Unattended intelligent inspection scheduling method and system based on priori knowledge

Abstract

The embodiment of the invention provides an unattended intelligent inspection scheduling method and system based on priori knowledge, and belongs to the technical field of unmanned aerial vehicle inspection scheduling. The unattended intelligent routing inspection scheduling method comprises the steps that routing inspection information of a current electric power system is acquired, and the routing inspection information comprises multiple pieces of machine nest group coordinate information and multiple pieces of tower coordinate information; the inspection information of the current power system is obtained, the initial inspection path is obtained according to the inspection information, then the unmanned aerial vehicles in the multiple aircraft nest groups are driven to execute the inspection task at the same time according to the initial inspection path, and when the multiple unmanned aerial vehicles conduct inspection at the same time, the real-time flight information of each unmanned aerial vehicle is obtained; the flight state of the unmanned aerial vehicle is determined according to the real-time flight information, an inspection path is adjusted, and an inspection task is executed according to the inspection path; and by adopting a multi-unmanned aerial vehicle synchronous inspection mode, a complex inspection scene can be simplified, and the efficiency and effect of unmanned aerial vehicle inspection are greatly improved.

Description

Technical Field

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

[0002] Power system inspections are the process of regularly inspecting, maintaining, and troubleshooting power equipment and facilities to ensure the stability, safety, and efficiency of the power system. For older distribution networks in rural and urban areas, regular, multi-point inspections of transmission towers are necessary to maintain line reliability.

[0003] Currently, transmission tower inspections are performed manually or by drones. Manual inspections require significant manpower and resources, are inefficient, and pose safety risks, leading to the widespread adoption of drones. Existing drone inspections typically rely on manual control, meaning one person per drone. However, this approach still requires specialized personnel, imposes stringent inspection conditions, and is only suitable for inspecting simple distribution towers. For complex distribution lines, inspection efficiency is low and control is challenging.

[0004] The inventors of this application discovered during the process of realizing the present invention that the above-mentioned solutions in the prior art have the defects of low inspection efficiency and great control difficulty. Summary of the Invention

[0005] The purpose of the embodiments of the present invention is to provide an unmanned intelligent inspection scheduling method and system based on prior knowledge, which has the functions of high inspection efficiency and convenient control.

[0006] To achieve the above objectives, an embodiment of the present invention provides an unmanned intelligent inspection scheduling method based on prior knowledge, comprising:

[0007] Obtaining inspection information of the current power system, wherein the inspection information includes coordinate information of multiple machine nest groups and coordinate information of multiple towers;

[0008] Acquire an initial inspection path according to the inspection information;

[0009] Driving the drones in the multiple machine nest groups to perform inspection tasks according to the initial inspection path;

[0010] Obtain the flight information of the current drone;

[0011] Determine the flight status of the drone based on the current flight information of the drone and adjust the inspection path;

[0012] Perform inspection tasks according to the inspection path.

[0013] Optionally, acquiring an initial inspection path according to the inspection information includes:

[0014] Divide a plurality of inspection areas according to the tower coordinate information;

[0015] Moving the plurality of machine nest groups to random positions of the plurality of inspection areas respectively;

[0016] An initial inspection path of the UAV is obtained according to the position of the machine nest group and the coordinate information of multiple towers in the inspection area.

[0017] Optionally, obtaining an initial inspection path of the UAV according to the position of the drone nest group and the coordinate information of multiple towers within the inspection area includes:

[0018] Perform preliminary screening of multiple tower coordinate information to obtain the coordinates of the tower to be flown;

[0019] The initial inspection path of the UAV is obtained according to the coordinates of the tower to be flown.

[0020] Optionally, preliminary screening of multiple tower coordinate information to obtain the coordinates of the tower to be flown includes:

[0021] Determining whether the tower coordinate information is located in a no-fly zone;

[0022] If it is determined that the tower coordinate information is located in a no-fly zone, deleting the tower coordinate information;

[0023] If it is determined that the tower coordinate information is not located in a no-fly zone, determining whether the tower corresponding to the tower coordinate information needs inspection;

[0024] When it is determined that the pole tower corresponding to the pole tower coordinate information needs to be inspected, obtaining the inspection point coordinates of the pole tower;

[0025] When it is determined that the pole tower corresponding to the coordinate information of the pole tower does not need to be inspected, the safety point coordinates of the pole tower are obtained.

[0026] Optionally, obtaining the current flight information of the UAV includes:

[0027] Obtain the real-time location coordinates and real-time remaining power of the current drone;

[0028] Obtain the drone nest group of the inspection area where the drone is currently located and its adjacent inspection areas;

[0029] Determine whether there is a vacancy signal in the nest group;

[0030] When it is determined that there is a vacant position signal in the machine nest group, the coordinates of the machine nest group are obtained.

[0031] Optionally, determining the flight status of the drone according to the current flight information of the drone and adjusting the inspection path includes:

[0032] According to formula (1), the real-time available power of the current drone is obtained.

[0033] Q U =Q F -Q L , (1)

[0034] Among them, Q U is the real-time available power of the current drone, Q F is the real-time remaining power of the current drone, Q L The remaining safe power of the drone;

[0035] Determine whether the current real-time available power of the drone is greater than or equal to a power threshold;

[0036] If it is determined that the current real-time available power of the drone is greater than or equal to the power threshold, it is determined that the current drone has sufficient power and continues to execute the inspection route;

[0037] When it is determined that the current real-time available power of the drone is less than the power threshold, it is determined that the current power of the drone is insufficient, and the drone is driven to be charged.

[0038] Optionally, driving the drone to charge includes:

[0039] Get the coordinates of the current machine nest group;

[0040] According to formula (2), the shortest distance between the current UAV and the nest group is obtained.

[0041]

[0042] Wherein, L is the distance between the current UAV and the nest group, x j is the x-axis coordinate of the nest group j, y j is the y-axis coordinate of the nest group j, z j is the z-axis coordinate of the nest group j, x t is the x-axis coordinate of the current drone, y t is the y-axis coordinate of the current drone, z t is the z-axis coordinate of the current drone, and j is an integer number;

[0043] According to formula (3), the power requirements of the current UAV and the nearest nest group are obtained.

[0044]

[0045] Among them, Q x is the required power, x jmin is the x-axis coordinate of the nest group closest to the current drone, and y jmin is the y-axis coordinate of the nest group closest to the current drone, z jmin is the z-axis coordinate of the nest group closest to the current drone, v is the flight speed of the drone, q v is the power consumption per unit time of the UAV when its flight speed is v.

[0046] Optionally, driving the drone to charge further includes:

[0047] Determine whether the current power demand of the drone is greater than the real-time remaining power;

[0048] If it is determined that the current power demand of the drone is greater than the real-time remaining power, driving the drone to land at an emergency point and issuing an emergency landing warning;

[0049] When it is determined that the current power requirement of the UAV is less than or equal to the real-time remaining power, the UAV is driven to land at the nearest nest group.

[0050] Optionally, determining the flight status of the drone according to the current flight information of the drone and adjusting the inspection path further includes:

[0051] Obtain the number of inspection points remaining in the inspection path within the current inspection area;

[0052] Determine whether the number of remaining inspection points in the inspection path within the current inspection area is less than or equal to 0;

[0053] If it is determined that the number of inspection points remaining in the inspection path within the current inspection area is less than or equal to 0, determine whether the number of inspection points remaining in the inspection path of the adjacent inspection area of ​​the current inspection area is greater than 0;

[0054] When it is determined that the number of remaining inspection points in the inspection path of the adjacent inspection area of ​​the current inspection area is greater than 0, the drone in the current inspection area and the drone in the adjacent inspection area cooperate to perform inspection;

[0055] When it is determined that the number of remaining inspection points in the inspection path of the adjacent inspection area of ​​the current inspection area is less than or equal to 0, the drone is driven to return to the drone nest group corresponding to the current inspection area;

[0056] When it is determined that the number of remaining inspection points in the inspection path within the current inspection area is greater than 0, the inspection task is continued.

[0057] On the other hand, the present invention also provides an unmanned intelligent inspection and dispatching system based on prior knowledge, comprising:

[0058] Multiple vehicle-mounted drone nest groups, each including a drone and two drone parking points;

[0059] The server is communicatively connected to the plurality of vehicle-mounted machine nest groups, and is used to execute any of the above-described unmanned intelligent inspection and scheduling methods.

[0060] Through the above technical solution, the unmanned intelligent inspection scheduling method and system based on prior knowledge provided by the present invention obtains the inspection information of the current power system, and obtains the initial inspection path according to the inspection information, and then drives the drones in multiple machine nest groups to perform inspection tasks at the same time according to the initial inspection path. When multiple drones are inspecting at the same time, the real-time flight information of each drone is obtained, the flight status of the drone is determined according to the real-time flight information, and the inspection path is adjusted, and the inspection task is performed according to the inspection path; the method of synchronous inspection of multiple drones can, on the one hand, simplify complex inspection scenarios and greatly improve the efficiency and effectiveness of drone inspections; on the other hand, it can realize autonomous inspection of drones, which is more intelligent and convenient.

[0061] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following detailed description, they are used to explain the embodiments of the present invention, but do not constitute a limitation of the embodiments of the present invention. In the accompanying drawings:

[0063] Figure 1 is a flow chart of an unmanned intelligent inspection scheduling method according to an embodiment of the present invention;

[0064] Figure 2 This is a flow chart of obtaining an initial inspection path based on inspection information in an unmanned intelligent inspection scheduling method according to an embodiment of the present invention;

[0065] Figure 3 This is a flow chart of obtaining an initial inspection path based on coordinates in an unmanned intelligent inspection scheduling method according to an embodiment of the present invention;

[0066] Figure 4 This is a flowchart of selecting towers in an unmanned intelligent inspection and scheduling method according to an embodiment of the present invention;

[0067] Figure 5 This is a flow chart of obtaining the flight information of a UAV in an unmanned intelligent inspection scheduling method according to an embodiment of the present invention;

[0068] Figure 6 This is a flow chart of analyzing the flight status of a drone in an unmanned intelligent inspection scheduling method according to an embodiment of the present invention;

[0069] Figure 7 The present invention is a flowchart of driving a drone to charge in an unmanned intelligent inspection scheduling method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0070] The following describes the specific implementation of the embodiment of the present invention in detail with reference to the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the embodiment of the present invention and is not used to limit the embodiment of the present invention.

[0071] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations. In the embodiments of this application, certain software, components, models, and other existing solutions in the industry may be mentioned. These should be considered as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of this application, but it does not mean that the applicant has or will necessarily use such solutions.

[0072] Figure 1 This is a flow chart of an unmanned intelligent inspection scheduling method according to an embodiment of the present invention. Figure 1 In the present invention, the unmanned intelligent inspection scheduling method may include:

[0073] In step S10, inspection information for the current power system is obtained. This inspection information includes the coordinate information of multiple machine nest groups and multiple tower coordinate information. Specifically, a machine nest group may include two drone locations. Initially, one location is occupied by a drone, while the other is vacant for other drones to dock. Tower coordinate information may include the coordinate location of the tower and its surroundings. Specifically, a machine nest group may include vehicle-mounted machine nests.

[0074] In step S11, an initial inspection path is obtained based on the inspection information. After obtaining the coordinate information of multiple drone nest groups and multiple towers, the initial inspection path can be determined based on this information. Specifically, the initial inspection path includes the initial inspection paths of multiple drones.

[0075] In step S12, the drones in the multiple machine nest groups are driven to perform inspection tasks according to the initial inspection paths. After the initial inspection paths of the multiple drones are obtained, the multiple drones can be driven to perform inspections along the corresponding initial inspection paths.

[0076] In step S13, the current UAV flight information is obtained, wherein the UAV flight information may include the real-time location of the UAV, the real-time remaining power, the coordinates of the drone nest group, etc.

[0077] In step S14, the drone's flight status is determined based on the current drone's flight information, and the inspection path is adjusted. After obtaining the drone's current flight information, the drone's flight status is determined based on this information, and the inspection path is adjusted accordingly. Specifically, this adjustment includes both modification and non-modification.

[0078] In step S15, the inspection task is executed according to the inspection path. After the inspection path is adjusted, the inspection is performed according to the adjusted inspection path, which includes executing the inspection task according to the original inspection path and executing the inspection task according to the modified inspection path.

[0079] In steps S10 through S15, the system first obtains inspection information for the current power system, then determines initial inspection routes for multiple drones based on this information. The drones in each of the multiple nest groups are then driven to perform inspections along their corresponding initial inspection routes, while simultaneously acquiring real-time flight information about the drones. The system then determines the drones' flight status based on their real-time flight information, adjusts the latest inspection routes, and executes inspections based on the real-time inspection routes.

[0080] Traditional inspections of transmission towers include manual inspections and drone inspections. Manual inspections require a lot of manpower and material resources, and have low inspection efficiency and certain safety hazards. Therefore, drone inspections are often used. Existing drone inspections are generally carried out with manual assisted control, that is, one person and one machine. However, this method still requires professional personnel to operate, and the inspection conditions are harsh. It can only inspect simple towers of distribution lines. For complex distribution lines, the inspection efficiency is low and the control is difficult. In this embodiment of the present invention, a method of synchronous inspection of drones using multiple machine nest groups is adopted. On the one hand, it can simplify complex inspection scenes and greatly improve the efficiency and effectiveness of drone inspections. On the other hand, it can realize autonomous drone inspections, which is more intelligent and convenient.

[0081] In this embodiment of the present invention, the coordinate information of multiple nest groups and multiple tower coordinate information can effectively display the relative position relationship between the transmission tower and the nest, and then the initial inspection path of the drone can be determined. The specific determination steps can be as follows: Figure 2Specifically, Figure 2 In the embodiment, the unmanned intelligent inspection scheduling method may further include:

[0082] In step S110, multiple inspection areas are divided based on the tower coordinate information. Before inspecting the towers, multiple inspection areas are first divided based on the distribution of the towers. Specifically, the inspection areas can be divided based on the number of towers or the total time required for regional inspections.

[0083] In step S111, multiple machine nest groups are moved to random positions in multiple inspection areas. The position of the machine nest group can be any position in the corresponding inspection area, or the vehicle-mounted machine nest can be driven to move to the starting position of the inspection path corresponding to the inspection area.

[0084] In step S112, the initial inspection path of the UAV is obtained based on the position of the machine nest group and the coordinate information of multiple towers in the inspection area. After determining the position of the machine nest group and the coordinate information of multiple towers in the inspection area, the initial inspection path in the inspection area can be converted. The specific conversion steps can be as follows: Figure 3 Specifically, Figure 3 In the embodiment, the unmanned intelligent inspection scheduling method may further include:

[0085] In step S1120, the coordinate information of multiple towers is preliminarily screened to obtain the coordinates of the tower to be flown. Among them, for some towers in the city, considering the obstruction of buildings and the impact on people's lives, the coordinate information of multiple towers in the inspection area needs to be further screened. The specific screening steps can be as follows: Figure 4 Specifically, Figure 4 In the tower screening step, the tower screening step may include:

[0086] In step S11200, it is determined whether the tower coordinate information is located in a no-fly zone. Certain areas within a city may have no-fly zones in consideration of confidentiality and security. Specifically, safe areas can be planned in advance, and high-rise buildings can be designated as no-fly zones.

[0087] In step S11201, if the tower coordinate information is determined to be located in a no-fly zone, the tower coordinate information is deleted. If the tower coordinate information is located in a no-fly zone, the tower coordinate information is canceled and deleted to meet regional flight requirements.

[0088] In step S11202, if the tower coordinates are determined not to be located in a no-fly zone, a determination is made as to whether the tower corresponding to the tower coordinates requires inspection. In non-no-fly zones, drones can fly below 120 meters, but should avoid crowded areas and obstacles such as tall buildings. If the tower corresponding to the tower coordinates is not located in a no-fly zone, further determination is made as to whether the tower requires inspection.

[0089] In step S11203, if it is determined that the tower corresponding to the tower coordinate information requires inspection, the inspection point coordinates of the tower are obtained. If the tower corresponding to the tower coordinate information requires inspection, it is necessary to obtain the preset waypoints and hovering time of the tower, that is, the inspection point and inspection time, so as to fully inspect the tower.

[0090] In step S11204, if it is determined that the tower corresponding to the tower coordinate information does not require inspection, the safety point coordinates of the tower are obtained. If the tower corresponding to the tower coordinate information does not require inspection, the safety passing point of the tower, i.e., the safety point coordinates of the tower, is obtained.

[0091] In steps S11200 to S11204, the tower coordinate information is first diagnosed to determine whether the corresponding tower is located in a no-fly zone. If the tower corresponding to the tower coordinate information is located in a no-fly zone, the tower coordinate information is cancelled and deleted. Otherwise, it is necessary to further determine whether the tower requires inspection. If the tower is located in a non-no-fly zone and requires inspection, the inspection point and hovering time of the tower are obtained. If the tower is located in a non-no-fly zone and does not require inspection, the coordinates of the safe point of the tower are obtained.

[0092] In step S1121, the initial inspection path of the drone is obtained based on the coordinates of the tower to be flown. The coordinates of the tower to be flown include the coordinates of multiple inspection points on the tower or the coordinates of safety points on the tower. The initial inspection path can be planned based on the principle of shortest path / shortest flight time, and a particle swarm algorithm can be used to find the optimal path.

[0093] In step S1120 to step S1121, the coordinate information of multiple towers is preliminarily screened, and the towers in the no-fly zone are removed to obtain the coordinates of multiple towers to be flown. The optimal initial inspection path of the drone can be planned based on the coordinates of the multiple towers to be flown.

[0094] In steps S110 through S112, multiple inspection areas are first divided based on the tower coordinates within the city. Multiple drone nests are then moved to random locations within each inspection area, and their coordinates are obtained. Based on the drone nest coordinates and the tower coordinates, the initial drone inspection path is determined, subject to the shortest path constraint.

[0095] In this embodiment of the present invention, when driving the drone to perform the inspection task according to the inspection path, it is necessary to always pay attention to the real-time power of the drone to ensure that the drone can stably perform the inspection task, that is, to obtain the flight information of the drone in real time. The specific acquisition steps can be as follows: Figure 5 Specifically, Figure 5 In the step of obtaining, the step of obtaining may include:

[0096] In step S130, the real-time position coordinates and real-time remaining power of the current drone are obtained. The real-time position coordinates of the current drone can be obtained in real time using an RTK module. The real-time position and real-time remaining power of the drone can reflect the current flight range of the drone.

[0097] In step S131, the drone's landing nest groups in the current inspection area and its adjacent inspection areas are obtained. Considering that during the inspection process, the drone's closest landing nest group is not limited to the nest groups within the inspection area, but may also include nest groups in adjacent inspection areas, the nest groups in adjacent inspection areas may also be considered when determining the landing nest group.

[0098] In step S132, it is determined whether there is a vacant parking signal in the machine nest group. A machine nest group may include two drone parking spaces. If there is a vacant parking space in the current machine nest group, a vacant parking signal will be sent, otherwise no vacant parking signal will be sent.

[0099] In step S133, if it is determined that there is a vacant position signal for the nest group, the coordinates of the nest group are obtained. If there is a vacant position signal for the nest group, it means that the nest group can be used for landing and charging of drones; if there is no vacant position signal for the nest group, it means that there are no parking spaces in the nest group, and thus the drone cannot be landed and charged.

[0100] In steps S130 through S133, the current drone's real-time RTK coordinates and remaining battery power are first acquired. Then, the drone's current inspection area and adjacent inspection areas are retrieved. If a nest group has vacant slots, indicating a parking space within that nest group, the coordinates of that nest group are acquired and used as available charging slots. Specifically, if a drone locates the nearest available charging nest group and prepares to fly toward it, the nest group's vacant slot information is updated promptly to avoid interference with other drones.

[0101] In this embodiment of the present invention, after obtaining the flight information of the UAV during flight, it is also necessary to analyze the current flight status of the UAV to determine how to adjust the inspection path. The specific analysis steps can be as follows: Figure 6 Specifically, Figure 6 In the example, the analyzing step may include:

[0102] In step S140, the real-time available power of the current drone is obtained according to formula (1):

[0103] Q U =Q F -Q L , (1)

[0104] Among them, Q U is the current real-time available power of the drone, Q F The current real-time remaining power of the drone, Q L The remaining safe power of the drone.

[0105] In step S141, it is determined whether the current real-time available power of the drone is greater than or equal to a power threshold. The power threshold is generally set to a small value, i.e., a warning power level.

[0106] In step S142, if the current drone's real-time available power is greater than or equal to the power threshold, the drone is determined to have sufficient power and the inspection route continues to be executed. If the current drone's real-time available power is greater than or equal to the power threshold, it indicates that the drone has sufficient power and can execute the inspection task according to the inspection route.

[0107] In step S143, when it is determined that the real-time available power of the current drone is less than the power threshold, it is determined that the current drone is short of power, and the drone is driven to charge. Among them, if the real-time available power of the current drone is less than the power threshold, it means that the current drone is short of power. Specifically, the inspection route planning of the same batch is generally planned according to the capabilities that the drone can complete, that is, the drone can complete the inspection according to the inspection route. However, for sudden situations, such as sudden power failure due to battery damage, it is necessary to suspend the inspection of the drone and land at the nearest machine nest group for charging or waiting for maintenance. For non-batch planning situations, the drone needs to replenish power in time and complete subsequent inspection tasks. Specifically, the method for quickly charging the drone and adjusting the inspection route can be as follows. Figure 7 Specifically, Figure 7 In the embodiment, the unmanned intelligent inspection scheduling method may further include:

[0108] In step S1430, the coordinates of the current nest group are obtained, wherein the coordinates of the current nest group are also the coordinates of the nest group with the vacancy signal.

[0109] In step S1431, the shortest distance between the current drone and the nest group is obtained according to formula (2):

[0110]

[0111] Among them, L is the distance between the current UAV and the nest group, x j is the x-axis coordinate of the nest group j, y j is the y-axis coordinate of the nest group j, z j is the z-axis coordinate of the nest group j, x t is the x-axis coordinate of the current drone, y t is the y-axis coordinate of the current drone, z t is the z-axis coordinate of the current drone, and j is an integer number.

[0112] In step S1432, the power requirements of the current drone and the nearest drone nest group are obtained according to formula (3):

[0113]

[0114] Among them, Q x is the power demand, x jmin is the x-axis coordinate of the nest group closest to the current drone, and y jmin is the y-axis coordinate of the nest group closest to the current drone, z jmin is the z-axis coordinate of the nest group closest to the current drone, v is the flight speed of the drone, q v is the power consumption per unit time of the drone when the flight speed is v. Specifically, considering that the flight path of the drone is affected by factors such as obstacles and no-fly zones in the city, the longest flight path of the drone is used as the flight path for power conversion.

[0115] In step S1433, it is determined whether the current power requirement of the drone is greater than the real-time remaining power.

[0116] In step S1434, if the current drone power demand is greater than the real-time remaining power, the drone is driven to land at the emergency point and an emergency landing warning is issued. If the current drone power demand is greater than the real-time remaining power, it indicates that the remaining power is insufficient to support the drone to fly to the nearest nest group, posing a risk of power outage. Therefore, the drone is driven to land at the emergency point and an emergency landing warning is issued, notifying personnel to handle the situation.

[0117] In step S1435, if the current drone power demand is less than or equal to the real-time remaining power, the drone is driven to land at the nearest nest group. If the current drone power demand is less than or equal to the real-time remaining power, it means that the remaining power is sufficient to support the drone to fly to the nearest nest group, and the drone can be driven to land at the nearest nest group for charging.

[0118] In steps S1430 to S1435, the coordinates of the current nest group with vacancies are obtained, the distances between the current drone and multiple nest groups with vacancies are calculated, the shortest distance is selected, and the required power for flight is calculated. By comparing the required power with the current drone's real-time remaining power, it can be determined whether the current drone can fly to the nearest nest group for charging. If the current drone cannot fly to the nearest nest group, it can select an emergency landing point and notify staff for processing. This method can realize autonomous inspection and autonomous charging of drones, making inspections more convenient and efficient.

[0119] In step S144, the number of remaining inspection points in the inspection path within the current inspection area is obtained. The number of remaining inspection points in the inspection path can be determined by sequentially numbering each inspection point in the inspection path.

[0120] In step S145 , it is determined whether the number of remaining inspection points in the inspection path within the current inspection area is less than or equal to 0.

[0121] In step S146, if it is determined that the number of inspection points remaining in the inspection path of the current inspection area is less than or equal to 0, it is determined whether the number of inspection points remaining in the inspection path of the adjacent inspection area of ​​the current inspection area is greater than 0. If the number of inspection points remaining in the current inspection path is less than or equal to 0, it means that the inspection in the current inspection area is completed, and it is necessary to further determine whether the inspection path of the adjacent area is completed.

[0122] In step S147, if it is determined that the number of inspection points remaining in the inspection path of the adjacent inspection area of ​​the current inspection area is greater than 0, the drone in the current inspection area cooperates with the drone in the adjacent inspection area to perform an inspection. If the number of inspection points remaining in the inspection path of the adjacent inspection area is greater than 0, it means that the adjacent inspection area has not been inspected, and the drone is driven to conduct a coordinated inspection with the drone in the adjacent inspection area to further improve inspection efficiency.

[0123] In step S148, if it is determined that the number of inspection points remaining in the inspection path of the adjacent inspection area of ​​the current inspection area is less than or equal to 0, the drone is driven to return to the machine nest group corresponding to the current inspection area. If the number of inspection points remaining in the inspection path of the adjacent inspection area is less than or equal to 0, it means that the adjacent inspection area has also been inspected, and the drone is driven to return to the starting machine nest group.

[0124] In step S149, if it is determined that the number of inspection points remaining in the inspection path within the current inspection area is greater than 0, the inspection task is continued. If there are still inspection points remaining in the inspection path within the current inspection area, it means that the inspection within the current inspection area is not completed, and the remaining inspection tasks are continued.

[0125] In steps S140 to S149, the real-time available power of the current drone is first obtained and compared with the power threshold. If the real-time available power of the drone is greater than or equal to the power threshold, it means that the current drone has sufficient power and can continue to perform the inspection task. Otherwise, it means that the current drone is insufficiently powered and needs to be charged before inspection can be performed. After the drone is fully charged, it is necessary to continue to perform the remaining inspection tasks. If the inspection tasks in the inspection area are executed, it is necessary to continue to determine whether the inspection tasks in the adjacent inspection areas have been completed. If the inspection tasks in the adjacent inspection areas are also completed, it returns to the starting machine nest group. Otherwise, it cooperates with the drones in the adjacent inspection areas to perform the inspection tasks, thereby further effectively improving the inspection efficiency and intelligence.

[0126] In this embodiment of the present invention, the acquisition of the initial inspection path of the drone can be planned based on the actual flight inspection capability of the drone. Specifically, the drone can inspect approximately 10-15 distribution network towers at a time. Based on the coordinates of multiple towers in each inspection area and the coordinates of the machine nest group, the total flight time is used as a constraint to select the number of distribution network towers to be inspected to ensure that multiple drones can complete the inspection in one batch. After the first batch of inspections is completed, it is possible to continue to determine whether there are towers to be inspected in each inspection area. If so, a second batch of inspections will be carried out according to the same constraints, otherwise the inspection will end. This method can effectively improve the stability and safety of drone inspections.

[0127] In another aspect, the present invention also provides an unmanned intelligent inspection and scheduling system based on prior knowledge. Specifically, the unmanned intelligent inspection and scheduling system may include multiple vehicle-mounted drone nest groups and a server. Specifically, the vehicle-mounted drone nest groups may include drones and two drone parking points. The server is communicatively connected to the multiple vehicle-mounted drone nest groups to execute any of the above unmanned intelligent inspection and scheduling methods.

[0128] Through the above technical solution, the unmanned intelligent inspection scheduling method and system based on prior knowledge provided by the present invention obtains the inspection information of the current power system, and obtains the initial inspection path according to the inspection information, and then drives the drones in multiple machine nest groups to perform inspection tasks at the same time according to the initial inspection path. When multiple drones are inspecting at the same time, the real-time flight information of each drone is obtained, the flight status of the drone is determined according to the real-time flight information, and the inspection path is adjusted, and the inspection task is performed according to the inspection path; the method of synchronous inspection of multiple drones can, on the one hand, simplify complex inspection scenarios and greatly improve the efficiency and effectiveness of drone inspections; on the other hand, it can realize autonomous inspection of drones, which is more intelligent and convenient.

[0129] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0130] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0131] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0132] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0133] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0134] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0135] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0136] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0137] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. An unmanned intelligent inspection scheduling method based on prior knowledge, characterized in that: include: Obtaining inspection information of the current power system, wherein the inspection information includes coordinate information of multiple machine nest groups and coordinate information of multiple towers; Acquire an initial inspection path according to the inspection information; Driving the drones in the multiple machine nest groups to perform inspection tasks according to the initial inspection path; Obtain the flight information of the current drone; Determine the flight status of the drone based on the current flight information of the drone and adjust the inspection path; Perform inspection tasks according to the inspection path.

2. The unmanned intelligent inspection and dispatching method according to claim 1, characterized in that: Acquiring an initial inspection path according to the inspection information includes: Divide a plurality of inspection areas according to the tower coordinate information; Moving the plurality of machine nest groups to random positions of the plurality of inspection areas respectively; An initial inspection path of the UAV is obtained according to the position of the machine nest group and the coordinate information of multiple towers in the inspection area.

3. The unmanned intelligent inspection and dispatching method according to claim 2, characterized in that: Acquiring an initial inspection path of the UAV according to the position of the drone nest group and the coordinate information of multiple towers in the inspection area includes: Perform preliminary screening of multiple tower coordinate information to obtain the coordinates of the tower to be flown; The initial inspection path of the UAV is obtained according to the coordinates of the tower to be flown.

4. The unmanned intelligent inspection and dispatching method according to claim 3 is characterized in that: Perform a preliminary screening of multiple tower coordinate information to obtain the coordinates of the tower to be flown, including: Determining whether the tower coordinate information is located in a no-fly zone; If it is determined that the tower coordinate information is located in a no-fly zone, deleting the tower coordinate information; If it is determined that the tower coordinate information is not located in a no-fly zone, determining whether the tower corresponding to the tower coordinate information needs inspection; When it is determined that the pole tower corresponding to the pole tower coordinate information needs to be inspected, obtaining the inspection point coordinates of the pole tower; When it is determined that the pole tower corresponding to the coordinate information of the pole tower does not need to be inspected, the safety point coordinates of the pole tower are obtained.

5. The unmanned intelligent inspection and dispatching method according to claim 2, characterized in that: Obtaining the current UAV's flight information includes: Obtain the real-time location coordinates and real-time remaining power of the current drone; Obtain the drone nest group of the inspection area where the drone is currently located and its adjacent inspection areas; Determine whether there is a vacancy signal in the nest group; When it is determined that there is a vacant position signal in the machine nest group, the coordinates of the machine nest group are obtained.

6. The unmanned intelligent inspection and dispatching method according to claim 5, characterized in that: Determining the flight status of the drone according to the current flight information of the drone and adjusting the inspection path includes: According to formula (1), the real-time available power of the current drone is obtained. Q U =Q F -Q L , (1) Among them, Q U is the real-time available power of the current drone, Q F is the real-time remaining power of the current drone, Q L The remaining safe power of the drone; Determine whether the current real-time available power of the drone is greater than or equal to a power threshold; If it is determined that the current real-time available power of the drone is greater than or equal to the power threshold, it is determined that the current drone has sufficient power and continues to execute the inspection route; When it is determined that the current real-time available power of the drone is less than the power threshold, it is determined that the current power of the drone is insufficient, and the drone is driven to be charged.

7. The unmanned intelligent inspection and dispatching method according to claim 6, characterized in that: Driving the drone to charge includes: Get the coordinates of the current machine nest group; According to formula (2), the shortest distance between the current UAV and the nest group is obtained. Wherein, L is the distance between the current UAV and the nest group, x j is the x-axis coordinate of the nest group j, y j is the y-axis coordinate of the nest group j, z j is the z-axis coordinate of the nest group j, x t is the x-axis coordinate of the current drone, y t is the y-axis coordinate of the current drone, z t is the z-axis coordinate of the current drone, and j is an integer number; According to formula (3), the power requirements of the current UAV and the nearest nest group are obtained. Among them, Q x is the required power, x jmin is the x-axis coordinate of the nest group closest to the current drone, and y jmin is the y-axis coordinate of the nest group closest to the current drone, z jmin is the z-axis coordinate of the nest group closest to the current drone, v is the flight speed of the drone, q v is the power consumption per unit time of the UAV when its flight speed is v.

8. The unmanned intelligent inspection and dispatching method according to claim 7, characterized in that: Driving the drone to charge also includes: Determine whether the current power demand of the drone is greater than the real-time remaining power; If it is determined that the current power demand of the drone is greater than the real-time remaining power, driving the drone to land at an emergency point and issuing an emergency landing warning; When it is determined that the current power requirement of the UAV is less than or equal to the real-time remaining power, the UAV is driven to land at the nearest nest group.

9. The unmanned intelligent inspection and dispatching method according to claim 6, characterized in that: Determining the flight status of the drone according to the current flight information of the drone and adjusting the inspection path further includes: Obtain the number of inspection points remaining in the inspection path within the current inspection area; Determine whether the number of remaining inspection points in the inspection path within the current inspection area is less than or equal to 0; If it is determined that the number of inspection points remaining in the inspection path within the current inspection area is less than or equal to 0, determine whether the number of inspection points remaining in the inspection path of the adjacent inspection area of ​​the current inspection area is greater than 0; When it is determined that the number of remaining inspection points in the inspection path of the adjacent inspection area of ​​the current inspection area is greater than 0, the drone in the current inspection area and the drone in the adjacent inspection area cooperate to perform inspection; When it is determined that the number of remaining inspection points in the inspection path of the adjacent inspection area of ​​the current inspection area is less than or equal to 0, the drone is driven to return to the drone nest group corresponding to the current inspection area; When it is determined that the number of remaining inspection points in the inspection path within the current inspection area is greater than 0, the inspection task is continued.

10. An unmanned intelligent inspection and dispatching system based on prior knowledge, characterized in that: include: Multiple vehicle-mounted drone nest groups, each including a drone and two drone parking points; The server is communicatively connected to the plurality of vehicle-mounted machine nest groups, and is used to execute the unmanned intelligent inspection and scheduling method as described in any one of claims 1 to 9.

Images