Methods, devices, electronic equipment and storage media for drone inspection tasks

Abstract

This invention provides a method, apparatus, electronic device, and storage medium for allocating drone inspection tasks, relating to the field of drone inspection technology. The method includes: determining candidate inspection tasks based on the target drone's current available power and estimated flight power consumption; calculating the distance between the inspection starting point of each candidate task and a given hangar, selecting at least one hangar with the shortest distance as the set of hangars to be allocated; constructing an objective function, the objective function being optimized by maximizing the ratio of task priority to total task time, and incorporating battery life loss as a penalty factor; wherein the total task time includes the target drone's task execution time and return time; solving the objective function, and outputting an inspection task allocation scheme. This invention collaboratively optimizes inspection tasks and charging scheduling within the same decision-making framework, achieving inspection tasks and drone return without relying on pre-defined flight paths, effectively avoiding path planning redundancy, thereby significantly improving inspection efficiency.

Description

Technical Field

[0001] This invention relates to the field of drone inspection technology, and in particular to a drone inspection task allocation method, device, electronic equipment and storage medium. Background Technology

[0002] With the maturation of drone technology and the expansion of its application areas, drones are being used more and more widely in areas such as power line inspection, infrastructure monitoring, and environmental monitoring. These tasks typically require drones to be performed regularly or on demand to ensure timely detection and handling of problems.

[0003] Existing methods for allocating drone inspection tasks typically rely on preset routes to complete inspection tasks and drone return, which can easily lead to redundancy in path planning and result in low inspection efficiency. Summary of the Invention

[0004] This invention provides a method, apparatus, electronic device, and storage medium for allocating drone inspection tasks, in order to solve the technical problem that the existing technology relies on preset routes to complete inspection tasks and drone return, which easily leads to path planning redundancy and low inspection efficiency.

[0005] This invention provides a method for allocating unmanned aerial vehicle (UAV) inspection tasks, including: Candidate inspection tasks are determined based on the target drone's current available power and estimated flight power consumption. Calculate the distance between the starting point of the candidate inspection task and each hangar, and select at least one hangar with the shortest distance as the hangar set to be assigned; An objective function is constructed, which aims to maximize the ratio of task priority to total task time and incorporates battery life loss as a penalty factor; wherein, the total task time includes the task execution time and return time of the target UAV. Solve the objective function and output the inspection task allocation scheme.

[0006] According to a method for allocating drone inspection tasks provided by the present invention, before determining candidate inspection tasks based on the drone's current available power and estimated flight power consumption, the method further includes: The battery health status of the target drone is calculated using a battery health model. Based on the battery health status, calculate the current available power of the target drone and the estimated flight power consumption for each inspection mission.

[0007] According to a method for allocating unmanned aerial vehicle (UAV) inspection tasks provided by the present invention, the step of determining candidate inspection tasks based on the current available power and estimated flight power consumption of the target UAV includes: For each inspection task, inspection tasks whose estimated flight power consumption is less than or equal to the current available power are selected as candidate inspection tasks.

[0008] According to a method for allocating drone inspection tasks provided by the present invention, the determination of battery life loss includes: The battery life loss of the target drone is determined based on the number of cycles used and the total cycle life of the target drone's battery.

[0009] According to the UAV inspection task allocation method provided by the present invention, after solving the objective function and outputting the inspection task allocation scheme, the method further includes: Using flight altitude and flight speed as decision variables, and the benefits of the safety party and the energy consumption party as decision variables, the desired flight altitude and desired flight speed are obtained by solving the Nash equilibrium through a hybrid strategy. The optimized inspection task allocation scheme is then optimized using the desired flight altitude and desired flight speed to obtain the optimized inspection task allocation scheme.

[0010] According to the UAV inspection task allocation method provided by the present invention, the safety party's benefit is determined based on the task failure probability, risk penalty factor, and risk exposure; the energy consumption party's benefit is determined based on the total flight energy consumption, delay penalty factor, and inspection delay.

[0011] According to the UAV inspection task allocation method provided by the present invention, after solving the objective function and outputting the inspection task allocation scheme, the method further includes: According to the inspection task allocation scheme, the inspection task is issued to the corresponding UAV. If the route switching condition is met during the UAV's inspection task, the current inspection task is switched to the preset safe route. The route switching condition includes at least one of the following: location data loss, wind speed growth rate greater than a preset threshold, and communication link termination.

[0012] The present invention also provides a drone inspection task allocation device, comprising: The flight data determination module is used to determine candidate inspection tasks based on the target UAV's current available power and estimated flight power consumption. The hangar determination module is used to calculate the distance between the starting point of the candidate inspection task and each hangar, and select at least one hangar with the shortest distance as the hangar set to be assigned. The objective function construction module is used to construct an objective function, which aims to maximize the ratio of task priority to total task time and incorporates battery life loss as a penalty factor; wherein, the total task time includes the task execution time and return time of the target UAV. The inspection task allocation module is used to solve the objective function and output the inspection task allocation scheme.

[0013] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the UAV inspection task allocation method described above.

[0014] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the UAV inspection task allocation method as described above.

[0015] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the UAV inspection task allocation method described above.

[0016] Based on a determined hangar to be allocated, this invention uses the sum of the target UAV's task execution time and return time as the total task time. The total task time takes into account the UAV's return and charging time after completing the inspection task, and constructs an objective function. The objective function aims to maximize the ratio of task priority to total task time, and incorporates battery life loss as a penalty factor. This effectively optimizes the return and charging path, thereby co-optimizing the inspection task and charging scheduling under the same decision framework. It achieves the inspection task and UAV return without relying on a set route, effectively avoiding path planning redundancy, and thus effectively improving inspection efficiency.

[0017] Furthermore, by switching to a preset safe flight path and adjusting flight speed and altitude when encountering emergencies, the present invention enables both the human and the machine to continue performing tasks through a downgrade strategy, still completing most of the predetermined inspection tasks and reducing downtime. Attached Figure Description

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

[0019] Figure 1 This is a flowchart illustrating the drone inspection task allocation method provided by the present invention.

[0020] Figure 2 This is a schematic diagram of the security-energy consumption game model provided by the present invention.

[0021] Figure 3This is the fault-tolerant degradation control timing diagram provided by the present invention; Figure 4 This is a schematic diagram of the structure of the drone inspection task allocation device provided by the present invention.

[0022] Figure 5 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0023] 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. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0024] Figure 1 This is a flowchart illustrating the drone inspection task allocation method provided by the present invention, as shown below. Figure 1 As shown, the method includes the following: S1. Determine candidate inspection tasks based on the target drone's current available power and estimated flight power consumption; In this embodiment of the invention, the current available power of the target drone is actually the remaining power of the target drone, which is used to support the drone's flight time; the estimated flight power consumption is the power consumed by the drone during its flight path while performing each inspection task.

[0025] In this embodiment of the invention, the flight time of the target drone can be determined based on the battery health status detection data, and a list of inspection tasks to be assigned can be obtained. The estimated power consumption during flight is then determined based on the flight paths of the inspection tasks. Each inspection task is assigned a priority. For example, higher-level inspection tasks have higher priority values, and lower-level inspection tasks have lower priority values, reflecting the urgency of the inspection tasks based on the priority values.

[0026] In this embodiment of the invention, for each target UAV, there may be multiple candidate inspection tasks.

[0027] S2. Calculate the distance between the starting point of the candidate inspection task and each hangar, and select at least one hangar with the shortest distance as the hangar set to be assigned. In this embodiment of the invention, the starting point of the inspection for the flight path can be determined in the candidate inspection task. Typically, the starting point of the inspection can be the starting flight point of the UAV, which may include a hangar and other stopping points.

[0028] In this embodiment of the invention, the distance between the starting point of each candidate inspection task and each hangar in the surrounding area can be determined. These distances are then sorted from shortest to longest, and the hangars at the top of the sorted list are selected as the hangar set to be assigned. For example, the hangar ranked first or the top three hangars can be selected as the hangar set to be assigned.

[0029] For each candidate inspection task, this embodiment of the invention can select multiple hangars that meet the conditions as a set of hangars to be assigned, avoiding the situation where the corresponding flight route cannot be assigned an inspection task due to some reason when only one hangar is selected, thereby ensuring planning redundancy and ensuring that the inspection task can be executed.

[0030] In this embodiment of the invention, the hangars in the designated hangar cluster serve as the return locations for drones after completing their inspection tasks, ensuring safe landing and necessary maintenance or charging upon completion. By selecting the hangar closest to the starting point as the drone's return location, this embodiment ensures sufficient return times for charging or maintenance during mission execution, and increases the probability of a safe return even in the event of unforeseen circumstances.

[0031] S3. Construct an objective function, which aims to maximize the ratio of task priority to total task time and incorporates battery life loss as a penalty factor; wherein, the total task time includes the task execution time and return time of the target UAV. In this embodiment of the invention, the expression of the objective function is as follows:

[0032] Where Z is the objective function, i is the task index, n is the total number of tasks, and P i Let T be the priority of task i. i D represents the total task time for task i. i This represents the current battery life loss of the drone corresponding to task i. It is a weighting factor used to balance the relationship between task priority and battery life loss.

[0033] By maximizing the ratio of task priority to total task time, this invention can ensure that more high-priority tasks are completed within a limited time, thereby improving overall task execution efficiency. Furthermore, by balancing the relationship between task priority and battery life loss through weighting coefficients, a suitable balance point is obtained, which optimizes both task allocation and battery life of the drone.

[0034] S4. Solve the objective function and output the inspection task allocation scheme.

[0035] In this embodiment of the invention, the objective function can be solved using MILP (Mixed Integer Linear Programming) to output the inspection task allocation scheme.

[0036] The inspection task in the inspection task allocation scheme output by the embodiment of the present invention includes the flight route of the UAV from the inspection start point to the inspection end point, and then from the inspection connection point to the return point. The return point is the location of the hangars to be allocated.

[0037] Based on the determination of the hangar to be allocated, this embodiment of the invention uses the sum of the target UAV's task execution time and return time as the total task time. The total task time takes into account the UAV's return and charging time after completing the inspection task, and constructs an objective function. The objective function aims to maximize the ratio of task priority to total task time, and combines battery life loss as a penalty factor. This can effectively optimize the return and charging path, thereby co-optimizing the inspection task and charging scheduling under the same decision framework. It achieves the inspection task and UAV return without relying on a set route, effectively avoiding path planning redundancy, and thus effectively improving inspection efficiency.

[0038] In one embodiment, before step S1, which determines candidate inspection tasks based on the drone's current available power and estimated flight power consumption, the method further includes: The battery health status of the target drone is calculated using a battery health model. Based on the battery health status, calculate the current available power of the target drone and the estimated flight power consumption for each inspection mission.

[0039] In this embodiment of the invention, a comprehensive data interface system can be constructed first. This system can seamlessly connect with multiple data sources, such as meteorological departments, airspace management departments, and hangar operation monitoring systems. Through these interfaces, the system can acquire a series of key data in real time. From a meteorological perspective, it can accurately acquire wind speed and direction information, as wind speed and direction directly affect the drone's flight attitude and energy consumption. Simultaneously, it collects temperature data, as temperature changes affect the drone's performance and battery status. From an airspace management perspective, real-time updates on no-fly zone information are crucial for ensuring the legal and compliant flight of drones. The system can promptly acquire the scope and changes of no-fly zones, thus providing accurate data for drone flight path planning. Furthermore, hangar information is also included in the data collection scope, including the status of equipment within the hangar and the storage environment. This hangar information is beneficial for the maintenance and storage of drones.

[0040] Meanwhile, the data interface system also collects various important data uploaded by the drone terminal. Specifically, this includes battery temperature, as excessively high or low temperatures can affect performance and lifespan; the number of battery cycles is also recorded, as battery performance gradually declines with increasing cycle count; the current State of Charge (SOC) is a key indicator for real-time monitoring, directly related to the drone's ability to complete its intended flight mission; furthermore, the drone's historical flight trajectory data is collected and stored in a time-series database. This database stores this data chronologically, facilitating subsequent analysis and tracking of the drone's flight status. For example, analyzing historical flight trajectories can assess the drone's flight efficiency and identify any abnormal flight behaviors.

[0041] In battery management, firstly, a battery health model is used to assess and predict battery state. This model can be based on two methods: Kalman filtering and regression analysis. Kalman filtering is a highly efficient self-recursive filter that can estimate the dynamic state of the system from a series of noisy measurements. It is suitable for dynamic battery changes and can estimate and correct the internal state of the battery in real time. Regression analysis can establish a relationship model between battery performance parameters and various influencing factors based on existing data, thereby predicting the future state of the battery. This embodiment of the invention combines these two methods to calculate the battery's SOH (State of Health). SOH is a comprehensive indicator reflecting battery performance, including capacity retention, internal resistance changes, and other aspects. Based on the SOH calculation results, the system can automatically update the remaining usable capacity of the battery, thereby rationally scheduling flight time and missions according to the remaining capacity; at the same time, it can also update the battery's lifetime distribution, that is, predict the performance degradation of the battery at different points in the future, providing a scientific basis for battery replacement and maintenance.

[0042] To further improve the accuracy of battery remaining capacity prediction, this embodiment of the invention periodically calibrates the parameters of the battery health model to avoid the need for continuous adjustment of model parameters to adapt to new situations due to changes in battery usage environment, operating mode, and other factors over time.

[0043] Since temperature has a significant impact on the chemical reactions and performance of batteries, a temperature control factor can be introduced during the calibration process. By taking temperature control into account, the remaining capacity of the battery under different temperature conditions can be predicted more accurately. At the same time, since different discharge rates lead to different rates of capacity decay, a discharge rate factor can also be introduced. By taking into account the influence of the discharge rate, the prediction results can be made closer to actual usage conditions.

[0044] In one embodiment, step S1, determining candidate inspection tasks based on the target drone's current available power and estimated flight power consumption, includes: For each inspection task, inspection tasks whose estimated flight power consumption is less than or equal to the current available power are selected as candidate inspection tasks.

[0045] In this embodiment of the invention, to ensure that the drone can complete its mission within a limited battery capacity while making full use of the battery, it is necessary to accurately assess and filter the power consumption along the flight path. Specifically, for each inspection mission, the estimated power consumption of the mission is calculated, i.e., the power required to complete the entire flight mission. Simultaneously, based on the drone's battery health status (such as remaining available capacity, battery health, etc.), the current available power of the drone is calculated, i.e., the maximum flight power that the drone can support under the current battery condition.

[0046] When selecting flight paths, inspection tasks whose estimated power consumption is less than or equal to the current available power are considered as candidate inspection tasks. Although these candidate inspection tasks may be close to or reach the limit of the drone's battery in terms of power consumption, they are still within the drone's flight capability range. This embodiment of the invention, by determining candidate inspection tasks based on estimated power consumption and current available power, ensures that the drone will not make an emergency landing due to insufficient power during mission execution, while also making full use of the remaining battery power and avoiding power waste.

[0047] By selecting paths where the estimated power consumption for flight is less than or equal to the current available power, this invention ensures that the drone has sufficient power to complete the entire flight mission, thereby effectively improving the mission completion rate and avoiding mission failure due to insufficient power.

[0048] In one embodiment, determining the battery life loss includes: The battery life loss of the target drone is determined based on the number of cycles used and the total cycle life of the target drone's battery.

[0049] In this embodiment of the invention, relevant data about the target drone battery can be collected to determine battery life degradation, including the number of used cycles and total cycle life. The number of used cycles refers to the number of charge-discharge cycles the battery has completed since it was put into use. Each charge-discharge cycle has a certain impact on the battery's internal structure and chemical properties, leading to a gradual decline in battery performance. Total cycle life, on the other hand, is the theoretically maximum number of charge-discharge cycles that the battery can complete, as determined during the design and testing phases. Total cycle life is usually provided by the battery manufacturer and is an important reference indicator for evaluating battery life.

[0050] This invention, through comparing these two parameters, allows us to determine the degree of battery life degradation of a target drone. Specifically, it calculates the ratio of the number of cycles used to the total cycle life. For example, if a battery's total cycle life is 1000 cycles, and it has already been used 500 times, then the battery's lifespan degradation can be considered to have reached 50%. This calculation method is simple and intuitive, quickly providing a rough estimate of battery life degradation.

[0051] Furthermore, to more accurately assess battery life loss, the actual usage environment and operating conditions of the battery can be considered. For example, if a battery frequently operates in high or low temperature environments, or frequently undergoes high-rate charging and discharging, its actual lifespan may be shorter than its theoretical lifespan. Therefore, when calculating life loss, appropriate correction factors for environmental factors and operating conditions can be introduced to make the assessment results more accurate.

[0052] This invention, through comparison of the number of cycles used and the total cycle life, can quickly and accurately assess the degree of battery life loss. Based on the assessment results, it can provide early warning that the battery is about to reach the end of its service life, reminding operators to replace the battery in time. This helps to avoid flight accidents caused by battery failure and improves the flight safety of drones.

[0053] In one embodiment, step S4, after solving the objective function and outputting the inspection task allocation scheme, further includes: S51. Using flight altitude and flight speed as decision variables, and the benefits of the safety party and the energy consumption party as decision variables, the desired flight altitude and desired flight speed are obtained by solving the Nash equilibrium through a hybrid strategy. The optimized inspection task allocation scheme is then optimized using the desired flight altitude and desired flight speed to obtain the optimized inspection task allocation scheme.

[0054] In this embodiment of the invention, the safety benefit is determined based on the mission failure probability, risk penalty factor, and risk exposure; the energy consumption benefit is determined based on the total flight energy consumption, delay penalty factor, and inspection delay.

[0055] The expression for the safe party's benefit is as follows: Us = -(P fail + γ*risk exposure) Where Us is the gain of the safe party, and P failMission failure probability is the likelihood of a drone crashing, losing communication, or experiencing flight control malfunctions under the current environment. It can be calculated based on historical data, environmental conditions (such as wind speed and visibility), and the drone's current status (such as battery level and equipment health). Risk exposure refers to the proportion of time or distance the drone is exposed to high-risk areas during flight. These high-risk areas may include areas with strong winds, signal blind spots, and the edges of no-fly zones. Calculating risk exposure requires comprehensive consideration of flight path planning, environmental monitoring data, and the drone's flight capabilities. The risk penalty factor γ is a weighting factor used to adjust the impact of risk exposure on safety benefits. A larger γ value indicates that the system places greater emphasis on risk exposure, thus adopting a more conservative strategy to ensure safety.

[0056] The expression for the energy consumption revenue is as follows: Ue = -(E consumption + δ*inspection delay) Where Ue is the energy consumption factor, and E is the energy consumption factor. consumption Total flight energy consumption is typically determined by factors such as flight distance, speed, and altitude. δ delay penalty factor represents the weight of time delay on the energy-consuming side; a larger δ value means the system pays more attention to time efficiency and thus adopts a more proactive strategy to reduce delay. Inspection delay refers to the difference between the actual completion time of a task and the expected time; the larger the delay, the worse the efficiency. A larger delay means the task execution efficiency is low, which may affect the scheduling and execution of subsequent tasks.

[0057] In this embodiment of the invention, safety and energy consumption are two different considerations. Safety focuses on the safety of the UAV when performing inspection tasks, which may include flight safety, environmental risks, and operational risks. Energy consumption focuses on the energy efficiency of the UAV when performing inspection tasks, which may include flight energy consumption, battery management, efficiency optimization, and inspection latency.

[0058] This invention can use real-time data such as task priority, wind speed, and equipment health parameters as input data. By using a hybrid strategy Nash equilibrium to solve the game between the safety side's payoff and the energy side's payoff, an optimized inspection task allocation scheme is determined. This optimized inspection task includes not only the inspection start point, inspection end point, and return point (the return point is the corresponding hangar in the hangar set to be allocated), but also the expected flight altitude and expected flight speed. Under the premise of ensuring safety, it can optimize energy consumption and time efficiency, and improve the efficiency and reliability of UAV inspection.

[0059] Please see Figure 2One embodiment provides a schematic diagram of a security-energy consumption game model, wherein the security-energy consumption game model is constructed from the security player's payoff and the energy player's payoff, wherein the optimal flight altitude and optimal flight speed are the desired flight altitude and desired flight speed.

[0060] In one embodiment, after step S4, solving the objective function and outputting the inspection task allocation scheme, the method further includes: S52. According to the inspection task allocation scheme, the inspection task is issued to the corresponding UAV. During the execution of the inspection task by the UAV, if the route switching condition is met, the current inspection task is switched to a preset safe route. The route switching condition includes at least one of the following: location data loss, wind speed growth rate exceeding a preset threshold, and communication link termination. In this embodiment of the invention, GPS is a key component for UAV positioning and navigation. In environments with tall buildings, canyons, or other obstacles, GPS signals may be interfered with or completely lost, causing the UAV to be unable to accurately locate itself. During flight, the UAV may encounter sudden strong winds; if the wind speed increase exceeds the UAV's designed maximum tolerance threshold, it may affect the UAV's stability and controllability. The communication link between the UAV and the ground control station is the foundation for remote control operations and data transmission. Any interruption of this communication link may cause the UAV to lose control or be unable to receive new commands. When at least one of the above situations occurs, for safety reasons, the current inspection task needs to be switched to a preset safe route, where the preset safe route is pre-set.

[0061] In this embodiment of the invention, while switching to a preset safe route, the flight speed is reduced to 70% of the optimal value, the flight altitude redundancy is increased by 20m, or the nearest backup site is landed based on the remaining battery power.

[0062] Please see Figure 3 In one embodiment, a fault-tolerant degradation control timing diagram is provided. For example... Figure 3 As shown, the system collects relevant data through sensors, and when these data trigger abnormal signals, it further identifies the type of abnormality. Based on the identified abnormality type, it generates a degradation strategy command and sends it to the corresponding UAV (unmanned aerial vehicle) flight controller to switch routes, adjust speeds, or return to home.

[0063] In one embodiment, before the drone takes off, a sensor and power health self-check, as well as a navigation system calibration, are performed to ensure that the inspection mission can be performed normally.

[0064] Implementing the embodiments of the present invention has the following beneficial effects: Based on the determination of the hangar to be allocated, this embodiment of the invention uses the sum of the target UAV's task execution time and return time as the total task time. The total task time takes into account the UAV's return and charging time after completing the inspection task, and constructs an objective function. The objective function aims to maximize the ratio of task priority to total task time, and combines battery life loss as a penalty factor. This can effectively optimize the return and charging path, thereby co-optimizing the inspection task and charging scheduling under the same decision framework. It achieves the inspection task and UAV return without relying on a set route, effectively avoiding path planning redundancy, and thus effectively improving inspection efficiency.

[0065] Furthermore, in the embodiments of the present invention, by switching to a preset safe flight path and adjusting the flight speed and altitude when encountering emergencies, the human and machine can continue to perform tasks through the downgrade strategy, and can still complete most of the predetermined inspection tasks, reducing downtime.

[0066] The UAV inspection task allocation device provided by the present invention is described below. The UAV inspection task allocation device described below and the UAV inspection task allocation method described above can be referred to in correspondence.

[0067] Please see Figure 4 The present invention provides a drone inspection task allocation device, comprising: Flight data determination module 410 is used to determine candidate inspection tasks based on the target UAV's current available power and estimated flight power consumption; The hangar determination module 420 is used to calculate the distance between the starting point of the candidate inspection task and each hangar, and select at least one hangar with the shortest distance as the hangar set to be assigned. The objective function construction module 430 is used to construct an objective function, which takes maximizing the ratio of task priority to total task time as the optimization objective and incorporates battery life loss as a penalty factor; wherein, the total task time includes the task execution time and return time of the target UAV. The inspection task allocation module 440 is used to solve the objective function and output the inspection task allocation scheme.

[0068] In one embodiment, before determining candidate inspection tasks based on the drone's current available power and estimated flight power consumption, the method further includes: The battery health status of the target drone is calculated using a battery health model. Based on the battery health status, calculate the current available power of the target drone and the estimated flight power consumption for each inspection mission.

[0069] In one embodiment, determining candidate inspection tasks based on the target UAV's current available power and estimated flight power consumption includes: For each inspection task, inspection tasks whose estimated flight power consumption is less than or equal to the current available power are selected as candidate inspection tasks.

[0070] In one embodiment, determining the battery life loss includes: The battery life loss of the target drone is determined based on the number of cycles used and the total cycle life of the target drone's battery.

[0071] In one embodiment, after solving the objective function and outputting the inspection task allocation scheme, the method further includes: Using flight altitude and flight speed as decision variables, and the benefits of the safety party and the energy consumption party as decision variables, the desired flight altitude and desired flight speed are obtained by solving the Nash equilibrium through a hybrid strategy. The optimized inspection task allocation scheme is then optimized using the desired flight altitude and desired flight speed to obtain the optimized inspection task allocation scheme.

[0072] In one embodiment, the safety-side benefit is determined based on the mission failure probability, risk penalty factor, and risk exposure; the energy-side benefit is determined based on total flight energy consumption, delay penalty factor, and inspection delay.

[0073] In one embodiment, after solving the objective function and outputting the inspection task allocation scheme, the method further includes: According to the inspection task allocation scheme, the inspection task is issued to the corresponding UAV. If the route switching condition is met during the UAV's inspection task, the current inspection task is switched to the preset safe route. The route switching condition includes at least one of the following: location data loss, wind speed growth rate greater than a preset threshold, and communication link termination.

[0074] Figure 5 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 5 As shown, the electronic device may include: a processor 510, a communications interface 520, a memory 530, and a communication bus 540, wherein the processor 510, the communications interface 520, and the memory 530 communicate with each other via the communication bus 540. The processor 510 can call logical instructions in the memory 530 to execute the UAV inspection task allocation method, including: Candidate inspection tasks are determined based on the target drone's current available power and estimated flight power consumption. Calculate the distance between the starting point of the candidate inspection task and each hangar, and select at least one hangar with the shortest distance as the hangar set to be assigned; An objective function is constructed, which aims to maximize the ratio of task priority to total task time and incorporates battery life loss as a penalty factor; wherein, the total task time includes the task execution time and return time of the target UAV. Solve the objective function and output the inspection task allocation scheme.

[0075] Furthermore, the logical instructions in the aforementioned memory 530 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0076] On the other hand, the present invention also provides a computer program product, the computer program product comprising a computer program, which can be stored on a non-transitory computer-readable storage medium, and when the computer program is executed by a processor, the computer is able to execute the UAV inspection task allocation method provided by the above methods, including: Candidate inspection tasks are determined based on the target drone's current available power and estimated flight power consumption. Calculate the distance between the starting point of the candidate inspection task and each hangar, and select at least one hangar with the shortest distance as the hangar set to be assigned; An objective function is constructed, which aims to maximize the ratio of task priority to total task time and incorporates battery life loss as a penalty factor; wherein, the total task time includes the task execution time and return time of the target UAV. Solve the objective function and output the inspection task allocation scheme.

[0077] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the UAV inspection task allocation method provided by the above methods, including: Candidate inspection tasks are determined based on the target drone's current available power and estimated flight power consumption. Calculate the distance between the starting point of the candidate inspection task and each hangar, and select at least one hangar with the shortest distance as the hangar set to be assigned; An objective function is constructed, which aims to maximize the ratio of task priority to total task time and incorporates battery life loss as a penalty factor; wherein, the total task time includes the task execution time and return time of the target UAV. Solve the objective function and output the inspection task allocation scheme.

[0078] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0079] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0080] 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 them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for allocating unmanned aerial vehicle (UAV) inspection tasks, characterized in that, include: Candidate inspection tasks are determined based on the target drone's current available power and estimated flight power consumption. Calculate the distance between the starting point of the candidate inspection task and each hangar, and select at least one hangar with the shortest distance as the hangar set to be assigned; An objective function is constructed, which aims to maximize the ratio of task priority to total task time and incorporates battery life loss as a penalty factor; wherein, the total task time includes the task execution time and return time of the target UAV. Solve the objective function and output the inspection task allocation scheme.

2. The UAV inspection task allocation method as described in claim 1, characterized in that, Before determining candidate inspection tasks based on the drone's current available power and estimated flight power consumption, the following steps are also included: The battery health status of the target drone is calculated using a battery health model. Based on the battery health status, calculate the current available power of the target drone and the estimated flight power consumption for each inspection mission.

3. The UAV inspection task allocation method as described in claim 1, characterized in that, The process of determining candidate inspection tasks based on the target UAV's current available power and estimated flight power consumption includes: For each inspection task, inspection tasks whose estimated flight power consumption is less than or equal to the current available power are selected as candidate inspection tasks.

4. The UAV inspection task allocation method as described in claim 1, characterized in that, The determination of battery life loss includes: The battery life loss of the target drone is determined based on the number of cycles used and the total cycle life of the target drone's battery.

5. The UAV inspection task allocation method as described in claim 1, characterized in that, After solving the objective function and outputting the inspection task allocation scheme, the following steps are also included: Using flight altitude and flight speed as decision variables, and the benefits of the safety party and the energy consumption party as decision variables, the desired flight altitude and desired flight speed are obtained by solving the Nash equilibrium through a hybrid strategy. The optimized inspection task allocation scheme is then optimized using the desired flight altitude and desired flight speed to obtain the optimized inspection task allocation scheme.

6. The UAV inspection task allocation method as described in claim 1, characterized in that, The safety benefits are determined based on the mission failure probability, risk penalty factor, and risk exposure; the energy consumption benefits are determined based on total flight energy consumption, delay penalty factor, and inspection delay.

7. The UAV inspection task allocation method as described in claim 1, characterized in that, After solving the objective function and outputting the inspection task allocation scheme, the following steps are also included: According to the inspection task allocation scheme, the inspection task is issued to the corresponding UAV. If the route switching condition is met during the UAV's inspection task, the current inspection task is switched to the preset safe route. The route switching condition includes at least one of the following: location data loss, wind speed growth rate greater than a preset threshold, and communication link termination.

8. A drone inspection task allocation device, characterized in that, include: The flight data determination module is used to determine candidate inspection tasks based on the target UAV's current available power and estimated flight power consumption. The hangar determination module is used to calculate the distance between the starting point of the candidate inspection task and each hangar, and select at least one hangar with the shortest distance as the hangar set to be assigned. The objective function construction module is used to construct an objective function, which aims to maximize the ratio of task priority to total task time and incorporates battery life loss as a penalty factor; wherein, the total task time includes the task execution time and return time of the target UAV. The inspection task allocation module is used to solve the objective function and output the inspection task allocation scheme.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the drone inspection task allocation as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the drone inspection task allocation as described in any one of claims 1 to 7.

Images