Intelligent inspection method based on unmanned aerial vehicle inspection coordination

Abstract

The invention discloses an intelligent routing inspection method based on unmanned aerial vehicle routing inspection cooperation, relates to the technical field of unmanned aerial vehicle routing inspection, and solves the technical problems that various factors of a routing inspection area cannot be comprehensively analyzed, and a reasonable routing inspection scheme cannot be further obtained through screening. According to the method, distribution characteristics, landforms, environmental factors and the like of inspection objects are fully considered to ensure that the inspection task of each inspection sub-region is clear and reasonable, the inspection tasks of the inspection sub-regions are accurately acquired through multiple channels, including state monitoring of specific equipment, environmental parameter acquisition, potential risk point investigation and the like, and the inspection efficiency is improved. According to the method, the unmanned aerial vehicle is subjected to inspection to improve the pertinence and effectiveness of inspection, the basic information of the unmanned aerial vehicle is quantitatively embodied, and is expressed by adopting specific numerical values including cruising ability, loading capacity, flight stability, configuration data and the like, so that the information and inspection qualitative information of inspection sub-regions are comprehensively considered, and the most suitable standard inspection unmanned aerial vehicle is screened out.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle inspection, and in particular to an intelligent inspection method based on unmanned aerial vehicle inspection collaboration. Background Art

[0002] With the continuous development of science and technology, drone technology has been widely used in various fields. In the field of inspection, the traditional manual inspection method has problems such as low efficiency, high cost and high risk. Drone inspection has the advantages of high efficiency, flexibility and safety. It can quickly and accurately obtain information about the inspection area and improve inspection efficiency and quality.

[0003] For example, the Chinese invention patent with publication number CN118092507A discloses a multi-UAV collaborative inspection method, device and storage medium; wherein the method includes: obtaining waypoint data of the inspection task, sorting a plurality of waypoint data according to the positional relationship between the take-off point and each waypoint to generate a first waypoint list; taking the preset waypoint data as the starting point, reading all waypoint data in the first waypoint list in sequence to generate a second waypoint list; dividing the second waypoint list into a plurality of route lists according to preset conditions; reading non-safe route waypoint data in each route list in sequence to generate a corresponding non-safe route list; calculating the optimal route path for each route list according to the safe route waypoint data in each route list; distributing the optimal route path for each route list and the corresponding non-safe route list to the corresponding UAV for execution.

[0004] Based on the contents disclosed in the above-mentioned comparative documents, although the existing technology can realize the reasonable selection of inspection routes, in the process of actual application, how to make a comprehensive judgment based on various factors in the inspection process becomes a problem that needs to be solved. At the same time, there is a lack of reasonable scheduling analysis based on the corresponding UAV's own parameter requirements in the inspection route, which will affect the overall scheduling. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides an intelligent inspection method based on drone inspection collaboration, which solves the problem of not being able to comprehensively analyze various factors of the inspection area and further not being able to screen out a reasonable inspection plan.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent inspection method based on drone inspection collaboration, the method specifically includes the following steps:

[0007] Step S01, dividing the inspection area into inspection sub-areas, acquiring the inspection tasks of the inspection sub-areas, and generating planning inspection information;

[0008] Step S02, performing a qualitative inspection analysis on the inspection sub-area according to the planned inspection information, screening standard inspection drones based on the basic information of the drones, and generating initial inspection information;

[0009] Step S03, based on the generated initial inspection information, identifying the inspection status of the standard inspection drone, determining whether inspection adjustment is required, and generating inspection adjustment determination information;

[0010] Step S04, analyzing the generated inspection and adjustment signal, screening different drones according to the task completion status, analyzing and selecting the adjustment drone in combination with the task intersection status, and generating adjustment information at the same time.

[0011] As a further solution of the present invention: the specific method of performing inspection qualitative analysis on the inspection sub-area in step S02 is:

[0012] Obtain all inspection sub-areas and label them as i, where i=1, 2, ..., j, where j represents the number of inspection sub-areas. At the same time, obtain the planned inspection information of inspection sub-area i, then score and evaluate the different inspection tasks in the planned inspection information, and characterize the inspection sub-areas based on the inspection tasks corresponding to the highest scoring values ​​to generate inspection qualitative information.

[0013] As a further solution of the present invention: the specific method of generating the initial inspection information in step S02 is:

[0014] All drones are obtained and labeled as a, where a=1, 2, ..., b, where b represents the number of drones. The basic information of the drones is then obtained, and the qualitative inspection information of the inspection sub-areas is obtained. The drones are selected based on their basic information to obtain standard inspection drones, and initial inspection information is generated.

[0015] As a further solution of the present invention: the specific method of identifying the inspection status of the standard inspection drone in step S03 is:

[0016] Take any standard inspection drone as the analysis object, obtain the inspection status information of the analysis object, and obtain the overall task inspection completion ratio of the analysis object. Get the total endurance of the standard inspection drone, record it as H, and get the current remaining endurance, record it as H1. Get the real-time inspection duration of the analysis object, record it as T1, and then calculate the remaining flight endurance based on the unfinished ratio.

[0017] As a further solution of the present invention: the specific method of calculating the remaining flight endurance in step S03 is:

[0018] Substitute the obtained parameters into the formula Calculate the unit consumption H of the standard inspection drone of the analysis object d , and θ is the completion ratio of task inspection, and ω is the preset proportional coefficient;

[0019] At the same time, according to the unit consumption H d To calculate the remaining flight time, substitute the parameters into the formula H2 = H d ×(1-θ)×ω to obtain the remaining flight endurance H2, where (1-θ) is the unfinished proportion and ω is the preset proportional coefficient, and the remaining flight endurance H2 is compared with the remaining endurance H1.

[0020] As a further solution of the present invention: the specific method of comparing the remaining flight endurance with the remaining flight endurance in step S03 is:

[0021] When the remaining endurance H1 is greater than the remaining flight endurance H2, no adjustment is required and a normal patrol signal is generated. Conversely, when the remaining endurance H1 is less than the remaining flight endurance H2, adjustment is required and a patrol adjustment signal is generated to further generate patrol adjustment judgment information.

[0022] As a further solution of the present invention: the specific method of analyzing the inspection adjustment signal in step S04 is:

[0023] Get all normal inspection sub-areas and record them as n, where n=1, 2, ..., m, where m represents the number of normal inspection sub-areas. At the same time, get the inspection drones corresponding to the normal inspection sub-areas and record them as a1, where a1=1, 2, ..., b1, where b1 represents the number of drones in the corresponding area. At the same time, get the remaining inspection tasks of the normal inspection sub-areas, and make an intersection judgment on the remaining inspection tasks of the normal inspection sub-areas and the remaining inspection tasks of the adjustment area.

[0024] As a further solution of the present invention: the specific method of performing intersection judgment on the remaining inspection tasks in step S04 is:

[0025] If there is an intersection between the two, the corresponding inspection drone will be marked as the drone to be adjusted. Otherwise, if there is no intersection between the two, it will not be selected.

[0026] As a further solution of the present invention: the specific method of generating the adjustment information in step S04 is:

[0027] All the drones to be adjusted are obtained, and the task completion ratios corresponding to the drones to be adjusted are calculated. The drones to be adjusted are sorted from large to small according to the task completion ratios. Then, the drones to be adjusted are selected according to their comprehensive performance and the adjustment standard information is generated.

[0028] As a further solution of the present invention: the specific method of selecting and generating the adjustment standard information according to the comprehensive performance of the drone to be adjusted in step S04 is as follows:

[0029] The endurance, load capacity and flight stability of the UAV to be adjusted are comprehensively scored, and the comprehensive evaluation value of the UAV to be adjusted is calculated. At the same time, the UAV to be adjusted with the largest comprehensive evaluation value is selected to generate adjustment standard information.

[0030] The present invention provides an intelligent inspection method based on drone inspection collaboration. Compared with the prior art, it has the following beneficial effects:

[0031] The present invention fully considers the distribution characteristics, topography, environmental factors, etc. of the inspection objects to ensure that the inspection tasks of each inspection sub-area are clear and reasonable, and accurately obtains the inspection tasks of the inspection sub-area through multiple channels, including status monitoring of specific equipment, environmental parameter collection, potential risk point investigation, etc., to improve the pertinence and effectiveness of the inspection, quantifies the basic information of the drone, and uses specific numerical values ​​to express it, including endurance, load capacity, flight stability, configuration data, etc., so as to comprehensively consider this information and the qualitative inspection information of the inspection sub-area to screen out the most suitable standard inspection drone. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a step method diagram of the present invention;

[0033] Figure 2 It is the process judgment diagram of the present invention;

[0034] Figure 3 It is the overall control system of the present invention. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0036] For example, see Figure 1 , Figure 2 and Figure 3 The present application provides an intelligent inspection method based on drone inspection collaboration, which specifically includes the following steps:

[0037] In step S01, the inspection area is divided into inspection sub-areas, and the inspection tasks of the inspection sub-areas are obtained, and the planned inspection information is generated. In the division process, the distribution characteristics, topography, environmental factors, etc. of the inspection objects are fully considered. At the same time, for each inspection sub-area, its specific inspection needs are deeply analyzed, and the inspection tasks of the area are accurately obtained through multiple channels. These tasks may include status monitoring of specific equipment, collection of environmental parameters of specific areas, and investigation of potential risk points.

[0038] Next, in step S02, a qualitative inspection analysis is performed on the inspection sub-area according to the planned inspection information, and standard inspection drones are screened in combination with the basic information of the drones, and initial inspection information is generated.

[0039] Obtain all inspection sub-areas, and label the inspection sub-areas as i, where i=1, 2, ..., j, where j represents the number of inspection sub-areas, then obtain the planned inspection information corresponding to the inspection sub-area i, and score and evaluate the inspection tasks corresponding to the planned inspection information. The specific value of the scoring evaluation here is scored by the operator for each inspection task, and the full score is 5 points. The inspection task corresponding to the highest score is selected as the inspection qualitative information of the corresponding inspection sub-area;

[0040] In a specific example, when inspecting a large wind farm, the entire wind farm is divided into multiple inspection sub-areas, such as wind turbine area A, wind turbine area B, substation area, etc. For the inspection sub-area of ​​wind turbine area A, after obtaining its planned inspection information, the operator scores each inspection task. Assuming that the inspection tasks include checking whether the appearance of the wind turbine blades is damaged, checking whether the wind turbine tower is rusted, and checking whether the electrical equipment is operating normally, the operator, after evaluation, believes that checking whether the appearance of the wind turbine blades is damaged is the most important, and gives it a high score of 4 points. The other tasks are 3 points and 2 points respectively. Therefore, checking whether the appearance of the wind turbine blades is damaged becomes the inspection qualitative information of this inspection sub-area.

[0041] Then all the drones are labeled as a, and a=1, 2, ..., b, where b represents the number of drones. Then the basic information of the drones is obtained, and the basic information here includes endurance, load capacity, flight stability and drone configuration data. At the same time, the basic information is quantified and expressed using specific numerical values. At the same time, the qualitative inspection information of the inspection sub-area is obtained, and the basic information of the drones is combined to select the drones to obtain standard inspection drones, and the initial inspection information is generated.

[0042] In a specific example, for example, UAV 1 has a flight time of 3 hours, a payload capacity of 5 kg of equipment, good flight stability (quantifiable as 80% stability), and is equipped with a high-definition camera and an infrared thermal imager. Other UAVs also have their own different basic information. Taking into account these basic information and the qualitative inspection information of the inspection sub-area, it is found that UAV 2's high-resolution camera and longer flight time are more suitable for inspecting the appearance of wind turbine blades. Therefore, UAV 2 is determined as the standard inspection UAV for wind turbine area A, and initial inspection information is generated, including the flight route of UAV 2, inspection schedule, key inspection areas, etc.

[0043] Next, in step S03, based on the generated initial inspection information, the inspection status of the standard inspection drone is identified, and at the same time, it is determined whether inspection adjustment is required, and inspection adjustment determination information is generated.

[0044] Take any standard inspection drone as the analysis object, and obtain the inspection status information of the analysis object, where the inspection status information is expressed as flight endurance. At the same time, obtain the overall task inspection completion ratio of the analysis object, and then calculate the remaining flight endurance based on the unfinished ratio. The specific calculation method is as follows:

[0045] Get the total endurance of the standard inspection drone as H, get the current remaining endurance as H1, and get the real-time inspection duration of the analysis object as T1. Then substitute the obtained parameters into the formula Calculate the unit consumption H of the standard inspection drone of the analysis object d , and θ is the completion ratio of task inspection, ω is the preset proportional coefficient, and according to the obtained unit consumption H d To calculate the remaining flight endurance, substitute the parameters into the formula H2 = Hd × (1-θ) × ω to calculate the remaining flight endurance H2, where (1-θ) is the unfinished proportion and ω is the preset proportional coefficient;

[0046] Then the remaining endurance H1 is compared with the remaining flight endurance H2. When the remaining endurance H1 is greater than the remaining flight endurance H2, it means that the standard inspection UAV corresponding to the analysis object can complete the inspection task and does not need to be adjusted. At the same time, a normal inspection signal is generated. On the contrary, when the remaining endurance H1 is less than the remaining flight endurance H2, it means that the standard inspection UAV corresponding to the analysis object cannot complete the inspection task and needs to be adjusted. At the same time, an inspection adjustment signal is generated, and inspection adjustment judgment information is further generated.

[0047] Next, in step S04, the generated inspection and adjustment signal is analyzed, different drones are screened according to the task completion status, and the adjustment drone is selected and analyzed in combination with the task intersection status, and the adjustment information is generated at the same time.

[0048] All normal inspection sub-areas are acquired and recorded as n. The normal inspection sub-area here refers to the sub-area corresponding to the generation of normal inspection signals, and n=1, 2, ..., m, where m represents the number of normal inspection sub-areas. At the same time, the inspection drone corresponding to the normal inspection sub-area is acquired and labeled as a1, and a1=1, 2, ..., b1, where b1 represents the number of drones in the corresponding area. The inspection drone obtained here is the inspection drone corresponding to the inspection sub-area that generates normal inspection signals. At the same time, the remaining inspection tasks of the normal inspection sub-area are acquired, and the remaining inspection tasks of the normal inspection sub-area are judged by the intersection with the remaining inspection tasks of the adjustment area. The adjustment area here refers to the sub-area that generates the inspection adjustment signal. If there is an intersection between the two, the corresponding inspection drone is marked as the drone to be adjusted. Otherwise, if there is no intersection between the two, it is not selected. The intersection judgment method here indicates that there are the same or similar inspection tasks in the remaining inspection tasks.

[0049] All the drones to be adjusted are obtained, and the task completion ratios corresponding to the drones to be adjusted are calculated. The drones to be adjusted are sorted from large to small according to the task completion ratios. Then, the drones to be adjusted are selected according to their comprehensive performance and the adjustment standard information is generated.

[0050] In a specific example, suppose that the mission completion ratio of a11 is 70% and the mission completion ratio of a12 is 60%. A11 and a12 are sorted from large to small according to the mission completion ratio. If the comprehensive performance of a11 is better than a12 in terms of endurance, load capacity and flight stability, then a11 can be selected first for mission adjustment to generate adjustment standard information.

[0051] Specifically, the endurance, load capacity and flight stability are comprehensively scored, and the values ​​of the three are summed up and calculated. Finally, the UAV to be adjusted with the largest sum is selected as the standard to generate adjustment information.

[0052] In a specific example, it is assumed that there are three drones to be adjusted, namely drone A, drone B and drone C.

[0053] For drone A:

[0054] In terms of battery life, assuming the full score is 10, it is evaluated as 8 points based on factors such as battery capacity and power consumption.

[0055] In terms of load capacity, the full score is also 10 points. Considering the weight and type of equipment it can carry, it is rated 7 points.

[0056] In terms of flight stability, the full score is 10 points, and the score is 6 points based on its flight performance in different environments.

[0057] The comprehensive score of drone A = 8+7+6=21 points.

[0058] For Drone B:

[0059] The battery life is rated 7 points.

[0060] The load capacity is rated 8 points.

[0061] Flight stability was rated 7 points.

[0062] The overall score of drone B = 7+8+7 = 22 points.

[0063] For Drone C:

[0064] The battery life is rated 6 points.

[0065] The load capacity is rated 9 points.

[0066] Flight stability was rated 8 points.

[0067] The overall score of drone C = 6+9+8 = 23 points.

[0068] By comparison, drone C has the highest comprehensive score. At this time, the adjustment information is generated based on drone C. For example, in a power inspection task, drone C can be arranged to complete the inspection sub-area tasks that require higher endurance, load and stability. At the same time, the subsequent inspection routes and task allocations are reasonably planned according to its performance characteristics to ensure that the entire inspection work is carried out efficiently and stably.

[0069] Embodiment 2, as Embodiment 2 of the present invention, is implemented on the basis of Embodiment 1, and differs from Embodiment 1 in that:

[0070] In step S03, compared with the adjustment and judgment method of embodiment 1, the adjustment and judgment method of this embodiment is to analyze and identify the task progress, establish an inspection task progress management system, track the task execution status of the drone in real time, and record the completed tasks and remaining tasks according to the preset inspection route and task list. By calculating the task completion ratio and time progress, it can be judged whether the inspection status is normal. If the task progress lags behind the planned time, it may be due to drone failure, environmental factors or other reasons. It is necessary to adjust the task allocation in time or take measures to speed up the progress.

[0071] In a specific example, suppose there is an inspection area, and the preset inspection task list contains 100 checkpoints. It is planned to complete all inspection tasks within 5 hours, so an average of 20 checkpoints should be completed per hour. When the inspection is 2 hours in, 40 checkpoints should be completed according to the plan. However, through the real-time tracking of the inspection task progress management system, it is found that only 25 checkpoints have actually been completed. At this time, 25÷100, that is, the task completion ratio is 25%, and 2÷5, that is, the time progress is 40%. Obviously, the task completion ratio is lower than the expected ratio under the corresponding time progress, indicating that the task progress lags behind the planned time. It may be that strong winds in some areas affect the flight of drones, or a drone has a minor fault that causes the inspection speed to decrease. At this time, it can be considered to assign some tasks near the lagging area to other drones, or adjust the flight parameters of the affected drones to speed up the inspection progress.

[0072] Embodiment 3, as the embodiment 3 of the present invention, focuses on combining the implementation processes of embodiment 1 and embodiment 2.

[0073] Some of the data in the above formulas are dimensionless and numerically calculated. Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0074] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An intelligent inspection method based on drone inspection collaboration is characterized by: The method specifically comprises the following steps: Step S01, dividing the inspection area into inspection sub-areas, acquiring the inspection tasks of the inspection sub-areas, and generating planning inspection information; Step S02, performing a qualitative inspection analysis on the inspection sub-area according to the planned inspection information, screening standard inspection drones based on the basic information of the drones, and generating initial inspection information; Step S03, based on the generated initial inspection information, identifying the inspection status of the standard inspection drone, determining whether inspection adjustment is required, and generating inspection adjustment determination information; Step S04, analyzing the generated inspection and adjustment signal, screening different drones according to the task completion status, analyzing and selecting the adjustment drone in combination with the task intersection status, and generating adjustment information at the same time.

2. The intelligent inspection method based on drone inspection collaboration according to claim 1 is characterized in that: The specific method of performing inspection qualitative analysis on the inspection sub-area in step S02 is: Obtain all inspection sub-areas and label them as i, where i=1, 2, ..., j, where j represents the number of inspection sub-areas. At the same time, obtain the planned inspection information of inspection sub-area i, then score and evaluate the different inspection tasks in the planned inspection information, and characterize the inspection sub-areas based on the inspection tasks corresponding to the highest scoring values ​​to generate inspection qualitative information.

3. The intelligent inspection method based on drone inspection collaboration according to claim 1 is characterized in that: The specific method of generating the initial inspection information in step S02 is: All drones are obtained and labeled as a, where a=1, 2, ..., b, where b represents the number of drones. The basic information of the drones is then obtained, and the qualitative inspection information of the inspection sub-areas is obtained. The drones are selected based on their basic information to obtain standard inspection drones, and initial inspection information is generated.

4. The intelligent inspection method based on drone inspection collaboration according to claim 1 is characterized in that: The specific method of identifying the inspection status of the standard inspection drone in step S03 is: Take any standard inspection drone as the analysis object, obtain the inspection status information of the analysis object, and obtain the overall task inspection completion ratio of the analysis object. Get the total endurance of the standard inspection drone, record it as H, and get the current remaining endurance, record it as H1. Get the real-time inspection duration of the analysis object, record it as T1, and then calculate the remaining flight endurance based on the unfinished ratio.

5. The intelligent inspection method based on drone inspection collaboration according to claim 4 is characterized in that: The specific method of calculating the remaining flight endurance in step S03 is: Substitute the obtained parameters into the formula Calculate the unit consumption H of the standard inspection drone of the analysis object d , and θ is the completion ratio of task inspection, and ω is the preset proportional coefficient; At the same time, according to the unit consumption H d To calculate the remaining flight time, substitute the parameters into the formula H2 = H d ×(1-θ)×ω to obtain the remaining flight endurance H2, where (1-θ) is the unfinished proportion and ω is the preset proportional coefficient, and the remaining flight endurance H2 is compared with the remaining endurance H1.

6. The intelligent inspection method based on drone inspection coordination according to claim 5 is characterized in that: The specific method of comparing the remaining flight endurance with the remaining flight endurance in step S03 is: When the remaining endurance H1 is greater than the remaining flight endurance H2, no adjustment is required and a normal patrol signal is generated. Conversely, when the remaining endurance H1 is less than the remaining flight endurance H2, adjustment is required and a patrol adjustment signal is generated to further generate patrol adjustment judgment information.

7. The intelligent inspection method based on drone inspection collaboration according to claim 1 is characterized in that: The specific method of analyzing the inspection and adjustment signal in step S04 is: Get all normal inspection sub-areas and record them as n, where n=1, 2, ..., m, where m represents the number of normal inspection sub-areas. At the same time, get the inspection drones corresponding to the normal inspection sub-areas and record them as a1, where a1=1, 2, ..., b1, where b1 represents the number of drones in the corresponding area. At the same time, get the remaining inspection tasks of the normal inspection sub-areas, and make an intersection judgment on the remaining inspection tasks of the normal inspection sub-areas and the remaining inspection tasks of the adjustment area.

8. The intelligent inspection method based on drone inspection coordination according to claim 7 is characterized in that: The specific method of performing intersection judgment on the remaining inspection tasks in step S04 is: If there is an intersection between the two, the corresponding inspection drone will be marked as the drone to be adjusted. Otherwise, if there is no intersection between the two, it will not be selected.

9. The intelligent inspection method based on drone inspection collaboration according to claim 1 is characterized in that: The specific method of generating the adjustment information in step S04 is: All the drones to be adjusted are obtained, and the task completion ratios corresponding to the drones to be adjusted are calculated. The drones to be adjusted are sorted from large to small according to the task completion ratios. Then, the drones to be adjusted are selected according to their comprehensive performance and the adjustment standard information is generated.

10. The intelligent inspection method based on drone inspection coordination according to claim 9 is characterized in that: The specific method of selecting and generating adjustment standard information according to the comprehensive performance of the drone to be adjusted in step S04 is: The endurance, load capacity and flight stability of the UAV to be adjusted are comprehensively scored, and the comprehensive evaluation value of the UAV to be adjusted is calculated. At the same time, the UAV to be adjusted with the largest comprehensive evaluation value is selected to generate adjustment standard information.

Images