Unmanned aerial vehicle formation communication fault diagnosis method and device, equipment and storage medium

Abstract

The invention discloses an unmanned aerial vehicle formation communication fault diagnosis method and device, equipment and a storage medium. The method comprises the following steps: acquiring at least one receiving signal obtained by receiving a sending signal of a to-be-detected unmanned aerial vehicle by other unmanned aerial vehicles; inputting the received signal into a trained communication link fault model based on a confidence rule base to obtain evaluation results and diagnosis output vectors of a plurality of different fault types; and according to the standard fault vector and the diagnosis output vector, selecting one of the evaluation results as a prediction fault type of the to-be-detected unmanned aerial vehicle. The kit is good in diagnosis effect and stability.

Description

Technical Field

[0001] The present invention belongs to the technical field of unmanned aerial vehicle formations, and in particular relates to a method and apparatus, equipment, and storage medium for diagnosing communication faults in unmanned aerial vehicle formations. Background Art

[0002] Drone fleets have shown broad potential in modern technology, encompassing diverse applications such as geological exploration, environmental monitoring, agricultural management, emergency rescue, and logistics. The technology's flexibility and efficiency have made it an indispensable tool, particularly in missions requiring wide-area coverage, precise positioning, and coordinated operations. However, as drone fleets grow in complexity, inter-fleet communication issues are becoming a key constraint to their efficient operation.

[0003] During drone formation operations, the communication system is a core component in maintaining the coordination and safety of the entire formation. Each drone must communicate in real time to exchange location information, flight status, and mission instructions to ensure that all drones in the formation fly in a coordinated manner according to the designated trajectory and relative positions. Especially in more complex mission scenarios, each drone in the formation must autonomously adjust to environmental changes, relying on stable communications to ensure these adjustments are rapidly communicated. However, in actual operations, drone formations inevitably encounter communication failures, which can seriously impact mission success and drone safety. Therefore, comprehensive diagnosis and countermeasures for communication failures in drone formations are essential.

[0004] Current communication fault diagnosis methods often lack sufficient robustness and accuracy when faced with unknown interference or complex environments, resulting in low fault identification rates. Existing technologies, which mostly rely on traditional models or rule-matching methods, struggle to accurately detect abnormal signals and faults in complex real-time communications. Therefore, there is an urgent need for intelligent methods that can accurately diagnose communication faults in interference environments. Summary of the Invention

[0005] The embodiments of the present invention provide a method and apparatus, equipment, and storage medium for diagnosing communication faults in a UAV formation, which can solve the problems of low detection accuracy and poor robustness of current communication fault diagnosis methods.

[0006] In a first aspect, an embodiment of the present invention provides a method for diagnosing communication faults in a UAV formation, the method comprising: Acquire at least one received signal obtained by another drone receiving a signal transmitted by the drone to be detected, wherein a communication link exists between the drone to be detected and the other drone; Inputting the received signal into a trained communication link fault model based on a confidence rule base to obtain multiple evaluation results and diagnostic output vectors for different fault types, wherein the diagnostic output vector is used to represent the total confidence of the evaluation result; According to the standard fault vector and the diagnostic output vector, one is selected from the evaluation results as the predicted fault type of the UAV to be detected.

[0007] In a second aspect, an embodiment of the present invention provides a UAV formation communication fault diagnosis device, comprising: an acquisition unit, the acquisition unit acquiring at least one received signal obtained by other drones receiving a signal transmitted by the drone to be detected, wherein a communication link exists between the drone to be detected and the other drones; an evaluation unit, configured to input the received signal into a trained communication link fault model based on a confidence rule base, and obtain evaluation results and diagnostic output vectors for a plurality of different fault types, wherein the diagnostic output vector is used to represent an overall confidence level of the evaluation result; A classification unit is configured to select one from the evaluation results as a predicted fault type of the UAV to be detected based on a standard fault vector and the diagnostic output vector.

[0008] In a third aspect, an embodiment of the present invention provides an electronic device comprising a processor and a memory, wherein the memory is used to store computer programs; the processor can be used to execute the computer program (instructions) stored in the memory to implement the method of the first aspect above.

[0009] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed, the method of the first aspect described above can be implemented.

[0010] Compared with the prior art, the embodiments of the present invention have the following advantages: since the communication link model in the present invention is constructed based on the confidence rule base, it can fully utilize the advantages of the confidence rule base such as high robustness and good detection performance, thereby improving the stability of fault detection and the fault recognition rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A schematic diagram of a UAV formation provided by an embodiment of the present invention; Figure 2 A flowchart of a method for diagnosing communication faults in a UAV formation provided by an embodiment of the present invention; Figure 3 A schematic diagram of the operation flow of a communication link failure model provided by an embodiment of the present invention; Figure 4 A schematic diagram of the structure of a UAV formation communication fault diagnosis device provided by an embodiment of the present invention; Figure 5 A schematic diagram of the communication topology of a UAV formation provided by an embodiment of the present invention; Figure 6 A schematic diagram of a diagnosis result provided by an embodiment of the present invention; Figure 7 A schematic diagram of another diagnostic result provided by an embodiment of the present invention; Figure 8 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0012] In the following description, specific details such as particular system structures and techniques are provided for purposes of illustration, not limitation, to facilitate a thorough understanding of the embodiments of the present invention. However, it will be apparent to those skilled in the art that the present invention may be practiced in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.

[0013] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0014] It will also be understood that the term "and / or" used in the present description and appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0015] As used in the present specification and the appended claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0016] In addition, in the description of the present specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0017] References to "one embodiment" or "some embodiments" in the present specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present invention. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in yet other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0018] The present invention will be further described in detail below with reference to specific examples, but the embodiments of the present invention are not limited thereto.

[0019] Example 1 As an example, see Figure 1 , a drone formation can include a leader drone and several follower drones The drones communicate with each other through the weight matrix To represent the communication connection, the matrix Elements Indicates follower drone and follower drones The communication weight between When and There is direct communication between , it means there is no direct communication link between the two.

[0020] For example, the dynamic equation of the leader UAV can be expressed as: , in, Indicates the leader drone status, represents a real number, is the dimension of the state space, and the superscript is added to the parameter represents the derivative of the parameter.

[0021] For example, the dynamic equation of the follower UAV can be expressed as: , in, 、 Follower drones Status and control inputs, To control the input dimension, 、 is a known system matrix.

[0022] In practical applications, communication links may fail, which can adversely affect the stability of the UAV formation and mission execution. Communication link failure can be indicated by: , in, In the actual communication link, the follower drone and follower drones The initial weights between In the actual communication link, the follower drone and leader drones The initial weights between 、 They represent the follower UAVs in the ideal communication link and follower drones , follower drone and leader drones The initial weights between For follower drones and follower drones The damage weight caused by communication failure, For follower drones and leader drones The damage weight caused by communication failure, is the total number of follower drones, Indicates that it includes 1 to The set of integers.

[0023] Example 2 The UAV formation communication fault diagnosis method provided by the embodiment of the present invention can be applied to electronic devices such as mobile terminals, personal laptops, supercomputers, etc. The embodiment of the present invention does not impose any restrictions on the specific type of electronic equipment.

[0024] Figure 2 The flowchart shown is a method for diagnosing communication faults in a UAV formation, as provided in an embodiment of the present invention. By way of example and not limitation, the method can be applied to the aforementioned electronic device. The method may include the following steps S201-S203, each of which is described below.

[0025] S201, obtaining at least one received signal obtained by other drones receiving a signal sent by the drone to be detected.

[0026] In one possible implementation, in order to ensure that the UAV formation can still operate stably in the event of a communication failure, the received signal at the receiving end can be monitored to determine whether there is an abnormality at the sending end.

[0027] Exemplarily, the received signal may satisfy the following formula: , in, For other drones The received signal, The drone to be detected in the drone formation The sending signal, Indicates other drones and drones to be detected The communication weight between For other drones and drones to be detected The damage weight between .

[0028] In one example, the communication failure manifests itself as a deviation in the input signal, that is, a change in the signal during transmission, which is specifically manifested as a communication failure parameter Affects the transmission signal Therefore, if an abnormal signal is detected, , it means that other drones and drones to be detected There is a communication failure between the other drones. Receive the drone to be tested The received signal obtained by the transmitted signal is input into the communication link fault model, and the model is used to determine whether there is a communication fault and further estimate the fault type.

[0029] Exemplarily, there is a communication link between the other drones and the drone to be detected.

[0030] S202 : Input the received signal into a trained communication link fault model based on a confidence rule base to obtain multiple evaluation results and diagnostic output vectors of different fault types.

[0031] In one possible implementation, a communication link fault model can be constructed based on a belief rule base. While the initial parameters of the communication link fault model can be determined by experts, the subjectivity of expert knowledge can lead to poor model accuracy. To improve model diagnostic accuracy, the model can be optimized. The optimization goal can be to find the optimal belief distribution, rule weights, and attribute weights to maximize the model's diagnostic accuracy for communication faults.

[0032] Exemplarily, the initial parameters of the communication link fault model may include the premise attributes of each received signal, the reference value and the reference point in each rule.

[0033] In one example, a communication link failure model can be optimized using a projected covariance matrix adaptive evolutionary strategy. This algorithm can reduce optimization complexity, improve efficiency, and achieve good optimization results. Specific steps include: sampling, constraining multiple objectives, projecting, selecting and reorganizing, and updating the solution matrix.

[0034] For example, the communication link failure model The rule can be described by the following formula: , in, Indicates other drones entered The received signal, is the total number of other drones, Indicates the In the rules The reference value, For the The evaluation results, For the The output of the rules includes The evaluation results, The confidence level of each evaluation result of the rule . For the The rule weight of the rule, For the Rule pair The attribute weight of .

[0035] Specifically, if It is believed that The rule is complete if it is not, otherwise it is incomplete.

[0036] For example, the diagnosis output vector can be used to represent the overall confidence of the assessment result.

[0037] Specifically, the diagnostic output vector can be expressed as , For the The overall confidence level of the evaluation result.

[0038] S203 , selecting one from the evaluation results as the predicted fault type of the UAV to be detected based on the standard fault vector and the diagnosis output vector.

[0039] In one possible implementation, in order to determine the specific type of communication link failure, a fault diagnosis strategy based on proximity classification can be adopted. First, the first Standard fault vectors for each fault type ; Then calculate the norm between it and the diagnostic output vector. Finally, select The standard fault vector with the smallest distance As the predicted fault type of the drone to be inspected.

[0040] In one example, the norm It can be calculated by the following formula: , in, express and The norm between is the norm parameter, For the The diagnostic output vector of the diagnostic results, For the The standard fault vector corresponding to the fault type of the diagnosis result.

[0041] For example, the predicted fault type of the drone to be detected can satisfy the following formula: .

[0042] Since the communication link model in the present invention is constructed based on the confidence rule base, it can fully utilize the advantages of the confidence rule base such as high robustness and good detection performance, thereby improving the stability of fault detection and the fault recognition rate.

[0043] Example 3 Figure 3 The following is a schematic diagram of the operation flow of a communication link fault model provided by an embodiment of the present invention. By way of example and not limitation, this operation flow is a specific description of step S202 in the above-mentioned diagnostic method. The process may include steps S301-S304, each of which is described below: S301: Determine the matching degree of each received signal with respect to each rule.

[0044] In one example, the received signal can be determined by the following formula: For the first The matching degree of the rules.

[0045] , in, For other drones Received signal For the first The matching degree of the rules, 、 Receive signal In the Reference points in the rules and in Reference point in the rule.

[0046] S302, according to each received signal The matching degree of the rule is determined The comprehensive matching degree of the rules.

[0047] For example, The comprehensive matching degree of the rules can satisfy the following formula:

[0048] in, For the The comprehensive matching degree of the rules, To receive the signal The relative attribute weights of .

[0049] in: , in, for The weight of .

[0050] S303, according to The comprehensive matching degree of the rules, The rule weight of the rule determines the The activation weight of the rule.

[0051] For example, the input information of the communication link The impact on each rule is different, and the activation weight can be used to measure this impact. The activation weight of the rule can satisfy the following formula: , in, For the The activation weights of the rules, and .

[0052] S304, after obtaining the activation weight of each rule, according to the activation weight of each rule and the activation weight of each rule The output vector of the evaluation result is determined The overall confidence level of the evaluation result.

[0053] In one example, when multiple rules are activated, knowledge reasoning can be performed using the following formula to integrate the activated rules and convert the input information Convert to confidence level of output result: , in, Indicates the Evaluation results The total confidence level, .

[0054] For example, Rule 1 The output vector of the evaluation result can be , indicating the Rule 1 The confidence level of the evaluation result.

[0055] Example 4 Figure 4 The diagram shows a schematic diagram of a UAV formation communication fault diagnosis device according to an embodiment of the present invention. As an example and not a limitation, the device 400 may include an acquisition unit 410 , an evaluation unit 420 , and a classification unit 430 .

[0056] Exemplarily, the acquisition unit 410 is used to obtain at least one received signal obtained by other drones receiving the sent signal of the drone to be detected, wherein a communication link exists between the drone to be detected and the other drones; the evaluation unit 420 is used to input the received signal into a trained communication link fault model based on a confidence rule base to obtain multiple evaluation results and diagnostic output vectors for the fault type, wherein the diagnostic output vector is used to represent the total confidence of the evaluation result; the classification unit 430 is used to select one from the evaluation results as the predicted fault type of the drone to be detected based on the standard fault vector and the diagnostic output vector.

[0057] In order to better illustrate the beneficial effects of the embodiments of the present invention, the following simulation experiments were conducted: Simulation Experiment 1 For example, see Figure 5 In the communication topology diagram, in the simulation experiment, the UAV formation is set to consist of 4 UAVs, and UAVs 2, 3, and 4 communicate with 1 respectively, and the three do not communicate with each other. (Depend on Figure 5 UAV 1 in the figure acts as ), and Follower drones (Respectively by Figure 5 UAVs 2, 3, and 4 act as components, and the state vector dimension , controls the input vector dimension . System Matrix is a 3×3 identity matrix , the system matrix for , the communication weight matrix Following the topology, where the leader and followers The communication link weight The initial state of the leader and follower 、 Generated by a mixture of normal distributions. Based on the scaling factor Proportional control strategy, adding a certain amount of random noise to generate control input .

[0058] In this system, the leader drone As a drone to be detected , all follower drones act as other drones, so at this time .

[0059] Considering the interference of communication links, a fault weight is introduced for the communication links between all leaders and each follower. First, a basic fault weight is randomly generated. Then, a large random perturbation is added to the base fault weight with a probability of 0.75. ,in is a random number uniformly distributed in the interval [0,1] to generate fault data; otherwise, add a small random perturbation The final fault weight or The generated fault weight With the initial communication weight Add up to get the communication weight with fault , and Perform bounds checking. Calculate the communication signal received by the follower and extract Compose the first three columns of data and compare the normal data fluctuation tolerance Tolerance for deviation from fault data , determine the fault type, store it in the fourth column, ignore arrive The process is repeated to generate 400 valid data samples, each of which contains 3 received signals. And a label indicating the actual fault type (stored in the 4th column). The four fault types correspond to fault type 1, fault type 2, fault type 3, and normal, and the four results have corresponding label values of 1, 2, 3, and 4, respectively.

[0060] Specifically, in the simulation experiment, Normalization is performed to ensure that the data is within the same time period to facilitate model training and testing. Set the reference value range [0, 0.3, 0.6, 1], by Compare with the reference point to calculate the matching degree and convert the input data into a form that the model can process. strip Rule matching degree First, normalize the attribute weights, calculate the activation strength of each rule, and then get the activation weight. Finally, integrate the activation rules and calculate the confidence of the output result. ( ), and obtain the diagnostic output vector The standard fault vector is defined in the model , fault type 1 corresponds to is [1,0,0,0], and fault type 2 corresponds to is [0,1,0,0], and fault type 3 corresponds to is [0,0,1,0], which normally corresponds to is [0,0,0,1]. Calculate the distance between the diagnostic output vector and each standard fault vector, and find the standard fault vector with the smallest distance to the diagnostic output vector. The corresponding fault type is the determined communication link fault type.

[0061] The number of rules in the confidence rule base is set to 64, the weight of each rule is set to 1, and the initial confidence is set. The input attribute weight is equal to the initial parameter and used to initialize the model. The approximately 400 samples in the dataset are divided into 200 training sets and 200 test sets. In the test set, 1-50 is , 51-100 , 101-150 , 151-200 The number of iterations of the projected covariance matrix adaptive evolutionary strategy is set to 200, from which the optimized belief distribution, rule weights and attribute weights are extracted.

[0062] The method provided by the present invention was tested using sample data under four fault types, and the diagnostic results obtained are as follows: Figure 6 As shown in the figure, the straight line represents the actual fault type (Actual Value), and the discrete points represent the predicted fault type (BRB Diagnostic Results) obtained based on the method provided by the present invention. It can be seen that the diagnostic accuracy of the present invention can reach 93.00%.

[0063] Considering the actual UAV communication link failure situation, the communication failure is observed within 100 seconds, of which there is a failure for 10 seconds. The actual UAV communication signal is tested and the diagnosis results are as follows: Figure 7 As shown in the figure, the accuracy of diagnosis is 97.00%. It can be seen that the method provided by the present invention can perform relatively accurate diagnosis.

[0064] Example 5 Figure 8 FIG. 1 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 8 The electronic device 800 shown may include: at least one processor 810 ( Figure 8 Only one processor is shown in the figure), a memory 820, and a computer program 830 stored in the memory 820 and executable on the at least one processor 810, wherein the processor 810 implements the steps of any of the above-mentioned method embodiments when executing the computer program 830.

[0065] The electronic device 800 may be a processing device such as a robot that can implement the above method. The embodiment of the present invention does not impose any limitation on the specific type of the electronic device.

[0066] Those skilled in the art will understand that Figure 8 The electronic device 800 is merely an example and does not constitute a limitation on the electronic device. The electronic device 800 may include more or fewer components than shown in the figure, or may combine certain components or different components. For example, the electronic device 800 may also include an input and output interface.

[0067] The processor 810 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASTC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gates, or transistor logic devices, or discrete hardware components. A general-purpose processor may be a microprocessor or any conventional processor.

[0068] In some embodiments, the memory 820 may be an internal storage unit, such as a hard disk or a memory. In other embodiments, the memory 820 may also be an external storage device, such as a plug-in hard disk, a smart memory card (SMC), a secure digital (SD) card, a flash card, etc. Furthermore, the memory 820 may include both an internal storage unit and an external storage device. The memory 820 is used to store an operating system, an application program, a boot loader, data, and other programs, such as the program code of the computer program. The memory 820 may also be used to temporarily store data that has been output or is about to be output.

[0069] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0070] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0071] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned various method embodiments can be implemented.

[0072] An embodiment of the present invention provides a computer program product. When the computer program product is run on an electronic device, the electronic device can implement the steps in the above-mentioned various method embodiments when executing the computer program product.

[0073] If the integrated unit is implemented as a software functional unit and sold or used as a standalone product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention can implement all or part of the process steps in the above-mentioned method embodiments by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a camera / terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal, and software distribution medium. Examples include USB flash drives, removable hard drives, magnetic disks, or optical disks. In some jurisdictions, based on legislation and patent practice, computer-readable media cannot be electric carrier signals or telecommunication signals.

[0074] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0075] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

Claims

1. A method for diagnosing communication faults in a UAV formation, characterized in that: include: Acquire at least one received signal obtained by another drone receiving a signal transmitted by the drone to be detected, wherein a communication link exists between the drone to be detected and the other drone; Inputting the received signal into a trained communication link fault model based on a confidence rule base to obtain multiple evaluation results and diagnostic output vectors for different fault types, wherein the diagnostic output vector is used to represent the total confidence of the evaluation result; According to the standard fault vector and the diagnostic output vector, one is selected from the evaluation results as the predicted fault type of the unmanned aerial vehicle to be detected.

2. The method according to claim 1, characterized in that The received signal satisfies the following formula: ， in, For other drones The received signal, The drone to be detected in the drone formation The sending signal, Indicates other drones and drones to be detected The communication weight between For other drones and drones to be detected The damage weight between .

3. The method according to claim 2, characterized in that The damage weight of the drone to be detected is not 0.

4. The method according to claim 1, wherein The communication link failure model is used to: Determining a matching degree of each received signal to each rule in the communication link fault model; According to each of the received signals The matching degree of the rule is determined The comprehensive matching degree of the rules, among which, is less than or equal to A positive integer, is the total number of rules; According to the said The comprehensive matching degree of the rules, The rule weight of the rule determines the The activation weight of the rule; After obtaining the activation weight of each rule, according to the activation weight of each rule and the activation weight of each rule The output vector of the evaluation result determines the The total confidence of the evaluation results, where The rule The output vector of the evaluation result is used to represent the The rule The confidence level of the evaluation result.

5. The method according to claim 4, characterized in that The received signal is The matching degree of the rules satisfies the following formula: ， in, For other drones Received signal Regarding the The matching degree of the rules, 、 Receive signal In the The reference points in the rule and in Reference point in the rule.

6. The method according to claim 5, characterized in that The said The comprehensive matching degree of the rules satisfies the following formula: ， in, For the said The comprehensive matching degree of the rules, To receive the signal The relative attribute weights of is the total number of received signals.

7. The method according to claim 4, characterized in that The said The total confidence of an evaluation result satisfies the following formula: ， in, Indicates the The total confidence level of the evaluation results, For the said The activation weights of the rules, Indicates the The rule The confidence level of the evaluation results, Indicates the Rule 1 The confidence level of the evaluation results, is the total number of evaluation results, 。 8. A UAV formation communication fault diagnosis device, characterized in that: include: an acquisition unit, configured to acquire at least one received signal obtained by other drones receiving a signal transmitted by the drone to be detected, wherein a communication link exists between the drone to be detected and the other drones; an evaluation unit, configured to input the received signal into a trained communication link fault model based on a confidence rule base, and obtain evaluation results and diagnostic output vectors for a plurality of different fault types, wherein the diagnostic output vector is used to represent an overall confidence level of the evaluation result; A classification unit is configured to select one from the evaluation results as a predicted fault type of the UAV to be detected based on a standard fault vector and the diagnostic output vector.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by the electronic device, the method according to any one of claims 1 to 7 is implemented.

Images