Electromagnetic Hazard Monitoring System, Methods, Terminals, and Media for Unmanned Aerial Vehicle (UAV) Swarms in Substations

Abstract

This invention discloses a substation electromagnetic hazard monitoring system, method, terminal, and medium using a swarm of unmanned aerial vehicles (UAVs), relating to the field of substation monitoring technology. The system includes: using a voltage and current predictor bound to the target substation to analyze preset operating control parameters of the substation to obtain voltage and current distribution information; loading a set of magnetic field barrier locations and a set of barrier strengths to perform electromagnetic field configuration on the voltage and current distribution information to obtain electromagnetic field distribution parameters; and when the real-time substation operating control parameters match the preset operating control parameters, performing UAV swarm collaborative scheduling based on the electromagnetic field distribution parameters to obtain electromagnetic field monitoring results. This invention solves the technical problem of low monitoring efficiency due to inaccurate scheduling in existing substation electromagnetic hazard monitoring technologies.

Description

Technical Field

[0001] This invention relates to the field of substation monitoring technology, specifically to a substation electromagnetic hazard monitoring system, method, terminal, and medium using unmanned aerial vehicle (UAV) swarms. Background Technology

[0002] With the rapid development of power systems, substations, as key nodes in power conversion and distribution, are of paramount importance for operational safety. Among these safety measures, stable monitoring of the electromagnetic environment is crucial for preventing equipment failures and ensuring power grid reliability. Traditional substation electromagnetic monitoring methods typically rely on fixed-deployment sensor networks. Using power equipment as a baseline, monitoring points are placed at specific equipment locations prone to anomalies in historical data. The overall operational status is assessed by collecting local electromagnetic field data. However, this monitoring strategy has inherent limitations: First, when multiple electrical devices in a substation operate simultaneously, the electromagnetic fields they generate will superimpose and interfere with each other, forming a complex electromagnetic environment. Fixed sensors can only capture the field strength at local points and cannot fully reflect the field distribution characteristics of the entire space, leading to distorted monitoring data. Second, as described in patent application CN112924765A, which describes the method of setting up electromagnetic environment monitoring points in substations in the prior art, it does not fully consider the influence of magnetic field barriers in the substation on electromagnetic wave propagation. These barriers will change the radiation path and intensity attenuation of the electromagnetic field, making the actual field strength distribution deviate significantly from the ideal model. This further reduces the monitoring accuracy and causes redundant monitoring resource scheduling, making it difficult to respond to dynamically changing electromagnetic hazards in real time. Summary of the Invention

[0003] This application provides a system, method, terminal, and medium for monitoring electromagnetic hazards in substations using unmanned aerial vehicle (UAV) swarms, which addresses the technical problem of low monitoring efficiency caused by inaccurate scheduling in existing substation electromagnetic hazard monitoring technologies.

[0004] In view of the above problems, firstly, this application provides a substation electromagnetic hazard monitoring system for unmanned aerial vehicle (UAV) swarms, including:

[0005] The control parameter analysis module is used to analyze the preset operating control parameters of the substation using a voltage and current predictor bound to the target substation, and obtain voltage distribution information and current distribution information.

[0006] The electromagnetic field configuration module is used to load the distribution location set and the blocking strength set of magnetic field barriers, perform electromagnetic field configuration on the voltage distribution information and the current distribution information, and obtain electromagnetic field distribution parameters.

[0007] The monitoring result acquisition module is used to obtain electromagnetic field monitoring results by performing UAV swarm collaborative scheduling based on the electromagnetic field distribution parameters when the real-time substation operation control parameters are consistent with the substation preset operation control parameters.

[0008] Secondly, this application provides a method for monitoring electromagnetic hazards in substations using a swarm of unmanned aerial vehicles (UAVs), including:

[0009] By using a voltage and current predictor bound to the target substation, the preset operating control parameters of the substation are analyzed to obtain voltage distribution information and current distribution information;

[0010] By loading the distribution location set and the blocking strength set of the magnetic field barrier, electromagnetic field configuration is performed on the voltage distribution information and the current distribution information to obtain electromagnetic field distribution parameters;

[0011] When the real-time substation operation control parameters are consistent with the substation preset operation control parameters, the UAV swarm collaborative scheduling is performed based on the electromagnetic field distribution parameters to obtain electromagnetic field monitoring results.

[0012] Thirdly, this application provides an intelligent terminal for monitoring electromagnetic hazards in substations, comprising:

[0013] Memory, used to store the first computer program;

[0014] The processor is used to read and execute the first computer program, thereby realizing the function of the substation electromagnetic hazard monitoring system for the first aspect of the unmanned aerial vehicle swarm.

[0015] Fourthly, this application provides a non-transitory computer-readable storage medium storing a second computer program, which, when executed by a processor, implements the functions of a substation electromagnetic hazard monitoring system for a drone swarm as described in the first aspect.

[0016] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0017] This application proposes a substation electromagnetic hazard monitoring system, method, terminal, and medium using a drone swarm. By digitally coupling the substation's topology, operating parameters, and the influence of magnetic field obstructions in the physical space, and dynamically scheduling the drone swarm for collaborative sensing, the accuracy of substation electromagnetic environment monitoring and the level of intelligent resource scheduling are significantly improved. Compared with traditional methods, the technical solution provided in this application significantly overcomes the problem of monitoring data distortion caused by electromagnetic field interference and magnetic field obstructions. On the one hand, it ensures the reliability of hazard identification by improving the accuracy of the electromagnetic field analysis model, reducing the risk of missed and false alarms. On the other hand, it achieves efficient utilization of monitoring resources by optimizing the drone scheduling strategy, providing a more forward-looking technical guarantee for the safe and stable operation of substations. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram of the substation electromagnetic hazard monitoring system for a drone swarm provided in an embodiment of this application.

[0020] Figure 2 A flowchart illustrating the method for monitoring electromagnetic hazards in substations using a drone swarm, as provided in this application embodiment.

[0021] Figure 3 This is a schematic diagram of the structure of a smart terminal provided in an embodiment of this application.

[0022] Figure 4 This is a schematic diagram of the structure of a non-transitory computer-readable storage medium provided in an embodiment of this application.

[0023] The components represented by each number in the attached diagram are explained below:

[0024] The system includes a control parameter analysis module 100, an electromagnetic field configuration module 200, a monitoring result acquisition module 300, an intelligent terminal 500, a memory 510, a processor 520, a first computer program 511, a computer-readable storage medium 600, and a second computer program 611. Detailed Implementation

[0025] This application provides a substation electromagnetic hazard monitoring system, method, terminal, and medium using unmanned aerial vehicle (UAV) swarms, which addresses the technical problem of low monitoring efficiency caused by inaccurate scheduling in existing substation electromagnetic hazard monitoring technologies.

[0026] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0027] It should be noted that the terms "comprising" and "having" are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or modules that are not explicitly listed or that are inherent to these processes, methods, products, or devices.

[0028] Example 1, as Figure 1 As shown, this application provides a substation electromagnetic hazard monitoring system for unmanned aerial vehicle (UAV) swarms, wherein the system includes:

[0029] The control parameter analysis module 100 is used to analyze the preset operating control parameters of the substation using a voltage and current predictor bound to the target substation, and obtain voltage distribution information and current distribution information.

[0030] In the early planning stage of substation electromagnetic environment monitoring, traditional methods typically rely on statistical analysis of historical operating data or real-time sensor readings under specific operating conditions to understand the distribution of electrical parameters. However, this method has significant limitations; it cannot perform forward-looking assessments, resulting in a lack of foresight in the development of monitoring plans and making it difficult to effectively allocate monitoring resources before potential electromagnetic hazards occur.

[0031] In the system provided in this application embodiment, the control parameter analysis module 100 includes:

[0032] Using the power facilities of the target substation's power facility distribution topology as input nodes, the power facility control parameters as input parameters, each circuit as an output node, and the voltage and current of each circuit as an output binary array, a graph neural network simulation is performed on the power facility distribution topology to obtain the voltage and current predictor architecture.

[0033] Using the power facility distribution topology as a constraint, collect the corresponding substation operation control record parameters and the historical calibration true values ​​of voltage and current for each circuit, train the voltage and current predictor architecture, and obtain the voltage and current predictor.

[0034] Among them, constrained by the power facility distribution topology, one-to-one corresponding substation operation control record parameters and historical calibration true values ​​of voltage and current for each circuit are collected, including:

[0035] Constrained by the power facility distribution topology and the substation operation control record parameters, collect historical voltage and current values ​​of several groups of each circuit during several operations;

[0036] Based on the historical voltage and current values ​​of each circuit in the aforementioned groups, the historical voltage and current values ​​are calculated using the same location lumped value to obtain the true historical voltage and current values ​​of each circuit.

[0037] The voltage and current predictor is associated with and stored in relation to the target substation.

[0038] In this embodiment, the power facilities of the target substation's power facility distribution topology are used as input nodes, power facility control parameters are used as input parameters, each circuit is used as an output node, and the voltage and current of each circuit are used as output binary arrays. A graph neural network simulation is performed on the power facility distribution topology to obtain a voltage and current predictor architecture. Specifically, the power facility distribution topology of the target substation is used as the input node in the graph neural network, and the power facility control parameters, such as the opening and closing states of circuit breakers and the tap positions of transformers, are used as input parameters. Each circuit is used as an output node, and the voltage and current of each circuit are used as output binary arrays. The power facility distribution topology of the target substation can be obtained through the design information of the target substation. The graph neural network simulation is constructed to learn the mapping relationship from the state of all power facilities to the electrical state of each circuit segment. The obtained voltage and current predictor architecture can predict the voltage and current of each circuit based on the power facility control parameters.

[0039] Constrained by the power facility distribution topology, one-to-one corresponding substation operation control record parameters and historical calibration true values ​​of voltage and current for each circuit are collected. Specifically, constrained by the power facility distribution topology and substation operation control record parameters, during normal substation operation, measuring instruments such as multimeters or voltage and current sensors installed on the circuits are used to collect several sets of historical voltage and current values ​​for each circuit during several operation periods.

[0040] Based on the historical voltage and current values ​​of several groups of circuits, the lumped values ​​of voltage and current at the same location are calculated separately. For example, the arithmetic mean of the historical voltage and current values ​​at the same location is calculated to obtain the true historical voltage and current values ​​of each circuit.

[0041] The constructed voltage and current predictor is trained using historical calibration values. This involves inputting substation operation control record parameters into the constructed voltage and current predictor, outputting predicted voltage and current values, and using a loss function such as MSE to obtain the difference between the predicted value and the historical calibration values. The internal parameters of the voltage and current predictor are then adjusted using a backpropagation algorithm for iterative training until convergence. For example, if the difference between the output voltage and current predicted value and the historical calibration values ​​is within ±5%, the training is considered complete, and the voltage and current predictor is obtained.

[0042] The voltage and current predictors are associated with and stored in relation to the target substation.

[0043] By introducing voltage and current predictors that are tied to the specific topology of the target substation, the substation's preset operating control parameters can be used as input to simulate its electrical operating characteristics, thereby calculating the voltage and current distribution information at various locations. This allows the monitoring method to comprehensively and in advance grasp the overall electrical status of the substation, providing an accurate data foundation for subsequent electromagnetic field analysis.

[0044] The electromagnetic field configuration module 200 is used to load the distribution location set and the blocking strength set of the magnetic field barrier, perform electromagnetic field configuration on the voltage distribution information and the current distribution information, and obtain electromagnetic field distribution parameters.

[0045] Traditional electromagnetic field calculation methods often treat the substation space as an ideal, uniform free space, and calculate based solely on voltage and current information. They ignore the magnetic field barriers that are widely present in the actual physical environment of the substation, such as building walls. These barriers have complex effects on electromagnetic wave propagation, such as absorption, reflection, and scattering, which leads to a significant deviation between the actual field strength distribution in the space and the calculation results.

[0046] In the system provided in this application embodiment, the electromagnetic field configuration module 200 includes:

[0047] The type of the first magnetic field barrier, the first barrier area, and the first barrier thickness are obtained, along with the distribution location of the first magnetic field barrier.

[0048] By processing the first barrier area and the first barrier thickness using a barrier strength configurator bound to the first magnetic field barrier type, a first barrier strength is obtained, wherein the barrier strength characterizes the magnetic field strength attenuation rate.

[0049] The distribution location of the first magnetic field barrier is associated with the first barrier strength and stored, and added to the distribution location set of the magnetic field barrier and the barrier strength set;

[0050] The barrier strength configurator takes the barrier area record value and barrier thickness record value of the preset magnetic field barrier type as input, and obtains the supervised configuration using the statistically obtained true value of the barrier strength.

[0051] Based on the voltage distribution information and the current distribution information, the electromagnetic field is configured to obtain the initial electromagnetic field distribution parameters;

[0052] Based on the distribution location set of the magnetic field barriers and the set of barriers strength, the initial electromagnetic field distribution parameters are corrected to obtain the electromagnetic field distribution parameters.

[0053] In this embodiment, a set of magnetic field barrier distribution locations and a set of barrier strengths are loaded, and electromagnetic field configuration is performed on voltage distribution information and current distribution information to obtain electromagnetic field distribution parameters.

[0054] Specifically, the location of the first magnetic field barrier is randomly selected. For example, the coordinates of the specific polygon vertices in the design drawings of the target substation are obtained as the location of the first magnetic field barrier, which is then processed. The type of the first magnetic field barrier at the location of the first magnetic field barrier is obtained, such as a concrete wall, and the corresponding first barrier area and first barrier thickness are obtained. The unit of the barrier area is square meters, and the unit of the barrier thickness is meters.

[0055] Obtain a barrier strength configurator. For example, a barrier strength configurator is constructed based on machine learning, wherein the input layer is used to receive the barrier area and a first barrier thickness, the hidden layer has 16 nodes and is activated using the ReLU function, and the output layer is used to output the predicted barrier strength.

[0056] The barrier strength configurator is trained using the recorded area and thickness values ​​of a preset magnetic field barrier type as input, and supervised by the statistically obtained true value of the barrier strength, until convergence. For example, training is considered complete when the output barrier strength error is within ±0.05. The barrier strength characterizes the attenuation rate of the magnetic field strength after passing through the barrier, and its value ranges from 0 to 1. The higher the barrier strength, the greater the attenuation of the magnetic field strength after passing through the barrier.

[0057] The first barrier strength is obtained by processing the first barrier area and the first barrier thickness using a barrier strength configurator bound to the first magnetic field barrier type. Here, the barrier strength configurator bound to the first magnetic field barrier type means that each barrier type is bound to a corresponding barrier strength configurator, with one barrier strength configurator corresponding to one barrier type.

[0058] The distribution location of the first magnetic field barrier is associated with the first barrier strength and stored together. A set of magnetic field barrier distribution locations and a set of barrier strengths are added.

[0059] Based on voltage and current distribution information, an electromagnetic field calculation method, such as the method of moments, is used to configure the electromagnetic field and obtain initial electromagnetic field distribution parameters. These initial electromagnetic field distribution parameters represent the electromagnetic field intensity distribution of the target substation without any obstructions.

[0060] Based on the distribution location set and the set of barrier strengths of magnetic field barriers, the initial electromagnetic field distribution parameters are corrected. For example, the corrected electromagnetic field strength at a certain point behind the barrier is equal to the initial electromagnetic field strength at that point in the initial electromagnetic field distribution minus the barrier strength. Other corrected electromagnetic field strengths are obtained using the same method, and the electromagnetic field distribution parameters are obtained by integrating them.

[0061] By loading a pre-established set of magnetic field barrier distribution locations and barrier strengths, the initial electromagnetic field configuration calculated based on voltage and current information is refined and corrected. This effectively integrates the electrical model and physical space model of the substation, taking into account not only the electrical characteristics of the source but also the spatial locations of various barriers and their barrier strengths on the electromagnetic field. This results in electromagnetic field distribution parameters that are closer to the complex physical environment of the substation, providing a basis for subsequent monitoring resource scheduling.

[0062] The monitoring result acquisition module 300 is used to obtain electromagnetic field monitoring results by performing UAV swarm collaborative scheduling based on the electromagnetic field distribution parameters when the real-time substation operation control parameters are consistent with the substation preset operation control parameters.

[0063] Traditional drone inspections often rely on fixed routes or manual experience to designate specific areas. This approach lacks specificity and fails to effectively link with calculated electromagnetic risk distribution. It may result in drones spending significant time inspecting safe areas while failing to adequately measure truly high-risk points, wasting resources and potentially delaying the discovery of real hazards. Furthermore, drone swarms are prone to task overlap or incomplete coverage, hindering synergy and ultimately preventing the collected monitoring results from fully and accurately reflecting the real-time electromagnetic environment.

[0064] In the system provided in this application embodiment, the monitoring result acquisition module 300 includes:

[0065] An electromagnetic field strength threshold is applied, and a hazard risk calculation is performed with the electromagnetic field distribution parameters to obtain a hazard risk coefficient set and a distribution location set. The hazard risk at each distribution location is equal to the difference between the electromagnetic field strength of the electromagnetic field distribution parameters and the electromagnetic field strength threshold.

[0066] Based on the set of hidden danger risk coefficients, extract the set of risk distribution locations that are greater than or equal to the threshold of the hidden danger risk coefficient from the set of distribution locations;

[0067] Based on the risk distribution location set, perform collaborative scheduling of the drone swarm;

[0068] Based on the risk distribution location set, the unmanned aerial vehicle (UAV) swarm collaborative scheduling is performed, including:

[0069] The risk distribution location set is sorted according to the risk coefficient from smallest to largest to obtain the risk distribution location sequence;

[0070] Assign a first weight to the sequence number and a second weight to the number of drones to be scheduled. Sum the weights to obtain the fitness function, wherein the fitness function is a maximum value optimization function.

[0071] Based on the fitness function and the risk distribution location set, the UAV swarm collaborative scheduling optimization is performed to obtain the UAV swarm retrieval scheme and perform the electromagnetic field sensing task.

[0072] In this embodiment, the real-time substation operation control parameters and the substation's preset operation control parameters are compared. For example, the deviation value of the same control parameter is calculated as the ratio of the deviation value to the preset operation control parameter, which is then used as the deviation value. The deviation value is calculated as: |real-time substation operation control parameter - preset operation control parameter| ÷ preset operation control parameter. A deviation threshold is set to assess the degree of deviation. For example, the deviation threshold is set to 0.2. When the deviation values ​​of multiple control parameters of the real-time substation are all less than the deviation threshold, the real-time substation operation control parameters are considered to be consistent with the preset operation control parameters; otherwise, they are considered inconsistent. When the real-time substation operation control parameters are consistent with the preset operation control parameters, based on the electromagnetic field distribution parameters, UAV swarm collaborative scheduling is performed to obtain electromagnetic field monitoring results.

[0073] An electromagnetic field strength threshold is applied, which is a fixed value set according to electromagnetic environment safety standards or safety regulations for a specific area of ​​the substation, such as 50 microtesla. The electromagnetic field strength threshold and electromagnetic field distribution parameters are then used to calculate hazard risk, resulting in a set of hazard risk coefficients and a set of distribution locations. The hazard risk at each distribution location is equal to the difference between the electromagnetic field strength of the electromagnetic field distribution parameters and the electromagnetic field strength threshold. If the deviation of the control parameter is less than 0, the hazard risk coefficient is considered to be 0, meaning there is no hazard risk.

[0074] Based on the set of hazard risk coefficients, risk locations with values ​​greater than or equal to a hazard risk coefficient threshold are extracted from the distribution location set and used as the risk distribution location set. The hazard risk coefficient threshold is a pre-set characteristic that defines the minimum risk level requiring intervention; for example, it can be set to 0.1.

[0075] The risk distribution locations are sorted from smallest to largest according to the risk coefficient of the hidden dangers, thus obtaining the risk distribution location sequence.

[0076] Assign a first weight to the sequence number and a second weight to the number of drones to be scheduled. Sum these weights to obtain the fitness function, which is a maximum value optimization function. Specifically, the fitness function = sequence number of the risk location in the risk distribution location sequence × first weight + number of drones to be scheduled at the risk location × second weight, where first weight + second weight = 1.

[0077] Based on the fitness function, a collaborative scheduling optimization of the UAV swarm is performed on the risk distribution location set to obtain a UAV swarm retrieval scheme. For example, multiple UAV swarm retrieval schemes are randomly obtained, and the corresponding fitness function results are calculated. An optimization algorithm, such as the bird flocking algorithm, is used to optimize the scheme to obtain the UAV swarm scheduling scheme with the largest fitness function, and then the electromagnetic field sensing task is executed.

[0078] By establishing a real-time operating parameter matching mechanism and driving the collaborative scheduling of the UAV swarm based on high-precision electromagnetic field distribution parameters, the precise matching of monitoring resources and risk distribution is achieved. This enables the UAV swarm to conduct precise monitoring in high-risk areas while avoiding unnecessary resource investment in low-risk areas, thus achieving a highly optimized allocation of monitoring resources overall.

[0079] Example 2, as Figure 2 As shown, based on the same inventive concept as the substation electromagnetic hazard monitoring system for drone swarms provided in Embodiment 1, this embodiment of the invention also provides a substation electromagnetic hazard monitoring method for drone swarms, including:

[0080] By using a voltage and current predictor bound to the target substation, the preset operating control parameters of the substation are analyzed to obtain voltage distribution information and current distribution information;

[0081] By loading the distribution location set and the blocking strength set of the magnetic field barrier, electromagnetic field configuration is performed on the voltage distribution information and the current distribution information to obtain electromagnetic field distribution parameters;

[0082] When the real-time substation operation control parameters are consistent with the substation preset operation control parameters, the UAV swarm collaborative scheduling is performed based on the electromagnetic field distribution parameters to obtain electromagnetic field monitoring results.

[0083] Specifically, by utilizing a voltage and current predictor linked to the target substation, the pre-set operating control parameters of the substation are analyzed to obtain voltage and current distribution information, including:

[0084] Using the power facilities of the target substation's power facility distribution topology as input nodes, the power facility control parameters as input parameters, each circuit as an output node, and the voltage and current of each circuit as an output binary array, a graph neural network simulation is performed on the power facility distribution topology to obtain the voltage and current predictor architecture.

[0085] Using the power facility distribution topology as a constraint, collect the corresponding substation operation control record parameters and the historical calibration true values ​​of voltage and current for each circuit, train the voltage and current predictor architecture, and obtain the voltage and current predictor.

[0086] Among them, constrained by the power facility distribution topology, one-to-one corresponding substation operation control record parameters and historical calibration true values ​​of voltage and current for each circuit are collected, including:

[0087] Constrained by the power facility distribution topology and the substation operation control record parameters, collect historical voltage and current values ​​of several groups of each circuit during several operations;

[0088] Based on the historical voltage and current values ​​of each circuit in the aforementioned groups, the historical voltage and current values ​​are calculated using the same location lumped value to obtain the true historical voltage and current values ​​of each circuit.

[0089] The voltage and current predictor is associated with and stored in relation to the target substation.

[0090] Specifically, the distribution location set and the blocking strength set of the loaded magnetic field barrier are used to perform electromagnetic field configuration on the voltage distribution information and the current distribution information to obtain electromagnetic field distribution parameters, including:

[0091] The type of the first magnetic field barrier, the first barrier area, and the first barrier thickness are obtained, along with the distribution location of the first magnetic field barrier.

[0092] By processing the first barrier area and the first barrier thickness using a barrier strength configurator bound to the first magnetic field barrier type, a first barrier strength is obtained, wherein the barrier strength characterizes the magnetic field strength attenuation rate.

[0093] The distribution location of the first magnetic field barrier is associated with the first barrier strength and stored, and added to the distribution location set of the magnetic field barrier and the barrier strength set;

[0094] The barrier strength configurator takes the barrier area record value and barrier thickness record value of the preset magnetic field barrier type as input, and obtains the supervised configuration using the statistically obtained true value of the barrier strength.

[0095] Based on the voltage distribution information and the current distribution information, the electromagnetic field is configured to obtain the initial electromagnetic field distribution parameters;

[0096] Based on the distribution location set of the magnetic field barriers and the set of barriers strength, the initial electromagnetic field distribution parameters are corrected to obtain the electromagnetic field distribution parameters.

[0097] Specifically, the distribution location set and the blocking strength set of the loaded magnetic field barrier are used to perform electromagnetic field configuration on the voltage distribution information and the current distribution information to obtain electromagnetic field distribution parameters, including:

[0098] An electromagnetic field strength threshold is applied, and a hazard risk calculation is performed with the electromagnetic field distribution parameters to obtain a hazard risk coefficient set and a distribution location set. The hazard risk at each distribution location is equal to the difference between the electromagnetic field strength of the electromagnetic field distribution parameters and the electromagnetic field strength threshold.

[0099] Based on the set of hidden danger risk coefficients, extract the set of risk distribution locations that are greater than or equal to the threshold of the hidden danger risk coefficient from the set of distribution locations;

[0100] Based on the risk distribution location set, perform collaborative scheduling of the drone swarm;

[0101] Based on the risk distribution location set, the unmanned aerial vehicle (UAV) swarm collaborative scheduling is performed, including:

[0102] The risk distribution location set is sorted according to the risk coefficient from smallest to largest to obtain the risk distribution location sequence;

[0103] Assign a first weight to the sequence number and a second weight to the number of drones to be scheduled. Sum the weights to obtain the fitness function, wherein the fitness function is a maximum value optimization function.

[0104] Based on the fitness function and the risk distribution location set, the UAV swarm collaborative scheduling optimization is performed to obtain the UAV swarm retrieval scheme and perform the electromagnetic field sensing task.

[0105] Example 3, as Figure 3 As shown, this embodiment of the invention also provides a smart terminal 500, comprising:

[0106] Memory 510 is used to store the first computer program 511;

[0107] The processor 520 is used to read and execute the first computer program 511, thereby realizing the function of the substation electromagnetic hazard monitoring system of the UAV swarm in Embodiment 1.

[0108] Example 4, as Figure 4 As shown, this embodiment of the invention also provides a non-transitory computer-readable storage medium 600, which stores a second computer program 611. When the second computer program 611 is executed by a processor, it implements the function of the substation electromagnetic hazard monitoring system for the UAV swarm as described in Embodiment 1.

[0109] The embodiments of this application have at least the following technical effects:

[0110] This application proposes a substation electromagnetic hazard monitoring system, method, terminal, and medium using a drone swarm. By digitally coupling the substation's topology, operating parameters, and the influence of magnetic field barriers in the physical space, and dynamically scheduling the drone swarm for collaborative sensing, the accuracy of substation electromagnetic environment monitoring and the level of intelligent resource scheduling are significantly improved. Specifically, by constructing a voltage and current predictor bound to the target substation, the voltage and current distribution inside the substation can be proactively deduced based on preset operating control parameters, providing a precise data foundation for subsequent electromagnetic field simulation. Furthermore, by loading the distribution location and intensity information of magnetic field barriers, the initial electromagnetic field configuration results are corrected, so that the final electromagnetic field distribution parameters can more realistically reflect the real physical field with various shielding and reflection effects, thereby improving the accuracy of monitoring and analysis from the source. Based on this, hazard risk calculation and location are performed, and this drives the collaborative scheduling of the drone swarm. This allows drone resources to be deployed in high-risk areas in a targeted manner, rather than being evenly or empirically dispersed throughout the entire station area, effectively avoiding the waste of monitoring resources. Compared with traditional methods, the technical solution provided in this application significantly overcomes the problem of monitoring data distortion caused by electromagnetic field interference and magnetic field obstructions. On the one hand, it ensures the reliability of hidden danger identification by improving the model accuracy of electromagnetic field analysis and reduces the risk of missed and false alarms. On the other hand, it realizes the efficient utilization of monitoring resources by optimizing the UAV scheduling strategy, providing a more forward-looking technical guarantee for the safe and stable operation of substations.

[0111] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0112] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0113] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. A substation electromagnetic hazard monitoring system for a drone swarm, characterized in that, The method comprises the following steps: a control parameter analysis module is used to analyze preset operation control parameters of a target transformer substation by using a voltage and current predictor bound to the target transformer substation, to obtain voltage distribution information and current distribution information; an electromagnetic field configuration module is used to load a magnetic field barrier distribution position set and a barrier strength set, to perform electromagnetic field configuration on the voltage distribution information and the current distribution information, to obtain electromagnetic field distribution parameters, including: performing electromagnetic field configuration based on the voltage distribution information and the current distribution information to obtain initial electromagnetic field distribution parameters; performing correction on the initial electromagnetic field distribution parameters based on the magnetic field barrier distribution position set and the barrier strength set to obtain the electromagnetic field distribution parameters; a monitoring result acquisition module is used to perform UAV cluster cooperative scheduling based on the electromagnetic field distribution parameters when real-time transformer substation operation control parameters are consistent with the preset operation control parameters of the transformer substation, to obtain electromagnetic field monitoring results.

2. The system of claim 1, wherein, The voltage and current predictor construction process comprises the following steps: taking power facility distribution topologies of the target transformer substation as input nodes, taking power facility control parameters as input parameters, taking each circuit as an output node, and taking voltage and current of each circuit as an output binary array, performing graph neural network simulation on the power facility distribution topologies to obtain a voltage and current predictor architecture; taking the power facility distribution topologies as constraints, collecting one-to-one corresponding transformer substation operation control record parameters and voltage and current historical calibration true values of each circuit, training the voltage and current predictor architecture to obtain the voltage and current predictor; storing the voltage and current predictor in association with the target transformer substation.

3. The system of claim 2, wherein, Taking the power facility distribution topologies as constraints, collecting one-to-one corresponding transformer substation operation control record parameters and voltage and current historical calibration true values of each circuit, comprises the following steps: taking the power facility distribution topologies and the transformer substation operation control record parameters as constraints, collecting voltage and current historical record values of each circuit at several times of operation; based on the several groups of voltage and current historical record values of each circuit, performing same-position centralized value calculation on voltage and current historical record values respectively to obtain voltage and current historical calibration true values of each circuit.

4. The system of claim 1, wherein, Loading a magnetic field barrier distribution position set and a barrier strength set comprises the following steps: obtaining a first magnetic field barrier type, a first barrier area and a first barrier thickness of a first magnetic field barrier distribution position; processing the first barrier area and the first barrier thickness by using a barrier strength configurator bound to the first magnetic field barrier type to obtain a first barrier strength, wherein the barrier strength represents a magnetic field strength decay rate; storing the first magnetic field barrier distribution position in association with the first barrier strength, and adding the first magnetic field barrier distribution position and the first barrier strength to the magnetic field barrier distribution position set and the barrier strength set; wherein the barrier strength configurator takes barrier area record values and barrier thickness record values of a preset magnetic field barrier type as input, and obtains a barrier strength true value as supervision configuration.

5. The system of claim 1, wherein, Performing UAV cluster cooperative scheduling based on the electromagnetic field distribution parameters comprises the following steps: loading an electromagnetic field intensity threshold, calculating a hidden danger risk with the electromagnetic field distribution parameter, obtaining a hidden danger risk coefficient set and a distribution position set, wherein the hidden danger risk of each distribution position is equal to the difference between the electromagnetic field intensity of the electromagnetic field distribution parameter and the electromagnetic field intensity threshold; based on the hidden danger risk coefficient set, extracting a risk distribution position set greater than or equal to the hidden danger risk coefficient threshold from the distribution position set; based on the risk distribution position set, performing the cooperative scheduling of the UAV cluster.

6. The system of claim 5, wherein, based on the risk distribution position set, performing the cooperative scheduling of the UAV cluster, including: sorting the risk distribution position set in ascending order of hidden danger risk coefficient to obtain a risk distribution position sequence; configuring a first weight for the serial number and a second weight for the number of UAVs to be dispatched, and adding them to obtain a fitness function, wherein the fitness function is a maximum value optimization function; based on the fitness function, based on the risk distribution position set, performing the cooperative scheduling optimization of the UAV cluster to obtain a UAV cluster scheduling scheme and performing the electromagnetic field sensing task.

7. A method for monitoring electromagnetic hazards of a substation by a drone swarm, characterized in that, including: using the voltage and current predictor bound to the target transformer substation to perform analysis on the preset operation control parameters of the transformer substation to obtain voltage distribution information and current distribution information; loading a magnetic field barrier distribution position set and a barrier strength set to perform electromagnetic field configuration on the voltage distribution information and the current distribution information to obtain electromagnetic field distribution parameters, including: based on the voltage distribution information and the current distribution information, performing electromagnetic field configuration to obtain initial electromagnetic field distribution parameters; based on the magnetic field barrier distribution position set and the barrier strength set, performing correction on the initial electromagnetic field distribution parameters to obtain the electromagnetic field distribution parameters; when the real-time transformer substation operation control parameters are consistent with the preset operation control parameters of the transformer substation, based on the electromagnetic field distribution parameters, performing the cooperative scheduling of the UAV cluster to obtain the electromagnetic field monitoring result.

8. A smart terminal, characterized by including: a memory for storing a first computer program; a processor for reading and executing the first computer program, thereby realizing the functions of the transformer substation electromagnetic hidden danger monitoring system of the UAV group as claimed in any one of claims 1-6.

9. A non-transitory computer-readable storage medium, comprising: the storage medium stores a second computer program, and the second computer program is executed by the processor to realize the functions of the transformer substation electromagnetic hidden danger monitoring system of the UAV group as claimed in any one of claims 1-6.

Images