An unmanned aerial vehicle inspection route determination method, device, equipment and medium

Abstract

The application provides a UAV inspection route determination method, device, equipment and medium. The UAV inspection route determination method comprises: a. obtaining basic geographic information, environmental state data and task requirements of a target area, wherein the geographic information of the target area is obtained through remote sensing data, the environmental state data is collected in real time through a sensor, and the task requirements include a starting point, an ending point of the inspection path and specific tasks of the inspection. The UAV inspection route determination method, device, equipment and medium introduce an environmental factor correction model and an adaptive optimization algorithm, thereby solving the problem that dynamic environmental changes are not fully considered in traditional path planning. The environmental factor correction model can pre-process the path in real time according to external factors such as wind speed, air temperature and atmospheric pressure, thereby generating a more accurate environmental evaluation map, and providing more comprehensive reference data for path planning.

Description

Technical Field

[0001] This invention relates to the field of unmanned aerial vehicle (UAV) inspection technology, specifically to a method, apparatus, equipment, and medium for determining UAV inspection routes. Background Technology

[0002] The UAV inspection route determination system consists of a path planning module, a UAV control module, a data acquisition and processing module, a task management module, and a communication module. The path planning module generates the optimal inspection path using algorithms based on geographic information, obstacle data, and weather data. The UAV control module is responsible for navigating the UAV according to the planned path, adjusting its flight speed and direction. The data acquisition module uses various sensors to collect real-time status data of the target area and transmits it to the ground station for analysis. The task management module is responsible for real-time adjustments based on task priority and resource scheduling. The communication module ensures real-time communication between the UAV and the ground control station, guaranteeing the stability of task coordination and data transmission.

[0003] The system also has some shortcomings in practical applications. In complex environments, existing path planning algorithms cannot fully consider all environmental factors, resulting in insufficient path optimization and affecting flight safety. The system has a weak ability to respond to emergencies and lacks an effective adaptive adjustment mechanism, which may prevent it from responding in a timely manner in dynamically changing environments. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a method, apparatus, equipment, and medium for determining unmanned aerial vehicle (UAV) inspection routes. This solves the problems of insufficient path optimization caused by path planning algorithms failing to fully consider all environmental factors, as well as the weak ability to respond to emergencies and the lack of an effective adaptive adjustment mechanism.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a method for determining an unmanned aerial vehicle (UAV) inspection route, comprising:

[0006] a. Obtain basic geographic information, environmental status data, and task requirements for the target area. The geographic information of the target area is obtained through remote sensing data, the environmental status data is collected in real time by sensors, and the task requirements include the starting point, ending point, and specific tasks of the inspection path.

[0007] b. Preprocess the target area using an environmental factor correction model to generate a preliminary environmental assessment map. The environmental factor correction model considers wind speed, temperature, and atmospheric pressure. The correction process is performed using the following formula:

[0008] C env (x)=α1·wind_speed(x)+α2·temperature(x)+α3·pressure(x)

[0009] Among them, C env (x) is the correction factor, windspeed(x), temperature(x), and pressure(x) are the wind speed, temperature, and air pressure at location x in the target area, respectively, and α1, α2, and α3 are the weighting coefficients of environmental factors.

[0010] c. A preliminary inspection path is generated using a path planning module based on an adaptive optimization algorithm. This path planning is optimized based on the preprocessed environmental assessment map and correction factors, using the following path optimization formula:

[0011]

[0012] Among them, P final For the final optimized inspection path, P i For the i-th path point in the path, Cost(P) i C represents the cost function of the path points, reflecting factors such as flight distance, time consumption, and energy consumption. env (P i ) is the path point P i Environmental correction factors;

[0013] d. The path is dynamically adjusted based on the drone's real-time flight status data, including the drone's current position, speed, flight altitude, and battery level, using the following adaptive adjustment mechanism to correct the path:

[0014] P adj =P final +δP

[0015] Among them, P adj The adjusted inspection path is represented by δP, which is the path adjustment amount generated from real-time status data. The specific adjustment is based on battery power and power consumption factors.

[0016] e. During the inspection process, monitor and acquire drone sensor data in real time, and dynamically correct the current path based on the real-time collected environmental data, using the following data feedback model:

[0017] P feedback =P adj ±δP feedback

[0018] Wherein, δP feedback Based on obstacle detection and flight status information, the path adjustment amount and feedback path ensure the real-time performance and safety of the inspection process.

[0019] f. Dynamically adjust the inspection route based on the type of emergency. If obstacles are encountered, battery power is low, or weather conditions change, adjust the route planning using the following event response mechanisms:

[0020]

[0021] Risk(P) is the risk assessment value at path P, taking into account obstacles and weather changes to ensure the smooth execution of the inspection task in the event of an emergency.

[0022] g. Dynamically select task priorities and path optimization objectives based on task requirements. Adjust task priorities along the path and optimize the execution order of inspection tasks under the influence of battery level and task urgency. Use the following priority adjustment model:

[0023] Priority(P)=α4·Urgency(P)+α5·Remaining_Power(P)

[0024] Where Urgency(P) represents the urgency of the path point P for the mission, RemainingPower(P) represents the remaining battery power of the drone, and α4 and α5 are adjustment coefficients;

[0025] h. During the inspection process, adjust the path planning and scheduling based on real-time data, and optimize task allocation and path selection according to new environmental changes and drone status;

[0026] i. During mission execution, generate mission reports and update the system in real time, feed back inspection results, route planning and environmental status to the ground control station, and generate real-time reports for subsequent analysis and mission adjustments;

[0027] j. Based on the remaining battery power of the drone, the inspection progress and task requirements, optimize the path of the remaining inspection tasks, use the battery power prediction model to predict the battery life, and adjust the subsequent path planning based on the prediction results to ensure the completion of the task.

[0028] k. Combine task status and environmental changes to generate a long-term task optimization model. By learning from historical task data, predict and optimize the path and resource scheduling in future inspection tasks.

[0029] I. Perform global optimization of the system, combining machine learning and deep learning methods to optimize path planning and task scheduling. Through training with historical data, automatically adjust path planning and task priorities to adapt to the changing inspection environment.

[0030] Preferably, the adaptive adjustment mechanism adopts the following steps: during the execution of the inspection task, the flight status of the UAV and the environmental changes in the target area are continuously monitored. Once an environmental change or system failure is detected, a new inspection path is quickly calculated through the adaptive adjustment algorithm. If the battery power is lower than a set threshold, the nearest charging point or return path is calculated, and the ground control station is notified for scheduling.

[0031] Preferably, the environmental status data is collected through the following sensors:

[0032] Wind speed sensor, used to acquire wind speed information in the flight area;

[0033] Temperature sensors are used to acquire air temperature information in the flight area;

[0034] Barometric pressure sensor, used to acquire atmospheric pressure information of the flight area;

[0035] GPS and obstacle sensors are used to provide flight path and obstacle information.

[0036] Preferably, the data collection during the execution of the inspection task includes the following steps: the camera and infrared sensor carried by the UAV collect image data of the target area in real time, transmit the collected image data to the ground control station for real-time analysis, and generate an equipment health report.

[0037] Preferably, the objective function in the path optimization process is set in the following manner:

[0038] ObjectiveFunction=λ1·Safety+λ2·Efficiency+λ3·EnvironmentalAdaptation

[0039] Wherein, λ1, λ2, and λ3 are the weighting coefficients for safety, efficiency, and environmental adaptability, respectively.

[0040] Preferably, the environmental status data is updated in real time and reflected in the path planning and adjustment process to ensure that the path has high dynamic adaptability during flight.

[0041] Preferably, the path planning algorithm communicates bidirectionally between the UAV's control system and the ground control station to optimize the inspection path in real time and make adjustments based on the actual flight status and environmental conditions.

[0042] Preferably, the adaptive optimization algorithm uses a combination of local search and global search to flexibly adjust the path in a dynamic environment, so as to ensure that the path planning remains optimal during long-term flight.

[0043] A drone inspection device for a waste incineration power plant includes a memory and a processor; the memory is used to store programs.

[0044] The processor is used to execute the program to implement the various steps of a method for determining an unmanned aerial vehicle (UAV) inspection route.

[0045] A storage medium storing a computer program, which, when executed by a processor, implements the various steps of the method for determining a drone inspection route.

[0046] This invention provides a method, apparatus, equipment, and medium for determining unmanned aerial vehicle (UAV) inspection routes. It offers the following advantages:

[0047] This invention relates to a method, apparatus, equipment, and medium for determining UAV inspection routes. By introducing an environmental factor correction model and an adaptive optimization algorithm, it addresses the problem of traditional path planning failing to adequately consider dynamic environmental changes. The environmental factor correction model can preprocess the path in real time based on external factors such as wind speed, temperature, and atmospheric pressure, thereby generating a more accurate environmental assessment map and providing more comprehensive reference data for path planning. This method significantly improves the adaptability and reliability of UAV inspection paths, ensuring the smooth execution of inspection tasks even in complex environments.

[0048] This invention employs an adaptive optimization algorithm combined with real-time flight status data to dynamically adjust the path, enabling the UAV to cope with unexpected events such as low battery power or abnormal flight altitude. By adjusting the path based on real-time information such as the UAV's current position, speed, and battery level, it effectively avoids mission interruptions or efficiency reductions caused by unforeseen circumstances. This path planning method with an adaptive adjustment mechanism greatly improves the flexibility and responsiveness of the UAV inspection system, ensuring the continuity and stability of long-term, high-load tasks. Therefore, this technical solution has strong innovation and practicality, providing effective technical support for the development of UAV inspection technology. Attached Figure Description

[0049] Figure 1 This is a schematic diagram of the UAV inspection route of the present invention;

[0050] Figure 2 This is a schematic diagram illustrating the impact of environmental factors on path optimization according to the present invention. Detailed Implementation

[0051] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0052] Example 1

[0053] like Figure 1-2 As shown, this embodiment of the invention provides a method, apparatus, device, and medium for determining an unmanned aerial vehicle (UAV) inspection route, including: a. acquiring basic geographic information, environmental status data, and task requirements of a target area, wherein the geographic information of the target area is acquired through remote sensing data, the environmental status data is collected in real time by sensors, and the task requirements include the starting point, ending point, and specific tasks of the inspection path.

[0054] b. Preprocess the target area using an environmental factor correction model to generate a preliminary environmental assessment map. The environmental factor correction model considers wind speed, temperature, and atmospheric pressure. The correction process is performed using the following formula:

[0055] C env (x)=α1·wind_speed(x)+α2·temperature(x)+α3·pressure(x)

[0056] Among them, C env (x) is the correction factor, windspeed(x), temperature(x), and pressure(x) are the wind speed, temperature, and air pressure at location x in the target area, respectively, and α1, α2, and α3 are the weighting coefficients of environmental factors.

[0057] c. A preliminary inspection path is generated using a path planning module based on an adaptive optimization algorithm. This path planning is optimized based on the preprocessed environmental assessment map and correction factors, using the following path optimization formula:

[0058]

[0059] Among them, P final For the final optimized inspection path, P i For the i-th path point in the path, Cost(P) i C represents the cost function of the path points, reflecting factors such as flight distance, time consumption, and energy consumption. env (P i ) is the path point P i The environmental correction factor and the objective function in the path optimization process are set in the following ways:

[0060] ObjectiveFunction=λ1·Safety+λ2·Efficiency+λ3·EnvironmentalAdaptation

[0061] Where λ1, λ2, and λ3 are the weight coefficients for safety, efficiency, and environmental adaptability, respectively. The adaptive optimization algorithm uses a combination of local and global search to flexibly adjust the path in a dynamic environment, ensuring that the path planning remains optimal during long-term flight.

[0062] d. The path is dynamically adjusted based on the drone's real-time flight status data, including the drone's current position, speed, flight altitude, and battery level, using the following adaptive adjustment mechanism to correct the path:

[0063] P adj =P final +δP

[0064] Among them, P adj The adjusted inspection path is δP, which is the path adjustment amount generated by real-time status data. The specific adjustment is based on battery power and power consumption factors. The adaptive adjustment mechanism adopts the following steps: During the execution of the inspection task, the flight status of the UAV and the environmental changes in the target area are continuously monitored. Once an environmental change or system failure is detected, a new inspection path is quickly calculated through the adaptive adjustment algorithm. If the battery power is lower than the set threshold, the nearest charging point or return path is calculated and the ground control station is notified for scheduling.

[0065] e. During the inspection process, monitor and acquire drone sensor data in real time, and dynamically correct the current path based on the real-time collected environmental data, using the following data feedback model:

[0066] P feedback =P adj ±δP feedback

[0067] Wherein, δP feedback Based on obstacle detection and flight status information, the path adjustment amount and feedback path ensure the real-time performance and safety of the inspection process.

[0068] f. Dynamically adjust the inspection route based on the type of emergency. If obstacles are encountered, battery power is low, or weather conditions change, adjust the route planning using the following event response mechanisms:

[0069]

[0070] Risk(P) is the risk assessment value at path P, taking into account obstacles and weather changes to ensure the smooth execution of inspection tasks in the event of emergencies.

[0071] g. Dynamically select task priorities and path optimization objectives based on task requirements. Adjust task priorities along the path and optimize the execution order of inspection tasks under the influence of battery level and task urgency. Use the following priority adjustment model:

[0072] Priority(P)=α4·Urgency(P)+α5·Remaining_Power(P)

[0073] Where Urgency(P) represents the urgency of the path point P for the mission, RemainingPower(P) represents the remaining battery power of the drone, and α4 and α5 are adjustment coefficients.

[0074] h. During the inspection process, adjust the path planning and scheduling based on real-time data, and optimize task allocation and path selection according to new environmental changes and drone status.

[0075] i. During mission execution, generate mission reports and update the system in real time, feed back inspection results, path planning and environmental status to the ground control station, and generate real-time reports for subsequent analysis and mission adjustments. Environmental status data is updated in real time and reflected in the path planning and adjustment process to ensure that the path has high dynamic adaptability during flight.

[0076] j. Based on the remaining battery power of the UAV, the inspection progress and task requirements, optimize the path of the remaining inspection tasks, use the battery power prediction model to predict the battery life, and adjust the subsequent path planning based on the prediction results to ensure the completion of the task. The path planning algorithm communicates bidirectionally with the ground control station through the UAV's control system to optimize the inspection path in real time and make adjustments according to the actual flight status and environmental conditions.

[0077] k. By combining task status and environmental changes, a long-term task optimization model is generated. By learning from historical task data, the path and resource scheduling in future inspection tasks are predicted and optimized.

[0078] I. Perform global optimization of the system, combining machine learning and deep learning methods to optimize path planning and task scheduling. Through training with historical data, automatically adjust path planning and task priorities to adapt to the changing inspection environment.

[0079] A drone inspection device for a waste-to-energy plant includes a memory and a processor. The memory stores the program.

[0080] The processor is used to execute programs that implement the various steps of a method for determining a drone inspection route.

[0081] A storage medium storing a computer program, which, when executed by a processor, implements the various steps of a method for determining a drone inspection route.

[0082] Example 2

[0083] The drone inspection route determination method provided by this invention is applied to the inspection of power equipment. Assuming the target area is a power transmission line, the task requirement is to proceed from starting point A to ending point B, and the inspection equipment is a drone equipped with a camera, temperature sensor, barometric pressure sensor, and wind speed sensor.

[0084] Step a: Obtain basic geographic information, environmental status data, and task requirements for the target area.

[0085] Geographic information of the target area: Geographic information of power lines is obtained through remote sensing satellite imagery data, and a digital map of the target area is generated. The latitude and longitude coordinates of the starting point A and the ending point B are:

[0086] Starting point A: Longitude 120.5384°, Latitude 30.3755°

[0087] Termination point B: Longitude 120.5508°, Latitude 30.3807°

[0088] Environmental status data: Environmental data is collected in real time through sensors on the drone. Assuming the environmental data of the drone's current location during the inspection process is as follows:

[0089] Wind speed: 6 m / s

[0090] Temperature: 28℃

[0091] Atmospheric pressure: 1012 hPa

[0092] Task Requirements: The inspection task requires an inspection from starting point A to ending point B. The inspection target is the equipment condition on the power transmission line. The inspection route must include the maintenance points of each piece of equipment, and the flight distance and energy consumption of the route must be optimized.

[0093] Step b: Use the environmental factor correction model to preprocess the target area and generate a preliminary environmental assessment map.

[0094] Environmental Correction Factor C env The calculation formula is as follows:

[0095] C env =w wind WindSpeed+w temp Temperature+w pressure

[0096] ·Pressure

[0097] Assume the environmental factor weighting coefficients are:

[0098] w wind =0.4

[0099] w temp =0.3

[0100] w pressure =0.3

[0101] Substitute the current environmental data to calculate the correction factor:

[0102] C env =0.4·6 + 0.3·28 + 0.3·1012 = 2.4 + 8.4 + 303.6 = 314.4

[0103] The correction factor C env =314.4 indicates the degree of impact of the current environment on the route planning. A similar correction factor is generated for each location point on the environmental assessment map to assess the environmental adaptability of the target area.

[0104] Step c: Generate a preliminary inspection path using a path planning module based on an adaptive optimization algorithm.

[0105] Based on the generated environmental assessment map and correction factors, an adaptive optimization algorithm (such as particle swarm optimization) is used for path planning. The objective function in the path optimization process is assumed to be:

[0106] ObjectiveFunction = w safety Safety+w efficiency Efficiency

[0107] +w env • Environmental Adaptation, which includes:

[0108] Safety reflects the safety of the flight path and avoidance of obstacles;

[0109] Efficiency reflects the time consumed by the path and the flight distance;

[0110] Environmental Adaptation reflects the adaptability of a pathway to environmental modification factors.

[0111] Assume the weighting coefficients for each item are:

[0112] w safety =0.5

[0113] w efficiency =0.3

[0114] w env =0.2

[0115] The optimized inspection path, obtained using this objective function, reduces unnecessary flight distance, avoids high-wind-speed areas, and ensures efficient completion of the inspection task. The final preliminary inspection path is shown in the figure below:

[0116] The process starts from point A (120.5384°, 30.3755°), proceeds to the first inspection point (120.5400°, 30.3765°), then to the second inspection point (120.5440°, 30.3790°), and so on, eventually reaching the final point B (120.5508°, 30.3807°).

[0117] Step d: Dynamically adjust the path based on the real-time flight status data of the UAV.

[0118] During drone flight, the system monitors the drone's flight status data in real time. For example, if the drone is currently flying to inspection point 2 with a battery level of 30%, the system automatically calculates the path adjustment amount based on the battery level and flight status.

[0119] Assume the formula for calculating the path adjustment amount is:

[0120]

[0121] Wherein, RemainingBattery=30 represents the remaining battery power, and Initial PathLength=10km is the initially calculated flight path length.

[0122]

[0123] Based on the adjustment amount, the path was shortened by 3 kilometers, and it was ensured that the path adjustment could still meet the task requirements. The final optimized inspection path length was 7 kilometers.

[0124] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for determining an inspection route using a drone, characterized in that, include: a. Acquire basic geographic information, environmental status data, and task requirements for the target area. The geographic information of the target area is acquired through remote sensing data; the environmental status data is collected in real-time by sensors; and the task requirements include the start and end points of the inspection path and the specific tasks to be performed. The environmental status data is collected through the following sensors: Wind speed sensor, used to acquire wind speed information in the flight area; Temperature sensors are used to acquire air temperature information in the flight area; Barometric pressure sensor, used to acquire atmospheric pressure information of the flight area; GPS and obstacle sensors are used to provide flight path and obstacle information; b. Preprocess the target area using an environmental factor correction model to generate a preliminary environmental assessment map. The environmental factor correction model considers wind speed, temperature, and atmospheric pressure. The correction process is performed using the following formula: C env (x)=α1·wind_speed(x)+α2·temperature(x)+α3·pressure(x) Among them, C env (x) is the correction factor, wind_speed(x), temperature(x), and pressure(x) are the wind speed, temperature, and air pressure at location x in the target area, respectively, and α1, α2, and α3 are the weighting coefficients of environmental factors. c. A preliminary inspection path is generated using a path planning module based on an adaptive optimization algorithm. This path planning is optimized based on the preprocessed environmental assessment map and correction factors, using the following path optimization formula: Among them, P final For the final optimized inspection path, P i For the i-th path point in the path, Cost(P) i C represents the cost function of the path points, reflecting factors such as flight distance, time consumption, and energy consumption. env (P i ) is the path point P i Environmental correction factors; d. The path is dynamically adjusted based on the drone's real-time flight status data, including the drone's current position, speed, flight altitude, and battery level, using the following adaptive adjustment mechanism to correct the path: P adj =P final +δP Among them, P adj The adjusted inspection path is represented by δP, which is the path adjustment amount generated from real-time status data. The specific adjustment is based on battery power and power consumption factors. e. During the inspection process, monitor and acquire drone sensor data in real time, and dynamically correct the current path based on the real-time collected environmental data, using the following data feedback model: P feedback =P adj ±δP feedback Wherein, δP feedback Based on obstacle detection and flight status information, the path adjustment amount and feedback path ensure the real-time performance and safety of the inspection process. f. Dynamically adjust the inspection route based on the type of emergencies, including encountering obstacles, low battery power, and weather changes. The route planning is adjusted through the following event response mechanism: Wherein, Risk(P) is the risk assessment value at path P. The data collection during the execution of the inspection task includes the following steps: the camera and infrared sensor on the UAV collect image data of the target area in real time, transmit the collected image data to the ground control station for real-time analysis, and generate an equipment health report; g. Dynamically select task priorities and path optimization objectives based on task requirements. Adjust task priorities along the path and optimize the execution order of inspection tasks under the influence of battery level and task urgency. Use the following priority adjustment model: Priority(P)=α4·Urgency(P)+α5·Remaining_Power(P) Where Urgency(P) represents the urgency of the path point P for the mission, RemainingPower(P) represents the remaining battery power of the drone, and α4 and α5 are adjustment coefficients; h. During the inspection process, adjust the path planning and scheduling based on real-time data, and optimize task allocation and path selection according to new environmental changes and drone status; i. During mission execution, generate mission reports and update the system in real time, feed back inspection results, route planning and environmental status to the ground control station, and generate real-time reports for subsequent analysis and mission adjustments; j. Based on the remaining battery power of the drone, the inspection progress and task requirements, optimize the path of the remaining inspection tasks, use the battery power prediction model to predict the battery life, and adjust the subsequent path planning based on the prediction results to ensure the completion of the task. k. Combine task status and environmental changes to generate a long-term task optimization model. By learning from historical task data, predict and optimize the path and resource scheduling in future inspection tasks. I. Perform global optimization of the system, combining machine learning and deep learning methods to optimize path planning and task scheduling. Through training with historical data, automatically adjust path planning and task priorities to adapt to the changing inspection environment.

2. The method for determining an unmanned aerial vehicle (UAV) inspection route according to claim 1, characterized in that: The adaptive adjustment mechanism employs the following steps: during the inspection mission, the flight status of the UAV and environmental changes in the target area are continuously monitored. Once an environmental change or system failure is detected, a new inspection path is quickly calculated using an adaptive adjustment algorithm. If the battery level is lower than a set threshold, the nearest charging point or return path is calculated, and the ground control station is notified for scheduling.

3. The method for determining an unmanned aerial vehicle (UAV) inspection route according to claim 1, characterized in that: The objective function in the path optimization process is set in the following way: ObjectiveFunction=λ1·Safety+λ2·Efficiency+λ3·EnvironmentalAdaptation Wherein, λ1, λ2, and λ3 are the weighting coefficients for safety, efficiency, and environmental adaptability, respectively.

4. The method for determining an unmanned aerial vehicle (UAV) inspection route according to claim 1, characterized in that: The environmental status data is updated in real time and reflected in the path planning and adjustment process, ensuring that the path has high dynamic adaptability during flight.

5. The method for determining an unmanned aerial vehicle (UAV) inspection route according to claim 1, characterized in that: The path planning algorithm communicates bidirectionally between the UAV's control system and the ground control station to optimize the inspection path in real time and make adjustments based on the actual flight status and environmental conditions.

6. The method for determining an unmanned aerial vehicle (UAV) inspection route according to claim 1, characterized in that: The adaptive optimization algorithm combines local and global search to flexibly adjust the path in a dynamic environment, ensuring that the path planning remains optimal throughout long-term flight.

7. A drone inspection device for a waste incineration power plant, characterized in that, Includes a memory and a processor; the memory is used to store programs; The processor is used to execute the program to implement each step of the method for determining a drone inspection route as described in any one of claims 1-6.

8. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements each step of the method for determining an unmanned aerial vehicle (UAV) inspection route as described in any one of claims 1-6.

Images