Unmanned aerial vehicle fault identification method based on whole flight process effect data monitoring

Abstract

The embodiment of the invention discloses an unmanned aerial vehicle fault identification method based on whole flight process effect data monitoring. A specific embodiment of the method comprises the following steps: carrying out data smoothing processing on each collected unmanned aerial vehicle effect data sequence; based on each target unmanned aerial vehicle effect data sequence, determining a normal flight stage and an interference flight stage in the flight process of the unmanned aerial vehicle swarm individuals, and determining an unmanned aerial vehicle swarm individual state wave equation; the fluctuation amplitude of each parameter in the interference flight stage process is solved; and identifying a fault module of the individual unmanned aerial vehicle according to the fluctuation amplitude of each parameter of the individual unmanned aerial vehicle swarm, performing hierarchical description on the influence degree of the working state of the unmanned aerial vehicle according to the fault module, establishing an unmanned aerial vehicle flight fault identification model, and performing fault identification on the whole flight process of the unmanned aerial vehicle. According to the embodiment, the fault features of the whole flight process of the unmanned aerial vehicle can be effectively identified, and the method has high practicability and expandability.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of drone fault identification, and more particularly to a drone fault identification method based on full-flight effect data monitoring. Background Art

[0002] Complex electromagnetic environments place high demands on the electromagnetic compatibility of UAV systems. Traditional UAV fault identification methods in complex electromagnetic environments rely primarily on identifying the operating status of the UAV based on its behavioral characteristics. Data fluctuations during flight are not integrated with fault identification technology, making it impossible to effectively describe the changes in the UAV's flight status. This makes it difficult to effectively identify complex, progressive faults. Furthermore, research on electromagnetic interference faults in UAV systems lacks system-level fault identification and standard classification. Therefore, research based on full-flight effect data monitoring and UAV system-level fault classification and analysis methods is urgently needed.

[0003] In recent years, data-driven fault identification methods have become a research hotspot. These methods analyze drone flight data and utilize machine learning or deep learning algorithms to build fault models, enabling early warning and accurate fault identification. However, existing data-driven methods typically rely on large amounts of historical fault data and use fault diagnosis models to determine the drone's final operating state. These methods are unable to specifically describe the changes in flight state and performance differences between drones during different flight phases, making it difficult to fully capture the fault characteristics of drones during flight. Summary of the Invention

[0004] The content of this disclosure is used to briefly introduce concepts that will be described in detail in the detailed description section below. The content of this disclosure is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0005] Some embodiments of the present disclosure propose a drone fault identification method, device, electronic device, and computer-readable medium based on full-flight effect data monitoring to solve the technical problems mentioned in the above background technology section.

[0006] In the first aspect, some embodiments of the present disclosure provide a method for identifying UAV faults based on monitoring effect data during the entire flight process, the method comprising: in response to detecting that a UAV swarm is interfered with by an electromagnetic pulse signal, based on a data storage module of a ground station and a UAV flight control, collecting effect data of each UAV during the entire flight process, wherein each UAV corresponds to a collected UAV effect data sequence, and each UAV effect data includes: longitude, latitude, altitude, horizontal speed, vertical speed, yaw angle, pitch angle, roll angle, flight mode, number of satellites, voltage, altitude, remaining power, and distance; performing data smoothing on each collected UAV effect data sequence to obtain each data sequence. According to the smoothed drone effect data sequence, it is used as the effect data sequence of each target drone; based on the above target drone effect data sequence, the normal flight stage and the interference flight stage in the individual flight process of the drone swarm are determined, and the individual state fluctuation equation of the drone swarm is determined; according to the above individual state fluctuation equation of the drone swarm, the fluctuation amplitude of each parameter during the interference flight stage is solved; according to the fluctuation amplitude of each parameter of the individual drone swarm, the fault module of the individual drone is identified, and according to the fault module, the degree of influence of the drone working state is graded and described, and a drone flight fault identification model is established; according to the above drone flight fault identification model, fault identification of the entire drone flight process is carried out.

[0007] In a second aspect, some embodiments of the present disclosure provide a UAV fault identification device based on effect data monitoring during the entire flight process, the device comprising: an acquisition unit, configured to respond to detection that a UAV swarm is interfered with by an electromagnetic pulse signal, and based on a data storage module of a ground station and a UAV flight control, collect effect data of each UAV during the entire flight process, wherein each UAV corresponds to a collected UAV effect data sequence, and each UAV effect data comprises: longitude, latitude, altitude, horizontal speed, vertical speed, yaw angle, pitch angle, roll angle, flight mode, number of satellites, voltage, altitude, remaining power, and distance from the ground; a data smoothing unit, configured to perform data smoothing processing on each collected UAV effect data sequence to obtain each data-smoothed UAV effect data sequence. , as the effect data sequence of each target drone; the determination unit is configured to determine the normal flight stage and the interference flight stage in the individual flight process of the drone swarm based on the above-mentioned effect data sequence of each target drone, and determine the individual state fluctuation equation of the drone swarm; the parameter fluctuation solving unit is configured to solve the fluctuation amplitude of each parameter during the interference flight stage according to the above-mentioned individual state fluctuation equation of the drone swarm; the model establishment unit is configured to identify the fault module of the individual drone according to the fluctuation amplitude of each parameter of the drone swarm, and according to the fault module, perform a graded description of the degree of influence on the working state of the drone, and establish a drone flight fault identification model; the fault identification unit is configured to perform fault identification of the entire drone flight process according to the above-mentioned drone flight fault identification model.

[0008] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.

[0009] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation of the first aspect is implemented.

[0010] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: through the drone fault identification method based on full-process flight effect data monitoring of some embodiments of the present disclosure, by collecting multiple parameter data of the drone in each flight phase in real time and comparing and analyzing them with the baseline data of the normal flight phase, the fluctuation characteristics of each parameter are solved, thereby determining whether the flight status of the drone is abnormal. Compared with traditional fault diagnosis methods, the present disclosure has the following advantages: First, by introducing full-process effect data monitoring, it can comprehensively cover the state changes of the drone in different flight phases, improving the comprehensiveness and accuracy of fault diagnosis; second, by solving the parameter fluctuation characteristics, it can effectively distinguish between normal flight fluctuations and abnormal fluctuations caused by faults, reducing the interference of environmental factors on fault diagnosis; finally, this method does not need to rely on a large amount of historical fault data, can effectively identify the fault characteristics of the drone throughout the flight process, and has strong practicality and scalability. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0012] Figure 1 is a flow chart of some embodiments of a UAV fault identification method based on full-flight effect data monitoring according to the present disclosure;

[0013] Figure 2 A single UAV fault identification diagram based on airborne data and ground station data in a UAV fault identification method based on full-flight effect data monitoring according to some embodiments of the present disclosure;

[0014] Figure 3 1 is a schematic structural diagram of some embodiments of a UAV fault identification device based on full-flight effect data monitoring according to the present disclosure;

[0015] Figure 4 It is a structural diagram of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0016] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0017] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other.

[0018] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0019] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0020] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0021] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0022] Figure 1 This is a process 100 of some embodiments of the UAV fault identification method based on full-flight process effect data monitoring of some embodiments of the present disclosure. The UAV fault identification method based on full-flight process effect data monitoring includes the following steps:

[0023] Step 101, in response to detecting that the drone swarm is interfered with by an electromagnetic pulse signal, based on the data storage module of the ground station and the drone flight control, the effect data of each drone during the entire flight process is collected.

[0024] In some embodiments, the execution entity (e.g., a computing device) of a drone fault identification method based on full-flight effect data monitoring can, in response to detecting electromagnetic pulse signal interference in a drone swarm, collect effect data for each drone throughout the entire flight process based on a ground station and the drone flight control's data storage module. Each drone corresponds to a sequence of collected drone effect data, and each drone effect data includes: longitude, latitude, altitude, horizontal speed, vertical speed, yaw angle, pitch angle, roll angle, flight mode, number of satellites, voltage, altitude, remaining battery power, and distance. The number of satellites may refer to the number of satellites that the individual drone can connect to during operation. The longitude and latitude may refer to the current longitude and latitude of the individual drone. The altitude may refer to the current height above the ground of the individual drone. The horizontal speed may refer to the current horizontal speed of the individual drone. The vertical speed may refer to the current vertical speed of the individual drone. Flight modes may include GPS mode, attitude mode, and manual mode. The voltage may refer to the current voltage of the individual drone. The remaining battery power may refer to the current remaining battery life of the drone. The distance may refer to the distance flown by the drone since startup. For example, a signal detection module built into the drone can be used to detect whether it is experiencing electromagnetic pulse signal interference. Another example is a regional signal detection module in a ground station that can detect whether the drone's flight area is experiencing electromagnetic pulse signal interference. For example, the regional signal detection module can be a pulse detector.

[0025] Step 102 : performing data smoothing processing on each collected UAV effect data sequence to obtain each data smoothed UAV effect data sequence as each target UAV effect data sequence.

[0026] In some embodiments, the above-mentioned execution entity can perform data smoothing processing on each collected drone effect data sequence to obtain each data smoothed drone effect data sequence as each target drone effect data sequence.

[0027] In practice, the aforementioned execution entity can average the collected drone effect data sequences based on the effect data length to obtain smoothed drone effect data sequences. If the data length is too long, that is, if the flight data is read too many times, the effect data length x can be appropriately increased; conversely, it can be shortened. The fundamental purpose is to reduce the impact of parameter jumps at a certain moment caused by external factors on the fault identification results. The specific value can be determined according to the situation. For example, in the example, x is 10.

[0028] For example, the collected flight data (drone effect data), that is, ground station data and airborne data, can be averaged every ten records to reduce the accidental error of drone flight data. Assuming that a total of N flight data are collected, the flight data sequence (drone effect data sequence) is D = {d1, d2, d3, ..., d N For flight data sequence d i The averaging algorithm is applied for processing, that is, the data of every ten records (the length of the effect data can be 10) are divided into a group (if the number of the last group of data is less than ten, no supplement is required), the average value of each group of data is calculated, and the flight data after preprocessing is generated. The time of each data is the time of the last record in the corresponding original flight data group. Assuming that there are K groups in total, the specific expression of the kth preprocessed data is:

[0029]

[0030] Ground station data refers to the drone data detected by the ground station. Airborne data can refer to the effect data detected by the drone itself.

[0031] Step 103: Based on the above-mentioned target drone effect data sequences, determine the normal flight phase and the interference flight phase during the flight of the individual drone swarm, and determine the individual state wave equation of the drone swarm.

[0032] In some embodiments, the above-mentioned execution entity can determine the normal flight phase and the interference flight phase during the flight of the individual drone swarm based on the above-mentioned target drone effect data sequences, and determine the individual drone swarm state wave equation.

[0033] In practice, the above-mentioned execution entity can, based on the above-mentioned target drone effect data sequences, describe the entire flight status of each parameter in the drone effect data in units of swarms, and compare the parameter change trends of each drone in the swarm to determine the normal flight stage and the interference flight stage during the swarm flight process.

[0034] For example, the parameter data collected in step 103 is used to describe the entire flight state in units of a swarm, and the normal flight stage and the disturbed stage of the swarm can be determined by the change trend of the flight parameters of each drone in the swarm (in the normal flight stage of the drone, the change trend of the flight parameters of each drone in the swarm is the same, and the fluctuation range is small. When the swarm begins to be disturbed, the flight parameters of the drones in the swarm fluctuate abnormally). Among them, since the latitude and longitude change range is small, the accuracy is increased to 0.01, that is:

[0035]

[0036] Among them, n {0,1}Represent the longitude and latitude parameters respectively.

[0037] For example, based on MATLAB software, the changes in 14 parameters of drones in the same swarm are plotted and compared separately, and the parameter change trends of different drones at different times in the same time period are compared to determine the flight status of the drones.

[0038] In practice, the above-mentioned execution entities can determine the individual state fluctuation equation of the drone swarm through the following formula:

[0039]

[0040] Where, ΔV ij Indicates the fluctuation amplitude of the jth parameter at the i-th moment, V ij Indicates the value of the jth parameter at the i-th moment, V maxj represents the maximum value of the jth parameter in the interference flight phase, V minj represents the minimum value of the jth parameter in the interference flight phase, V avej represents the average value of the jth parameter during the normal flight phase.

[0041] Step 104 , according to the individual state fluctuation equation of the UAV swarm, solve the fluctuation amplitude of each parameter during the interference flight phase.

[0042] In some embodiments, the execution entity may solve the fluctuation amplitude of each parameter during the interference flight phase based on the individual state fluctuation equation of the drone swarm.

[0043] During the data analysis process, due to the different recording units of airborne data and ground data, the recording errors are also different. Therefore, when calculating the flight data parameters of the UAV, the airborne data are selected separately. The normal data of the time T1 after the UAV enters the route recorded by the ground station data is the normal benchmark data. The data after T1 is selected as the formal test data. The data fluctuation after T1 is solved and plotted according to the UAV swarm individual state fluctuation equation (1). Due to the differences in the recorded data parameters, the x-axis and y-axis horizontal velocity component parameter analysis of the airborne data analysis part are uniformly replaced by the horizontal velocity parameters in the ground station data in the ground station analysis stage. In addition, the flight model, distance, and remaining power parameters are analyzed using the ground station data throughout the process.

[0044]

[0045] Where, ΔV ij is the jth parameter i The fluctuation amplitude at the moment, V ij is the jth parameter i The parameter value at the moment, V maxjis the maximum value of the jth parameter in the interference flight phase, V minj is the minimum value of the jth parameter in the interference flight phase, V avej is the average value of the jth parameter in the normal flight phase, and the UAV fault is identified according to the following fault types.

[0046] For example, fault types can include: SF1, SF2, and SF3. SF1 indicates an undetected fault, system degradation, or sluggishness; SF2 indicates a fault detected from the ground station and log files; and SF3 indicates a system state change, resulting in system loss of control. For another example, SF1 can be further subdivided into SF1.1 and SF1.2. SF1.1 indicates a degradation in drone performance with minimal impact on normal operation; SF1.2 indicates system lag and sluggishness. SF2 can be further subdivided into SF2.1, SF2.2, SF2.3, and SF2.4. SF2.1 indicates damage to the GPS module and a decrease in the number of GPS satellites; SF2.2 indicates a fluctuation in drone flight speed data greater than 0.5; SF2.3 indicates a change in flight attitude, with fluctuations in yaw, roll, or pitch angle data greater than 0.5; and SF2.4 indicates a disconnection of the remote control link. SF3 can be further subdivided into SF3.1 and SF3.2. SF3.1 indicates the triggering of system fault protection, resulting in a mode change; and SF3.2 indicates drone downtime.

[0047] It should be noted that the above parameters can be any one of: longitude, latitude, altitude, horizontal speed, vertical speed, yaw angle, pitch angle, roll angle, flight mode, number of satellites, voltage, altitude, remaining power, and distance.

[0048] Step 105 , based on the fluctuation amplitude of each parameter of the individual drone swarm, the fault module of the individual drone is identified, and based on the fault module, the degree of influence on the working status of the drone is graded and described, and a drone flight fault identification model is established.

[0049] In some embodiments, the above-mentioned execution entity can identify the fault module of an individual drone based on the fluctuation amplitude of each parameter of the drone swarm, and based on the fault module, perform a graded description of the degree of impact on the drone's working status to establish a drone flight fault identification model.

[0050] In practice, the above-mentioned execution entity can identify the fault module of an individual drone through the following steps, and then grade the impact of the fault module on the drone's working status to establish a drone flight fault identification model:

[0051] The first step is to determine the fluctuation range of each parameter of the individual drone swarm and identify the faulty module of the individual drone.

[0052] In the second step, combining the behavioral characteristics of drones with the working status of drones, the faults are classified and graded according to the severity of the impact of the fault module on the individual status of the swarm, and the drone fault status under the fault level is described to establish a drone flight fault identification model.

[0053] For example, different modules of a drone determine the size of different parameters of the drone. When the parameters of a drone fluctuate abnormally, it means that the corresponding module of the drone is interfered with and damaged. Specifically, the drone's flight attitude: the pitch angle, roll angle, and yaw angle are determined by the gyroscope and accelerometer. Flight control: the x-axis speed, y-axis speed, and vertical speed are measured by GPS and then controlled by the accelerometer and gyroscope. The drone's onboard data storage is determined by the drone's data storage module. The number of GPS satellites in the drone is determined by the GPS module. Combined with the drone's behavioral characteristics and working status, the fault is graded and described according to the degree of impact of the fault module on the drone's working status. A fault identification model that can realize the entire drone flight process is established, as shown in Table 1:

[0054] Table 1 Fault classification and classification definition table

[0055]

[0056] Table 2 UAV system fault classification table

[0057]

[0058]

[0059] In the fault identification process below, SF1 is a minor fault type, determined by slight fluctuations in the drone's flight parameters, indicating a decrease in performance but still operable. SF1.1 is defined as a fluctuation in sensor data within the range of 0.3-0.5; SF1.2 is defined as a fluctuation in sensor data within the range of 0.5-0.7.

[0060] SF2 is a moderate fault type, indicating changes in the number of satellites and the remote control link. Under this fault type, the normal operation of the drone is affected. In the following judgment process, SF2.1 indicates that the number of satellites fluctuates within a range of 0.5-1. In this case, the drone's GPS module is damaged, seriously affecting the drone's positioning. SF2.2 fault type indicates that the drone's flight speed data fluctuates by more than 0.5. In this case, the drone's GPS measurement module or accelerometer and gyroscope modules are damaged, affecting the drone's normal operation. SF2.3 fault type indicates that the drone's flight attitude is affected. In this case, the drone's gyroscope and accelerometer modules are damaged. SF2.4 indicates that the remote control link is affected. In this case, various parameters fluctuate significantly at the same time, making it impossible to obtain flight information.

[0061] SF3 is a serious fault type, and the judgment standard is that the drone will crash directly, indicating that the drone cannot continue to operate. Among them, SF3.1 mainly means that the drone's fault protection mode automatically switches to return or hover mode, and SF3.2 means that the drone has crashed and the drone flight log cannot be saved.

[0062] It should be noted that the UAV flight fault identification model is a fault identification rule model composed of Table 1 and Table 2.

[0063] Step 106: Perform fault identification for the entire UAV flight process based on the UAV flight fault identification model.

[0064] In some embodiments, the above-mentioned execution entity can perform fault identification throughout the entire UAV flight process based on the above-mentioned UAV flight fault identification model.

[0065] In practice, the above-mentioned executive entity can use the above-mentioned drone flight fault identification model and the fluctuation amplitude of each parameter of the drone swarm individuals to perform fault identification on the entire flight process of the drone swarm individuals.

[0066] For example, based on the UAV flight fault identification model, combined with the fluctuation of individual swarm parameters, the fault of the swarm individual (UAV swarm individual) during the whole flight process is identified; a certain swarm individual is selected as an example, according to the UAV swarm individual state fluctuation equation and the reference time in step 104, the fluctuation of each parameter of the UAV system is analyzed based on the ground station flight data and the airborne data, for the UAV system in the swarm, such as Figure 2 As shown in the figure, the parameter fluctuation diagram based on airborne data at the top is compared with the fluctuation parameters based on ground station data at the bottom. The results show that:

[0067] Analysis of the faults: The fault identification diagram shows that the drone's x-axis, y-axis, and vertical speeds all dropped to zero at 13:34:51. The drone's range parameter also dropped to zero at 13:33:47. The drone then reached the target area and began landing at 13:33:53, lasting 55 seconds and completing the landing at 13:34:48. While the drone's onboard data showed no significant anomalies during the flight, ground station data indicated that the drone's flight mode switched multiple times before reaching its destination, with the yaw angle parameter exhibiting unusual fluctuations. At 13:34:56, all parameters suddenly dropped to zero, at which point the remote control link was disconnected.

[0068] Conclusion 1: At 13:34:51, the drone's x-axis speed, y-axis speed, and vertical speed all dropped to zero, and the drone's altitude remained unchanged. At this time, the drone arrived at the destination. The drone disconnected from the ground station 5 seconds after arriving at the destination, and the drone's data link was interrupted.

[0069] Conclusion 2: The drone's flight mode parameters changed multiple times at 13:33:19, and the deflection angle underwent an abnormal mutation, indicating that the drone's gyroscope module malfunctioned and the drone was interfered with.

[0070] Conclusion 3: According to the fault detection and assessment method, although the drone did not fall, it experienced GPS failure (SF2.1), abnormal drone flight speed (SF2.2), abnormal attitude (SF2.3), remote control link interruption (SF2.4), and drone mode change (SF3.1) during the flight.

[0071] In summary, the present invention innovatively constructs a UAV fault identification model, which establishes a parameter fluctuation equation based on the UAV flight state and analyzes the fluctuation of various parameters of the UAV during the interference process; by sorting out the results of ground station observation records and airborne data records, combined with the dynamic change trend of the swarm flight state, the problem of inaccurate state evaluation of the swarm flight process is solved, and the swarm flight state monitoring is realized.

[0072] A UAV fault identification method based on the monitoring of the effect data of the entire flight process was designed, which solved the problem of unclear fluctuations in the parameters of the UAV system under complex electromagnetic environments and realized the analysis and evaluation of the working status of each module of the UAV system.

[0073] Research on electromagnetic interference failures in UAV systems lacks system-level fault identification and standardized classification. This invention offers excellent interpretability. By analyzing fluctuations in various UAV parameters and ground station observations and records, it can determine the severity of the failure and classify it. This approach, to a certain extent, enables full-flight fault identification for UAV systems.

[0074] Because failures in actual flight missions are often sudden and unpredictable, a fault identification model was constructed by analyzing the swarm's dynamic flight state and the fluctuations in drone parameters. This model also considered two primary flight data sets: onboard data and ground station data. This model encompasses nearly all possible nonlinear behaviors of quadrotor drone systems, ensuring the model's versatility and robustness.

[0075] Further references Figure 3 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a UAV fault identification device based on full-flight effect data monitoring. These device embodiments are similar to Figure 1 Corresponding to the method embodiments shown, the UAV fault identification device based on full-flight effect data monitoring can be specifically applied to various electronic devices.

[0076] like Figure 3As shown, some embodiments of the UAV fault identification device 300 based on flight whole process effect data monitoring include: an acquisition unit 301, configured to respond to the detection of UAV swarm being interfered with by electromagnetic pulse signals, based on the data storage module of the ground station and the UAV flight control, to collect the effect data of each UAV during the whole flight process, wherein each UAV corresponds to the collected UAV effect data sequence, and each UAV effect data includes: longitude, latitude, altitude, horizontal speed, vertical speed, yaw angle, pitch angle, roll angle, flight mode, number of satellites, voltage, altitude, remaining power, and distance; a data smoothing unit 302, configured to perform data smoothing processing on each collected UAV effect data sequence to obtain each data smoothed UAV effect data sequence as each target UAV The invention provides a method for determining the normal flight phase and the interference flight phase of the individual drone swarm based on the effect data sequences of the target drones; the determination unit 303 is configured to determine the normal flight phase and the interference flight phase of the individual drone swarm flight process, and determine the individual drone swarm state fluctuation equation based on the above-mentioned individual drone swarm state fluctuation equation; the parameter fluctuation solving unit 304 is configured to solve the fluctuation amplitude of each parameter during the interference flight phase according to the above-mentioned individual drone swarm state fluctuation equation; the model building unit 305 is configured to identify the fault module of the individual drone according to the fluctuation amplitude of each parameter of the individual drone swarm, and to perform a graded description of the degree of influence on the working state of the drone according to the fault module, and to establish a drone flight fault identification model; the fault identification unit 306 is configured to perform fault identification of the entire drone flight process according to the above-mentioned drone flight fault identification model.

[0077] It is understandable that the units recorded in the UAV fault identification device 300 based on the full-process flight effect data monitoring are similar to the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the UAV fault identification device 300 based on flight full process effect data monitoring and the units included therein, and will not be repeated here.

[0078] Reference below Figure 4 , which shows a schematic structural diagram of an electronic device (such as a computing device) suitable for implementing some embodiments of the present disclosure. Figure 4 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present disclosure. Figure 4As shown, the computer device includes a processor, a memory and a network interface connected via a system bus, wherein the memory may include a non-volatile storage medium and an internal memory. The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions, which, when executed, can enable the processor to execute any front-end page monitoring method. The processor is used to provide computing and control capabilities to support the operation of the entire computer device. The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium, which, when executed by the processor, can enable the processor to execute any front-end page monitoring method. The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 4 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present disclosure, and does not constitute a limitation on the computer device to which the solution of the present disclosure is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0079] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0080] In one embodiment, the processor is used to run a computer program stored in a memory to implement the following steps: in response to detecting that the drone swarm is interfered with by an electromagnetic pulse signal, based on the data storage module of the ground station and the drone flight control, the effect data of each drone during the entire flight process is collected, wherein each drone corresponds to a collected drone effect data sequence, and each drone effect data includes: longitude, latitude, altitude, horizontal speed, vertical speed, yaw angle, pitch angle, roll angle, flight mode, number of satellites, voltage, altitude, remaining power, and distance; data smoothing is performed on each collected drone effect data sequence to obtain smoothed data of each data. The human-machine effect data sequence is used as the effect data sequence of each target UAV; based on the above-mentioned each target UAV effect data sequence, the normal flight stage and the interference flight stage in the individual flight process of the UAV swarm are determined, and the individual state fluctuation equation of the UAV swarm is determined; according to the above-mentioned individual state fluctuation equation of the UAV swarm, the fluctuation amplitude of each parameter during the interference flight stage is solved; according to the fluctuation amplitude of each parameter of the individual UAV swarm, the fault module of the individual UAV is identified, and according to the fault module, the degree of influence of the UAV working state is described in a graded manner, and a UAV flight fault identification model is established; according to the above-mentioned UAV flight fault identification model, fault identification of the entire UAV flight process is performed.

[0081] An embodiment of the present disclosure also provides a computer-readable storage medium, on which a computer program is stored. The computer program includes program instructions. The method implemented when the program instructions are executed can refer to the various embodiments of the drone fault identification method based on full-flight effect data monitoring disclosed in the present disclosure.

[0082] The computer-readable storage medium may be an internal storage unit of the computer device described in the aforementioned embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a SmartMedia Card (SMC), a Secure Digital (SD) card, a flash memory card, etc., provided on the computer device.

[0083] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0084] The above description is only an illustration of some preferred embodiments of the present disclosure and the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A method for identifying UAV faults based on full-flight effect data monitoring, characterized in that: include: In response to detecting that the drone swarm is interfered with by an electromagnetic pulse signal, the effect data of each drone during the entire flight process is collected based on the data storage module of the ground station and the drone flight control, wherein each drone corresponds to a sequence of collected drone effect data, and each drone effect data includes: longitude, latitude, altitude, horizontal speed, vertical speed, yaw angle, pitch angle, roll angle, flight mode, number of satellites, voltage, altitude, remaining power, and distance; Performing data smoothing processing on each collected UAV effect data sequence to obtain each data smoothed UAV effect data sequence as each target UAV effect data sequence; Based on the effect data sequences of each target drone, determining the normal flight phase and the interference flight phase of the drone swarm individual flight process, and determining the state wave equation of the drone swarm individual; According to the individual state fluctuation equation of the UAV swarm, the fluctuation amplitude of each parameter during the interference flight phase is solved; Based on the fluctuation amplitude of each parameter of the individual drone swarm, the fault module of the individual drone is identified. Based on the fault module, the degree of impact on the working status of the drone is graded and described, and a drone flight fault identification model is established; According to the UAV flight fault identification model, fault identification of the entire UAV flight process is performed.

2. The method according to claim 1, characterized in that The step of performing data smoothing on each collected UAV effect data sequence to obtain each data smoothed UAV effect data sequence includes: According to the length of the effect data, the average value of each collected UAV effect data sequence is taken to obtain each data smoothed UAV effect data sequence.

3. The method according to claim 2, characterized in that The determining of the normal flight phase and the interference flight phase during the flight of the individual drone swarms based on the effect data sequences of the respective target drones includes: Based on the effect data sequences of each target UAV, the entire flight state is described for each parameter in the UAV effect data in units of swarms, and the parameter change trends of each UAV in the swarm are compared to determine the normal flight stage and the interference flight stage during the swarm flight process.

4. The method according to claim 3, characterized in that Determining the individual state wave equation of the drone swarm includes: Where, ΔV ij Indicates the fluctuation amplitude of the jth parameter at the i-th moment, V ij Indicates the value of the jth parameter at the i-th moment, V maxj represents the maximum value of the jth parameter in the interference flight phase, V minj represents the minimum value of the jth parameter in the interference flight phase, V avej represents the average value of the jth parameter during the normal flight phase.

5. The method according to claim 4, characterized in that The method of identifying the fault modules of individual drones based on the fluctuation amplitude of each parameter of the drone swarm and describing the degree of impact on the working status of the drones according to the fault modules to establish a drone flight fault identification model includes: Determine the fluctuation range of each parameter of individual drone swarms and identify the faulty modules of individual drones; Combining the behavioral characteristics and working status of drones, the faults are classified and graded according to the severity of the impact of the fault module on the individual status of the swarm, and the drone fault status under the fault level is described to establish a drone flight fault identification model.

6. The method according to claim 5, characterized in that The method of performing fault identification of the entire UAV flight process according to the UAV flight fault identification model includes: By using the UAV flight fault identification model and combining the fluctuation amplitude of each parameter of the UAV swarm individuals, fault identification is performed on the entire flight process of the UAV swarm individuals.

7. A UAV fault identification device based on full-flight effect data monitoring, characterized in that: include: The collecting unit is configured to collect effect data of each drone during the entire flight process based on the data storage module of the ground station and the drone flight control in response to detecting that the drone swarm is interfered with by the electromagnetic pulse signal, wherein each drone corresponds to a sequence of collected drone effect data, and each drone effect data includes: longitude, latitude, altitude, horizontal speed, vertical speed, yaw angle, pitch angle, roll angle, flight mode, number of satellites, voltage, altitude, remaining battery power, and distance; a data smoothing unit configured to perform data smoothing processing on each collected UAV effect data sequence to obtain each data smoothed UAV effect data sequence as each target UAV effect data sequence; a determination unit configured to determine, based on the effect data sequences of each target drone, a normal flight phase and an interference flight phase during the flight of an individual drone swarm, and determine a state wave equation of the individual drone swarm; a parameter fluctuation solving unit configured to solve the fluctuation amplitude of each parameter during the interference flight phase according to the individual state fluctuation equation of the drone swarm; The model building unit is configured to identify the fault modules of individual drones based on the fluctuation amplitude of each parameter of the drone swarm, and to describe the degree of influence on the working state of the drones in a graded manner based on the fault modules, thereby establishing a drone flight fault identification model; The fault identification unit is configured to perform fault identification during the entire UAV flight process according to the UAV flight fault identification model.

8. An electronic device, characterized in that: include: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.

9. A computer-readable medium, characterized in that A computer program is stored thereon, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images