UAV gimbal posture abnormality detection method, system, device and storage medium

Abstract

The present invention provides a method, system, device and storage medium for detecting abnormal posture of a drone gimbal, including creating a target container and an actual container; setting the target posture parameters of the drone at each moment according to the flight path of the drone, and storing the target posture parameters in the target container; after the drone takes off, the sensor collects the actual posture parameters of the drone in real time and stores them in the data frame of the actual container; the data of the two containers are updated in real time, and when the data in the container reaches the sliding window width, the data in the actual container is subjected to algorithmic analysis. The present invention can obtain the real-time posture information of the drone and the gimbal and save the records, and perform algorithmic analysis on the saved information records at the same time. When the posture abnormality occurs and the abnormality lasts for an unacceptable time, the drone will react to avoid major accidents and false alarms, ensure work efficiency, reduce the difficulty of controlling the drone, and achieve stable operation of the drone.

Description

Technical Field

[0001] The present invention relates to the field of unmanned aerial vehicle (UAV) detection technology, and in particular to a method, system, device and storage medium for detecting abnormal posture of a UAV gimbal. Background Art

[0002] The rapid expansion of wind power installations around the world has increased the demand for wind farm operation and maintenance inspections. The wind power operation and maintenance inspection work, which was originally highly dependent on manpower, is undergoing a transformation due to the application of intelligent, digital, and unmanned technologies. In addition to making wind power operation and maintenance more efficient, the industry generally believes that the application of drones has solved the pain points of traditional wind farm operation and maintenance.

[0003] Existing methods for detecting abnormal postures of UAVs are mainly based on abnormal judgment using deep learning technology, which needs to be immediate and accurate to avoid major abnormalities. However, when establishing an external environment model, the accuracy rate has not been able to reach 100%, which can cause certain safety hazards.

[0004] Under the training of a large number of sample data sets, the aircraft itself responds to possible real-time command anomalies and ensures that the determined gimbal and aircraft dynamic flight information is accurate, avoiding false alarms and ensuring work efficiency; however, the feedback time and feedback speed are not accurate enough. A time difference of one second is enough to cause a wind power inspection drone in special fields to crash.

[0005] However, in the current existing technology, since the drone is at high altitude when flying, there are interferences such as light and wind, which often make it difficult for the drone to adjust its attitude to the ideal state, and then there will be a large difference between the ideal attitude and the actual attitude. If the actual attitude is different from the ideal attitude, including whether the drone and the cloud mounted on the drone reach the predetermined deflection angle, pitch angle, and coordinate position and other data information, it means that there are major hidden dangers in the flight process of the drone, and correct adjustments need to be made in time. There are many restrictions on human control of drones, and the relevant real-time parameters are difficult to adjust. Once there is a problem with the recognition result, it may reduce work efficiency. For continuous wind power detection, efficiency is a very important influencing factor. Summary of the invention

[0006] In view of the defects in the prior art, the purpose of the present invention is to provide a method for detecting abnormal posture of a drone gimbal system, comprising the following steps:

[0007] Create target container and actual container;

[0008] Setting target attitude parameters of the UAV at each moment according to the flight path of the UAV, and storing the target attitude parameters in the target container;

[0009] After the drone takes off, the sensor collects the actual attitude parameters of the drone in real time and stores them in the data frame of the actual container;

[0010] The data of the two containers are updated in real time, and an algorithm analysis is performed on the data in the actual container to determine whether the target container data and the actual container data are stable;

[0011] When the target container data and the actual container data are stable, and the data in the container reaches the sliding window width, it is determined whether the attitude of the UAV is abnormal; when the actual attitude parameter is outside the attitude deviation threshold and the deviation time exceeds the attitude judgment time, the UAV is abnormal, an error is reported and the flight attitude of the UAV is adjusted; when the actual attitude parameter is within the attitude deviation threshold, the UAV is not abnormal, and detection is stopped after the flight ends.

[0012] The steps of determining whether the actual posture parameters are abnormal are:

[0013] Without control mode detection, when the actual command parameters of the UAV are within the preset command deviation threshold, the current posture of the UAV is normal; when the actual command parameters are outside the command deviation threshold and the command deviation time exceeds the command judgment time, the current posture of the UAV is abnormal.

[0014] Furthermore, the step of determining whether the actual posture parameters are abnormal also includes:

[0015] Position mode detection: when the actual position parameter of the drone is within the preset position deviation threshold, the current posture of the drone is normal; when the actual position parameter is inconsistent with the target position parameter of the drone at the set time and the position deviation time exceeds the position determination time, the current position of the drone is abnormal;

[0016] Furthermore, the step of determining whether the actual posture parameters are abnormal also includes:

[0017] Speed ​​mode detection: when the actual speed parameter of the drone is within the preset speed deviation threshold, the current posture of the drone is normal; when the actual speed parameter is inconsistent with the target speed parameter of the drone at the set time and the speed deviation time exceeds the speed judgment time, the current speed of the drone is abnormal.

[0018] Furthermore, the step of determining whether the actual posture parameters are abnormal also includes:

[0019] Gimbal rotation angle mode detection: when the actual rotation angle parameter of the drone is within the preset rotation angle deviation threshold, the current posture of the drone is normal; when the actual rotation angle parameter is inconsistent with the target rotation angle parameter of the drone at the set time and the rotation angle deviation time exceeds the rotation angle judgment time, the current speed of the drone is abnormal.

[0020] Furthermore, the target attitude parameters include a target yaw angle, a target pitch angle and a target roll angle;

[0021] The setting range of the target yaw angle is -10 to 10 degrees, the setting range of the target pitch angle is -45 to 45 degrees, and the setting range of the target roll angle is -30 to 30 degrees.

[0022] Furthermore, the steps of sliding window processing are:

[0023] The sliding window width is 100 frames and the rate is 13-20 Hz;

[0024] Set sliding window threshold;

[0025] A slider with a width of 100 frames is specified to slide at a speed of 13-20 Hz. The sliding direction is in the order of abnormal deviation time. The abnormal deviation time is the duration from the moment when the data abnormality occurs to the previous frame moment when the data normally appears. When the difference is greater than the sliding window threshold, the number is discarded and the remaining data is output after noise cleaning.

[0026] Furthermore, it is applied to the detection method of abnormal posture of the UAV gimbal system;

[0027] The detection system comprises:

[0028] A data acquisition module, used to collect data on the attitude information of the drone when the drone is flying;

[0029] A posture detection module, which determines whether the flight posture of the UAV is abnormal based on the data collected by the data collection module;

[0030] The system control module controls the flight attitude of the UAV according to the result of the attitude detection module.

[0031] Further, a memory for storing a computer program;

[0032] A processor is used to execute the computer program to apply the method for detecting abnormal posture of a drone gimbal system.

[0033] Furthermore, a computer program is stored on the computer-readable storage medium, and the computer program is executed by the processor to implement the method for detecting abnormal posture of a drone gimbal system.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] The present invention can obtain the real-time posture information of the UAV and the gimbal and save the records, and at the same time perform algorithm analysis on the saved information records, and judge the dynamic flight information of the UAV and the gimbal in the algorithm analysis. When the posture is abnormal, an immediate response is made to avoid major abnormalities in the UAV, avoid false alarms, and ensure work efficiency; the present invention can reduce the difficulty of controlling the UAV and achieve stable operation of the UAV. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0037] Figure 1 A schematic diagram of an algorithm analysis process provided by an embodiment of the present invention;

[0038] Figure 2 A schematic diagram of a posture abnormality detection system provided by an embodiment of the present invention;

[0039] Figure 3 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention;

[0040] Figure 4 A schematic diagram of the structure of a computer-readable storage medium provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0041] The present invention is described in detail below in conjunction with specific embodiments. The following embodiments will help those skilled in the art to further understand the present invention, but are not intended to limit the present invention in any form. It should be noted that, for those of ordinary skill in the art, several changes and improvements can also be made without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

[0042] As used herein, the term "including" and its variations mean open inclusion, i.e., "including but not limited to". Unless otherwise stated, the term "or" means "and / or". The term "based on" means "based at least in part". The terms "an example embodiment" and "an embodiment" mean "at least one example embodiment". The term "another embodiment" means "at least one additional embodiment". The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0043] Figure 1 A schematic diagram of an algorithm analysis flow provided for an embodiment of the present invention.

[0044] During the flight of the drone system, it is necessary to adjust its attitude in time. The attitude information includes the drone position, the angle of the drone gimbal and the flight speed of the drone. The basis for determining the drone attitude is the difference between the target position information sent per unit time and the actual position information; the attitude information is roll, yaw, and pitch respectively; pitch is the rotation around the X axis, also called the pitch angle. Yaw is the rotation around the Y axis, also called the yaw angle. Roll is the rotation around the Z axis, also called the roll angle.

[0045] The target attitude parameters include a target yaw angle, a target pitch angle and a target roll angle; the setting range of the target yaw angle is -10 to 10 degrees, the setting range of the target pitch angle is -45-45 degrees, and the setting range of the target roll angle is -30 to 30 degrees.

[0046] However, since the drone is flying at high altitude, there are interferences from light, wind, etc., which often make it difficult for the drone to adjust its attitude to the ideal state, and then there will be a big difference between the ideal attitude and the actual attitude. If the actual attitude is far from the ideal attitude, it means that there are major hidden dangers in the flight process of the drone, and it is necessary to make correct adjustments in time.

[0047] A method for detecting abnormal gimbal attitude is used to detect whether the gimbal mounted on a running UAV reaches a predetermined deflection angle, pitch angle, coordinate position and other data information, automatically give feedback to the system, and timely intervene in appropriate operations to adjust the aircraft status and update the system data.

[0048] The following steps are involved:

[0049] Create target container and actual container;

[0050] Setting target attitude parameters of the UAV at each moment according to the flight path of the UAV, the target attitude parameters including the target instruction of the UAV, the target position, the target rotation angle of the gimbal and / or the target speed of the UAV, and storing the target attitude parameters in the target container;

[0051] After the drone takes off, the sensor collects the actual attitude parameters of the drone in real time and stores them in the data frame of the actual container; the actual attitude parameters include the actual command of the drone, the actual position, the actual rotation angle of the gimbal and / or the actual speed of the drone;

[0052] The data of the two containers are updated in real time, and an algorithm analysis is performed on the data in the actual container to determine whether the target container data and the actual container data are stable;

[0053] When the target container data and the actual container data are stable, and the data in the container reaches the sliding window width, it is determined whether the attitude of the UAV is abnormal; when the actual attitude parameter is outside the attitude deviation threshold and the deviation time exceeds the attitude judgment time, the UAV is abnormal, an error is reported and the flight attitude of the UAV is adjusted; when the actual attitude parameter is within the attitude deviation threshold, the UAV is not abnormal, and detection is stopped after the flight ends.

[0054] The role of sliding window technology is that it can effectively integrate the relationship between real-time data and overall data, and analyze experimental data when the sample size is sufficient. The data format of automatic drone inspections is frame data, so new data frames can be synchronized instantly in the container and the original data frames can be deleted. At the same time, the container size is also controllable, which greatly enhances the credibility of the data.

[0055] The steps of sliding window processing are:

[0056] The sliding window width is 100 frames and the rate is 13-20 Hz;

[0057] Set sliding window threshold;

[0058] A slider with a width of 100 frames is specified to slide at a speed of 13-20 Hz. The sliding direction is in the order of abnormal deviation time. The abnormal deviation time is the duration from the moment when the data abnormality occurs to the previous frame moment when the data normally appears. When the difference is greater than the sliding window threshold, the number is discarded and the remaining data is output after noise cleaning.

[0059] When determining whether the position of the drone is at the predetermined position, the variance and related difference calculations can be performed using the drone position data within the window time, and the data results obtained after algorithm processing; if it meets the set threshold, the specific range of the threshold varies in each dimension, but the same standard is to ensure data stability; filter noise, and then finally use the deviation time to determine whether there is an abnormality in the posture position. If it meets the set threshold, it can be considered that the drone is at the predetermined position or can be approximately at the predetermined position near the predetermined position.

[0060] The criteria for judging whether the target container data and the actual container data are stable are as follows:

[0061] Set stability threshold;

[0062] In theory, when the variance between the command and the actual state is 0 under the limit state, it is considered that the current command and the response are both in a stable state. The inverse of the actual state tends to be stable under the speed control requirement, which is also the basis for judging the relevant data. It can be considered that the UAV is at the target position. When the variance is not zero but less than the set stability threshold, it is considered that it is close to the target position and can be approximated to be at the target position.

[0063] In this embodiment, the extreme value of the stability threshold is 3. When the variance value between the target container data and the actual container data is in the range of 0-3, we consider that the target container data and the actual container data are stable.

[0064] After the drone takes off, the sensor collects the actual attitude parameters of the drone in real time and saves them in data frames. The actual attitude parameters include the actual command of the drone, the actual position, the actual rotation angle of the gimbal and the actual speed of the drone. The data in the data frame is analyzed by algorithm to determine whether the drone is stable.

[0065] Determine whether the drone's posture is abnormal, and if so, adjust the drone's current posture;

[0066] The steps of determining whether the drone posture is abnormal are as follows:

[0067] Setting a deviation threshold as a reference for determining abnormalities, wherein the deviation threshold includes a command deviation threshold, a position deviation threshold, an angle deviation threshold and a speed deviation threshold;

[0068] Set the deviation time, which is the duration of the abnormality of the drone. The deviation time includes the command deviation time, position deviation time, angle deviation threshold and speed deviation time;

[0069] Setting the determination time, which includes the instruction determination time, the position determination time, the angle determination time and the speed determination time;

[0070] Without control mode detection, when the actual command parameters of the drone are within the attitude deviation threshold, the current command of the drone is normal; when the actual attitude parameters are outside the instruction deviation threshold and the instruction deviation time exceeds the instruction judgment time, the current attitude of the drone is abnormal;

[0071] In this embodiment, we require that the no-control mode detection can achieve the following effect: when the actual attitude parameters are (10,10,10), we require that in the future, the drone control mode remains unchanged; the drone needs to always maintain the flight parameters of (10,10,10); that is, when the flight parameters of the drone are not the above parameters but (20,20,20), the flight parameters are maintained at (20,20,20) and this state lasts for 10s. The drone is in this state abnormal and the system reports an error.

[0072] Position mode detection: when the actual position parameter of the drone is within the position deviation threshold, the current posture of the drone is normal; when the actual position parameter is inconsistent with the target position parameter of the drone at the set time and the position deviation time exceeds the position determination time, the current position of the drone is abnormal;

[0073] Speed ​​mode detection: when the actual speed parameter of the drone is within the speed deviation threshold, the current posture of the drone is normal; when the actual speed parameter is inconsistent with the target speed parameter of the drone at the set time and the speed deviation time exceeds the speed judgment time, the current speed of the drone is abnormal.

[0074] Gimbal rotation angle mode detection: when the actual rotation angle parameter of the drone is within the preset rotation angle deviation threshold, the current posture of the drone is normal; when the actual rotation angle parameter is inconsistent with the target rotation angle parameter of the drone at the set time and the rotation angle deviation time exceeds the rotation angle judgment time, the current speed of the drone is abnormal.

[0075] The update frame rate of the data frame data is 25-50 Hz.

[0076] The algorithm analysis step is: calculate the data using the Lagrange interpolation formula, which is:

[0077]

[0078]

[0079] , where n=100.

[0080] The specific calculation method of interpolation is mainly used to fit the curvature. For the standard rate curve, linear interpolation or least squares fitting methods can be used to determine the threshold interval of future data samples. When the actual value arrives, it can be used as a judgment method to enhance the robustness of the system.

[0081] Furthermore, the algorithm analysis step also includes variance;

[0082] The variance analysis is performed, and the formula is:

[0083]

[0084] or

[0085] D(X)=∫x 2 f(x)dx-μ 2

[0086] Where n = 100;

[0087] Furthermore, the algorithm analysis step also includes cross entropy;

[0088] Then we analyze it with cross entropy loss, the formula is:

[0089]

[0090] Among them, n=100.

[0091] In some embodiments of the present disclosure, Figure 2 The schematic diagram of the posture abnormality detection system provided in the embodiment of the present invention is applied to the posture abnormality detection method applied to the drone gimbal system provided in the above embodiment. Figure 2 As shown, the abnormal posture detection system may include:

[0092] The data acquisition module 001 is used to collect data on the attitude information of the drone when the drone is flying.

[0093] The attitude detection module 002 determines whether the flight attitude of the UAV is abnormal based on the data collected by the data collection module.

[0094] The system control module 003 controls the flight attitude of the UAV according to the result of the attitude detection module.

[0095] It is understandable that various aspects of the technical solution of the present disclosure can be implemented as a system, method or program product. Therefore, various aspects of the technical solution of the present disclosure can be specifically implemented in the following forms, i.e., a complete hardware implementation method, a complete software implementation method (including firmware, microcode, etc.), or an implementation method combined with hardware and software, which can be collectively referred to as "circuit", "module" or "platform" here. Those skilled in the art should understand that each unit or each module or each step of the present disclosure above can be implemented with a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented with a program code executable by a computing device, so that they can be stored in a storage medium and executed by a computing device, and in some cases, the steps shown or described can be performed in an order different from that herein, or they can be made into each integrated circuit module respectively, or multiple modules or steps therein can be made into a single integrated circuit module to implement.

[0096] Figure 3 According to some embodiments of the present disclosure, a schematic diagram of the structure of an electronic device is shown. Figure 3 The electronic device 600 implemented according to the implementation method in this embodiment is described in detail. Figure 3The electronic device 600 shown is merely an example and should not impose any limitations on the functions and scope of use of any embodiment of the technical solution disclosed herein.

[0097] like Figure 3 As shown, the electronic device 600 is in the form of a general computing device. The components of the electronic device 600 may include but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different platform components (including the storage unit 620 and the processing unit 610), a display unit 640, etc.

[0098] Among them, the storage unit stores program codes, and the program codes can be executed by the processing unit 610, so that the processing unit 610 executes the implementation of each functional module of the detection system for the abnormal posture of the drone gimbal system in this embodiment.

[0099] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access unit (RAM) 6201 and / or a cache storage unit 6202 , and may further include a read-only storage unit (ROM) 6203 .

[0100] The storage unit 620 may also include a program / utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0101] Bus 630 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0102] The electronic device 600 may also communicate with one or more external devices 700 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may communicate with one or more devices that enable a user to interact with the electronic device 600, and / or communicate with any device that enables the electronic device to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed through an input / output (I / O) interface 650. Furthermore, the electronic device 600 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 through the bus 630. It should be understood that although Figure 3Not shown, other hardware and / or software modules may be used in conjunction with electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms.

[0103] In some embodiments of the present disclosure, a computer-readable storage medium is also provided, on which a computer program is stored. When the computer program is executed by a processor, the various functional modules in the detection system for the abnormal posture of the drone gimbal system in the above disclosure can be realized.

[0104] Although this embodiment does not list other specific implementation methods in detail, in some possible implementation methods, various aspects of the technical solution described in the present disclosure can also be implemented in the form of a program product, which includes program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps of the implementation method described in the image stitching method area of ​​the technical solution of the present disclosure according to various embodiments of the technical solution of the present disclosure.

[0105] Figure 4 According to some embodiments of the present disclosure, a schematic diagram of the structure of a computer-readable storage medium is shown. Figure 4 As shown, a program product 800 for implementing the above method in the implementation method of the technical solution of the present disclosure is described, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. Of course, the program product produced according to this embodiment is not limited to this. In the technical solution of the present disclosure, the readable storage medium can be any tangible medium containing or storing a program, and the program can be used by or in combination with an instruction execution system, an apparatus or a device.

[0106] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0107] Computer readable storage media may include data signals propagated in baseband or as a carrier-area, wherein readable program codes are carried. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination thereof.

[0108] The program code for performing the operation of the technical solution of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as C or similar programming languages. The program code may be executed entirely on the user computing device, locally on the user device, as an independent software package, locally on the user computing device, locally on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0109] In this embodiment, for abnormal system data, feedback is not given immediately, because this will record a lot of error data; generally, an interval processing solution is adopted, which can eliminate the influence of error data and greatly improve the stability of the system - it can avoid frequent false alarms in the system due to the appearance of special data frames, so that the pilot takes over the flight and affects work efficiency. In this way, it can be ensured that the instantaneous moment of each frame can be recorded, so that when the recorded data of unstable data in the container reaches the calibrated threshold time interval, the abnormal situation will be reported, which greatly enhances the accuracy of the abnormality judgment system and achieves the effect of real-time monitoring.

[0110] The above describes the specific embodiments of the present invention. It should be understood that the present invention is not limited to the above specific embodiments, and those skilled in the art can make various changes or modifications within the scope of the claims, which does not affect the essence of the present invention. In the absence of conflict, the embodiments of the present application and the features in the embodiments can be combined with each other arbitrarily.

Claims

1. A method for detecting abnormal posture of a UAV gimbal system, characterized in that: The following steps are involved: Create target container and actual container; Setting target attitude parameters of the UAV at each moment according to the flight path of the UAV, and storing the target attitude parameters in the target container; After the drone takes off, the sensor collects the actual attitude parameters of the drone in real time and stores them in the data frame of the actual container; The data of the two containers are updated in real time, and an algorithm analysis is performed on the data in the actual container to determine whether the target container data and the actual container data are stable; When the target container data and the actual container data are stable, and the data in the container reaches the sliding window width, it is determined whether the attitude of the drone is abnormal; when the actual attitude parameter is outside the attitude deviation threshold and the deviation time exceeds the attitude judgment time, the drone is abnormal, an error is reported and the flight attitude of the drone is adjusted; when the actual attitude parameter is within the attitude deviation threshold, the drone is not abnormal, and the detection is stopped after the flight ends; The determining whether the posture of the drone is abnormal includes: Without control mode detection, when the actual attitude parameters of the UAV are within the preset attitude deviation threshold, the current attitude of the UAV is normal; when the actual attitude parameters are outside the attitude deviation threshold and the attitude deviation time exceeds the attitude determination time, the current attitude of the UAV is abnormal; Position mode detection: when the actual position parameter of the drone is within the preset position deviation threshold, the current posture of the drone is normal; when the actual position parameter is inconsistent with the target position parameter of the drone at the set time and the position deviation time exceeds the position determination time, the current position of the drone is abnormal; Speed ​​mode detection: when the actual speed parameter of the drone is within the preset speed deviation threshold, the current posture of the drone is normal; when the actual speed parameter is inconsistent with the target speed parameter of the drone at the set time and the speed deviation time exceeds the speed determination time, the current speed of the drone is abnormal; Gimbal rotation angle mode detection: when the actual rotation angle parameter of the drone is within the preset rotation angle deviation threshold, the current posture of the drone is normal; when the actual rotation angle parameter is inconsistent with the target rotation angle parameter of the drone at the set time and the rotation angle deviation time exceeds the rotation angle judgment time, the current speed of the drone is abnormal.

2. The method for detecting abnormal posture of a UAV gimbal system according to claim 1, characterized in that: The target attitude parameters include target yaw angle, target pitch angle and target roll angle; The setting range of the target yaw angle is -10 to 10 degrees, the setting range of the target pitch angle is -45 to 45 degrees, and the setting range of the target roll angle is -30 to 30 degrees.

3. The method for detecting abnormal posture of a UAV gimbal system according to claim 1, characterized in that: The processing steps of the sliding window are: The sliding window width is 100 frames and the rate is 13-20 Hz; Set sliding window threshold; A slider with a width of 100 frames is specified to slide at a speed of 13-20 Hz. The sliding direction is in the order of abnormal deviation time. The abnormal deviation time is the duration from the moment when the data abnormality occurs to the previous frame moment when the data normally appears. When the difference is greater than the sliding window threshold, the data is discarded and the remaining data is output after noise cleaning.

4. A detection system for abnormal posture of the UAV gimbal system, characterized in that: Applicable to the method for detecting abnormal posture of the UAV gimbal system as described in any one of claims 1 to 3; The detection system comprises: A data acquisition module, used to collect data on the attitude information of the drone when the drone is flying; A posture detection module, which determines whether the flight posture of the UAV is abnormal based on the data collected by the data collection module; The system control module controls the flight attitude of the UAV according to the result of the attitude detection module.

5. The device for detecting abnormal posture of the UAV gimbal system is characterized by: include: Memory for storing computer programs; A processor, configured to implement the method for detecting abnormal posture of a drone gimbal system as described in any one of claims 1 to 3 when executing the computer program.

6. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the method for detecting abnormal posture of the unmanned aerial vehicle gimbal system according to any one of claims 1 to 3 is implemented.

Images