A flight test system for online verification and debugging of fault diagnosis algorithms

Abstract

The present invention discloses a flight test system for realizing online verification and debugging of a fault diagnosis algorithm, and relates to the field of aircraft fault monitoring. The flight test system selects a fixed-wing UAV and a secondary developed flight control algorithm based on the typical fault generation mechanism of the fixed-wing UAV actuator, and simulates two typical actuator faults of rudder sticking and rudder loosening. In combination with an onboard computer equipped with an online fault diagnosis algorithm, the system utilizes flight status data sent in real time by a flight controller to perform online real-time monitoring of the multi-dimensional flight status information of the fixed-wing UAV. In conjunction with an independently developed fault diagnosis information monitoring and parameter adjustment ground station, the system can meet the requirements of online verification and debugging of the fault diagnosis algorithm for the fixed-wing UAV actuator fault.

Description

Technical Field

[0001] The present invention relates to the field of aircraft fault monitoring, and in particular to a flight test system for realizing online verification and debugging of a fault diagnosis algorithm. Background Art

[0002] As modern aircraft capabilities continue to expand, their structures become more complex. Simultaneously, they are subject to a variety of external factors, increasing the probability of failure and posing challenges to their reliability. If an aircraft malfunctions during a mission and is not promptly detected and effectively addressed, it not only impacts mission completion but can also lead to the aircraft being scrapped, reducing its potential for reuse. Therefore, simulating and diagnosing typical aircraft faults is crucial for validating aircraft fault diagnosis algorithms, ensuring proper aircraft operation, and forming the foundation for implementing effective fault-tolerance measures.

[0003] Existing fault simulation technology primarily relies on creating targeted models within simulation software for the components, systems, and entire aircraft to be simulated, based on specific simulation requirements. This model then simulates faults using the established models. However, even the most complex environmental modeling still struggles to approximate the impact of the actual environment on an aircraft's flight state. Consequently, fault diagnosis algorithms debugged using the resulting flight state data can exhibit poor robustness in practical applications. Summary of the Invention

[0004] In response to the above problems and technical requirements, the inventors have proposed a flight test system for online verification and debugging of fault diagnosis algorithms. The technical solution of the present invention is as follows:

[0005] A flight test system for realizing online verification and debugging of a fault diagnosis algorithm includes the following steps:

[0006] drone and sensor group;

[0007] A fault simulation component includes a remote controller and a floating mechanism mounted on the drone. The remote controller is used to provide a fault simulation signal.

[0008] The flight controller connects the sensor group, remote controller and rudder servos, and is used to control the corresponding rudder of the drone to simulate the corresponding fault according to the fault simulation signal;

[0009] The onboard computer provides an operating framework for the fault diagnosis algorithm and receives flight status data from the flight controller to perform online fault diagnosis tests.

[0010] The flight control ground station establishes a communication connection with the flight controller via a digital radio, and is used to plan the drone's automatic route and adjust relevant parameters of the flight controller;

[0011] The fault diagnosis information monitoring and parameter adjustment ground station establishes a communication connection with the onboard computer through a digital radio, which is used to monitor the UAV flight status and fault diagnosis information, as well as to realize online debugging of parameters related to the fault diagnosis algorithm.

[0012] Its further technical solution is that the UAV adopts a fixed-wing UAV, including propellers, fuselage, ailerons, X-tail, and a battery compartment, flight controller and onboard computer are installed inside the fuselage;

[0013] The propeller is attached to the front of the fuselage to provide thrust;

[0014] Ailerons are located on both sides of the fuselage and are used to provide rolling moment;

[0015] The X-tail is used to provide pitch and yaw moments and serves as the object of fault simulation for the drone.

[0016] A further technical solution is that the loose floating mechanism includes a base, a rotating component, a connecting rod, and two connecting lines of the same length;

[0017] The base is used to fix the entire floating mechanism to the drone body;

[0018] The rotating shaft of the rotating component is coaxially connected to a servo and fixed to the base. The servo is driven by the flight controller to make the rotating shaft drive the rotating surface on it to rotate in the clockwise and counterclockwise directions.

[0019] The connecting rod is connected to a servo, and one end of the connecting rod is fixed to the base, and the other end is considered as the movable end;

[0020] One end of a first connecting line is fixed to the movable end, and the other end passes through a small hole on the first end of the rotating surface and is connected to one side of a movable part of a control surface. One end of a second connecting line is fixed to the movable end, and the other end passes through a small hole on the second end of the rotating surface and is connected to the other side of the movable part of the same control surface. The first and second ends of the rotating surface are opposite, and when the rotating surface is in the initial position, the line connecting the first and second ends is perpendicular to the fuselage.

[0021] Driven by the flight controller, the servo moves the movable end along the direction of the fuselage, driving the two connecting lines to be in a tight or loose state; when the rotating surface rotates in different directions, it drives the movable part of the control surface connected to the connecting line to steer in the corresponding direction.

[0022] A further technical solution is to control the corresponding control surface of the UAV to simulate the corresponding fault according to the fault simulation signal, including:

[0023] The remote control is equipped with a fault mode switch, a fault type lever, and a fault position lever, which generate corresponding fault simulation signals based on the selected switch and lever position;

[0024] When the flight controller interprets the fault simulation signal as normal, it outputs the rudder and servo signals according to the original flight control parameters to control the drone to fly normally.

[0025] When the flight controller interprets the fault simulation signal as a fault, it outputs the corresponding rudder servo signal according to the simulated fault type and fault location, and simulates a rudder stuck fault or a rudder loose and floating fault through the floating mechanism.

[0026] Its further technical solution is that when the fault type is a rudder stuck fault, the flight controller reads the immediate control signal of the selected faulty rudder servo and continuously outputs it to the faulty rudder servo as a constant control signal, so that the rotating surface of the loose floating mechanism is fixed at the current position. At this time, the faulty rudder is stuck at the immediate angle and no longer responds to the original flight control parameters.

[0027] Its further technical solution is that when the fault type is a loose rudder failure, the flight controller sends a minimum control signal to the selected faulty rudder servo, so that the connecting line of the loosening mechanism is in a loose state. At this time, the faulty rudder is no longer controlled by the servo.

[0028] The further technical solution is that the working process of the flight test system includes:

[0029] After initializing the flight test system, the flight controller controls the UAV to automatically fly along the preset route;

[0030] Select the type and location of the simulated fault on the remote controller, generate a fault simulation signal and send it to the flight controller. The flight controller will control the corresponding control surface through the floating mechanism to simulate the corresponding fault according to the received fault simulation signal.

[0031] The flight controller transmits real-time flight status data to the onboard computer equipped with a fault diagnosis algorithm to obtain fault diagnosis information;

[0032] The fault diagnosis information and flight status data are displayed by the fault diagnosis information monitoring and parameter adjustment ground station through data communication; in this process, the fault diagnosis information monitoring and parameter adjustment ground station provides a parameter adjustment interface to realize online debugging of relevant parameters of the fault diagnosis algorithm.

[0033] A further technical solution is to initialize the flight test system, including:

[0034] Re-power on the flight controller, drone, onboard computer, and data radio in order;

[0035] Restart the data path and fault diagnosis algorithm of the onboard computer, and restart the fault diagnosis information monitoring and parameter adjustment ground station and the flight control ground station.

[0036] Its further technical solution is that the working process of the flight test system also includes:

[0037] According to different fault diagnosis algorithms, the information displayed and monitored by the fault diagnosis information monitoring and parameter adjustment ground station and the algorithm parameters that need to be debugged are replaced, and the flight status data required by the fault diagnosis algorithm carried by the onboard computer is replaced to ensure the versatility of the flight test system.

[0038] Its further technical solution is that the fault diagnosis information monitoring and parameter adjustment ground station is a visual interface developed based on Python.

[0039] The beneficial technical effects of the present invention are:

[0040] The above-mentioned flight test system analysis is based on the typical fault generation mechanism of the fixed-wing UAV actuator, and a fault simulation component is constructed to realize two typical faults. Combined with the secondary developed flight control algorithm, it can simulate the two typical faults of the actuator's rudder stuck and rudder loose at any time. In conjunction with the fault diagnosis algorithm installed on the onboard computer, the UAV can be directly debugged in the actual engineering application stage, and the online debugging of the fault diagnosis algorithm can be realized through the coordinated cooperation of the independently developed ground station, so that the fault diagnosis algorithm has real engineering application value, rather than only being able to be used on the simulation model.

[0041] Before use, the flight test system requires ground-based component initialization, and the pilot remotely controls the drone's takeoff and automatic flight path. Field tests have shown that the flight test system's command transmission, fault simulator response, data acquisition, and communication rates exceed 100Hz. It also supports ground-based observation and debugging of fault diagnosis algorithms. This system can be applied to online debugging and verification of fault diagnosis algorithms for various fixed-wing UAVs, improving their robustness and demonstrating broad application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 This is an architectural diagram of a flight test system for online verification and debugging of fault diagnosis algorithms provided in this application.

[0043] Figure 2 These are structural diagrams of the loose floating mechanism provided in this application from different perspectives, where (a) is the main view and (b) is the front view.

[0044] Figure 3 It is a workflow diagram of the flight test system provided in this application. DETAILED DESCRIPTION

[0045] The specific embodiments of the present invention will be further described below with reference to the accompanying drawings.

[0046] One embodiment of the present application provides a flight test system for online verification and debugging of fault diagnosis algorithms. Figure 1 As shown, the flight test system includes a UAV, a flight controller, a sensor group, a fault simulation component, an onboard computer, a flight control ground station, and a fault diagnosis information monitoring and parameter adjustment ground station.

[0047] In this embodiment, the UAV is a fixed-wing UAV, including a propeller 1, a fuselage 2, ailerons 3, and an X-tail 4. The propeller 1 is connected to the front of the fuselage and is used to provide pulling force. The fuselage 2 is internally equipped with a battery compartment, a flight controller, and an onboard computer; optionally, the flight controller is fixed at the center of gravity of the fixed-wing UAV. The ailerons 3 are located on both sides of the fuselage and are used to provide rolling torque. The X-tail 4 is used to provide pitch and yaw torque, and at the same time has a certain fault tolerance capability, which can improve the safety of the flight test. In this embodiment, the X-tail 4 serves as the object of the UAV fault simulation. The sensor group includes an inertial navigation module, GPS, airspeed meter, etc.

[0048] The fault simulation component includes a remote control, a fault simulation program, and a floating mechanism installed on the drone. The remote control primarily controls the flight of the fixed-wing drone and is equipped with a fault mode switch, a fault type lever, and a fault position lever. The fault mode switch selects whether to perform fault simulation on the drone. The fault type lever selects whether to perform a stuck or floating rudder fault. The fault position lever selects one of the four X-tail fins as the faulty rudder. Based on the selected switch and lever position, a corresponding fault simulation signal is generated and sent to the flight controller. The fault simulation program, which is installed on the flight controller, executes the fault simulation process for controlling the X-tail fin.

[0049] Each tail fin in X-Tail 4 is equipped with a loose floating mechanism to simulate the corresponding failure of the control surface. Figure 2As shown in Figures (a) and (b), the floating mechanism comprises a base 5, a rotating component 6, a connecting rod 7, and two connecting wires of equal length. The base 5 is used to secure the entire floating mechanism to the drone fuselage 2. The rotating shaft of the rotating component 6 is coaxially connected to a servo and fixed to the base 5. Driven by the flight controller, the servo causes the rotating shaft to rotate the rotating surface on it in clockwise and counterclockwise directions. The connecting rod 7 is connected to the servo, with one end fixed to the base and the other end acting as a movable end. Driven by the flight controller, the servo causes the movable end to move in the direction of the fuselage. One end of the first connecting wire 8a is fixed to the movable end, and the other end passes through a small hole on the first end of the rotating surface and connects to one side of the movable part of a control surface. Similarly, one end of the second connecting wire 8b is fixed to the movable end, and the other end passes through a small hole on the second end of the rotating surface and connects to the other side of the same movable part of the control surface. The first and second ends of the rotating surface are opposite each other, and when the rotating surface is in the initial position shown, the line connecting the first and second ends is perpendicular to the fuselage. The connection point of the connecting lines 8a, 8b at the movable part of the control surface is at the same distance from the tail of the stabilizer surface of the tail wing.

[0050] According to the connection principle of the above components, the movement of the connecting rod 7 can drive the two connecting lines to be in a tight or loose state, and when the rotating surface rotates in different directions in the tight state, it can drive the movable part of the rudder surface connected to the connecting line to steer in the corresponding direction. Figure 2 As shown, when the rotating surface rotates counterclockwise, the first connecting line 8a is pulled forward to steer the connected tail wing upward; when the rotating surface rotates clockwise, the second connecting line 8b is pulled forward to steer the connected tail wing downward.

[0051] The flight controller connects the sensor group, remote control, and rudder servos. It is equipped with a newly developed flight control algorithm to control the fixed-wing drone's autonomous flight and provide flight status data to the onboard computer. The flight controller also controls the drone's corresponding rudder surface to simulate corresponding faults based on the fault simulation signals provided by the remote control. Specifically, the flight controller includes:

[0052] (1) When the flight controller analyzes the fault simulation signal and finds that there is no fault, the flight controller outputs the rudder and servo signals according to the original flight control parameters to control the normal flight of the UAV. That is, the flight controller applies the maximum control signal to each rudder and servo, so that the connecting rod moves toward the tail to the preset position. At this time, the two connecting lines are in a tight state, so that the corresponding rudder and servo are kept tightly connected, and the X tail is controlled to achieve normal output signal response.

[0053] (2) When the flight controller interprets the fault simulation signal as a fault, the flight controller outputs the corresponding rudder servo signal according to the simulated fault type and fault location, and simulates a rudder stuck fault or a rudder loose and floating fault through the loose floating mechanism.

[0054] A stuck fault occurs when a control surface is momentarily stuck at a certain angle during normal, trouble-free flight. Therefore, when the actuator fault demand indicates a simulated stuck fault, the remote controller's fault mode, fault type, and fault location levers are switched to the corresponding positions, sending a simulated stuck fault signal to the flight controller. Upon receiving this signal, the flight controller reads the immediate control signal from the selected faulty control surface servo and continuously outputs it as a constant control signal to the faulty control surface servo, fixing the rotating surface of the release mechanism at its current position. The faulty control surface is now stuck at its immediate angle and no longer responds to the original flight control parameters.

[0055] A loose-floating fault is a condition in which the servo output shaft is momentarily unloaded due to the loosening of the rudder surface during normal, trouble-free flight. Therefore, when the actuator fault requirement indicates that the simulated fault type is a loose-floating fault, the remote controller's fault mode, fault type, and fault location levers are switched to corresponding positions, thereby sending a loose-floating fault simulation signal to the flight controller. Upon receiving this signal, the flight controller sends a minimum control signal to the selected servo for the faulty rudder surface, causing the connecting wires of the loose-floating mechanism to become loose. At this point, the faulty rudder surface is no longer controlled by the servo. Specifically, when the rotating surface rotates counterclockwise, the first connecting wire 8a is loose and cannot achieve a forward pull effect, preventing the connected tail from ruddering upward and responding to control. When the rotating component rotates clockwise, the second connecting wire 8b is loose and cannot achieve a forward pull effect, preventing the connected tail from ruddering downward and responding to control.

[0056] The onboard computer provides the operating framework for the fault diagnosis algorithm. It also offers serial communication capabilities to receive flight status data from the flight controller and store it in a global variable library, providing both offline and online data support for the fault diagnosis algorithm. Optionally, the onboard computer uses a Windows operating system and supports multiple programming environments, including Python and C++.

[0057] The flight control ground station establishes a communication connection with the flight controller via communication equipment (such as a data transmission radio) to adjust flight controller parameters (such as control surface neutrality and PID coefficients). It also supports changing flight status and automatic routes based on fault simulation needs. The fault diagnosis information monitoring and parameter adjustment ground station is a Python-based visualization interface that communicates with the onboard computer via a data transmission radio to visualize flight status and fault diagnosis information. It also provides a parameter adjustment interface for online debugging of parameters related to the fault diagnosis algorithm.

[0058] Based on the above flight test system, typical faults of actuators can be simulated and used for online verification and debugging of fault diagnosis algorithms. Figure 2The flowchart shown includes the following contents:

[0059] After initializing the flight test system, the flight controller controls the drone's automatic flight along a preset route and transmits flight status data via the serial port to the onboard computer. The onboard computer saves the received flight status data and writes it to the global variable library. The type and location of the simulated fault are selected on the remote controller, generating a fault simulation signal that is sent to the flight controller. Based on the received fault simulation signal, the flight controller controls the corresponding control surface through the floating mechanism to simulate the corresponding fault and transmits the real-time flight status data to the onboard computer equipped with the fault diagnosis algorithm. The fault diagnosis algorithm can read the corresponding flight status data as needed, perform online fault diagnosis testing, and obtain fault diagnosis information.

[0060] Through data communication, the fault diagnosis information monitoring and parameter adjustment ground station displays fault diagnosis information and flight status data. During this process, the data communication between the onboard computer and the fault diagnosis information monitoring and parameter adjustment ground station allows the diagnostic results and key information of each round of the fault diagnosis algorithm to be written into the global variable library, which is then transmitted to the ground and displayed on the fault diagnosis information monitoring and parameter adjustment ground station, realizing real-time monitoring of the fault diagnosis algorithm conclusions and key information. At the same time, the data communication between the onboard computer and the fault diagnosis information monitoring and parameter adjustment ground station allows the fault diagnosis algorithm to create a parameter adjustment interface, write debugging parameters through the fault diagnosis information monitoring and parameter adjustment ground station and upload them to the onboard computer. The onboard computer receives and writes them into the global variable library for use by the onboard fault diagnosis algorithm, realizing online debugging of the fault diagnosis algorithm.

[0061] Optionally, depending on the fault diagnosis algorithm, the information displayed and monitored by the fault diagnosis information monitoring and parameter adjustment ground station, as well as the algorithm parameters that require debugging, can be replaced. This also allows for the replacement of the flight status data used by the fault diagnosis algorithm in the onboard computer to ensure the versatility of the flight test system. For fault simulation components that have simulated actuator failures, fault disconnection can be performed at any time to ensure the safety of the flight test system.

[0062] During the above work process, the flight test system needs to be initialized first, including:

[0063] (1) Re-power on the flight controller, drone, onboard computer, and data transmission radio in order. Specifically, first re-power on the flight controller to reset the attitude, position, and other measurement information and the servo output signal. Then re-power on the fixed-wing drone so that the control voltage of the propeller and servo returns to the neutral value. After the above operations are completed, re-power on the onboard computer and data transmission radio and start them. After the above process, the initialization operation of the fixed-wing drone, flight controller, onboard computer, and data transmission radio is completed.

[0064] (2) Restart the data path and fault diagnosis algorithm of the onboard computer, and restart the fault diagnosis information monitoring and parameter adjustment ground station and the flight control ground station.

[0065] Furthermore, the flight test system can be expanded to include multiple sensors to meet the needs of different fault diagnosis algorithms, enabling measurement of more parameters to support diverse data acquisition requirements. Furthermore, the number of flight states in the data path can be freely increased or decreased. This interchangeable and addable component approach makes the flight test system highly scalable and practical, and has broad application prospects for online debugging and verification of fault diagnosis algorithms.

[0066] Taking the fault detection and identification (FDI) algorithm within the fault diagnosis algorithm as an example, the FDI algorithm is written as an online process and embedded in a reserved algorithm location on the onboard computer. Based on the algorithm's requirements, the flight controller transmits flight status data, such as attitude angle, attitude angular velocity, and control surface variables, via a serial port to the onboard computer. The onboard computer decodes the received data and writes it into a global variable library. During each algorithm cycle, the FDI algorithm reads data from the global variable library and completes its execution. During this main process, the flight test system also transmits the FDI algorithm's thresholds, test values, and final results to the FDI ground station for visualization, providing a crucial basis for real-time algorithm debugging. Furthermore, pre-set debugging options on the FDI ground station, such as threshold initialization time, threshold amplification ratio, and reinitialization, allow real-time parameter modifications to be uploaded to the onboard computer, enabling online debugging of the FDI algorithm.

[0067] It should be noted that the onboard computers, flight controllers and other equipment used in this application all support real-time fault simulation and signal output of no more than 10ms. These high-real-time hardware equipment supports enable the flight test system of this application to achieve high-real-time control and fault simulation through program control, so that the simulated faults have a higher rate of change, thereby meeting the real-time requirements of online debugging and verification of fault diagnosis algorithms.

[0068] The above description is only a preferred embodiment of the present application, and the present invention is not limited to the above embodiment. It is understood that other improvements and variations directly derived or imagined by those skilled in the art without departing from the spirit and concept of the present invention should be considered to be included in the scope of protection of the present invention.

Claims

1. A flight test system for online verification and debugging of fault diagnosis algorithms, characterized by: include: drone and sensor group; a fault simulation component, comprising a remote controller and a floating mechanism mounted on the UAV, wherein the remote controller is used to provide a fault simulation signal; A flight controller connected to the sensor group, the remote controller, and the rudder servo, configured to control the corresponding rudder of the UAV to simulate a corresponding fault according to the fault simulation signal; The onboard computer provides an operating framework for the fault diagnosis algorithm and receives flight status data from the flight controller to perform online fault diagnosis testing. The flight control ground station establishes a communication connection with the flight controller via a data transmission radio, and is used to plan the automatic route of the UAV and adjust the relevant parameters of the flight controller; A fault diagnosis information monitoring and parameter adjustment ground station establishes a communication connection with the onboard computer via a data transmission radio, is used to monitor the flight status and fault diagnosis information of the UAV, and realize online debugging of parameters related to the fault diagnosis algorithm; The floating mechanism includes a base, a rotating component, a connecting rod, and two connecting lines of the same length; The base is used to fix the entire floating mechanism on the UAV body; The rotating shaft of the rotating component is coaxially connected to a steering gear and fixed to the base. The steering gear, driven by the flight controller, causes the rotating shaft to drive the rotating surface thereon to rotate in a clockwise and counterclockwise direction. The connecting rod is connected to a servo, and one end of the connecting rod is fixed to the base, and the other end is regarded as a movable end; One end of a first connecting line is fixed to the movable end, and the other end passes through a small hole on the first end of the rotating surface and is connected to one side of a movable part of a control surface; one end of a second connecting line is fixed to the movable end, and the other end passes through a small hole on the second end of the rotating surface and is connected to the other side of the movable part of the same control surface; wherein the first end and the second end of the rotating surface are opposite to each other, and when the rotating surface is in the initial position, the line connecting the first end and the second end is perpendicular to the fuselage; The servo, driven by the flight controller, moves the movable end in the direction of the fuselage, thereby driving the two connecting lines to be in a tight or loose state; when the rotating surface rotates in different directions, the movable part of the rudder surface connected to the connecting line is driven to steer in the corresponding direction; The method of controlling the corresponding control surface of the UAV to simulate the corresponding fault according to the fault simulation signal includes: The remote control is provided with a fault mode switch, a fault type lever, and a fault position lever, and generates a corresponding fault simulation signal based on the selected switch and lever position; When the flight controller interprets the fault simulation signal as being fault-free, the flight controller outputs a control surface and servo signal according to the original flight control parameters to control the UAV to fly normally; When the flight controller interprets the fault simulation signal as indicating a fault, the flight controller outputs a corresponding rudder servo signal according to the simulated fault type and fault location, and simulates a rudder stuck fault or a rudder loose and floating fault through the floating mechanism; When the fault type is a rudder stuck fault, the flight controller reads the real-time control signal of the selected faulty rudder servo and continuously outputs it as a constant control signal to the faulty rudder servo, so that the rotating surface of the loose floating mechanism is fixed at the current position. At this time, the faulty rudder is stuck at the real-time angle and no longer responds to the original flight control parameters. When the fault type is a rudder loose fault, the flight controller sends a minimum control signal to the selected faulty rudder servo, so that the connecting line of the loose floating mechanism is in a loose state. At this time, the faulty rudder is no longer controlled by the servo. The working process of the flight test system includes: After initializing the flight test system, the flight controller controls the UAV to automatically fly along a preset route; Selecting the type and location of the simulated fault on the remote controller, generating a fault simulation signal and sending it to the flight controller, and the flight controller controlling the corresponding control surface through the floating mechanism to simulate the corresponding fault according to the received fault simulation signal; The flight controller transmits the real-time flight status data to the onboard computer equipped with the fault diagnosis algorithm to obtain fault diagnosis information; The fault diagnosis information monitoring and parameter adjustment ground station displays the fault diagnosis information and flight status data through data communication; in this process, the fault diagnosis information monitoring and parameter adjustment ground station provides a parameter adjustment interface to realize online debugging of relevant parameters of the fault diagnosis algorithm.

2. The flight test system for realizing online verification and debugging of fault diagnosis algorithm according to claim 1, characterized in that: The UAV is a fixed-wing UAV, including a propeller, a fuselage, ailerons, and an X-tail. A battery compartment, the flight controller, and the onboard computer are installed inside the fuselage. The propeller is connected to the front of the fuselage to provide pulling force; The ailerons are located on both sides of the fuselage and are used to provide rolling torque; The X-tail is used to provide pitch and yaw moments and serves as a fault simulation object for the drone.

3. The flight test system for realizing online verification and debugging of fault diagnosis algorithm according to claim 1, characterized in that: Initializing the flight test system, including: Re-power on the flight controller, the drone, the onboard computer, and the data transmission radio in sequence; The data path and fault diagnosis algorithm carried by the onboard computer are restarted, and the fault diagnosis information monitoring and parameter adjustment ground station and the flight control ground station are restarted.

4. The flight test system for realizing online verification and debugging of fault diagnosis algorithm according to claim 1, characterized in that: The working process of the flight test system also includes: According to different fault diagnosis algorithms, the information displayed and monitored by the fault diagnosis information monitoring and parameter adjustment ground station and the algorithm parameters that need to be debugged are replaced, and the flight status data required for the fault diagnosis algorithm carried by the onboard computer is replaced to ensure the versatility of the flight test system.

5. The flight test system for realizing online verification and debugging of fault diagnosis algorithm according to claim 1, characterized in that: The fault diagnosis information monitoring and parameter adjustment ground station is a visual interface developed based on Python.

Images