Adaptive control method, system, terminal and medium for cable tunnel drone inspection

Abstract

The present invention discloses an adaptive control method, system, terminal and medium for cable tunnel drone inspection, and relates to the field of drone control technology. The key points of the technical solution are: using a range sensor to collect the oblique distance between the drone and the inner wall of the cable tunnel during flight; using the measurement direction of the range sensor corresponding to the largest oblique distance and the smallest oblique distance in the distance sequence and the central viewing angle direction of the camera to be in the same plane as a constraint, determining the flight reference plane of the drone; solving the flight pitch angle of the drone in the flight reference plane; correcting the flight direction of the drone according to the flight reference plane and the flight pitch angle, and simultaneously starting the camera to collect images. The present invention can correct the flight direction of the drone regularly, and can realize the adaptive control of the drone flying along the extension direction of the cable tunnel under poor illumination conditions and weak signal coverage.

Description

Technical Field

[0001] The present invention relates to the field of unmanned aerial vehicle control technology, and more specifically, to a cable tunnel unmanned aerial vehicle inspection adaptive control method, system, terminal and medium. Background Art

[0002] Cable tunnel drone inspection is a modern method of cable tunnel monitoring using drone technology. Drones can be equipped with a variety of sensors, such as cameras, high-precision infrared imaging, partial discharge detection and gas detection, to automatically collect data and send it back to the operation and maintenance control center. In this way, inspection efficiency can be improved, the risk of manual inspection can be reduced, and comprehensive monitoring of the internal environment of the tunnel can be achieved.

[0003] At present, the image recognition technology is mainly used to obtain environmental information during the flight of UAVs. For example, cable tunnels do not always maintain straight passages. Affected by geographical factors, there may be many changes in the curves in the cable tunnels. Therefore, it is necessary to perceive the environmental data inside the cable tunnel to provide reference data for the attitude control of the UAV during the flight. However, due to the poor illumination conditions inside the cable tunnel, the quality of the image information collected without fill light is poor, resulting in poor accuracy of image recognition; in addition, in long tunnels or underground tunnels, due to the obstruction of physical structures, the signal is difficult to fully cover, which reduces the timeliness of image recognition processing to a certain extent.

[0004] Therefore, how to study and design an adaptive control method, system, terminal and medium for cable tunnel drone inspection that can overcome the above-mentioned defects is a problem that we urgently need to solve. Summary of the invention

[0005] In order to address the deficiencies in the prior art, the purpose of the present invention is to provide an adaptive control method, system, terminal and medium for cable tunnel drone inspection, which can regularly correct the flight direction of the drone and realize adaptive control of the drone flying along the extension direction of the cable tunnel under poor illumination conditions and weak signal coverage.

[0006] The above technical objectives of the present invention are achieved through the following technical solutions:

[0007] In a first aspect, a method for adaptively controlling a cable tunnel drone inspection is provided, wherein the drone is equipped with a camera and a plurality of ranging sensors symmetrically distributed around the camera, comprising the following steps:

[0008] The oblique distance between the UAV and the inner wall of the cable tunnel is collected by the distance measuring sensor during the flight, and multiple oblique distances collected at the same time form a distance sequence;

[0009] The flight reference plane of the UAV is determined by taking the measurement direction of the distance sensor corresponding to the largest oblique distance and the smallest oblique distance in the distance sequence and the central viewing direction of the camera as the constraint that they are in the same plane;

[0010] The flight pitch angle of the UAV in the flight reference plane is solved according to the inner diameter of the cable tunnel, the maximum oblique measurement distance, the minimum oblique measurement distance and the oblique measurement angle of the ranging sensor;

[0011] The flight direction of the UAV is corrected according to the flight reference plane and the flight pitch angle, and the camera is started to collect images at the same time.

[0012] Furthermore, the oblique measurement angles between the distance measurement direction of each distance measurement sensor and the central viewing angle direction of the camera are equal.

[0013] Furthermore, the flight pitch angle of the UAV in the flight reference plane is specifically solved as follows:

[0014] ;

[0015] in, Indicates the inner diameter of the cable tunnel; Indicates the maximum oblique distance or the minimum oblique distance collected by the ranging sensor located on the upward side of the flight reference plane; Indicates the minimum oblique distance or maximum oblique distance collected by the ranging sensor located on the downward side of the flight reference plane. The upward side and the downward side of the flight reference plane are divided by the central viewing direction of the camera. Indicates the oblique measurement angle of the ranging sensor; Indicates the pitch angle of the drone in the flight reference plane. A value greater than 0 is a pitch angle, and a value less than 0 is an elevation angle.

[0016] And, when When is the minimum oblique distance, is the maximum oblique distance; on the contrary, when When is the maximum oblique distance, is the minimum oblique measurement distance.

[0017] Furthermore, the method further comprises:

[0018] The offset distance of the UAV from the center of the cable tunnel in the flight reference plane is solved according to the maximum oblique measurement distance and the flight pitch angle of the UAV in the flight reference plane;

[0019] Alternatively, the offset distance of the UAV from the center of the cable tunnel in the flight reference plane is solved according to the minimum oblique measurement distance and the flight pitch angle of the UAV in the flight reference plane.

[0020] Furthermore, the calculation formula of the offset distance is specifically:

[0021] ;

[0022] Or, the calculation formula of the offset distance is specifically:

[0023] ;

[0024] in, Indicates The offset distance for the basic solution; Indicates Offset distance for the base solution.

[0025] Furthermore, the method further comprises:

[0026] After the flight direction of the UAV is corrected according to the flight reference plane and the flight pitch angle, the pitch angle variable in the unit time is calculated by the ratio of the flight pitch angle to the correction period;

[0027] In the next correction cycle, the flight direction of the UAV is dynamically corrected according to the pitch angle variable within the unit time.

[0028] Furthermore, the method further comprises:

[0029] During the flight of the UAV, multiple distance measuring sensors are synchronously controlled to rotate in a positive and negative alternating manner in the circumferential direction of their own distribution, and each distance measuring sensor collects a corresponding oblique distance set;

[0030] When extracting the maximum oblique distance and the minimum oblique distance from the distance sequence, the abnormal data in the oblique distance set are deleted;

[0031] Among them, all oblique distances in the oblique distance set show a monotonous change trend in chronological order, and the abnormal data are the data showing extreme points in the oblique distance set.

[0032] In a second aspect, a cable tunnel drone inspection adaptive control system is provided, which is used to implement the cable tunnel drone inspection adaptive control method as described in the first aspect, including:

[0033] The distance acquisition module is used to collect the oblique distance between the UAV and the inner wall of the cable tunnel during flight through a distance measuring sensor. Multiple oblique distances collected at the same time form a distance sequence;

[0034] The plane determination module is used to determine the flight reference plane of the UAV by constraining that the measurement direction of the distance measurement sensor corresponding to the largest oblique distance and the smallest oblique distance in the distance sequence and the central viewing direction of the camera are in the same plane;

[0035] An angle solving module is used to solve the flight pitch angle of the UAV in the flight reference plane according to the inner diameter of the cable tunnel, the maximum oblique measurement distance, the minimum oblique measurement distance and the oblique measurement angle of the distance measurement sensor;

[0036] The correction control module is used to correct the flight direction of the UAV according to the flight reference plane and the flight pitch angle, and simultaneously start the camera to collect images.

[0037] In a third aspect, a computer terminal is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the adaptive control method for cable tunnel drone inspection as described in any one of the first aspects is implemented.

[0038] In a fourth aspect, a computer-readable medium is provided, on which a computer program is stored, and the computer program is executed by a processor to implement the adaptive control method for cable tunnel drone inspection as described in any one of the first aspects.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] 1. The cable tunnel drone inspection adaptive control method provided by the present invention measures the oblique distance between the drone and the inner wall of the cable tunnel during flight through a plurality of ranging sensors symmetrically distributed around the camera, and determines the flight reference plane representing the bending direction of the cable tunnel through the measurement directions of the ranging sensors corresponding to the maximum oblique distance and the minimum oblique distance, and then solves the flight pitch angle of the drone in the flight reference plane in combination with the inner diameter of the cable tunnel, the maximum oblique distance, the minimum oblique distance and the oblique angle of the ranging sensor, so that the flight direction of the drone can be corrected regularly, and the adaptive control of the drone flying along the extension direction of the cable tunnel can be realized under poor illumination conditions and weak signal coverage;

[0041] 2. The present invention calculates the offset distance of the UAV from the center of the cable tunnel in the flight reference plane according to the flight pitch angle of the UAV in the flight reference plane and the maximum oblique measurement distance or the minimum oblique measurement distance. According to the offset distance, the UAV can be controlled to fly along the central axis direction in the cable tunnel as much as possible, thereby effectively ensuring the safety and stability of the UAV flight.

[0042] 3. After the present invention corrects the flight direction of the UAV according to the flight reference plane and the flight pitch angle, the flight direction of the UAV is dynamically corrected according to the pitch angle variable within the unit time in the next correction cycle, which can reduce the probability of the UAV colliding at a place with a large bending degree in the cable tunnel, thereby improving the safety of the UAV flight;

[0043] 4. During the flight of the UAV, the present invention synchronously controls multiple ranging sensors to rotate in a positive and negative alternating manner in the circumferential direction of their own distribution. Each ranging sensor collects a corresponding oblique distance set, and when the maximum oblique distance and the minimum oblique distance are extracted from the distance sequence, the abnormal data in the oblique distance set is deleted, which can filter out the interference of pipes or cables in the cable tunnel to the distance measurement process, and effectively improve the accuracy and reliability of oblique distance measurement. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of this application, and do not constitute a limitation of the embodiments of the present invention. In the drawings:

[0045] Figure 1 is a flow chart of Embodiment 1 of the present invention;

[0046] Figure 2 is a schematic diagram of determining the flight reference plane in Embodiment 1 of the present invention;

[0047] Figure 3 is a schematic diagram of solving the flight pitch angle in embodiment 1 of the present invention;

[0048] Figure 4 It is a system block diagram in Example 2 of the present invention. DETAILED DESCRIPTION

[0049] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.

[0050] Embodiment 1: Adaptive control method for inspection of cable tunnel by unmanned aerial vehicle. The unmanned aerial vehicle of the present invention is equipped with a camera and a plurality of ranging sensors symmetrically distributed around the camera, such as Figure 1 As shown, the following steps are included:

[0051] S1: The oblique distance between the UAV and the inner wall of the cable tunnel is collected by the distance measuring sensor during the flight. Multiple oblique distances collected at the same time form a distance sequence;

[0052] S2: Determine the flight reference plane of the UAV based on the constraint that the measurement direction of the distance sensor corresponding to the largest oblique distance and the smallest oblique distance in the distance sequence and the central viewing direction of the camera are in the same plane;

[0053] S3: Calculate the flight pitch angle of the UAV in the flight reference plane according to the inner diameter of the cable tunnel, the maximum oblique measurement distance, the minimum oblique measurement distance and the oblique measurement angle of the ranging sensor;

[0054] S4: Correct the flight direction of the UAV according to the flight reference plane and the flight pitch angle, and start the camera to collect images at the same time.

[0055] In step S1, the oblique angle between the ranging direction of each ranging sensor and the central viewing angle of the camera is equal. The ranging directions of the multiple ranging sensors are distributed in a cone-shaped divergent manner. Generally, the number of ranging sensors is an even number, and each two constitutes a group. The arrangement azimuth angle difference between the two ranging sensors in a group is 180 degrees.

[0056] In step S2, the maximum oblique distance and the minimum oblique distance can better indicate the bending direction of the cable tunnel. However, considering that there may be two maximum oblique distances and two minimum oblique distances in a distance sequence, when determining the flight reference plane of the drone, the central viewing direction of the camera can also be placed in the same plane as a supplementary constraint, so as to accurately determine the flight reference plane.

[0057] In addition, the maximum oblique measurement distance and the minimum oblique measurement distance may be extracted from distance measurement sensors corresponding to a group of distance measurement sensors, which may be used as a screening condition to screen out the final maximum oblique measurement distance and the minimum oblique measurement distance.

[0058] like Figure 2 and Figure 3 As shown, the measuring directions of the four distance measuring sensors are A, B, C, and D, O is the camera, and Z is the central viewing direction of the camera. In this embodiment, the smallest oblique distance is collected by the distance measuring sensor corresponding to the measuring direction B, and the largest oblique distance is collected by the distance measuring sensor corresponding to the measuring direction D, so the flight reference plane is the BDZ plane.

[0059] In step S3, considering that the length difference between the curved tunnel and the straight tunnel is small within a short distance, the present invention treats the axial cross section of the cable tunnel as equivalent to a rectangular surface when solving the flight pitch angle, such as Figure 3 As shown in the figure, the specific expression for solving the flight pitch angle of the UAV in the flight reference plane is:

[0060] ;

[0061] in, Indicates the inner diameter of the cable tunnel; Indicates the maximum oblique distance or the minimum oblique distance collected by the ranging sensor located on the upward side of the flight reference plane; Indicates the minimum oblique distance or maximum oblique distance collected by the ranging sensor located on the downward side of the flight reference plane. The upward side and the downward side of the flight reference plane are divided by the central viewing direction of the camera. Indicates the oblique measurement angle of the ranging sensor; Indicates the pitch angle of the drone in the flight reference plane. A value greater than 0 is a pitch angle, and a value less than 0 is an elevation angle.

[0062] It should be noted that the flight pitch angle represents the angle difference between the camera's central viewing angle (shooting direction) and the extension direction of the cable tunnel. If the flight pitch angle is a depression angle, the UAV's depression angle needs to be controlled to be lowered, that is, the front end of the UAV needs to be raised for flight; if the flight pitch angle is an elevation angle, the UAV's elevation angle needs to be controlled to be lowered, that is, the front end of the UAV needs to be lowered for flight.

[0063] It should be noted that the above-mentioned elevation angle, depression angle, lift and depression are all relative situations described based on regarding the flight reference plane as a vertical plane.

[0064] The adaptive control method for cable tunnel drone inspection recorded in the present invention can control the drone to fly along the central axis direction in the cable tunnel as much as possible, effectively ensuring the safety and stability of the drone flight, and also solves the offset distance of the drone from the center of the cable tunnel in the flight reference plane based on the minimum oblique measurement distance and the flight pitch angle of the drone in the flight reference plane.

[0065] like Figure 3 As shown, represents the distance between the UAV in the flight reference plane and the cable tunnel close to the measurement direction B, and The distance between the UAV in the flight reference plane and the cable tunnel close to the measurement direction D is shown in the figure. and The value of and The mean value minus the corresponding or , the offset distance can be calculated.

[0066] For example, the calculation formula for the offset distance is:

[0067] ;

[0068] in, Indicates is the offset distance for basic solution. It should be noted that when When the minimum oblique distance is collected, The maximum oblique distance is collected; otherwise, When the maximum oblique distance is collected, What is collected is the minimum oblique measurement distance.

[0069] like Figure 3 As shown, The minimum oblique distance is collected. The value of is greater than 0, Control the drone to measure along the deviation Move in the direction of the ranging sensor.

[0070] In addition, the present invention can also solve the offset distance of the UAV from the center of the cable tunnel in the flight reference plane according to the maximum oblique measurement distance and the flight pitch angle of the UAV in the flight reference plane.

[0071] For example, the calculation formula for the offset distance is:

[0072] ;

[0073] in, Indicates is the offset distance for basic solution. It should be noted that when When the minimum oblique distance is collected, The maximum oblique distance is the set; on the contrary, when When the maximum oblique distance is collected, What is collected is the minimum oblique measurement distance.

[0074] like Figure 3 As shown, The maximum oblique distance is collected. The value of is greater than 0, Control the drone to measure along the deviation Move in the direction of the ranging sensor.

[0075] The cable tunnel drone inspection adaptive control method described in the present invention aims to reduce the probability of a drone colliding in a portion of a cable tunnel with a large curvature and improve the safety of drone flight. After the flight direction of the drone is corrected according to the flight reference plane and the flight pitch angle, the pitch angle variable within a unit time is calculated by the ratio of the flight pitch angle to the correction period; in the next correction period, the flight direction of the drone is dynamically corrected according to the pitch angle variable within the unit time.

[0076] In addition, during the flight of the unmanned aerial vehicle, the present invention synchronously controls multiple ranging sensors to rotate in a positive and negative alternating manner in a circumferential direction of their own distribution, and each ranging sensor correspondingly collects an oblique distance set; when the maximum oblique distance and the minimum oblique distance are extracted from the distance sequence, the abnormal data in the oblique distance set is deleted; wherein, all the oblique distances in the oblique distance set show a monotonous change trend in time sequence, and the abnormal data are data showing extreme value points in the oblique distance set.

[0077] The present invention can filter out the interference of pipelines or cables in the cable tunnel on the distance measurement process, and effectively improve the accuracy and reliability of oblique distance measurement.

[0078] Embodiment 2: Cable tunnel drone inspection adaptive control system, the system is used to implement the cable tunnel drone inspection adaptive control method as described in Embodiment 1, such as Figure 4 As shown, it includes a distance acquisition module, a plane determination module, an angle solving module and a correction control module.

[0079] Among them, the distance acquisition module is used to collect the oblique distance between the UAV and the inner wall of the cable tunnel during flight through the ranging sensor, and multiple oblique distances collected at the same time constitute a distance sequence; the plane determination module is used to determine the flight reference plane of the UAV with the measurement direction of the ranging sensor corresponding to the largest oblique distance and the smallest oblique distance in the distance sequence and the central viewing direction of the camera being in the same plane as a constraint; the angle solving module is used to solve the flight pitch angle of the UAV in the flight reference plane according to the inner diameter of the cable tunnel, the largest oblique distance, the smallest oblique distance and the oblique angle of the ranging sensor; the correction control module is used to correct the flight direction of the UAV according to the flight reference plane and the flight pitch angle, and simultaneously start the camera for image acquisition.

[0080] The present invention also records a computer terminal, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the adaptive control method for cable tunnel drone inspection as described in Example 1 is implemented.

[0081] The present invention also records a computer-readable medium on which a computer program is stored. The computer program is executed by a processor to implement the adaptive control method for cable tunnel drone inspection as described in Example 1.

[0082] Working principle: The present invention uses multiple ranging sensors symmetrically distributed around the camera to measure the oblique distance between the UAV and the inner wall of the cable tunnel during flight, and determines the flight reference plane characterizing the bending direction of the cable tunnel through the measurement directions of the ranging sensors corresponding to the maximum oblique distance and the minimum oblique distance. The flight pitch angle of the UAV in the flight reference plane is solved in combination with the inner diameter of the cable tunnel, the maximum oblique distance, the minimum oblique distance and the oblique angle of the ranging sensor. The flight direction of the UAV can be corrected at regular intervals, and adaptive control of the UAV flying along the extension direction of the cable tunnel can be achieved under poor illumination conditions and weak signal coverage.

[0083] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0084] 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 generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. 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.

[0085] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate 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 A function specified in one or more boxes.

[0086] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0087] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An adaptive control method for cable tunnel drone inspection, characterized in that: The drone is equipped with a camera and a plurality of ranging sensors symmetrically distributed around the camera, and includes the following steps: The oblique distance between the UAV and the inner wall of the cable tunnel is collected by the distance measuring sensor during the flight, and multiple oblique distances collected at the same time form a distance sequence; The flight reference plane of the UAV is determined by taking the measurement direction of the distance sensor corresponding to the largest oblique distance and the smallest oblique distance in the distance sequence and the central viewing direction of the camera as the constraint that they are in the same plane; The flight pitch angle of the UAV in the flight reference plane is solved according to the inner diameter of the cable tunnel, the maximum oblique measurement distance, the minimum oblique measurement distance and the oblique measurement angle of the ranging sensor; Correct the flight direction of the drone according to the flight reference plane and flight pitch angle, and start the camera to collect images at the same time; The specific expression for solving the flight pitch angle of the UAV in the flight reference plane is: h=(L1+L2)sinαcosθ+(L2-L1)cosαsinθ; Wherein, h represents the inner diameter of the cable tunnel; L1 represents the maximum oblique distance or the minimum oblique distance collected by the ranging sensor located on the upward side of the flight reference plane; L2 represents the minimum oblique distance or the maximum oblique distance collected by the ranging sensor located on the downward side of the flight reference plane. The upward side and the downward side in the flight reference plane are divided by the central viewing direction of the camera; α represents the oblique angle of the ranging sensor; θ represents the flight pitch angle of the drone in the flight reference plane. A value greater than 0 is a pitch angle, and a value less than 0 is an elevation angle. Furthermore, when L1 is the minimum oblique measurement distance, L2 is the maximum oblique measurement distance; conversely, when L1 is the maximum oblique measurement distance, L2 is the minimum oblique measurement distance.

2. The cable tunnel drone inspection adaptive control method according to claim 1 is characterized in that: The oblique measurement angle between the distance measurement direction of each distance measurement sensor and the central viewing angle direction of the camera is equal.

3. The cable tunnel drone inspection adaptive control method according to claim 1 is characterized in that: The method further includes: The offset distance of the UAV from the center of the cable tunnel in the flight reference plane is solved according to the maximum oblique measurement distance and the flight pitch angle of the UAV in the flight reference plane; Alternatively, the offset distance of the UAV from the center of the cable tunnel in the flight reference plane is solved according to the minimum oblique measurement distance and the flight pitch angle of the UAV in the flight reference plane.

4. The cable tunnel drone inspection adaptive control method according to claim 3 is characterized in that: The calculation formula of the offset distance is specifically: Or, the calculation formula of the offset distance is specifically: Wherein, ΔD(L1) represents the offset distance solved based on L1; ΔD(L2) represents the offset distance solved based on L2.

5. The cable tunnel drone inspection adaptive control method according to claim 1 is characterized in that: The method further includes: After the flight direction of the UAV is corrected according to the flight reference plane and the flight pitch angle, the pitch angle variable in the unit time is calculated by the ratio of the flight pitch angle to the correction period; In the next correction cycle, the flight direction of the UAV is dynamically corrected according to the pitch angle variable within the unit time.

6. The cable tunnel drone inspection adaptive control method according to claim 1 is characterized in that: The method further includes: During the flight of the UAV, multiple distance measuring sensors are synchronously controlled to rotate in a positive and negative alternating manner in the circumferential direction of their own distribution, and each distance measuring sensor collects a corresponding oblique distance set; When extracting the maximum oblique distance and the minimum oblique distance from the distance sequence, the abnormal data in the oblique distance set are deleted; Among them, all oblique distances in the oblique distance set show a monotonous change trend in chronological order, and the abnormal data are the data showing extreme points in the oblique distance set.

7. Cable tunnel drone inspection adaptive control system, characterized by: The system is used to implement the cable tunnel drone inspection adaptive control method according to any one of claims 1 to 6, comprising: The distance acquisition module is used to collect the oblique distance between the UAV and the inner wall of the cable tunnel during flight through a distance measuring sensor. Multiple oblique distances collected at the same time form a distance sequence; The plane determination module is used to determine the flight reference plane of the UAV by constraining that the measurement direction of the distance measurement sensor corresponding to the largest oblique distance and the smallest oblique distance in the distance sequence and the central viewing direction of the camera are in the same plane; An angle solving module is used to solve the flight pitch angle of the UAV in the flight reference plane according to the inner diameter of the cable tunnel, the maximum oblique measurement distance, the minimum oblique measurement distance and the oblique measurement angle of the distance measurement sensor; The correction control module is used to correct the flight direction of the UAV according to the flight reference plane and the flight pitch angle, and simultaneously start the camera to collect images.

8. A computer terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the adaptive control method for cable tunnel drone inspection as described in any one of claims 1 to 6 is implemented.

9. A computer readable medium having a computer program stored thereon, characterized in that: The computer program is executed by a processor to implement the adaptive control method for cable tunnel drone inspection as described in any one of claims 1 to 6.

Images