claim 1, characterized in that, The risk rating and the corresponding hidden danger disposal plan include: Low risk: Regular inspections are required, and no emergency intervention is needed; Medium risk: Arrange for drone inspections to monitor the development of hidden dangers; High risk: Dispatch a repair team for emergency disposal.

7. An intelligent decision-making device for handling hidden dangers in a transmission line, comprising a memory, a processor, and a program stored in the memory, characterized in that, When the processor executes the program, it implements the method described in any one of claims 1-6.

8. A storage medium, on which a program is stored, characterized in that, When the program is executed, it implements the method described in any one of claims 1-6.

Images