An extreme weather vehicle synchronization coordination power grid inspection scheduling method and system

Abstract

An extreme weather vehicle-aircraft synchronous cooperative power grid inspection scheduling method and system. A wind field representation model is constructed to calculate the wind received by the unmanned aerial vehicle, a wind field coupling kinematics model is established and the ground speed is derived, the instantaneous power and state of charge evolution are calculated in combination with the flight state and the wind field; the effective propulsion speed is calculated according to the ground speed and the task direction to determine the task accessibility; the vehicle-aircraft synchronous cooperative constraint is established, the same parking point take-off and landing and the vehicle waiting during the task period are specified, and the upper and lower limit constraints of the state of charge are set; the task points and parking points are spatially clustered and distributed; a multi-objective function based on task coverage, completion time, state of charge and load balancing is constructed, and the optimal scheduling scheme is solved. The present application can realize efficient inspection scheduling of vehicle-aircraft cooperation under extreme weather conditions, and at the same time enhance the endurance reliability of the unmanned aerial vehicle under wind field disturbance and the stability and balance of the overall scheduling.

Description

Technical Field

[0001] This invention belongs to the field of artificial intelligence, specifically relating to a method and system for synchronous and coordinated power grid inspection and scheduling of vehicles and machinery under extreme weather conditions. Background Technology

[0002] With the continuous expansion of power distribution networks, the increasing complexity of line structures, and the frequent occurrence of extreme weather events, researchers have been actively exploring methods for conducting power grid inspections using a combination of inspection vehicles and drones to improve inspection coverage and enhance operational flexibility. With the development of drone platforms, vehicle-mounted power replenishment platforms, and intelligent dispatching technologies, vehicle-drone collaborative inspection methods have been widely applied. Among these, the synchronous collaborative mode, due to its advantages such as clear organizational relationships, well-defined take-off and landing locations, and easy implementation of operational procedures, has high engineering application value in power grid inspection scenarios.

[0003] Currently, vehicle-machine collaborative power inspection methods mostly focus on path planning or general task allocation, and do not adequately consider the coupling relationship between vehicles waiting in place, drones taking off and landing at the same point and recovering at the same point, closed-loop execution of task batches, and energy replenishment constraints in synchronous collaborative mode. At the same time, it is difficult to form a systematic scheduling method applicable to extreme weather scenarios. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a method and system for power grid inspection and scheduling under extreme weather conditions, based on vehicle-machine synchronous coordination. It comprehensively evaluates task reachability and energy status by constructing a wind field coupled motion model and an UAV energy evolution model. Furthermore, based on vehicle-machine coordination constraints and multi-objective optimization, it achieves reasonable allocation and optimal scheduling of inspection task points and parking points.

[0005] The first aspect of this application discloses a power grid inspection and dispatching method for synchronized vehicle-machine coordination under extreme weather conditions, employing the following technical solution: A wind field characterization model for UAV inspection and scheduling under extreme weather conditions is constructed to calculate the wind field experienced by the UAV at its current location; a UAV kinematic model considering wind field coupling is established, and the UAV ground speed is derived by combining the wind field characterization model. The instantaneous power of the UAV is calculated based on the UAV flight state and wind field characterization model, and the energy evolution of the UAV is deduced by combining the UAV's state of charge; the effective propulsion speed of the UAV is calculated based on the UAV's ground speed and the direction of the mission target, which is used to determine whether the mission point is reachable; Establish a synchronous and collaborative relationship between vehicles and drones, spatially restricting drones to take off and recover at the same parking point, and temporally restricting vehicles to remain waiting during drone mission execution; set minimum state of charge constraints and safe state of charge constraints; Establish a set of task points, vehicle parking points, and vehicle-mounted drones for the inspection area; use spatial clustering to assign each task point to the nearest parking point for executing inspection tasks; construct a multi-objective optimization function including task coverage, task completion time, state of charge, and task load balance, and solve for the optimal scheduling scheme.

[0006] Furthermore, the wind field characterization model includes: Let the wind field vector field be Used to indicate the time when the drone is Spatial location The synthetic wind field velocity at the location; then the UAV's spatial position The wind field is the sum of the background wind term, the wind shear term, and the local gust disturbance term; Set the maximum allowable wind speed threshold When satisfied When this happens, the corresponding drone inspection operation shall be suspended; Indicates at time Spatial location The magnitude of the composite wind field velocity vector.

[0007] Furthermore, the UAV kinematic model considering wind field coupling includes: Let the airspeed of the drone be... Then the ground speed of the UAV is the sum of its airspeed and the combined wind speed; No. drones in the future The position is the current location coordinates plus the time interval of the drone. Displacement within; the displacement is a time interval The product of the drone's ground speed and the ground speed.

[0008] Furthermore, the calculation process for the energy evolution of the UAV includes: The instantaneous power of the UAV is a weighted sum of the UAV's basic hovering power, the square of its airspeed, the square of its vertical motion velocity, and the square of the velocity modulus of the synthesized wind field. Integrating the instantaneous power over the time interval yields the cumulative energy consumption; then the UAV at time [time value missing]... The state of charge is defined as the ratio of the remaining charge to the maximum battery capacity of the drone. The energy evolution of drones can then be used to predict drone energy in future moments. The state of charge is represented and calculated as follows: First, the state of charge (SOC) is calculated based on the instantaneous power and the drone's maximum battery energy over a time interval. The rate of descent within the time frame, and then the drone's position at any given moment. Subtracting the decrease in charge from the state of charge of the UAV at the future time, we obtain the state of charge of the UAV at the future time. The state of charge.

[0009] Furthermore, the process for determining whether a task point is reachable includes: For task points Calculate its relationship with the first The drone's current location is The target direction unit vector; Interchange the target direction unit vector with the... Multiply the ground speed of the drone to obtain the effective propulsion speed of the drone along the target direction; If the effective propulsion speed is less than or equal to 0, then the mission point is determined. Unreachable.

[0010] Furthermore, the minimum state of charge constraint and the safe state of charge constraint include: The minimum state of charge constraint is described as follows: the state of charge of the UAV before takeoff is not lower than the minimum state of charge threshold for the UAV to take off and perform the inspection mission. The safe state of charge constraint is described as follows: the state of charge of the UAV during mission execution is not lower than the minimum safe state of charge threshold.

[0011] Furthermore, the multi-objective optimization function includes: Maximize total task coverage; the total task coverage is calculated as the ratio of the number of completed tasks to the total number of task points at the final task completion time.

[0012] Minimize the total task completion time; the maximum completion time of the inspection task among all task points; Maximize the minimum state of charge of the system; Maximize the degree of drone task load balancing, where the degree of task load balancing is the variance of the number of tasks performed by all drones.

[0013] The second aspect of this application discloses a vehicle-machine synchronous collaborative power grid inspection and dispatching system under extreme weather conditions, which implements the power grid inspection and dispatching method described in the first aspect of this application. The system includes: The wind field coupling modeling module is used to construct a wind field characterization model for UAV inspection and scheduling under extreme weather conditions, and to calculate the wind field experienced by the UAV at its current location; it also establishes a UAV kinematic model that takes into account wind field coupling, and derives the UAV ground speed based on the wind field characterization model. Energy consumption modeling module; used to calculate the instantaneous power of the UAV based on the UAV flight state and wind field characterization model, and to infer the energy evolution of the UAV in combination with the UAV's state of charge; calculate the effective propulsion speed of the UAV based on the ground speed of the UAV and the direction of the mission target, used to determine whether the mission point is reachable; Vehicle-to-machine (V2M) collaboration module; used to establish a synchronous collaboration relationship between the vehicle and the drone, spatially limiting the drone to take off and recover at the same parking point, and temporally limiting the vehicle to remain waiting during the drone mission; setting minimum state of charge constraints and safe state of charge constraints; The scheduling scheme optimization module is used to establish a set of task points, vehicle parking points, and vehicle-mounted drones in the inspection area; spatial clustering is used to assign each task point to the nearest parking point for executing inspection tasks; a multi-objective optimization function including task coverage, task completion time, charge state, and task load balance is constructed to solve for the optimal scheduling scheme.

[0014] The beneficial effects of this invention are that, compared with the prior art, 1. This invention establishes a dynamic wind field model, a UAV kinematic model, and an energy consumption model under extreme weather conditions. These models can comprehensively reflect the impact of strong wind disturbances on the UAV's mission reachability, flight energy consumption, and state of charge evolution, thereby improving the adaptability of the synchronous and collaborative inspection method to complex wind environments.

[0015] 2. This invention establishes a synchronous and collaborative scheduling mechanism for vehicle parking, simultaneous take-off and landing of UAVs, simultaneous recovery at the same point, and batch closed-loop execution. It can clearly characterize the coupling relationship between the inspection vehicle waiting in place and the UAV returning for recovery, thereby improving the engineering feasibility and operational safety of the synchronous and collaborative inspection scheme.

[0016] 3. By incorporating task coverage, task completion time, minimum state of charge, and load balancing indicators into the scheduling evaluation system, this invention can comprehensively optimize the synchronous collaborative inspection scheme under extreme weather conditions, thereby improving the scheduling rationality and task execution efficiency of vehicle-machine synchronous collaborative inspection. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating the vehicle-machine synchronous collaborative inspection and scheduling process of the present invention; Figure 2 This invention provides a traditional vehicle-machine synchronous collaborative simulation three-dimensional trajectory diagram. Figure 3 This is a planar projection diagram of the traditional vehicle-machine synchronous collaborative simulation of the present invention; Figure 4 This is a dynamic evolution diagram of the progress of the traditional vehicle-machine synchronous collaborative task according to the present invention; Figure 5 This invention provides a conventional vehicle-machine synchronous collaborative unmanned aerial vehicle swarm charge state diagram. Figure 6 This is the timing diagram of the state of the conventional vehicle-machine synchronous collaborative UAV of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of this invention. The embodiments described in this application are merely some embodiments of this invention, and not all embodiments. Based on the spirit of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of this invention.

[0019] Synchronous coordination usually refers to the process where an inspection vehicle releases a drone to perform the current batch of inspection tasks after arriving at the parking point, waits at the parking point for the drone to complete its task and return for retrieval, and then the vehicle moves to the next parking point to continue its work.

[0020] However, vehicle-to-drone (V2D) synchronous collaborative inspection under extreme weather conditions still faces many challenges. Changes in wind speed, wind direction, and vertical wind shear often have a significant impact on UAV flight trajectories, mission accessibility, and energy consumption. Especially under strong wind disturbances, UAVs are prone to problems such as track deviation, reduced propulsion capability, and weakened endurance. Existing V2D collaborative inspection methods mostly focus on path planning or general task allocation, and do not adequately consider the coupling relationships between vehicle waiting in place, simultaneous UAV take-off and landing and simultaneous recovery, closed-loop execution of task batches, and energy replenishment constraints in synchronous collaborative modes, making it difficult to form a systematic scheduling method suitable for extreme weather scenarios.

[0021] Example 1 As an embodiment of this application, a specific implementation method for a vehicle-machine synchronous collaborative power grid inspection and scheduling method under extreme weather conditions is disclosed. The execution flow of the method embodiment is as follows: Figure 1 .

[0022] S1: As one implementation method of the embodiment, acquire task point data, vehicle parking point data, road network data, UAV parameter data and meteorological environment data of the inspection area; Meteorological environmental data should include at least wind speed, wind direction, wind shear information at height, and local gust disturbance information.

[0023] Furthermore, establish a set of inspection task points, a set of vehicle parking points, and a set of vehicle-mounted drones, specifically as follows: Let the set of inspection points be... , The total number of inspection points; among them, the first Task points Spatial coordinates are ; Let the set of vehicle parking points be , The total number of vehicle parking spots; among which, the first individual rest stops The position is recorded as ; Let the vehicle-mounted drones be assemblies. , This represents the total number of vehicle-mounted drones; among which, Indicates the first One drone.

[0024] Furthermore, at discrete time... Below, the vehicle's position is recorded as , No. The location of the drone is recorded as Define task completion status variables. If the task point At any moment If the inspection has already been completed by any drone, then... ,otherwise .

[0025] Then time The number of completed tasks is The corresponding task coverage rate is The final moment Total task coverage This indicates the percentage of task points that were completed after the entire vehicle-machine synchronous collaborative inspection process. When the time is right, it means that all inspection points have been completed; when This indicates that there are still unfinished inspection points.

[0026] S2: As one implementation method of the example, a dynamic wind field model, a UAV kinematic model, and an energy consumption and state of charge model under extreme weather conditions are constructed. 2.1 Construct an engineering wind field characterization model for UAV inspection and scheduling under extreme weather conditions.

[0027] Let the wind field vector field be , Indicates spatial location, then the drone's spatial location. The wind field received can be written as: Then the drone is in position The wind field at a location is written as: ; in, As background wind, The wind shear term varies with altitude. This represents the local gust disturbance term. All three terms represent three-dimensional wind speed vectors in the same ground coordinate system, with units of m / s and consistent physical dimensions.

[0028] In further explanation, the wind field model here is an engineered wind field representation model for UAV inspection and scheduling, not a complete meteorological numerical forecasting model. Its role is to provide environmental input for UAV mission reachability assessment, energy consumption estimation, SOC evolution, and return-to-home safety assessment.

[0029] Furthermore, background wind items The basic wind speed and direction information corresponding to the meteorological and environmental data summary is used to represent the dominant background wind in the inspection area; Corresponding altitude wind shear information is used to represent the wind speed increment caused by changes in the drone's flight altitude; This corresponds to local gust disturbance information, used to represent local wind speed changes caused by localized strong winds, sudden gusts, or terrain-induced wind bypass. All three items can be written in three-dimensional vector form, represented as follows: ; ; ; After the three factors are combined, the drone will be in position. The wind field at a location can be written as: ; in, , , The directional components are used to describe the effects of horizontal lateral, horizontal longitudinal, and vertical wind fields, respectively.

[0030] In one specific implementation, the background wind term can be determined based on wind speed and direction from meteorological data, for example... ;in, For a moment Background wind speed, Background wind direction angle.

[0031] The height wind shear term can be represented approximately linearly, for example... ;in, For high wind shear variables, This is the current altitude of the drone. For reference height. This is the wind shear direction angle.

[0032] The local gust disturbance term can be expressed as: ;in, The number of sources of gust disturbance; For the first The intensity of disturbance from each gust of wind. For the first The center of the gust, The area affected by gusts of wind. This refers to the frequency of gust disturbances; For the initial phase, This is the unit vector representing the direction of the gust.

[0033] In a further implementation, to ensure flight feasibility under extreme weather conditions, a maximum permissible wind speed threshold is set. When satisfied When this occurs, the corresponding drone inspection operation should be stopped.

[0034] Here, Indicates at time Spatial location The magnitude of the composite wind field velocity vector represents the actual composite wind speed experienced by the drone at its current location. Because... It is a three-dimensional wind speed vector, therefore its magnitude can be expressed as: ; , , These represent the components of the composite wind field in the three directions, respectively.

[0035] use The physical meaning is that the wind field affecting the drone does not originate from a single direction, but rather from the combined effect of background wind, wind shear, and local gusts, resulting in a composite wind speed. If this composite wind speed exceeds... This indicates that the current wind field has exceeded the permissible range for drone safety inspection operations. Continuing to carry out the mission may lead to track deviation, insufficient propulsion, excessive energy consumption, or an increased risk of returning to base. Therefore, it is necessary to stop the corresponding drone inspection operation.

[0036] In a further implementation, a kinematic model of the UAV considering the coupling effect of the wind field is constructed. Let the airspeed of the UAV be... According to the principle of velocity superposition, its ground velocity satisfies .

[0037] Furthermore, the principle of velocity superposition means that, in a fixed ground coordinate system, the actual speed of a drone relative to the ground is determined by the speed of the drone relative to the air and the wind speed relative to the ground.

[0038] In this application, the airspeed of the drone is denoted as... This represents the flight speed of the drone relative to the surrounding air mass; ground speed is denoted as... , representing the actual speed of the drone relative to the ground; the wind field at the current location is denoted as . This represents the wind speed relative to the ground at the current location. Therefore, the relationship between the three is: ; Under tailwind conditions, This will increase the drone's actual speed relative to the ground; under headwind conditions, It will reduce the drone's effective propulsion capability toward the target mission point; under crosswind conditions, This can cause lateral deviations in the drone's flight path. Therefore, the velocity superposition principle is used to explain how wind field disturbances affect the actual flight path of a drone.

[0039] Furthermore, the UAV position update satisfies the discrete update equation, expressed as: ; For the first The actual ground speed of the drone in the ground coordinate system. is the discrete time step.

[0040] Furthermore, let the current target task point be... Then the unit vector of the UAV along the target direction is : ; The effective propulsion speed of the UAV along the target direction is: ; When satisfied At that time, it was determined that the corresponding UAV was temporarily unreachable from the mission point under the current wind field conditions.

[0041] Furthermore, constraints are established: the UAV's flight process must satisfy maximum airspeed constraints, maximum climb or descent speed constraints, and trajectory smoothing constraints. These three constraints correspond to horizontal / three-dimensional flight speed capability, vertical maneuverability, and the magnitude of heading change between adjacent time points, thereby ensuring the physical feasibility of the UAV's flight trajectory under extreme weather conditions. Specifically: (1) Maximum airspeed constraint: This constraint is used to limit the horizontal / three-dimensional flight speed capability of a drone; its physical meaning is: airspeed vector. The modulus, which is the actual flight speed that the drone's own power system needs to provide, must not exceed the drone's maximum permissible airspeed. .

[0042] In further explanation, the power capability limitation of a drone refers to the overall magnitude of the velocity vector, rather than the velocity component in a single direction. Because a drone flies in three-dimensional space, its airspeed may simultaneously include... , , The vector has components in three directions, therefore the vector magnitude can comprehensively reflect the actual flight speed requirement of the UAV at the current moment. If... This indicates that the flight maneuver exceeds the maximum speed capability provided by the UAV's power system, making it difficult to execute in actual flight. Therefore, the trajectory or control command should be deemed infeasible.

[0043] (2) Maximum climb or descent speed constraint: This constraint is used to limit the vertical maneuverability of a drone; its physical meaning is: the vertical speed of the drone. The size does not exceed the safe vertical speed range of the drone. This refers to the maximum allowable ascent or descent speed for the drone.

[0044] Further explanation is needed, as the drone's ability to ascend or descend is limited by its vertical maneuverability. If... This indicates that the drone is climbing; if This indicates that the drone is descending. Since both ascent and descent must not exceed the drone's safe vertical speed range, a [specific speed range] is used. Simultaneously constrain the ascent and descent speeds. If This indicates that excessively rapid vertical maneuvering of the drone may lead to attitude instability, sudden increase in energy consumption, or increased landing safety risks.

[0045] (3) Track smoothing constraint: This constraint is used to limit the magnitude of the change in heading of the UAV between adjacent time points. The physical meaning of this constraint is: the UAV at time... heading angle and time heading angle The deviation between them shall not exceed the maximum allowable heading change angle between two adjacent discrete moments. .

[0046] In further explanation, This represents the magnitude of the heading change between two adjacent time steps, which is essentially the turning intensity of the drone's actual flight trajectory. If this difference is too large, it indicates that the drone needs to complete a sharp turn in a short period, easily leading to drastic changes in flight attitude, an uneven trajectory, increased control difficulty, and further increased energy consumption. Especially under strong winds or gusts, excessive heading changes can amplify the impact of wind disturbances on flight stability. Therefore, setting trajectory smoothing constraints can limit the maximum turning amplitude of the drone between adjacent time steps, ensuring that the drone's trajectory remains continuous, smooth, and executable even in extreme weather conditions.

[0047] In summary, the three constraints constrain the UAV's flight process from the aspects of speed capability, vertical maneuverability, and trajectory smoothness, respectively, with the aim of avoiding scheduling results that generate flight maneuvers that the UAV cannot actually perform.

[0048] 2.2 Constructing a model of UAV energy consumption and state of charge. Let the first... The instantaneous power of the drone is: ; In the formula, Basic hovering power; , and These are the correlation coefficients for airspeed, vertical velocity, and wind field disturbance, respectively. In the instantaneous power model, the airspeed, vertical velocity, and wind field disturbance terms are all used to reflect the speed-related energy consumption effects.

[0049] Drones in the area The cumulative energy consumption within is ; Assume the maximum battery energy of the drone is The remaining power is Its state of charge is then defined as: ; During a continuous flight interval without recharging, if the drone was fully charged at takeoff, the remaining battery power... This can be expressed as the maximum battery energy. Subtract the cumulative energy consumption this time If the battery was not fully charged before takeoff or if it was recharged en route, the remaining battery power will be... It should be the initial remaining power at the start time of this calculation minus the cumulative energy consumption within this interval. .

[0050] Energy evolution satisfies: ; That is, the state of charge (SOC) during the time interval The decrease within.

[0051] When the drone recharges on the vehicle platform, its state of charge is updated to: ; in, Energy replenishment rate per unit time This is for the time required to replenish energy.

[0052] Regarding the energy consumption and state of charge model for drones, it should be noted that in the cumulative energy consumption calculation formula, The definition is: the first unmanned The cumulative time interval of an aircraft in a continuous flight mission is the length of time from the start of this takeoff or the last refueling completion to the end of the current moment or the current recovery moment. Therefore, the cumulative energy consumption should correspond to the energy consumption within a single flight batch / takeoff and landing closed loop. If the UAV completes refueling at a certain parking point, the SOC after refueling is updated according to the refueling model, and the subsequent cumulative energy consumption is recalculated from the new starting moment, which is consistent with actual vehicle-mounted refueling scenarios.

[0053] S3: As one implementation method of the embodiment, a vehicle-machine synchronous collaborative inspection and scheduling model is established to uniformly model the set of inspection task points, the set of vehicle parking points, and the set of vehicle-mounted drones. 3.1 Establish a vehicle motion model.

[0054] Vehicles move on a road network, assuming the vehicle starts from a parking point. Drive to the parking point The shortest path length is The corresponding travel time is ; Average vehicle speed.

[0055] Assume the vehicle is at the parking point The length of stay is Its discrete expression is ; Indicates the vehicle is in individual rest stops Discrete dwell time is the discrete time step.

[0056] Because this application adopts a synchronous collaborative mode, the vehicle arrives at the parking point. The drone is then released to perform the current batch of tasks, and the system waits at the designated parking point for the drone to return and be retrieved after completing its mission. This reflects the length of waiting time required for the vehicle to complete the synchronous closed-loop operation at the current parking point.

[0057] In synchronous collaborative mode This is related to the drone's mission execution time, return time, recovery time, and recharging preparation time. If the drone's execution time at the current parking point is relatively long, then... Increase, corresponding The time spent by the vehicle will also increase; if the drone completes its mission and returns quickly, the time the vehicle spends will be shortened accordingly.

[0058] 3.2 Establish a vehicle-machine synchronous collaboration model.

[0059] For the rest stop For drones launched from a location, their takeoff and landing points and recovery and landing points satisfy the following: ; That is, the first Take-off and parking points for drones and recycling depot All are current vehicle parking points In other words, the drone takes off from its current parking point, completes its current mission, and then returns to the same parking point for recovery.

[0060] However, the vehicle-machine synchronization and cooperation model is not limited to this single spatial constraint. A complete synchronization and cooperation relationship includes the following meanings: First, the vehicle arrives at the parking point. Only after that can the drones be released to perform the current batch of tasks; Second, the A drone from its parking spot For takeoff, both the takeoff point and the recovery point must satisfy the following: ; Third, the vehicle remains stationary while the drone is performing its mission, and its position remains at its current parking point during this waiting phase. Vehicles should not leave in advance; Fourth, only when all drones released from the current docking point return... Only after the vehicle has been recovered can it be moved to the next parking location.

[0061] Therefore, the formula itself expresses the constraints of simultaneous takeoff and simultaneous recovery, while the synchronous coordination model also includes temporal logic such as vehicle waiting in place, batch execution of UAVs, UAV return and recovery, and vehicle relocation. This part can be interpreted as a combination of "spatial simultaneous constraint, temporal waiting constraint, and batch closed-loop execution".

[0062] Furthermore, let the radius of the task point determination be... This is used to determine whether the drone has successfully reached the mission point. When the condition is met... At that time, it was determined that the drone had successfully reached the mission point. . Indicates the first Current location of the drone With mission points The spatial distance between them. The value of is related to the field of view of the UAV inspection sensor, the shooting distance, the positioning error, and the accuracy of task point identification.

[0063] Furthermore, let the recovery radius be... This is used to determine whether the drone has entered the recoverable range of its current parking point. When the condition is met... At that time, the judgment of the first The drone enters the current parking point. Recyclable range. Indicates the first Current location of the drone Vehicle parking points The spatial distance between them. The value of is related to the vehicle platform size, the drone landing accuracy, the positioning error, and the safety buffer distance.

[0064] 3.3 Establish a vehicle-machine synchronous coordination constraint system.

[0065] (1) The minimum takeoff charge state threshold constraint must be met before the UAV takes off. ; Indicates the first The state of charge of a drone before takeoff, i.e., the percentage of its current remaining power relative to its maximum battery capacity; This represents the minimum state of charge threshold at which a drone is allowed to take off and perform inspection tasks.

[0066] This constraint means that the drone must have sufficient remaining power before taking off to perform a new mission. If This indicates that the first The drone currently has insufficient power and should not be assigned new inspection missions. It needs to continue recharging on the vehicle platform or remain docked. This constraint is designed to mitigate the risk of mission interruption, failed return-to-home, or forced landing caused by drones taking off with low power.

[0067] (2) The UAV meets energy security constraints during mission execution. , This indicates the minimum safe state of charge threshold that a drone must maintain during mission execution.

[0068] The meaning of this constraint is: The first Throughout the entire process of performing inspection missions, returning to base, and entering the recovery phase, the remaining battery percentage (i.e., state of charge) of the drone must not fall below a safe threshold. .if Below This indicates that the drone is approaching a low battery risk state and should not continue to perform new inspection tasks. It should return to base or enter the recharge process first.

[0069] The difference between minimum takeoff state of charge threshold constraints and energy security constraints lies in: Used to determine whether a drone is ready to take off and perform a new mission; Used to determine the minimum safe battery level of a drone during mission execution. The former is typically used before the mission begins, while the latter is used throughout the entire flight.

[0070] Example 2 In one embodiment, the workflow of this application is described based on the model and constraints constructed in S2-S3 above.

[0071] First, the engineered wind field characterization model for UAV inspection scheduling under extreme weather conditions constructed in this application plays the following role in vehicle-UAV collaborative inspection tasks: When the vehicle arrives at the parking point Afterwards, the drone corresponding to the current parking point... Take off and execute the mission assigned to the vicinity of the parking point. Before and during the execution of the task, it is necessary to consider the current wind field. Determine whether the drone meets the flight conditions.

[0072] First, regarding the task points , No. The drone's current location is The target direction unit vector is: ; The effective propulsion speed of the UAV along the target direction is: ; If satisfied This indicates that under the current wind conditions, the drone cannot fly towards the mission point. Effective progress has been made, but this mission point is currently inaccessible to drones.

[0073] Secondly, it is necessary to determine whether the wind field at the current location exceeds the maximum permissible wind speed threshold: ; If this condition is met, it means that the current wind speed exceeds the safe operating capability of the drone, and the corresponding drone inspection operation needs to be stopped.

[0074] Secondly, during mission execution, the UAV's state of charge needs to be updated based on the energy consumption model. The instantaneous power of the drone is: ; in, Based on basic hovering power, , and These are the correlation coefficients for airspeed, vertical motion, and wind field disturbance, respectively. It can be seen that the wind field term... This will directly affect the drone's instantaneous power, and thus the rate at which its SOC (State of Charge) decreases.

[0075] Based on the UAV energy consumption and state of charge model: Drones in the area The cumulative energy consumption within is ; state of charge is Energy evolution satisfies When the drone recharges on the vehicle platform, its state of charge is updated to: .

[0076] Therefore, wind field disturbances will pass through Simultaneously affects the effective propulsion speed of the drone. and power consumption When the wind is too strong, the mission objective may be temporarily unreachable; when the wind causes increased energy consumption, It will drop even faster, thus triggering energy security constraints. Or return-to-base recovery logic.

[0077] At the synchronization and coordination level, vehicles are at parking points. After releasing the drone, remain in place until all drones released at the current parking point have returned. The vehicle's dwell time is... If strong winds cause the drone's execution time to increase or its return time to increase, the vehicle's waiting time at the current parking point will be [reduced / decreased]. This increases accordingly. Therefore, wind field disturbances not only affect the flight status of drones, but also further affect vehicle synchronization waiting time and total mission completion time.

[0078] In summary, this application utilizes an engineering-based wind field characterization model. Effective speed of advancement Power consumption State of charge The vehicle's dwell time is Variables such as these are used to embed the impact of extreme weather into the synchronous closed-loop scheduling process of "task reachability judgment → energy consumption update → SOC safety constraint → same-point recycling → vehicle waiting".

[0079] S4. Divide the inspection tasks into batches. Execute collaborative inspection tasks and conduct collaborative inspections for evaluation.

[0080] 4.1 Based on the spatial relationship between task points and parking points, the task points to be inspected are divided into task batches corresponding to each parking point; forming a set of task points to be inspected, a set of vehicle parking points, and the spatial relationship between task points and parking points as constructed in S1.

[0081] In one specific implementation, the task batching method can employ spatial clustering. The following is a reference example: For each task point Calculate the distance from each animal to all parking spots and assign it to the nearest parking spot. Forming task batches : ; This represents the total number of vehicle parking spots.

[0082] 4.2 Referring to the collaborative operation process described in Example 2, the drones released from the current parking point perform the corresponding batch of inspection tasks and return to the current parking point after completing the batch of tasks; until all parking points have completed their batch of tasks.

[0083] Furthermore, task completion time and load balancing metrics are introduced to evaluate the synchronous collaborative inspection process.

[0084] Specifically, set task points The inspection task is completed at the following time. The total task completion time is , This represents the total number of inspection points to be inspected.

[0085] Let the first The number of mission points ultimately completed by the drone was The average workload of each drone is , Let be the total number of vehicle-mounted drones. Then, define the task load balancing metric as follows: .

[0086] In further explanation, the first The number of task points finally completed by a drone represents the actual number of task points that the drone completed during flight inspections. It is a statistical result after the total task points are distributed among the drones.

[0087] Define the minimum state of charge index of the system as ; Furthermore, considering task coverage, total task completion time, minimum system state of charge, and load balancing, the scheduling objective vector is constructed as follows: ; in, These are the parameters to be optimized. They should include at least one or more of the following: vehicle parking time parameter, mission point determination radius parameter, UAV minimum takeoff charge state parameter, recovery radius parameter, and recharge rate parameter.

[0088] The scheduling target vector contains four aspects of scheduling objectives: (1) This corresponds to maximizing the final task coverage. Since optimization problems can usually be written in minimization form, we use... This represents maximizing task coverage. See S1. .

[0089] (2) This corresponds to minimizing the total task completion time.

[0090] (3) This corresponds to maximizing the minimum state of charge of the system. Since we want the minimum charge to be as high as possible, it is written in the minimization objective vector as... .

[0091] (4) This corresponds to minimizing the imbalance in drone mission load. The smaller the value, the more balanced the task allocation among the drones; The larger the value, the more tasks some drones are assigned, while others are assigned fewer tasks.

[0092] The scheduling objective of this application is to achieve, while meeting the constraints of wind farm safety, energy safety, simultaneous take-off and landing recovery, and vehicle synchronous waiting, the highest possible mission coverage, the shortest possible mission completion time, the highest possible minimum SOC, and the most balanced UAV load.

[0093] Furthermore, for different For each group, the values ​​are used for simulation or search. This corresponds to a specific synchronization and coordination scheduling scheme. Each synchronization and coordination scheduling scheme is executed according to the process described in Example 2 to obtain the corresponding... , , and And the target vector is scheduled by the target vector. Evaluation of the merits and demerits of the scheme.

[0094] In one implementation, priority screening can be used in engineering applications. and The preferred approach is to select the solution that completes all tasks and whose minimum SOC (State of Charge) does not fall below the safety threshold. Then, from among the candidate solutions that meet the above safety conditions, a final selection is made. Smaller The smaller solution is used as the final synchronous collaborative inspection and scheduling result.

[0095] If extreme weather conditions do not exist and The proposed solution should be downgraded according to the principle of safety priority, that is, prioritizing the protection of [the system / entity]. Secondly, improve Consider shortening it again. and reduce This ensures that, under extreme weather conditions such as strong winds, the dispatching results will not simply pursue coverage or efficiency, but will also take into account the safe return of drones and the synchronous closed-loop execution of vehicles and drones.

[0096] In one reference implementation, a power distribution network inspection simulation scenario is constructed to simulate and verify the vehicle trajectory, UAV 3D trajectory, planar projection trajectory, dynamic evolution of task progress, UAV swarm charge state, and state timing during the synchronous and collaborative inspection process.

[0097] In one embodiment, to verify the effectiveness of the vehicle-drone synchronous collaborative power grid inspection and scheduling method proposed in this invention under extreme weather conditions, a power distribution network inspection simulation scenario was constructed in the experimental part. Task points, vehicle parking points, and road networks were set up within the inspection area, and verification was conducted using a synchronous collaborative operation method where inspection vehicles are equipped with multiple drones. In the synchronous collaborative mode, after the inspection vehicle arrives at the current parking point, it releases drones to execute the corresponding batch of inspection tasks and waits at that parking point. After all drones released at the current parking point have completed their tasks and returned for retrieval, the inspection vehicle then moves to the next parking point to continue executing subsequent inspection tasks. The synchronous collaborative scheduling process is as follows: Figure 1 As shown.

[0098] In this implementation case, the simulation scenario selects a typical urban power distribution network inspection area, with a geographical range of 11.5km × 6.9km. The scenario includes 52 simulated pole / tower task points and 4 key stopping points. The inspection vehicle travels along a predetermined road network, and the vehicle-mounted platform carries 4 industrial-grade drones. All drones operate at a uniform inspection height of 20m during the inspection process. To reflect the impact of extreme weather on synchronous and collaborative inspection, wind field disturbances are introduced into the simulation, and the traditional vehicle-drone synchronous and collaborative operation process is analyzed.

[0099] Figure 2 This is a three-dimensional trajectory diagram for the conventional vehicle-machine synchronous cooperative simulation of this invention. (From...) Figure 2 As can be seen, in the synchronous collaborative mode, inspection vehicles move sequentially between various parking points according to a preset road network, while drones take off from their current parking point to perform inspection tasks within the corresponding area and return to their original parking point for recovery after completing their tasks. Since the vehicles remain in a waiting state while the drones are performing their tasks, the synchronous coordination between vehicle parking and drone takeoffs and landings is clearly reflected in the 3D trajectory. This method features clearly defined takeoff and landing locations, a clear recovery relationship, and a stable scheduling process, and can effectively reflect the operational mechanism of traditional synchronous collaborative inspections.

[0100] Figure 3 This is a planar projection diagram of the conventional vehicle-machine synchronous cooperative simulation of the present invention. Figure 3As can be seen, the inspection vehicle proceeds sequentially to each parking point on the planar road network. The drone performs its corresponding batch of inspection tasks around the current parking point. The task execution range is mainly constrained by the current parking point location, the drone's endurance, and recovery conditions. Unlike the asynchronous collaborative mode, in the synchronous collaborative mode, the drone must return to its original parking point after completing the current task before the vehicle can continue to the next parking point. Therefore, the batch-based inspection characteristic centered on the parking points can be clearly shown in the planar projection diagram. This result indicates that although the synchronous collaborative mode is clearer in terms of organization and management, vehicle waiting time can limit the overall operational efficiency to some extent.

[0101] Figure 4 This is a dynamic evolution diagram of the progress of the traditional vehicle-machine synchronous collaborative task according to the present invention. Figure 4 As can be seen, during the synchronous collaborative inspection process, the task completion progress gradually increases over time. However, because the vehicles must wait for all drones in the current batch to complete their tasks and be recovered before they can be moved, the task progress curve exhibits a relatively obvious phased characteristic. The task completion rate slows down in stages during vehicle waiting and drone return; however, the task completion rate is relatively fast during the peak drone execution phase. This phenomenon indicates that the synchronous collaborative mode can ensure a complete closed loop in the task execution process, but its serialized waiting mechanism leads to an increase in the total task completion time.

[0102] Figure 5 This is a charge state diagram for a conventional vehicle-machine synchronized and cooperative unmanned aerial vehicle swarm, as described in this invention. Figure 5 It is evident that the rate of SOC decline varies among different UAVs during inspections due to differences in task distance, wind conditions, and flight time. During the inspection mission, the UAV's SOC continuously decreases; after returning to its original parking point and recharging, the SOC begins to recover, exhibiting a clear alternating charging and discharging characteristic. In the synchronous collaborative mode, since all UAVs return to their original parking points for recovery, their recharging process closely corresponds to the vehicle's parking process, effectively ensuring UAV operational safety and mission closed-loop execution. Particularly under strong wind conditions, the SOC decline is more pronounced, indicating that extreme weather significantly increases UAV flight energy consumption and further impacts the operation duration and energy margin of synchronous collaborative inspections.

[0103] Figure 6 This is a timing diagram showing the state of a conventional vehicle-machine synchronized and cooperative unmanned aerial vehicle (UAV) according to the present invention. Figure 6It is evident that the UAV primarily experiences three states during the inspection process: execution, return, and docking. These states cycle through each other in the sequence of "takeoff and execution—return and recovery—parking and recharging—execution again." Due to the synchronous collaborative mode, the vehicle does not move until the UAV returns and is recovered. Therefore, the UAV state transitions strictly correspond to the vehicle's parking process, resulting in a highly regular and manageable overall state evolution. This result indicates that traditional vehicle-UAV synchronous collaborative inspection has good stability in terms of task organization and state control; however, due to the constraints of the vehicle waiting in place and the UAV's simultaneous recovery, the overall task completion time is relatively long.

[0104] Furthermore, comparing the traditional vehicle-machine synchronous collaborative mode with the asynchronous collaborative mode, it can be seen that, under the condition of ensuring 100% task coverage, the task completion time of the synchronous collaborative mode is 6940s and 12000s under windless and 10m / s wind speed conditions, respectively, with minimum state of charge of 53.82% and 20.04%, respectively. This result indicates that the traditional synchronous collaborative mode has high operational stability and a clearer operational closed loop; however, under extreme weather conditions, the serial time loss caused by vehicle waiting and drone recovery is quite significant.

[0105] In summary, this implementation case verifies that the vehicle-machine synchronous collaborative inspection and scheduling method of the present invention can realize the synchronous cooperation between inspection vehicles and drones under extreme weather conditions. It can clearly reflect the coupling relationship between vehicle parking, drone take-off and landing at the same point and recovery at the same point, closed-loop execution of task batches, and refueling process, providing an implementation basis for the subsequent engineering application of the synchronous collaborative inspection and scheduling method.

[0106] As an embodiment of this application, a vehicle-machine synchronous collaborative power grid inspection and dispatching system under extreme weather conditions is disclosed. Employing the specific implementation method described above for power grid inspection and dispatching, the system includes: The wind field coupling modeling module is used to construct a wind field characterization model for UAV inspection and scheduling under extreme weather conditions, and to calculate the wind field experienced by the UAV at its current location; it also establishes a UAV kinematic model that takes into account wind field coupling, and derives the UAV ground speed based on the wind field characterization model. Energy consumption modeling module; used to calculate the instantaneous power of the UAV based on the UAV flight state and wind field characterization model, and to infer the energy evolution of the UAV in combination with the UAV's state of charge; calculate the effective propulsion speed of the UAV based on the ground speed of the UAV and the direction of the mission target, used to determine whether the mission point is reachable; Vehicle-to-machine (V2M) collaboration module; used to establish a synchronous collaboration relationship between the vehicle and the drone, spatially limiting the drone to take off and recover at the same parking point, and temporally limiting the vehicle to remain waiting during the drone mission; setting minimum state of charge constraints and safe state of charge constraints; The scheduling scheme optimization module is used to establish a set of task points, vehicle parking points, and vehicle-mounted drones in the inspection area; spatial clustering is used to assign each task point to the nearest parking point for executing inspection tasks; a multi-objective optimization function including task coverage, task completion time, charge state, and task load balance is constructed to solve for the optimal scheduling scheme.

[0107] As an embodiment of this application, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is loaded onto the processor, it employs the specific implementation method described above for the power grid inspection and scheduling method.

[0108] As an embodiment of this application, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, it adopts the specific implementation method described above for the power grid inspection and scheduling method.

[0109] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0110] This disclosure can be a system, method, and / or computer program product. A computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of this disclosure.

[0111] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example—but not limited to—electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination of the foregoing. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0112] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0113] Computer program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing the status information of the computer-readable program instructions to implement various aspects of this disclosure.

[0114] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the protection scope of the claims of the present invention.

Claims

1. A method for synchronous and coordinated power grid inspection and scheduling of vehicles and machinery under extreme weather conditions, characterized in that, include: A wind field characterization model for UAV inspection and scheduling under extreme weather conditions is constructed to calculate the wind field experienced by the UAV at its current location. A kinematic model of the UAV considering wind field coupling is established, and the ground velocity of the UAV is derived by combining the wind field characterization model. The instantaneous power of the UAV is calculated based on the UAV flight state and wind field characterization model, and the energy evolution of the UAV is deduced by combining the UAV's state of charge; the effective propulsion speed of the UAV is calculated based on the UAV's ground speed and the direction of the mission target, which is used to determine whether the mission point is reachable; Establish a synchronous and collaborative relationship between vehicles and drones, spatially restricting drones to take off and recover at the same parking point, and temporally restricting vehicles to remain waiting during drone mission execution; set minimum state of charge constraints and safe state of charge constraints; Establish a set of task points, vehicle parking points, and vehicle-mounted drones for the inspection area; Spatial clustering is used to assign each task point to the nearest parking point for performing inspection tasks; a multi-objective optimization function including task coverage, task completion time, charge state, and task load balance is constructed to solve for the optimal scheduling scheme.

2. The method for synchronous and coordinated power grid inspection and scheduling of vehicles under extreme weather conditions according to claim 1, characterized in that, The wind field characterization model includes: Let the wind field vector field be Used to indicate the time when the drone is Spatial location The synthetic wind field velocity at the location; then the UAV's spatial position The wind field is the sum of the background wind term, the wind shear term, and the local gust disturbance term; Set the maximum allowable wind speed threshold When satisfied When this happens, the corresponding drone inspection operation shall be suspended; Indicates at time Spatial location The magnitude of the composite wind field velocity vector.

3. The method for synchronous and coordinated power grid inspection and scheduling of vehicles and machinery under extreme weather conditions according to claim 1, characterized in that, The UAV kinematic model that takes into account wind field coupling includes: Let the airspeed of the drone be... Then the ground speed of the UAV is the sum of its airspeed and the combined wind speed; No. drones in the future The position is the current location coordinates plus the time interval of the drone. Displacement within; the displacement is a time interval The product of the drone's ground speed and the ground speed.

4. The method for synchronous and coordinated power grid inspection and dispatching under extreme weather conditions according to claim 1, characterized in that, The calculation process for the energy evolution of the unmanned aerial vehicle includes: The instantaneous power of the UAV is a weighted sum of the UAV's basic hovering power, the square of its airspeed, the square of its vertical motion velocity, and the square of the velocity modulus of the synthesized wind field. Integrating the instantaneous power over the time interval yields the cumulative energy consumption; then the UAV at time [time value missing]... The state of charge is defined as the ratio of the remaining charge to the maximum battery capacity of the drone. The energy evolution of drones can then be used to predict drone energy in future moments. The state of charge is represented and calculated as follows: First, the state of charge (SOC) is calculated based on the instantaneous power and the drone's maximum battery energy over a time interval. The rate of descent within the time frame, and then the drone's position at any given moment. Subtracting the decrease in charge from the state of charge of the UAV at the future time, we obtain the state of charge of the UAV at the future time. The state of charge.

5. The method for synchronous and coordinated power grid inspection and dispatching under extreme weather conditions according to claim 1, characterized in that, The process for determining whether a task point is reachable includes: For task points Calculate its relationship with the first The drone's current location is The target direction unit vector; Interchange the target direction unit vector with the... Multiply the ground speed of the drone to obtain the effective propulsion speed of the drone along the target direction; If the effective propulsion speed is less than or equal to 0, then the mission point is determined. Unreachable.

6. The method for synchronous and coordinated power grid inspection and scheduling of vehicles and machinery under extreme weather conditions according to claim 1, characterized in that, The minimum state of charge constraint and the safe state of charge constraint include: The minimum state of charge constraint is described as follows: the state of charge of the UAV before takeoff is not lower than the minimum state of charge threshold for the UAV to take off and perform the inspection mission. The safe state of charge constraint is described as follows: the state of charge of the UAV during mission execution is not lower than the minimum safe state of charge threshold.

7. The method for synchronous and coordinated power grid inspection and scheduling of vehicles and machinery under extreme weather conditions according to claim 1, characterized in that, The multi-objective optimization function includes: Maximize total task coverage; the total task coverage is calculated as the ratio of the number of completed tasks to the total number of task points at the final task completion time. Minimize the total task completion time; the maximum completion time of the inspection task among all task points; Maximize the minimum state of charge of the system; Maximize the degree of drone task load balancing, where the degree of task load balancing is the variance of the number of tasks performed by all drones.

8. A vehicle-machine synchronous collaborative power grid inspection and dispatching system under extreme weather conditions, executing the power grid inspection and dispatching method as described in any one of claims 1-7, characterized in that, The system includes: The wind field coupling modeling module is used to construct a wind field characterization model for UAV inspection and scheduling under extreme weather conditions, and to calculate the wind field experienced by the UAV at its current location; it also establishes a UAV kinematic model that takes into account wind field coupling, and derives the UAV ground speed based on the wind field characterization model. Energy consumption modeling module; used to calculate the instantaneous power of the UAV based on the UAV flight state and wind field characterization model, and to infer the energy evolution of the UAV in combination with the UAV's state of charge; calculate the effective propulsion speed of the UAV based on the ground speed of the UAV and the direction of the mission target, used to determine whether the mission point is reachable; Vehicle-to-machine (V2M) collaboration module; used to establish a synchronous collaboration relationship between the vehicle and the drone, spatially limiting the drone to take off and recover at the same parking point, and temporally limiting the vehicle to remain waiting during the drone mission; setting minimum state of charge constraints and safe state of charge constraints; The scheduling scheme optimization module is used to establish a set of task points, vehicle parking points, and vehicle-mounted drones in the inspection area; spatial clustering is used to assign each task point to the nearest parking point for executing inspection tasks; a multi-objective optimization function including task coverage, task completion time, charge state, and task load balance is constructed to solve for the optimal scheduling scheme.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the computer program is loaded into the processor, it implements the power grid inspection and scheduling method according to any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the power grid inspection and scheduling method according to any one of claims 1-7.

Images