Fault detection method and device based on unmanned system data driving and medium

Abstract

The invention discloses a fault detection method and device based on unmanned system data driving and a medium, and the method comprises the steps: enabling an unknown unmanned system to be connected with a controller, collecting the state data of the unknown unmanned system in an offline manner, and constructing a state data matrix and an evolution state data matrix based on the collected state data; and constructing a fault detector based on the state data matrix and the evolution state data matrix, connecting the fault detector with the unknown unmanned system, and performing fault detection based on the state data of the unmanned system through the fault detector. According to the method, the closed-loop noise-carrying state data of the unknown unmanned system is collected offline, pre-physical process identification is not needed, then the fault detector is constructed based on the collected state data, and fault detection is carried out through the fault detector, so that an alarm can be triggered in time when the unmanned system is in an abnormal state, and the fault detection efficiency is improved. Therefore, fault detection of any unmanned system which operates stably is realized.

Description

Technical Field

[0001] The present application relates to the technical field of unmanned system failure, and in particular to a failure detection method, device and medium based on unmanned system data drive. Background Art

[0002] At a time when artificial intelligence is leading technological innovation, unmanned systems represented by unmanned vehicles, robots, drones, and unmanned boats have become a big stage for artificial intelligence technology to display its strength. At the same time, with the development of big data and computing technology, data-driven is applied to unmanned systems, and the stability and optimization of unmanned systems are improved through data-driven controllers.

[0003] In the actual operation process, in addition to stability and basic optimality, the input and state of the system need to be restricted to ensure the safety of the system operation. For example, in an unmanned vehicle fleet, if the distance between any unmanned vehicle cannot guarantee a certain lower limit, then the unmanned vehicle will collide. However, when an abnormal state occurs, such as a sudden failure of one of the unmanned vehicles, causing it to be out of control, the safe distance between the vehicle and other vehicles cannot be guaranteed, which may cause a collision and cause a series of serious subsequent consequences. For this reason, it is necessary to detect the abnormal state of the unmanned system. However, the current fault detection model of the unmanned system generally detects specific types of inorganic system faults, and cannot be applied to the fault detection of unknown unmanned systems.

[0004] Therefore the prior art still needs to be improved and enhanced. Summary of the invention

[0005] The technical problem to be solved by the present application is to provide a fault detection method, device and medium based on unmanned system data drive in view of the deficiencies of the existing technology.

[0006] In order to solve the above technical problems, the first aspect of the present application provides a fault detection method based on unmanned system data drive, wherein the fault detection method based on unmanned system data drive specifically includes: Connect the unknown unmanned system to the controller, collect the state data of a certain number of collection moments offline, and construct the state data matrix and the evolution state data matrix based on the collected state data; constructing a fault detector based on the state data matrix and the evolution state data matrix; The fault detector is connected to the unknown unmanned system, and the fault detector performs fault detection based on the status data of the unmanned system.

[0007] In the unmanned system data-driven fault detection method, the offline collection of status data at a certain number of collection moments specifically includes: Setting initial state data for the unknown unmanned system and transmitting the initial state data to a controller; generating a control input by the controller and applying the control input to the unknown unmanned system; Collecting state data of the unknown unmanned system at a new moment formed based on the control input; The state data at the new moment is used as the initial state data, and the step of transmitting the initial state data to the controller is re-executed until state data at a certain number of collection moments are collected.

[0008] The fault detection method based on unmanned system data drive, wherein the construction of the fault detector based on the state data matrix and the evolution state data matrix specifically includes: Constructing a first semi-positive definite programming problem based on the state data matrix and the evolution state data matrix, and solving the first semi-positive definite programming problem to determine an optimal solution to the first semi-positive definite programming problem; A second semi-positive programming problem is constructed based on the optimal solution of the first semi-positive programming problem, and the second semi-positive programming problem is solved to construct a fault detector.

[0009] In the data-driven fault detection method for unmanned systems, the first semi-positive programming problem is expressed as: , , , , in, It means to solve the determinant value, Representation Dimension The real positive definite symmetric matrix to be solved is represents the real number to be solved, represents the state data matrix, represents the evolution state data matrix, represents the first intermediate matrix, represents the second intermediate matrix, The dimension is The identity matrix of The dimension is The all-zero matrix, The dimension is The all-zero matrix, represents a constant between 0 and 1. Representation Matrix The transpose of Representation Matrix The transpose of represents a known constant greater than or equal to zero, Indicates the number of time steps collected offline.

[0010] In the data-driven fault detection method for unmanned systems, the second semi-positive programming problem is expressed as: , , , , , , , , , in, It means to solve the determinant value, It means taking the maximum value in the braces. Indicates the dimension to be solved The matrix of is the scalar to be solved, represents the optimal solution to the first semidefinite programming problem, represents the inverse matrix of the optimal solution to the first semidefinite programming problem, represents the third intermediate matrix, represents the fourth intermediate matrix, The dimension is The all-zero matrix, represents a constant, The dimension is The identity matrix of The dimension is The all-zero matrix, represents a known constant greater than or equal to zero, represents the number of time steps collected offline, Indicates the initial upper limit value when the unknown unmanned system is running online; The fault detector is expressed as: , in, represents a fault detector, represents the optimal solution to the second semidefinite programming problem.

[0011] The fault detection method based on unmanned system data drive, wherein the connecting the fault detector to the unknown unmanned system is specifically: The fault detector is connected to an output item of the unknown unmanned system so that the fault detector is connected to a closed-loop system formed by the unknown unmanned system and a controller, wherein the fault detector is in parallel with the controller.

[0012] The fault detection method based on unmanned system data drive, wherein the fault detection based on the state data of the unmanned system by the fault detector specifically includes: Obtain status data of unknown unmanned systems at each collection moment through fault detectors; determining a fault detector state based on the state data, and generating an alarm message when the fault detector state does not meet a preset requirement; The fault detector states are: when hour, ; when when, It is expressed as: , in, express The fault detector status at time, express Status data at the moment, express Status data at the moment, represents the state data matrix, represents the evolution state data matrix, Representation Matrix The right inverse matrix of ; The preset requirements are: , in, express The transpose of Indicates a fault detector.

[0013] A second aspect of the present application provides a fault detection device based on unmanned system data drive, wherein the fault detection device based on unmanned system data drive specifically includes: An offline collection module is used to connect the unknown unmanned system to the controller, collect the state data of a certain number of collection moments offline, and construct a state data matrix and an evolution state data matrix based on the collected state data; A construction module, used for constructing a fault detector based on the state data matrix and the evolution state data matrix; A fault detection module is used to connect the fault detector to the unknown unmanned system and perform fault detection based on the status data of the unmanned system through the fault detector.

[0014] A third aspect of the present application provides a computer-readable storage medium, which stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps in any of the unmanned system data-driven fault detection methods described above.

[0015] A fourth aspect of the present application provides a terminal device, comprising: a processor and a memory; The memory stores a computer-readable program executable by the processor; When the processor executes the computer-readable program, the steps in any of the above-described unmanned system data-driven fault detection methods are implemented.

[0016] Beneficial effects: Compared with the prior art, the present application provides a method, device and medium for fault detection based on data-driven unmanned systems. The method includes connecting an unknown unmanned system to a controller, collecting state data at a certain number of collection moments offline, and constructing a state data matrix and an evolution state data matrix based on the collected state data; constructing a fault detector based on the state data matrix and the evolution state data matrix; connecting the fault detector to the unknown unmanned system, and performing fault detection based on the state data of the unmanned system through the fault detector. The present application collects closed-loop noisy state data of an unknown unmanned system offline without prior physical process identification, and then constructs a fault detector based on the collected state data, and performs fault detection through the fault detector, so that an alarm can be triggered in time when an abnormal state occurs in the unmanned system, thereby realizing fault detection of any stably operating unmanned system. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 A flow chart of a fault detection method based on unmanned system data drive provided in an embodiment of the present application.

[0019] Figure 2 The block diagram of the detection system formed by the physical process, controller and fault detector.

[0020] Figure 3 The figure is a state trajectory evolution diagram of an unmanned system according to a specific embodiment.

[0021] Figure 4 It is a trajectory diagram of the detection state of the fault detector of this specific embodiment.

[0022] Figure 5 A principle block diagram of a fault detection device based on unmanned system data drive provided in an embodiment of the present application.

[0023] Figure 6 A functional block diagram of a terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] The embodiments of the present application provide a method, device and medium for fault detection based on unmanned system data drive. In order to make the purpose, technical solution and effect of the present application clearer and more specific, the present application is further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0025] It will be understood by those skilled in the art that, unless expressly stated, the singular forms "one", "said", and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be an intermediate element. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein includes all or any unit and all combinations of one or more associated listed items.

[0026] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those generally understood by those skilled in the art to which this application belongs. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with those in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless specifically defined as here.

[0027] It should be understood that the sequence numbers and sizes of the steps in this embodiment do not mean the order of execution. The execution order of each process is determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application.

[0028] The application content is further explained below through the description of embodiments in conjunction with the accompanying drawings.

[0029] This embodiment provides a fault detection method based on unmanned system data drive, such as Figure 1 As shown, the method includes: S10, connecting the unknown unmanned system to the controller, collecting state data at a certain number of collection moments offline, and constructing a state data matrix and an evolution state data matrix based on the collected state data.

[0030] Specifically, connecting the unknown unmanned system with the controller means connecting the physical process of the unknown unmanned system with the controller to form a closed-loop system. The physical process is the physical motion process of the unmanned aerial vehicle system, and the dynamic equation of the physical process can be expressed as: , in, express t The state data of the unknown unmanned system at any time, its dimension is ; express t The unknown disturbance received by the unknown unmanned system at the time has the dimension , and satisfies for all moments Both , represents a known constant greater than or equal to zero, Indicates unknown disturbance The second norm of ; matrix express unknown real matrix of dimension, control matrix express unknown real matrix of dimension; control gain matrix express The dimension of the matrix can be guaranteed The control gain matrix of the Shure stabilization Can be determined based on data drive.

[0031] Exemplarily, the offline collection of status data at a certain number of collection moments specifically includes: Setting initial state data for the unknown unmanned system and transmitting the initial state data to a controller; generating a control input by the controller and applying the control input to the unknown unmanned system; Collecting state data of the unknown unmanned system at a new moment formed based on the control input; The state data at the new moment is used as the initial state data, and the step of transmitting the initial state data to the controller is re-executed until state data at a certain number of collection moments are collected.

[0032] Specifically, the initial state data is randomly generated, that is, an arbitrary initial value is applied to the closed-loop system formed by the unknown unmanned system and the controller. Of course, in practical applications, an initial state data can also be pre-set, and then the pre-set initial state data is used as the initial state data of the unknown unmanned system when performing offline collection. When an arbitrary initial value is applied to the closed-loop system formed by the unknown unmanned system and the controller, the physical process of the unknown unmanned system transmits the state data to the controller in real time during operation. The controller multiplies the state data with the control gain matrix K and transmits it back to the physical process through the control matrix B. The physical process generates the state data of a new moment according to this control input, and then transmits the state data to the controller, and the state data of a certain number of collection moments are directly collected in a cycle.

[0033] Furthermore, the certain number is preset, and may also be determined according to preset requirements of the state data matrix, such as the certain number being the minimum state data amount that makes the state data matrix a full row rank matrix. Equal to the number of steps of the closed-loop system Add 1, that is , and satisfies That is, the operation of the closed-loop system Steps will be collected The state of the physical process of length , The state data matrix and the evolution state data matrix are constructed using a certain amount of collected state data, where the state data matrix and the evolution state data matrix are expressed as: , , in, represents the state data matrix, Represents the evolution state data matrix.

[0034] It should be noted that after constructing the state data matrix and the evolution state data matrix, it will be detected whether the state data matrix has full row rank. If it has full row rank, it means that the state data matrix meets the requirements. Otherwise, if it does not have full row rank, it means that the state data matrix meets the requirements and it is necessary to continue the above offline collection process until the constructed state data matrix has full row rank.

[0035] S20. Construct a fault detector based on the state data matrix and the evolution state data matrix.

[0036] Specifically, the fault detector is used to monitor the abnormal state of the unmanned system, wherein the construction process of the fault detector can construct a semi-positive definite programming problem based on the state data matrix and the evolution state data matrix, and then construct the fault detector based on the optimal solution of the semi-positive definite programming problem, wherein the semi-positive definite programming problem can include a first semi-positive definite programming problem and a second semi-positive definite programming problem, and the optimal solution of the semi-positive definite programming problem is the optimal solution of the second semi-positive definite programming problem, that is, the fault detector can be expressed as: , in, represents a fault detector, represents the optimal solution to the semidefinite programming problem.

[0037] Exemplarily, constructing a fault detector based on the state data matrix and the evolution state data matrix specifically includes: Constructing a first semi-positive definite programming problem based on the state data matrix and the evolution state data matrix, and solving the first semi-positive definite programming problem to determine an optimal solution to the first semi-positive definite programming problem; A second semi-positive programming problem is constructed based on the optimal solution of the first semi-positive programming problem, and the second semi-positive programming problem is solved to construct a fault detector.

[0038] Specifically, the first semi-positive definite programming problem is expressed as: , , , , in, It means to solve the determinant value, Representation Dimension The real positive definite symmetric matrix to be solved is represents the real number to be solved, represents the state data matrix, represents the evolution state data matrix, represents the first intermediate matrix, represents the second intermediate matrix, The dimension is The identity matrix of The dimension is The all-zero matrix, The dimension is The all-zero matrix, is a constant between 0 and 1, Representation Matrix The transpose of Representation Matrix The transpose of represents a known constant greater than or equal to zero, Indicates the number of time steps collected offline.

[0039] Furthermore, the second semi-positive definite programming problem is expressed as: , , , , , , , , , in, It means to solve the determinant value, It means taking the maximum value in the braces. Indicates the dimension to be solved The matrix of is the scalar to be solved, represents the optimal solution to the first semidefinite programming problem, represents the inverse matrix of the optimal solution to the first semidefinite programming problem, represents the third intermediate matrix, represents the fourth intermediate matrix, The dimension is The all-zero matrix, represents a constant, represents a known constant greater than or equal to zero, The dimension is The identity matrix of The dimension is The all-zero matrix, represents a known constant greater than or equal to zero, represents the number of time steps collected offline, Indicates the initial upper limit of the unknown unmanned system when it is running online.

[0040] It should be noted that the solution process of the first semi-positive programming problem and the second semi-positive programming problem can be performed using existing processes, which will not be described in detail here. At the same time, when obtaining a fault detector constructed based on the state data matrix and the evolution state data matrix, other methods can also be used to construct it, for example, by fusing the state data matrix and the evolution state data matrix, etc., as long as a fault detector that can detect faults in an unmanned system can be constructed.

[0041] S30, connecting the fault detector to the unknown unmanned system, and performing fault detection based on the status data of the unmanned system through the fault detector.

[0042] Specifically, after obtaining the fault detector, during the unmanned system operation phase, such as Figure 2 As shown, the physical process, the controller and the fault detector can be connected, and the state data at each moment can be detected for abnormality by the fault detector, and when the state data is detected to be abnormal, an early warning is issued to inform the unmanned system of the abnormality. When the physical process, the controller and the fault detector are connected, the fault detector is connected to the output item of the unknown unmanned system, so that the fault detector is connected to the closed-loop system formed by the unknown unmanned system and the controller, and the fault detector is in parallel with the controller.

[0043] Further, when the fault detector performs fault detection based on the status data of the unmanned system, the fault detector can obtain the status data of the unmanned system, and then determine the state of the fault detector based on the status data, and finally determine whether the status data is abnormal based on the state of the fault detector. Based on this, the fault detector performs fault detection based on the status data of the unmanned system specifically includes: Obtain status data of unknown unmanned systems at each collection moment through fault detectors; The fault detector state is determined based on the state data, and an alarm message is generated when the fault detector state does not meet a preset requirement.

[0044] Specifically, the fault detector state is used to reflect the fault state of the state data, wherein the fault detector state can be calculated based on the state time, and the fault detector can be expressed as: when hour, ; when when, It is expressed as: , in, express The fault detector status at time, express Status data at the moment, express Status data at the moment, represents the state data matrix, represents the evolution state data matrix, Representation Matrix The right inverse matrix of .

[0045] Furthermore, the prediction requirement is a pre-set basis for determining whether the state data is abnormal, that is, when the fault detector state meets the preset requirement, it means that the state data is normal, and when the fault detector state does not meet the preset requirement, it means that the state data is abnormal. The preset requirement is: , in, express The transpose of Indicates a fault detector.

[0046] In summary, this embodiment provides a fault detection method, device and medium based on unmanned system data drive, the method includes connecting an unknown unmanned system to a controller, collecting state data of a certain number of collection moments offline, and constructing a state data matrix and an evolution state data matrix based on the collected state data; constructing a fault detector based on the state data matrix and the evolution state data matrix; connecting the fault detector to the unknown unmanned system, and performing fault detection based on the state data of the unmanned system through the fault detector. This application collects closed-loop noisy state data of an unknown unmanned system offline without prior physical process identification, and then constructs a fault detector based on the collected state data, and performs fault detection through the fault detector, so that an alarm can be triggered in time when an abnormal state occurs in the unmanned system, thereby realizing fault detection of any stably running unmanned system.

[0047] In order to illustrate the effect of the unmanned system data-driven fault detection method adopted in the embodiment of the present application, a specific example is given below.

[0048] like Figure 3 and Figure 4 The figure shows the effect of a robot embodiment using the safety controller of the present invention running for 50 unit times. The system matrix of the dynamic equation of the physical process of the robot is: , , Number of running steps collected offline , , , by solving the first semi-positive definite programming problem, we get: , The operating range of the given system initial value is , and get , by solving the second semidefinite programming problem, we get the fault detector: , By installing a fault detector for an unknown unmanned system and running it for 50 units of time, we get Figure 3 The state trajectory evolution diagram shown in Figure 4 The trajectory diagram of the fault detector detection state is shown.

[0049] Depend on Figure 3 It can be seen that the fault occurs after 25 steps, and the fault detector alarms. Figure 4 It can be seen that when the fault detector state does not meet the preset requirements, the fault alarm will sound an alarm, which further indicates the effectiveness of the fault detector.

[0050] Based on the above-mentioned unmanned system data-driven fault detection method, the present application embodiment provides an unmanned system data-driven fault detection device, such as Figure 5 As shown, the unmanned system data-driven fault detection device specifically includes: The offline collection module 100 is used to connect the unknown unmanned system to the controller, collect the state data of a certain number of collection moments offline, and construct a state data matrix and an evolution state data matrix based on the collected state data; A construction module 200, configured to construct a fault detector based on the state data matrix and the evolution state data matrix; The fault detection module 300 is used to connect the fault detector to the unknown unmanned system and perform fault detection based on the status data of the unmanned system through the fault detector.

[0051] Based on the above-mentioned unmanned system data-driven fault detection method, this embodiment provides a computer-readable storage medium, which stores one or more programs. The one or more programs can be executed by one or more processors to implement the steps in the unmanned system data-driven fault detection method as described in the above-mentioned embodiment.

[0052] Based on the above-mentioned unmanned system data-driven fault detection method, the present application also provides a terminal device, such as Figure 6As shown, it includes at least one processor 20; a display screen 21; and a memory 22, and may also include a communications interface 23 and a bus 24. The processor 20, the display screen 21, the memory 22, and the communications interface 23 may communicate with each other through the bus 24. The display screen 21 is configured to display a preset user guide interface in the initial setting mode. The communications interface 23 may transmit information. The processor 20 may call the logic instructions in the memory 22 to execute the method in the above embodiment.

[0053] In addition, the logic instructions in the memory 22 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product.

[0054] The memory 22 is a computer-readable storage medium that can be configured to store software programs, computer executable programs, such as program instructions or modules corresponding to the methods in the embodiments of the present disclosure. The processor 20 executes functional applications and data processing by running the software programs, instructions or modules stored in the memory 22, that is, implementing the methods in the above embodiments.

[0055] The memory 22 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 22 may include a high-speed random access memory and may also include a non-volatile memory. For example, a variety of media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, may also be a transient storage medium.

[0056] In addition, the specific process of loading and executing the multiple instruction processors in the above-mentioned storage medium and the terminal device has been described in detail in the above-mentioned method, and will not be described one by one here.

[0057] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A fault detection method based on unmanned system data drive, characterized in that: The fault detection method based on unmanned system data drive specifically includes: Connect the unknown unmanned system to the controller, collect the state data of a certain number of collection moments offline, and construct the state data matrix and the evolution state data matrix based on the collected state data; constructing a fault detector based on the state data matrix and the evolution state data matrix; The fault detector is connected to the unknown unmanned system, and the fault detector performs fault detection based on the status data of the unmanned system.

2. The unmanned system data-driven fault detection method according to claim 1, characterized in that: The offline collection of status data at a certain number of collection moments specifically includes: Setting initial state data for the unknown unmanned system and transmitting the initial state data to a controller; generating a control input by the controller and applying the control input to the unknown unmanned system; Collecting state data of the unknown unmanned system at a new moment formed based on the control input; The state data at the new moment is used as the initial state data, and the step of transmitting the initial state data to the controller is re-executed until a certain number of state data at the collection moments are collected.

3. The unmanned system data-driven fault detection method according to claim 1, characterized in that: The constructing of a fault detector based on the state data matrix and the evolution state data matrix specifically includes: Constructing a first semi-positive definite programming problem based on the state data matrix and the evolution state data matrix, and solving the first semi-positive definite programming problem to determine an optimal solution to the first semi-positive definite programming problem; A second semi-positive programming problem is constructed based on the optimal solution of the first semi-positive programming problem, and the second semi-positive programming problem is solved to construct a fault detector.

4. The unmanned system data-driven fault detection method according to claim 3 is characterized in that: The first semi-positive programming problem is stated as: ， ， ， ， in, It means to solve the determinant value, Representation Dimension The real positive definite symmetric matrix to be solved is represents the real number to be solved, represents the state data matrix, represents the evolution state data matrix, represents the first intermediate matrix, represents the second intermediate matrix, The dimension is The identity matrix of The dimension is The all-zero matrix, The dimension is The all-zero matrix, represents a constant between 0 and 1. Representation Matrix The transpose of Representation Matrix The transpose of represents a known constant greater than or equal to zero, Indicates the number of time steps collected offline.

5. The unmanned system data-driven fault detection method according to claim 3, characterized in that: The second semidefinite programming problem is stated as: ， ， ， ， ， ， ， ， ， in, It means to solve the determinant value, It means taking the maximum value in the braces. Indicates the dimension to be solved The matrix of is the scalar to be solved, represents the optimal solution to the first semidefinite programming problem, represents the inverse matrix of the optimal solution to the first semidefinite programming problem, represents the third intermediate matrix, represents the fourth intermediate matrix, The dimension is The all-zero matrix, represents a constant, The dimension is The identity matrix of The dimension is The all-zero matrix, represents a known constant greater than or equal to zero, represents the number of time steps collected offline, It indicates that the upper limit of the initial value when the unknown unmanned system is running online is known; The fault detector is expressed as: ， in, represents a fault detector, represents the optimal solution to the second semidefinite programming problem.

6. The method for fault detection based on unmanned system data drive according to claim 1, characterized in that: The step of connecting the fault detector to the unknown unmanned system is as follows: The fault detector is connected to an output item of the unknown unmanned system so that the fault detector is connected to a closed-loop system formed by the unknown unmanned system and a controller, wherein the fault detector is in parallel with the controller.

7. The unmanned system data-driven fault detection method according to claim 1 or 6, characterized in that: The performing fault detection based on the status data of the unmanned system by the fault detector specifically includes: Obtain status data of unknown unmanned systems at each collection moment through fault detectors; determining a fault detector state based on the state data, and generating an alarm message when the fault detector state does not meet a preset requirement; The fault detector states are: when hour, ; when when, It is expressed as: ， in, express The fault detector status at time, express Status data at the moment, express Status data at the moment, represents the state data matrix, represents the evolution state data matrix, Representation Matrix The right inverse matrix of ; The preset requirements are: ， in, express The transpose of Indicates a fault detector.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps in the unmanned system data-driven fault detection method as described in any one of claims 1-7.

9. A terminal device, characterized in that: include: Processor and memory; The memory stores a computer-readable program executable by the processor; When the processor executes the computer-readable program, the steps of the unmanned system data-driven fault detection method as described in any one of claims 1 to 7 are implemented.

Images