A flight inspection method and system based on intelligent unmanned aerial vehicles

Abstract

The present invention discloses a flight inspection method and system based on an intelligent unmanned aerial vehicle, relating to the technical field of unmanned aerial vehicle inspection, including: establishing a remote control and telemetry link and a data link between the unmanned aerial vehicle and the ground control station, evaluating the task requirements of the unmanned aerial vehicle, and determining and testing and verifying the required minimum endurance time; obtaining the unmanned aerial vehicle status data through the remote control and telemetry link, and transmitting the unmanned aerial vehicle status data to the ground control station, and the ground control station calculates the flight trajectory according to the obtained unmanned aerial vehicle status data; the ground control sends a flight control instruction to the unmanned aerial vehicle and sends a task operation instruction to the mission payload system; the unmanned aerial vehicle executes the received flight control instruction and task operation instruction, and feeds back the execution status and task data to the ground control station through the data link, continuously monitoring and recording the flight status and task data. The present invention can continuously collect data, transmit data in real time, and does not require multiple collections, improving the inspection work efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of drone patrol, and specifically provides a flight patrol method and system based on intelligent drones. Background Art

[0002] In 2019, Hainan Power Grid put into operation a drone operation support platform, including two major systems: an aircraft patrol sharing platform and operation tool classes. The operation management platform is mainly used for the control of drone inspection plans and the input of inspection results. The operation tool software includes an automatic driving APP, route design, equipment defect identification, and tree obstacle hazard analysis tools, etc. Up to now, Hainan Power Grid has a total of 272 drones, including 49 special drones (such as flamethrower, infrared, night vision, lidar, night lighting, etc.), 5 fixed-wing drones, and 205 training aircraft, and is equipped with corresponding aircraft patrol data workstations and processing software.

[0003] In 2023, Hainan Power Grid used drones to patrol 7,227.8 kilometers of transmission lines and 7,382 kilometers of corridors, and discovered 8,800 defects. Drone inspection can provide real-time information to support disaster assessment and emergency repair decision-making. Under extreme weather conditions such as continuous typhoons, Hainan Power Grid mobilized more than a hundred drones to conduct pre-disaster inspections and post-disaster obstacle inspections, giving full play to the emergency response capabilities of drones. Drones equipped with functions such as night vision and infrared can effectively conduct inspections at night and in complex environments. The use of fixed-wing drones has improved the efficiency of post-disaster investigation and rapid corridor inspections. Generally speaking, drone line patrol is more efficient than traditional manual line patrol, saving human resources, and has become the general pattern of "mainly aircraft patrol and supplemented by human patrol" in Hainan Power Grid. However, there are still some problems in the existing drone inspection operations: the amount of data collected in a single time is limited, and multiple shootings are required, which affects the inspection efficiency. The endurance of some models is poor, unable to meet the inspection requirements of long lines, and may even lead to the risk of crashing and economic losses.

[0004] Generally speaking, Hainan Power Grid has fully introduced drones to conduct transmission line inspections and achieved remarkable benefits, but there is still room for further improvement and perfection in terms of airborne equipment performance, data processing, and personnel training. Summary of the Invention

[0005] In view of the above existing problems, the present invention is proposed.

[0006] Therefore, to solve the above technical problems, the present invention provides the following technical solution: A flight patrol method based on intelligent drones, including: establishing a remote control and telemetry link and a data link between the drone and the ground control station, evaluating the drone mission requirements, and determining the required minimum endurance time, and testing and verifying the required minimum endurance time;

[0007] Obtain the UAV status data through the remote control and telemetry link, and transmit the UAV status data to the ground control station. The ground control station calculates the flight trajectory based on the obtained UAV status data;

[0008] The ground control station sends flight control instructions to the UAV through the remote control and telemetry link, and sends mission operation instructions to the mission payload system through the data link;

[0009] The UAV executes the received flight control instructions and mission operation instructions, and feeds back the execution status and mission data to the ground control station through the data link. The ground station continuously monitors and records the flight status and mission data.

[0010] As a preferred solution of the flight inspection method based on an intelligent UAV according to the present invention, wherein: the determination of the required minimum endurance time includes,

[0011] Investigate the length of the line to be inspected, the average height of the line, the terrain and the environmental conditions;

[0012] Estimate the flight speed of the UAV, and calculate the minimum flight time required for one inspection. The calculation formula for the flight speed of the UAV is as follows:

[0013] v = v0·e -αh

[0014] Wherein, v is the flight speed, v0 is the basic flight speed, h is the average flight height, and α is the height adjustment coefficient;

[0015] The calculation formula for the minimum flight time required for one inspection is:

[0016]

[0017] Wherein, t is the flight time, d is the flight distance, β is the terrain complexity coefficient, and ΔS is the proportion of the additional flight time increased by the terrain;

[0018] Combined with the power consumption of the payload equipment and the backup power, determine the minimum required endurance time. The calculation formula is:

[0019]

[0020] Wherein, ΔT is the environmental temperature adjustment factor, P is the power consumption, E is the total power, T is the endurance time, and γ is the temperature adjustment coefficient.

[0021] As a preferred solution of the flight inspection method based on an intelligent UAV according to the present invention, wherein: the test and verification of the required minimum endurance time includes,

[0022] Conduct ground tests to verify the normal power supply of the battery pack and the endurance time of the UAV, and write an automated test program to simulate the working status and load of actual inspections;

[0023] Operate the devil monitoring device to monitor the battery discharge and power supply situation, verify the power supply stability, and at the same time test the maximum endurance time under full load conditions and check it against the calculated value;

[0024] According to the test results, further optimize and adjust the power supply system.

[0025] As a preferred solution of the flight inspection method based on intelligent unmanned aerial vehicles according to the present invention, wherein: the calculation of the unmanned aerial vehicle flight trajectory includes,

[0026] Based on the minimum required endurance time T determined according to the unmanned aerial vehicle mission requirements and the minimum flight time t required for one inspection, plan the preliminary key line L1;

[0027] Segment the key line L1, and equally divide the entire key line L1 into multiple sub-line segments L i (i = 1, 2, 3,..., n);

[0028] For each sub-line segment L i , estimate its required flight time t and compare it with the endurance time T. If the required flight time ≤ endurance time, then this sub-line segment L i can be flown in one go;

[0029] If the required flight time > endurance time, then deploy a temporary site on this sub-line segment L i , and the temporary site includes a temporary power exchange site or a fuel supply point;

[0030] Determine the number m of temporary sites that need to be deployed on each sub-line segment L i , and calculate the ratio of the required flight time to the endurance time, and record the integer part of the ratio as k i , then at least k i temporary sites are required for this sub-line segment; i

[0031] Equally divide the sub-line segment L i into k i +1 sub-segments, and the estimated flight time of each sub-segment does not exceed the minimum required endurance time;

[0032] Deploy temporary sites at the k i segment points;

[0033] Repeat the above steps for all sub-line segments, and count the total number of temporary sites M = Σm i ;

[0034] Combined with the positions of M temporary stations, the flight path of the critical line L1 is optimized using a path optimization algorithm to obtain the optimized critical line L2; the calculation formula of the path optimization algorithm is as follows:

[0035]

[0036] Where L is the complete set of lines, L i is the i-th segment of the line, v i is the flight speed of the i-th segment, θ i is the flight difficulty coefficient of the i-th segment, Cost(L i ) is the energy consumption cost of the i-th segment;

[0037] For the optimized route L2, simulate the flight and verify whether the task can be successfully completed. If there are sub-lines that cannot be completed in one go, add temporary stations at the segmentation points of these sub-lines;

[0038] Repeat counting the total number of temporary stations to the optimized route L2 until a feasible critical line scheme L n is determined, enabling the UAV to complete the entire task within the endurance time limit.

[0039] As a preferred embodiment of the flight inspection method based on an intelligent UAV according to the present invention, wherein: the flight control instructions include takeoff, turning, ascending, and descending the flight altitude;

[0040] The task operation instructions include camera shooting, temperature sensing, and chemical detection.

[0041] As a preferred embodiment of the flight inspection method based on an intelligent UAV according to the present invention, wherein: the feedback of the execution status and task data to the ground control station through the data link includes,

[0042] Continuously collect the execution status data of the UAV through the remote control and telemetry link, including flight speed, altitude, and battery power;

[0043] Continuously collect the task data of the UAV through the data link, including the working data of the task payload system cameras and sensors;

[0044] Analyze the collected data and identify possible abnormal patterns. When an anomaly is detected, the UAV executes an emergency landing procedure and issues an alarm, requesting manual intervention from the ground control station;

[0045] Record all flight and task execution data in real time and transmit it to the ground control station to generate a flight report.

[0046] As a preferred solution of the flight inspection method based on intelligent drones according to the present invention, wherein: the emergency landing procedure includes a first landing level, a second landing level, and a third landing level;

[0047] The first landing level is the minor anomaly handling layer. When there are small-scale meteorological changes or minor sensor failures, the autonomous system of the drone will automatically adjust the flight parameters and issue an alarm according to the current anomaly situation, including reducing the flight speed, changing the flight path, and slowly landing;

[0048] When the ground control station receives the anomaly alarm, the staff determines whether manual intervention is required based on the real-time data. If the flight state returns to normal after autonomous adjustment, the mission will continue;

[0049] The second landing level is the moderate anomaly handling layer. When encountering moderate strong convective weather or flight control anomalies caused by partial system failures, the autonomous system response measures will be initiated. The autonomous system response measures include:

[0050] Lock the current position and report the anomaly details to the ground station through the data link;

[0051] The ground staff analyzes the cause of the anomaly and provides multiple optional emergency solutions, predicting the success rate of each solution;

[0052] Select the best solution among the emergency solutions and issue an execution command through the remote control link;

[0053] The drone acts according to the execution command. If it returns to normal, the mission will continue; otherwise, it will be upgraded to a serious anomaly and enter the third-level processing;

[0054] The third landing level is the serious anomaly handling layer. When a serious failure, extreme weather, or flight control system malfunction occurs, the ground control station will terminate all normal tasks;

[0055] The staff jointly analyzes the cause of the anomaly and the degree of danger, and determines whether the anomaly constitutes a flight crisis;

[0056] According to the current position, remaining power, surrounding terrain, and meteorology of the drone, calculate multiple forced landing solutions;

[0057] The staff selects the landing route and alternate airport with the least risk according to the forced landing solutions and issues the command to the drone;

[0058] The drone performs a forced landing in full manual mode, shuts down all non-emergency systems, and turns on the distress mode;

[0059] The ground rescue team will immediately be dispatched to the alternate airport to guide the drone to land and control the scene;

[0060] After landing, the drone automatically switches to the locked mode and waits to be repaired and returned to the field;

[0061] The rescue team conducts full - process monitoring. When it is found that the route seriously deviates from the planned route, the landing instruction is terminated and it is changed to search for the nearest emergency landing point;

[0062] If the landing is successful, a thorough analysis of the abnormal reasons is carried out, the emergency plan is improved, and the relevant systems are upgraded and transformed.

[0063] Another object of the present invention is to provide a flight inspection system based on an intelligent drone. To solve the above - mentioned technical problems, the present invention provides the following technical solutions: A flight inspection system based on an intelligent drone includes: a task evaluation and preparation module, a flight trajectory planning module, a task execution monitoring module, an abnormal handling module, and a post - event analysis module;

[0064] The task evaluation and preparation module is used to evaluate the drone task requirements, determine the required minimum endurance time and conduct ground tests, verify the calculation results, and optimize and adjust the power supply system;

[0065] The flight trajectory planning module is used to determine the number and positions of temporary stations for each evaluated flight time, adopt a path optimization algorithm to obtain the optimized key line, and determine the final feasible key line plan;

[0066] The task execution monitoring module is used to send flight control and task operation instructions, receive the feedback execution status and task data, identify abnormal patterns, and issue alarms;

[0067] The abnormal handling module is used for emergency abnormal situations and executes the emergency landing procedure;

[0068] The post - event analysis module is used to analyze the abnormal reasons, improve the emergency plan, and upgrade and transform the relevant systems.

[0069] A computer device includes a memory and a processor. The memory stores a computer program. It is characterized in that when the processor executes the computer program, the steps of the above - mentioned flight inspection method based on an intelligent drone are realized.

[0070] A computer - readable storage medium stores a computer program. It is characterized in that when the computer program is executed by a processor, the steps of the above - mentioned flight inspection method based on an intelligent drone are realized.

[0071] Advantages of the present invention: Establishing a remote control and telemetry link and a data link, as well as evaluating mission requirements and endurance time, ensures that the UAV can be safely and effectively controlled and meets mission requirements; by obtaining UAV status data and calculating the flight trajectory, the ground control station can monitor the UAV in real time and optimize the flight route, thereby improving mission efficiency; by sending flight control instructions and mission operation instructions, the ground control station can remotely control the UAV to perform various operations, expanding the functions of the UAV; the UAV feeds back the execution status and mission data, and the ground station continuously monitors, and this closed-loop control ensures the safe and reliable execution of the mission; by investigating the line conditions and calculating the required minimum endurance time in combination with various factors, risks can be effectively avoided and the mission success rate can be guaranteed; by verifying the endurance time through ground tests and optimizing the power supply system, this provides strong guarantee for the UAV's endurance ability; by segmentally planning key lines, deploying temporary sites, and optimizing the path, the entire mission can be completed within the endurance time limit. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following-described drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0073] Figure 1 Structural schematic diagram of the terminal in the first embodiment of the present invention;

[0074] Figure 2 Flow schematic diagram in the first embodiment of the present invention;

[0075] Figure 3 Structural schematic diagram of the computer device in the third embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0076] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will make a detailed description of the specific embodiments of the present invention in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0077] Many specific details are set forth in the following description in order to fully understand the present invention, but the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0078] Embodiment 1

[0079] Reference Figures 1-3 , which is an embodiment of the present invention, provides a flight inspection method based on an intelligent unmanned aerial vehicle.

[0080] First of all, the flight inspection method based on an intelligent unmanned aerial vehicle provided in this application can be applied to a terminal as shown in Figure 1 . As shown in Figure 1 , the terminal may include one or two (only one is shown in Figure 1 ) processors and a memory for storing data. Among them, the processor may include, but is not limited to, a processing system such as a microprocessor MCU or a programmable logic device FPGA. The above terminal may further include a transmission device for communication functions and an input / output device. Those of ordinary skill in the art can understand that the structure shown in Figure 1 is only schematic and does not limit the structure of the above terminal. For example, the terminal may further include more or fewer components than those shown in Figure 1 , or have a different configuration from that shown in Figure 1 .

[0081] The memory can be used to store computer programs, such as the computer program corresponding to the flight inspection method based on an intelligent unmanned aerial vehicle in this embodiment. The processor executes various functional applications and data processing by running the computer program stored in the memory, that is, the above method is realized. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage systems, flash memory, or other non-volatile solid-state memories. In some instances, the memory may further include a memory remotely set relative to the processor, and these remote memories may be connected to the terminal through a network. Examples of the above network include, but are not limited to, the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0082] The transmission device is used to receive or send data via a network. The above network includes a wireless network provided by the communication provider of the terminal. In one instance, the transmission device includes a network adapter (abbreviated as NIC), which can be connected to other network devices through a base station and thus can communicate with the Internet. In one instance, the transmission device may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0083] As shown in Figure 2 , the embodiment of the present invention provides a flight inspection method based on an intelligent unmanned aerial vehicle. Taking the method applied to the terminal in Figure 1 as an example, the method includes the following steps:

[0084] S1: Establish a remote control and telemetry link and a data link between the UAV and the ground control station, evaluate the UAV mission requirements, and determine the minimum required endurance time.

[0085] S1.1: Determining the minimum required endurance time includes

[0086] Investigating the length of the line to be patrolled, the average height of the line, the terrain and environmental conditions;

[0087] Investigating the line length, height, terrain and environment helps to comprehensively evaluate the factors affecting the UAV flight and provides accurate parameters for subsequent calculations;

[0088] Estimate the UAV flight speed and calculate the minimum flight time required for one patrol. The UAV flight speed calculation formula is as follows:

[0089] v = v0·e -αh

[0090] where v is the flight speed, v0 is the basic flight speed, h is the average flight height, and α is the height adjustment coefficient, which scientifically considers the influence of height on speed and improves the calculation accuracy;

[0091] The formula for calculating the minimum flight time required for one patrol is:

[0092]

[0093] where t is the flight time, d is the flight distance, β is the terrain complexity coefficient, and ΔS is the additional flight time ratio increased by the terrain, which comprehensively considers the distance and terrain complexity and improves the accuracy of time estimation;

[0094] Combined with the power consumption of the payload equipment and the backup power, determine the minimum required endurance time. The calculation formula is:

[0095]

[0096] where ΔT is the environmental temperature adjustment factor, P is the power consumption, E is the total power, T is the endurance time, and γ is the temperature adjustment coefficient. Considering multiple influencing factors such as power consumption, power and temperature can more accurately estimate the endurance ability.

[0097] S1.2: Select a suitable large-capacity lithium battery pack or fuel cell pack to replace the original battery;

[0098] Consider the brand, model and their energy density, discharge characteristics and other parameters of the optional battery packs;

[0099] According to the endurance time requirement, weight and space limitation, screen out the battery packs that meet the requirements.

[0100] S1.3: Conduct ground tests to verify the normal power supply of the battery pack and the endurance time of the UAV.

[0101] Write an automated test program to simulate the working status and load of actual inspections.

[0102] Use monitoring equipment to monitor the battery discharge and power supply situation, and verify the power supply stability.

[0103] Test the maximum endurance time under full load conditions and compare it with the calculated value.

[0104] According to the test results, further optimize and adjust the power supply system.

[0105] S2: Obtain the UAV status data through the remote control and telemetry link, and transmit the UAV status data to the ground control station. The ground control station calculates the flight trajectory based on the obtained UAV status data.

[0106] S2.1: Based on the minimum required endurance time T determined by the UAV mission requirements and the minimum flight time t required for one inspection, plan the preliminary critical line L1.

[0107] Perform segmented processing on the critical line L1, including

[0108] Step 1: Divide the entire critical line L1 into multiple sub-line segments Li (i = 1, 2, 3,..., n) according to a certain length (e.g., 10 km), where the length of the first sub-line segment L1 and the last sub-line segment Ln may not be equal to that of other equally divided sub-line segments. i (i = 1, 2, 3,..., n), where the length of the first sub-line segment L1 and the last sub-line segment Ln n may not be equal to that of other equally divided sub-line segments.

[0109] Step 2: For each sub-line segment Li i , estimate its required flight time ti and compare it with the endurance time T. If the required flight time ti ≤ T, then this sub-line segment Li i can be flown in one go.

[0110] Step 3: If the required flight time ti > T, then deploy a temporary site on this sub-line segment Li i , and the temporary site includes a temporary battery replacement site or a fuel supply point.

[0111] Step 4: Determine the number m of temporary sites that need to be deployed on each sub-line segment Li i , calculate the ratio of the required flight time to the endurance time, and take the integer part and record it as k i , then at least k i temporary sites are required for this sub-line segment; i Step 5: Divide the sub-line segment Li

[0112] equally into k i sub-line segmentsi +1 sub - segment, with the expected flight time of each sub - segment not exceeding the minimum required endurance time;

[0113] Step 6: Deploy temporary stations at k i segment points for UAV battery swapping or fuel refueling;

[0114] Step 7: Repeat the above steps for all sub - line segments, and count the total number of temporary stations M = Σm i ;

[0115] Step 8: Combine the locations of the UAV base and M temporary stations, and use a path optimization algorithm to optimize the flight path of the critical line L1 to obtain the optimized critical line L2; the calculation formula of the path optimization algorithm is as follows:

[0116]

[0117] where L is the complete set of lines, L i is the i - th segment of the line, v i is the flight speed of the i - th segment, θ i is the flight difficulty coefficient of the i - th segment, and Cost(L i ) is the energy consumption cost of the i - th segment;

[0118] Step 9: For the optimized route L2, simulate the flight and verify whether the task can be successfully completed. If there are sub - line segments that cannot be completed in one go, add temporary stations at the segment points of these sub - line segments;

[0119] Repeat steps 7 to 9 until a feasible critical line plan L n is determined, enabling the UAV to complete the entire task within the endurance time limit.

[0120] S3: The ground control station sends flight control instructions to the UAV through the remote control and telemetry link, and sends operation instructions to the mission payload system through the data link.

[0121] S3.1: The flight control instructions smoothly sent by the ground control station through the remote control and telemetry link include flight control instructions such as take - off, turning, ascending or descending the flight altitude, etc.;

[0122] The operation instructions sent to the mission payload system of the UAV through the data link include operation instructions such as camera shooting, temperature sensing, or chemical detection, etc.

[0123] S4: The UAV executes the received control instructions, and feeds back the execution status and mission data to the ground control station through the data link. The ground station continuously monitors and records the flight status and mission data.

[0124] S4.1: Continuously collect basic flight status data of the UAV, such as flight speed, altitude, battery power, etc., through the remote control and telemetry link, and at the same time receive the working data of the camera and sensors of the mission payload system through the data link;

[0125] The built-in algorithm of the monitoring system analyzes the collected data to identify possible abnormal patterns, such as sudden drop in power, abnormal flight speed, etc.;

[0126] When an anomaly is detected, the UAV executes an emergency landing procedure and issues an alarm, requesting manual intervention from the ground control station;

[0127] Record all flight and mission execution data in real time and transmit it to the ground control station to generate a flight report, providing data support for subsequent flight plans and UAV performance optimization.

[0128] S4.2: The emergency landing procedure includes the first landing level, the second landing level, and the third landing level;

[0129] The first landing level is the minor anomaly handling layer. When there are small-scale meteorological changes or minor sensor failures, the autonomous system of the UAV will automatically adjust the flight parameters according to the current anomaly and issue an alarm, including reducing the flight speed, changing the flight path, and slowly landing;

[0130] When the ground control station receives the anomaly alarm, the staff judges whether manual intervention is needed based on the real-time data. If the flight status returns to normal after autonomous adjustment, the mission will continue;

[0131] The second landing level is the moderate anomaly handling layer. When encountering moderate severe convective weather or flight control anomalies caused by partial system failures, start the autonomous system response measures, and the autonomous system response measures include:

[0132] Lock the current position and report the anomaly details to the ground station through the data link;

[0133] The ground staff analyzes the cause of the anomaly and provides multiple optional emergency plans, predicting the success rate of each plan;

[0134] Select the best plan in the emergency plan and issue an execution command through the remote control link;

[0135] The UAV acts according to the execution command. If it returns to normal, the mission will continue; otherwise, it will be upgraded to a serious anomaly and enter the third-level processing;

[0136] The third landing level is the serious anomaly handling layer. When a serious failure, extreme weather, or flight control system malfunction occurs, the ground control station will terminate all normal tasks;

[0137] The staff jointly analyzes the cause and risk level of the anomaly to judge whether the anomaly constitutes a flight crisis;

[0138] Based on the current position, remaining power, surrounding terrain, and meteorology of the UAV, multiple forced landing plans are calculated;

[0139] According to the forced landing plan, the staff selects the landing route and alternate airport with the least risk and issues instructions to the UAV;

[0140] The UAV performs a forced landing in full manual mode, shuts down all non-emergency systems, and turns on the distress mode;

[0141] The ground rescue team immediately sets out to the alternate airport to guide the UAV to land and control the scene;

[0142] After landing, the UAV automatically switches to the locked mode and waits to be repaired and returned to the field;

[0143] The rescue team conducts full-process monitoring. When it is found that the route seriously deviates from the predicted route, the landing instruction is terminated and it is changed to search for a nearby emergency landing point;

[0144] If the landing is successful, a thorough analysis of the abnormal reasons is carried out, the emergency plan is improved, and the relevant systems are upgraded and transformed;

[0145] When facing different scenarios of serious anomalies, this level can be further divided into multiple sub-levels, including,

[0146] When the fuel runs out and the power is completely exhausted within a foreseeable time, the UAV will switch to the "gliding mode", shut down all non-essential systems and equipment, and only keep the most basic flight control system running;

[0147] The ground station must track the energy state of the UAV, accurately predict the endurance time of the remaining power, and specify a possible best forced landing area for it according to factors such as terrain and weather;

[0148] Based on this, the artificial intelligence system combines the current state data to calculate an optimal forced landing route, and the UAV will automatically load this route and strictly taxi according to the route;

[0149] When encountering extreme weather, such as tornadoes, hailstorms, lightning, etc., such anomalies usually come suddenly and there is not enough reaction time;

[0150] Continuously monitor the global satellite meteorological data. When it is detected that there are signs of extreme weather forming within a radius of 100 kilometers, immediately terminate all UAVs from performing tasks.

[0151] Embodiment 2

[0152] An embodiment of the present invention provides a flight inspection system based on an intelligent unmanned aerial vehicle (UAV), including: a task evaluation and preparation module, a flight trajectory planning module, a task execution monitoring module, an exception handling module, and a post-event analysis module;

[0153] The task evaluation and preparation module is used to evaluate the UAV task requirements, determine the required minimum endurance time, conduct ground tests, verify the calculation results, and optimize and adjust the power supply system;

[0154] The flight trajectory planning module is used to determine the number and locations of temporary stations for each evaluated flight time, adopt a path optimization algorithm to obtain an optimized key line, and determine a final feasible key line plan;

[0155] The task execution monitoring module is used to send flight control and task operation instructions, receive the feedback execution status and task data, identify abnormal patterns, and issue alarms;

[0156] The exception handling module is used for emergency abnormal situations and executes an emergency landing procedure;

[0157] The post-event analysis module is used to analyze the causes of exceptions, improve the emergency plan, and upgrade and transform relevant systems.

[0158] For the specific limitations of the flight inspection system based on an intelligent UAV, reference can be made to the limitations of the flight inspection method based on an intelligent UAV in the above text, which will not be elaborated here. Each module in the above flight inspection system based on an intelligent UAV can be implemented in whole or in part through software, hardware, and their combinations. The above modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so as to facilitate the processor to call and execute the operations corresponding to the above modules.

[0159] Embodiment 3

[0160] Refer to Figure 3 , for the third embodiment of the present invention, on the basis of the first two embodiments, the present invention embodiment provides a computer device, which can be a server, and its internal structure diagram can be as Figure 3 shown. The computer device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium.

[0161] The database of the computer device is used to store action detection data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by a processor, it implements the steps in any of the above embodiments of the sparse tensor operation acceleration method.

[0162] Those skilled in the art can understand that Figure 3 the structure shown in is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0163] In one embodiment, the embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the steps in any of the above embodiments of the sparse tensor operation acceleration method.

[0164] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0165] Embodiment 4

[0166] For an embodiment of the present invention, a flight inspection method based on an intelligent unmanned aerial vehicle is provided. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0167] Test preparation and implementation process

[0168] To verify the feasibility and effectiveness of this invention, we conducted a series of field tests. First, an 110-kilometer power transmission line was selected as the route to be inspected. The terrain of this line is complex, passing through mountains, plains, and towns, with an average altitude of 650 meters. According to historical meteorological data, the annual average temperature in this area is 15°C.

[0169] We used a fixed-wing drone, model XX001, with a basic cruising speed of 80 km / h. According to the formula provided in the invention content, we estimated the actual flight speed of this drone on this line:

[0170] v = 80*(1 - 0.2*650 / 2000) = 68 (km / h)

[0171] where v0 = 80 km / h, h = 650 m, and α = 0.2.

[0172] Next, we needed to calculate the minimum flight time t required for this drone to patrol this line once:

[0173] t = 110 / 68*(1 + 0.3) = 2.26 (hours)

[0174] where d = 110 km and β = 0.3 (complex mountain terrain coefficient).

[0175] Due to considering factors such as the power consumption of the payload equipment and temperature, we needed to leave enough margin for the endurance time. In the invention, the power consumption P = 200 W, the total power C = 30000 Wh, and the temperature adjustment factor γ = 1.1 were given. We calculated the minimum required endurance time T:

[0176] T = 30000 / (200*1.1) = 136.4 (hours)

[0177] Obviously, the flight time of 2.26 hours is far less than the endurance time of 136.4 hours.

[0178] Therefore, we selected a large-capacity lithium battery pack XXB-5000 as the power source, with an energy density of 260 Wh / kg, which meets the energy requirements for the drone to patrol once.

[0179] To verify the performance of the new battery pack, we conducted a series of ground tests. An automated test program was written to simulate the power consumption and load conditions under actual working states. Professional monitoring equipment was used to monitor the discharge curve and power supply stability of the battery. The final test results showed that under full-load conditions, this battery pack could support the drone to fly continuously for 2.8 hours, which was basically consistent with the theoretical estimated value. This confirmed that the new battery pack meets the endurance time requirements and the invention scheme can be implemented.

[0180] Comparison Table of Endurance and Mission Time

[0181]

[0182] As can be clearly seen from the above table, with the original battery pack, even under ideal conditions, the maximum endurance time is only 46.2 hours. And a single inspection of this transmission line takes 2.26 hours, which means that the battery must be replaced or recharged after each inspection, bringing great inconvenience to on-site operations.

[0183] In contrast, we replaced the original battery with the XXB-5000 large-capacity lithium battery pack. The new battery pack has an energy density as high as 260 Wh / kg, a total power of 30000 Wh, and a theoretical endurance time of up to 136.4 hours. In actual tests, the endurance time under full-load conditions is 134.1 hours, which is basically consistent with the theoretical value. This shows that the new battery pack can support the drone to continuously perform dozens or even hundreds of line inspection tasks without the need to replace or refuel midway, greatly improving work efficiency.

[0184] In addition, we noticed that temperature is also an important factor affecting endurance. At an ambient temperature of 15°C, the temperature adjustment factor is 1.1, and the impact on endurance time is limited. However, if the ambient temperature rises to 35°C, the adjustment factor will increase to 1.4, and the endurance time will be shortened to about 96 hours at that time. Therefore, when performing tasks in a high-temperature environment, it is necessary to appropriately increase the battery capacity or adjust the work strategy.

[0185] Generally speaking, by adopting the XXB-5000 battery pack with high energy density and combining with fine task assessment and planning, the inventive solution can significantly extend the endurance time of the drone, ensure the efficient completion of the line inspection task, and avoid the time-consuming and laborious process of returning to the field for replacement midway, with significant practical value and innovation. This solution makes up for the deficiencies of the existing technology and is an ideal power solution for transmission line inspection operations.

[0186] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not restrictive. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A flight inspection method based on an intelligent unmanned aerial vehicle, characterized in that: include: Establish a remote control telemetry link and data link between the UAV and the ground control station, evaluate the UAV mission requirements, determine the minimum required flight time, and test and verify the required minimum flight time; The drone status data is obtained through the remote control telemetry link and transmitted to the ground control station, which calculates the flight trajectory based on the obtained drone status data; The ground control station sends flight control instructions to the UAV through the remote control and telemetry link, and sends mission operation instructions to the mission payload system through the data link; The UAV executes the received flight control instructions and mission operation instructions, and feeds back the execution status and mission data to the ground control station through the data link. The ground control station continuously monitors and records the flight status and mission data until the patrol is completed; Calculating the flight trajectory includes, According to the minimum required endurance time T and the minimum flight time t required for one patrol determined by the UAV mission requirements, a preliminary key route L1 is planned; The key line L1 is segmented and the entire key line L1 is divided into multiple sub-line segments L according to a certain length. i (i=1,2,3,...,n); For each subline segment L i， Estimate the required flight time t and compare it with the endurance time T. If the required flight time ≤ the endurance time, then the sub-line segment L i Can be completed in one flight; If the required flight time is greater than the endurance time, then in this sub-line segment L i Deploy temporary sites on the vehicle, wherein the temporary sites include temporary battery replacement sites or fuel supply points; Determine each subline segment L i The number of temporary sites that need to be deployed on i , and calculate the ratio of the required flight time to the endurance time, and take the integer part of the ratio as k i， Then the sub-line segment needs at least k i temporary sites; Subline segment L i Divide into k i +1 sub-segment, each with an estimated flight time not exceeding the minimum required endurance; In k i Deploy temporary sites at each staging point; Repeat the above steps for all sub-line segments and count the total number of temporary sites M = Σm i ; Combined with the locations of the M temporary sites, the flight path of the key route L1 is optimized using the path optimization algorithm to obtain the optimized key route L2; the calculation formula of the path optimization algorithm is as follows: Among them, L is the complete set of lines, L i is the i-th section of the line, v i is the flight speed of the i-th segment, θ i is the flight difficulty coefficient of the i-th segment, Cost(L i ) is the energy consumption cost of the i-th segment; For the optimized route L2, simulate the flight and verify whether the task can be successfully completed. If there is a sub-route that cannot be completed in one go, add a temporary stop at the segment point of the sub-route; Repeat the total number of temporary stops to optimize route L2 until a feasible key route plan L is determined. n , enabling the drone to complete the entire mission within the flight time limit.

2. The flight inspection method based on an intelligent unmanned aerial vehicle according to claim 1, characterized in that: Determining the required minimum endurance time includes: Investigate the length of the route to be inspected, the average height of the route, the terrain and the environmental conditions; Estimate the flight speed of the drone and calculate the minimum flight time required for a patrol. The calculation formula for the flight speed of the drone is as follows: v=v0·e -αh Among them, v is the flight speed, v0 is the basic flight speed, h is the average flight altitude, and α is the altitude adjustment coefficient; The formula for calculating the minimum flight time required for one patrol is: Where t is the flight time, d is the flight distance, β is the terrain complexity coefficient, and ΔS is the proportion of additional flight time added by the terrain; Combine the power consumption and reserve power of the load equipment to determine the minimum required endurance time. The calculation formula is: Among them, ΔT is the ambient temperature adjustment factor, P is the power consumption, E is the total power, T is the battery life, and γ is the temperature adjustment coefficient.

3. The flight inspection method based on an intelligent unmanned aerial vehicle as claimed in claim 2, characterized in that: The minimum endurance required for the test verification includes: Conduct ground tests to verify the normal power supply of the battery pack and the flight time of the drone, and write automated test programs to simulate the working conditions and loads of actual inspections; Operate the Devil monitoring equipment to monitor battery discharge and power supply, check power supply stability, and test the maximum endurance time under full load conditions, and check it against the calculated value; Based on the test results, further optimization and adjustment are made to the power supply system.

4. The flight inspection method based on an intelligent unmanned aerial vehicle as claimed in claim 3, characterized in that: The flight control instructions include take-off, turning, raising and lowering the flight altitude; The mission operation instructions include camera photography, temperature sensing and chemical detection.

5. The flight inspection method based on an intelligent unmanned aerial vehicle as claimed in claim 4, characterized in that: Feedback of the execution status and mission data to the ground control station via a data link includes: Continuously collect the drone's performance status data, including flight speed, altitude, and battery power, through the remote control telemetry link; Continuously collect UAV mission data through data links, including the working data of the mission payload system camera and sensors; Analyze the collected data and identify possible abnormal patterns. When an abnormality is detected, the drone executes the emergency landing procedure and sounds an alarm, requesting manual intervention from the ground control station; All flight and mission execution data are recorded in real time and transmitted to the ground control station to generate a flight report.

6. The flight inspection method based on an intelligent unmanned aerial vehicle as claimed in claim 5, characterized in that: The emergency landing procedure includes a first landing level, a second landing level, and a third landing level; The first landing level is a minor anomaly handling level. When a small-scale weather change or a minor sensor failure occurs, the drone's autonomous system will automatically adjust flight parameters and issue an alarm based on the current abnormal situation, including reducing flight speed, changing routes, and landing slowly. When the ground control station receives an abnormal alarm, the staff will determine whether manual intervention is required based on real-time data. If the flight status returns to normal after autonomous adjustment, the mission will continue; The second landing level is a moderate anomaly handling layer. When encountering moderate severe convective weather or flight control anomalies caused by partial system failures, the autonomous system response measures are initiated. The autonomous system response measures include: Lock the current position and report abnormal details to the ground station via data link; Ground staff analyze the cause of the anomaly and provide a variety of optional emergency plans, predicting the success rate of each plan; Select the best plan among the emergency plans and issue execution commands through the remote control link; The drone acts according to the command. If it returns to normal, it continues to perform the mission; otherwise, it is upgraded to a serious abnormality and enters the third level of processing; The third landing level is the severe abnormality handling level. When a severe failure, extreme weather or flight control system malfunction occurs, the ground control station will terminate all normal tasks. The staff jointly analyzes the cause of the anomaly and the degree of danger, and determines whether the anomaly constitutes a flight crisis; Calculate multiple forced landing plans based on the current location of the drone, remaining battery power, surrounding terrain and weather; The staff will select the landing route and alternate airport with the least risk according to the forced landing plan, and issue the instructions to the drone; The drone performed a forced landing in full manual mode, shutting down all non-emergency systems and turning on distress mode; The ground rescue team was immediately dispatched to the alternate airport to guide the drone to land and control the scene; After landing, the drone automatically switches to locked mode and waits for inspection and return; The rescue team monitors the entire process. If they find that the aircraft has seriously deviated from the planned route, they will terminate the landing order and look for the nearest emergency landing point instead. If the landing is successful, the cause of the anomaly will be thoroughly analyzed, the emergency plan will be improved, and the relevant systems will be upgraded.

7. A system using the flight inspection method based on an intelligent unmanned aerial vehicle as described in any one of claims 1 to 6, characterized in that: include: Mission assessment preparation module, flight trajectory planning module, mission execution monitoring module, exception handling module and post-event analysis module; The mission assessment preparation module is used to assess the mission requirements of the UAV, determine the minimum required flight time and conduct ground tests, verify the calculation results, and optimize and adjust the power supply system; The flight trajectory planning module is used to evaluate the flight time for each segment, determine the number and location of temporary stops, use a path optimization algorithm to obtain an optimized key route, and determine a final feasible key route plan; The mission execution monitoring module is used to send flight control and mission operation instructions, receive feedback execution status and mission data, identify abnormal modes, and issue alarms; The exception handling module is used for emergency exception situations and executes emergency landing procedures; The post-analysis module is used to analyze the cause of the abnormality and improve the emergency plan, and upgrade and transform related systems.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the flight inspection method based on an intelligent unmanned aerial vehicle described in any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the flight inspection method based on an intelligent unmanned aerial vehicle described in any one of claims 1 to 6 are implemented.

Images