Variable shape aircraft fault detection model generation method and fault detection method

Abstract

The invention provides a variable shape aircraft fault detection model generation method and a fault detection method, and the method comprises the steps: obtaining a variable shape aircraft fault detection model based on each wingspan change rate, an initial value of an aircraft state variable, and a preset variable shape aircraft flight linear change parameter model; obtaining a state control feedback matrix corresponding to each wingspan change rate; flight simulation data are generated based on to-be-simulated data, the to-be-simulated data comprise an initial value of an aircraft state variable, a wingspan change rate and a state control feedback matrix, and each group of flight simulation data comprises flight state parameters at multiple moments; generating sample data based on the flight simulation data, wherein the sample data comprises the flight simulation data and a fault tag corresponding to the flight simulation data; and training based on the multiple groups of sample data to obtain a variable shape aircraft fault detection model. According to the invention, the fault of the variable-shape aircraft can be effectively detected.

Description

Technical Field

[0001] The present invention relates to the technical field of aircraft fault detection, and in particular to a method for generating a fault detection model for a deformable aircraft and a fault detection method. Background Art

[0002] Shape-shifting aircraft have attracted widespread attention because they can change their shape structure (retractable wings) in real time according to different flight phases and mission conditions to adapt to today's more complex flight environment. While this adaptability enhances the performance of the aircraft, it also brings great challenges to the design of the control system and increases the risk of aircraft failure. However, there is no effective method for detecting failures of shape-shifting aircraft in the prior art. Summary of the invention

[0003] The present invention provides a method for generating a fault detection model of a shape-changing aircraft and a fault detection method, so as to solve the defect that there is no effective detection of the fault of the shape-changing aircraft in the prior art, and realize the effective detection of the fault of the shape-changing aircraft.

[0004] The present invention provides a method for generating a fault detection model for a deformable aircraft, comprising: Based on each wingspan change rate, the initial value of the aircraft state variable and a preset flight linear change parameter model of the deformable aircraft, a state control feedback matrix corresponding to each wingspan change rate is obtained; Generate flight simulation data based on the data to be simulated, wherein the data to be simulated includes the initial value of the aircraft state variable, the wingspan change rate and the state control feedback matrix, and each group of the flight simulation data includes flight state parameters at multiple moments; Generate sample data based on the flight simulation data, wherein the sample data includes the flight simulation data and a fault label corresponding to the flight simulation data, when the wingspan change rate corresponding to the state control feedback matrix included in the flight simulation data is inconsistent with the wingspan change rate included in the flight simulation data, the fault label is a fault, and when the wingspan change rate corresponding to the state control feedback matrix included in the flight simulation data is consistent with the wingspan change rate included in the flight simulation data, the fault label is a no-fault; A deformable aircraft fault detection model is obtained by training based on multiple groups of sample data.

[0005] According to a method for generating a fault detection model for a deformable aircraft provided by the present invention, the flight state parameters include flight speed, angle of attack, pitch angle, pitch angular velocity and flight altitude, and the aircraft state variables include change in flight speed, change in angle of attack, change in pitch angle, change in pitch angular velocity and change in flight altitude.

[0006] According to a method for generating a fault detection model for a deformable aircraft provided by the present invention, the flight linear variation parameter model is: ; in, , is the wingspan change rate, is the flight speed, is the state control feedback matrix, is the aircraft state variable, Indicates the interference during the flight of the aircraft. , , , is the preset fitting matrix.

[0007] According to a method for generating a fault detection model for a deformable aircraft provided by the present invention, the fitting matrix in the flight linear variation parameter model is obtained by linearizing the nonlinear dynamic equations of the deformable aircraft at each working point in the flight envelope, and then fitting and simplifying them.

[0008] According to a method for generating a fault detection model for a deformable aircraft provided by the present invention, the fault detection model for a deformable aircraft is constructed based on a decision tree algorithm.

[0009] The present invention also provides a method for detecting faults of a deformable aircraft, comprising: Acquiring flight state parameters of the aircraft to be detected, and inputting the flight state parameters into a deformable aircraft fault detection model; Obtaining a fault detection result output by the deformable shape aircraft fault detection model; The deformable shape aircraft fault detection model is generated based on the deformable shape aircraft fault detection model generation method as described in any one of the above items.

[0010] The present invention also provides a device for generating a fault detection model for a deformable aircraft, comprising: A controller determination module, for obtaining a state control feedback matrix corresponding to each of the wingspan change rates based on each wingspan change rate, an initial value of an aircraft state variable, and a preset flight linear change parameter model of a shape-shifting aircraft; A simulation module, used to generate flight simulation data based on data to be simulated, wherein the data to be simulated includes initial values ​​of the aircraft state variables, the wingspan change rate, and the state control feedback matrix, and each set of the flight simulation data includes flight state parameters at multiple moments; A data set generating module, used for generating sample data based on the flight simulation data, wherein the sample data includes the flight simulation data and a fault label corresponding to the flight simulation data, when the wingspan change rate corresponding to the state control feedback matrix included in the flight simulation data is inconsistent with the wingspan change rate included in the flight simulation data, the fault label is a fault, and when the wingspan change rate corresponding to the state control feedback matrix included in the flight simulation data is consistent with the wingspan change rate included in the flight simulation data, the fault label is a no-fault; A training module is used to obtain a deformable aircraft fault detection model through training based on multiple groups of sample data.

[0011] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it implements any one of the above-described methods for generating a deformable shape aircraft fault detection model and / or a deformable shape aircraft fault detection method.

[0012] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for generating a fault detection model for a deformable aircraft and / or the method for detecting a fault of a deformable aircraft as described above are implemented.

[0013] The present invention also provides a computer program product, comprising a computer program, which, when executed by a processor, implements any of the above-mentioned methods for generating a fault detection model for a deformable aircraft and / or a method for detecting a fault for a deformable aircraft.

[0014] The method for generating a fault detection model for a shape-shifting aircraft and the method for fault detection provided by the present invention obtain a flight linear variation parameter model of the shape-shifting aircraft in advance, obtain a state control feedback matrix corresponding to each wingspan change rate based on the model, and then generate flight simulation data in a fault state and a non-fault state based on a combination of aircraft state variables, wingspan changes, and the state control feedback matrix. Sample data are generated based on these flight simulation data to train a shape-shifting aircraft fault detection model, thereby achieving effective detection of shape-shifting aircraft faults based on the shape-shifting aircraft fault detection model. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 It is a flow chart of the method for generating a fault detection model for a deformable aircraft provided by the present invention.

[0017] Figure 2 The system stability control effectiveness of the flight linear variation parameter model of the variable shape aircraft in the variable shape aircraft fault detection model generation method provided by the present invention is shown in FIG. Figure 1 .

[0018] Figure 3 The system stability control effectiveness of the flight linear variation parameter model of the variable shape aircraft in the variable shape aircraft fault detection model generation method provided by the present invention is shown in FIG. Figure 2 .

[0019] Figure 4 Schematic diagram of the effectiveness of system stability control of the flight linear variation parameter model of the variable shape aircraft in the variable shape aircraft fault detection model generation method provided by the present invention Figure 3 .

[0020] Figure 5 Schematic diagram of the effectiveness of system stability control of the flight linear variation parameter model of the variable shape aircraft in the variable shape aircraft fault detection model generation method provided by the present invention Figure 4 .

[0021] Figure 6 The system stability control effectiveness of the flight linear variation parameter model of the variable shape aircraft in the variable shape aircraft fault detection model generation method provided by the present invention is shown in FIG. Figure 5 .

[0022] Figure 7 It is a schematic diagram of the training process of the deformable aircraft fault detection model provided by the present invention.

[0023] Figure 8 It is a schematic diagram of the model confusion matrix in the deformable aircraft fault detection model generation method provided by the present invention.

[0024] Fig. 9 It is a flow chart of the deformable aircraft fault detection method provided by the present invention.

[0025] Fig.10 It is a structural schematic diagram of a deformable aircraft fault detection model generating device provided by the present invention.

[0026] Fig.11 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0028] Combine the following Figure 1-Figure 8 The present invention describes a method for generating a deformable aircraft fault detection model. Figure 1 As shown, the method for generating a fault detection model for a deformable aircraft includes the following steps: S110, based on each wingspan change rate, the initial value of the aircraft state variable and the preset flight linear change parameter model of the shape-shifting aircraft, obtaining the state control feedback matrix corresponding to each wingspan change rate; S120, generating flight simulation data based on the data to be simulated, the data to be simulated including initial values ​​of aircraft state variables, wingspan change rate, and state control feedback matrix, and each set of flight simulation data includes flight state parameters at multiple moments; S130, generating sample data based on the flight simulation data, wherein the sample data includes the flight simulation data and a fault label corresponding to the flight simulation data, when the wingspan change rate corresponding to the state control feedback matrix included in the flight simulation data is inconsistent with the wingspan change rate included in the flight simulation data, the fault label is fault, and when the wingspan change rate corresponding to the state control feedback matrix included in the flight simulation data is consistent with the wingspan change rate included in the flight simulation data, the fault label is no fault; S140, training based on multiple groups of sample data to obtain a deformable aircraft fault detection model.

[0029] The method provided by the present invention realizes fault detection of a shape-changing aircraft in a data-driven manner to meet the special needs of shape-changing aircraft. Data-driven is a thinking mode that makes decisions and takes actions based on data. Its advantage is that more scientific and accurate decision-making and prediction results can be obtained through the collection, analysis, processing and application of data. In order to achieve the above functions, the present invention first establishes a flight linear parameter-varying (LPV) model of a shape-changing aircraft based on the principle of flight dynamics and the linearization method. Specifically, the flight linear parameter-varying model is: ; in, , is the wingspan change rate, is the flight speed, is the state control feedback matrix, is the vehicle state variable, Indicates the interference during the flight of the aircraft. , , , is the preset fitting matrix.

[0030] The fitting matrix in the flight linear variation parameter model is obtained by linearizing the nonlinear dynamic equations of each working point of the deformable aircraft in the flight envelope, and then fitting and simplifying them. The following is an explanation of the construction process of the model: By studying the specific impact of wing extension and retraction on the aerodynamic performance of the aircraft, aerodynamic analysis tools are used to simulate and pre-calculate the effects of various flight environments, various working conditions, and different wingspan deformation rates. The aerodynamic parameters of the aircraft were obtained and the data were imported into the Matlab environment. The lift coefficient was derived using data fitting technology. , drag coefficient , pitch moment coefficient The calculation formula of key aerodynamic parameters is as follows: ; (1.1) in, Indicates the flight speed, represents the angle of attack, represents the pitch angular velocity, represents the elevator deflection angle, It is found that the above aerodynamic parameters are significantly affected by the wingspan deformation and the change of flight speed. Therefore, the least squares fitting method is used to establish the relationship between aerodynamic parameters and wingspan deformation rate. and Mach number The relationship between them is as follows: ; (1.2) From the results of equations (1.1) and (1.2), it can be seen that the aerodynamic parameters of the variable-span aircraft are significantly different from those of general aircraft. The most critical difference lies in the aerodynamic parameters and wingspan deformation rate of this aircraft. The extension and retraction of its wings can directly affect its aerodynamic characteristics.

[0031] After establishing the aerodynamic parameter expressions related to wing extension and retraction, the longitudinal nonlinear dynamic model of the aircraft's variable shape flight is further constructed as follows: ; (1.3) in, represents the pitch angle, h represents the flight altitude, represents the engine thrust, represents the moment of inertia, is the acceleration due to gravity, Indicates the mass of the aircraft. ,resistance and pitch moment Respectively expressed as: ; (1.4) in, is the dynamic pressure, is the reference area of ​​the wing.

[0032] From the analysis of equations (1-3) and (1-4), we can see that the dynamic model of the shape-shifting aircraft incorporates the factor of wing deformation, which indicates that during the shape-shifting flight, the extension and retraction of the wing will cause a significant change in the aerodynamic characteristics of the aircraft, stimulating additional dynamic responses, thus affecting the overall flight trajectory. This interaction between wing deformation and flight dynamics is the core feature of the shape-shifting aircraft design and is crucial to the design of the controller.

[0033] The Jacobian linearization technology based on LPV modeling is used to linearize the nonlinear dynamic equation (1.3) of the variable-length aircraft at each working point in the flight envelope. Through fitting and simplification, an LPV model suitable for variable-shape flight is successfully constructed: ; (1.5) in, , state variables ; They represent the change in flight speed, angle of attack, pitch angle, pitch velocity, and flight altitude, respectively. , Represents the change in throttle stick control. The matrix coefficients are ; (1.6) ; (1.7) ; (1.8) (1.9) Taking into account factors such as modeling errors, external disturbances, and additional uncertainties caused by wing extension and retraction, the LPV model (1.5) of the variable-length aircraft deformation flight is rewritten as ; (1.10) Among them, d represents the external interference during the flight. Indicates the change in state characteristics caused by deformation, represents the change of input characteristics caused by deformation, d, , It can be predefined, for example, .

[0034] Compound Interference , then formula (1.10) can be simplified to ; (1.11) According to the constructed LPV model, the present invention performs state feedback design on the closed-loop control system through the pole configuration method and introduces state feedback control: the expression of the state feedback control law is: ; (1.12) Substituting into equation (1.11), the closed-loop system is transformed into ; (1.13) Therefore, if a state feedback gain matrix is ​​designed , which makes Asymptotically stable, then when hour, , by calculating the optimal gain matrix, the closed-loop poles are assigned to the specified positions to ensure the stability of the closed-loop system. In other words, the state feedback gain matrix includes the control parameters used to control the flight stability of the shape-shifting aircraft. Its principle is based on the complete controllability of the system state, that is, if the original system state is completely controllable, there must be a state feedback gain matrix , making the closed-loop system controllable and able to Configurable to any desired pole position.

[0035] Based on the flight linear variation parameter model provided by the present invention, the dynamic response process of the closed-loop system of the aircraft can be simulated, thereby realizing the simulation of the flight parameters of the aircraft. The simulation can be realized by Matlab. First, the parameters are initialized, the specific values ​​of the state matrix and the input matrix are input, and the controllability discriminant matrix is ​​used. Determine whether the system is controllable. Then, use the pole placement method to design the state feedback controller, and let the vector , the eigenvalue of the closed-loop system represents the behavioral characteristics of the system. If the eigenvalue is in the left half plane (the real part is negative), it means that the system is stable. The initial setting is: -6, -5+i, -5-i, -3+2i, -3-2i, then set the wingspan deformation rate The value of , using the solve function Design the corresponding state feedback gain matrix to configure the poles of the closed-loop system to The specified position and calculate the state matrix of the closed-loop system and eigenvalues .

[0036] Then, initialize the variables. Set the state variables , input variable , and introduce an initial small perturbation , to simulate the interference of the external environment and the uncertainties caused by the deformation of the wings during flight. Then, based on the state space equation of the discrete-time linear time-invariant system (LTI) and the approximate integration method, the dynamic response process of the closed-loop system is simulated through cyclic iteration.

[0037] The flight linear variation parameter model of the shape-changing aircraft provided by the present invention is combined with the wingspan deformation rate The time response curves of the five state parameters (speed change, angle of attack change, pitch angle change, pitch angle velocity change, and flight altitude change) obtained under different values ​​are shown in the figure below: Figure 2-6 shown. Figure 2 is the time response curve of the speed change, Figure 3 is the time response curve of the angle of attack change, Figure 4 is the time response curve of the pitch angle change, Figure 5 is the time response curve of the pitch angular velocity change, Figure 6 is the time response curve of the flight altitude change. In general, the dynamic performance of the flight linear change parameter model of the deformable aircraft established by the present invention is very excellent. No matter how the value changes, the five state parameters can reach a steady state in a relatively short time (within 3s), and the response speed is relatively fast; after reaching the steady state, the state is basically kept unchanged, and the anti-interference ability is relatively strong; the overall overshoot is not too large, and the stability of the system is relatively good.

[0038] It can be seen from the foregoing description that the flight linear variation parameter model of the shape-changing aircraft provided by the present invention can simulate the flight state parameters of the shape-changing aircraft under stable control through the wingspan change rate and the initial values ​​of the aircraft state variables. Based on this, the present invention first obtains the state control feedback matrix corresponding to each of the wingspan change rates through each wingspan change rate, the initial values ​​of each aircraft state variable and the preset shape-changing aircraft linear variation parameter model of the flight. The state control feedback matrix obtained at this time can simulate the flight state parameters under a fault-free state. Therefore, sample data with a fault label of no fault can be constructed. When there is a fault, the controller of the shape-changing aircraft cannot recognize the change in the wingspan change rate. Therefore, the correspondence between the wingspan change rate and the state control feedback matrix can be disrupted to construct sample data with a fault label of faulty. For example, for the wingspan change rate = 0.1, and the control state feedback matrix when there is no fault is obtained through the flight linear variation parameter model. , the control state feedback matrix can be calculated at the wingspan change rate =0.1 controls the aircraft to fly stably. However, for the wingspan change rate =0.3, the control state feedback matrix is ​​still used due to the fault Control the aircraft, so the wingspan change rate = 0.3, using the control state feedback matrix By performing simulation, the flight status parameters of the aircraft under fault conditions can be obtained.

[0039] Through the above method, multiple sets of sample data can be constructed for model training. The specific process of constructing sample data for model training can be described as follows: First, the parameters of the closed-loop system transfer function are set and initialized, and the wingspan deformation rate is selected They are =0.1, =0.3, =0.6, =0.9, representing four different fault conditions (one normal state and three different fault conditions). Take the value to get four different state matrices ,use Function to calculate the state feedback gain and obtain different state feedback gain matrices , , , , so that the poles of the closed-loop system are located at the preset positions .

[0040] After that, initialize the state variables and input variables , and added random noise to the initial state vector to simulate the uncertainty in the actual system. Then, the experiment used a loop iteration method to continuously update the state vector , to simulate the dynamic behavior of the aircraft. In order to fully test the system performance, 50 simulation experiments were defined, and in each simulation, the data was saved every 20 steps. Finally, all simulation data were saved to a file. Since each simulation generates 500 lines of data, after 50 iterations, a total of 25,000 lines of flight simulation data were generated.

[0041] Next, the generated data set is preprocessed. After reading the flight simulation data in the file, the data set is divided into a training set and a test set, and the total number of rows in the data set and the proportion of the test set and the training set are specified. Then, in order to ensure the stability and comparability of the data, the training set and the test set are z-score standardized. This process makes the mean of the processed data 0 and the standard deviation 1, which is helpful for the training and evaluation of subsequent algorithms. After that, the experiment specifies columns 1-5 as feature columns (containing key features related to fault detection: flight speed, angle of attack, pitch angle, pitch angular velocity, and flight altitude), and the 6th column as the label column (indicating the fault status of the aircraft). Finally, the labels and features of the processed training set and test set are saved in a new Excel file.

[0042] The fault detection model is trained by the constructed sample data to obtain a variable shape aircraft fault detection model. The variable shape aircraft fault detection model is a classification model that outputs a classification result of fault or no fault.

[0043] like Figure 7 As shown, in one possible implementation, the shape-changing aircraft fault detection model is constructed based on a decision tree algorithm, that is, the decision tree algorithm model is trained by constructed sample data to obtain a shape-changing aircraft fault detection model for detecting shape-changing aircraft faults.

[0044] The training process of the decision tree algorithm model can include: Using a loop iteration method, the feature data and label data of the training set are read respectively, and they are stored in the initialized empty matrices "train_features_data" and "train_labels_data", respectively; then, using the same method, the feature data and label data of the test set are read respectively, and they are stored in the initialized empty matrices "test_features_data" and "test_labels_data", respectively.

[0045] Second, use The function builds a decision tree model for the training set. Various parameter indicators are added to the function to improve the classification accuracy of the model.

[0046] Next, the classification accuracy of the training set is calculated and the results are output. If the accuracy does not meet the experimental requirements, it will be adjusted according to the performance of the model. The parameter indicators of the function set the maximum depth of the tree "MaxNumSplits" to 100, the minimum parent node sample size "MinParentSize" to 10, the minimum number of samples for each leaf node "MinLeafSize" to 10, the splitting criterion "SplitCriterion" to take the Gini index "gdi", and "Prune" to select "on" to post-prune the tree. After the model is built, the model is learned and trained with the training set data, and the classification accuracy of the training set is calculated to ensure that the model can fit the training data more accurately. Then, the trained decision tree model is applied to the test set data, and it is classified and predicted. The classification accuracy of the normal state and the four fault states is shown in Table 1. The classification accuracy of all five states is higher than 98.5%, and the average classification accuracy of the fault state is as high as 99.8%. It fully proves that the decision tree model has excellent performance in the detection and identification of variable-length faults.

[0047] Table 1

[0048] Then, the K-fold cross-validation method was used to evaluate the model performance.

[0049] First, through loop iteration, multiple unclassified feature and label files are read one by one, and they are stacked vertically in sample order to form a feature matrix and label vector.

[0050] Next, the constructed decision tree model is The experiment defines the number of folds. 5. Use the decision tree model to train the data.

[0051] Then, the performance of the model is evaluated. The true positives ( ), false positive examples ( )、True counterexample( ) and false counterexamples ( ), and then calculate the accuracy, precision, recall, Value and other performance indicators.

[0052] Finally, use The function calculates the confusion matrix and uses The function is visualized and the classification results are added to each cell to more intuitively show the classification performance of the model. From the preprocessed data set, 5000 rows of feature data are randomly selected from each group for testing to verify whether the model can accurately diagnose each fault. The span deformation rate corresponding to the span length change command of the control system is calculated. The data sets with different expected values ​​of are input into the decision tree model respectively, and the corresponding confusion matrix is ​​obtained, as shown in Figure 8 As shown. The accuracy, precision, recall and The values ​​are shown in Table 2. It can be seen that the classification accuracy of the model is very high, the comprehensive performance is very good, it has a good prediction effect, and it can quickly and accurately detect and identify the wingspan deformation fault of the variable shape aircraft.

[0053] Table 2

[0054] In summary, in one implementation of the method provided by the present invention, through precise decision tree algorithm design, reliable system verification and comprehensive performance evaluation, after detecting that the aircraft is in a fault state, fault identification is performed on different fault states of the variable shape aircraft, and the classification accuracy of each type of fault reaches more than 98.5%. The constructed model not only has high accuracy and stability, but also provides a reliable idea and method for fault diagnosis and safety assurance of variable shape aircraft related to variable length.

[0055] Based on the above-mentioned variable shape aircraft fault detection model generation method, the present invention also provides a variable shape aircraft fault detection method, such as Fig. 9 As shown, including: S210, obtaining flight state parameters of the aircraft to be detected, and inputting the flight state parameters into a deformable aircraft fault detection model; S220, obtaining a fault detection result output by a fault detection model for a deformable shape aircraft; The shape-changing aircraft fault detection model is generated based on the shape-changing aircraft fault detection model generation method provided by the present invention.

[0056] The following is a description of the deformable shape aircraft fault detection model generation device provided by the present invention. The deformable shape aircraft fault detection model generation device described below and the deformable shape aircraft fault detection model generation method described above can be referred to each other. Fig.10 As shown, the deformable aircraft fault detection model generation device provided by the present invention includes: The controller determination module 1010 is used to obtain the state control feedback matrix corresponding to each wingspan change rate based on each wingspan change rate, the initial value of the aircraft state variable and the preset flight linear change parameter model of the shape-changing aircraft; The simulation module 1020 is used to generate flight simulation data based on the data to be simulated, wherein the data to be simulated includes the initial value of the aircraft state variable, the wingspan change rate and the state control feedback matrix, and each set of flight simulation data includes flight state parameters at multiple moments; The data set generation module 1030 is used to generate sample data based on the flight simulation data, wherein the sample data includes the flight simulation data and a fault label corresponding to the flight simulation data, and when the wingspan change rate corresponding to the state control feedback matrix included in the flight simulation data is inconsistent with the wingspan change rate included in the flight simulation data, the fault label is a fault, and when the wingspan change rate corresponding to the state control feedback matrix included in the flight simulation data is consistent with the wingspan change rate included in the flight simulation data, the fault label is a no-fault; The training module 1040 is used to obtain a deformable aircraft fault detection model through training based on multiple groups of sample data.

[0057] Fig.11 An example of a physical structure diagram of an electronic device is shown in FIG. Fig.11As shown, the electronic device may include: a processor (processor) 1110 , a communication interface (Communications Interface) 1120 , a memory (memory) 1130 and a communication bus 1140 , wherein the processor 1110 , the communication interface 1120 , and the memory 1130 communicate with each other via the communication bus 1140 . The processor 1110 can call the logic instructions in the memory 1130 to execute the variable shape aircraft fault detection model generation method and / or the variable shape aircraft fault detection method, which comprises: based on each wingspan change rate, the initial value of the aircraft state variable and the preset variable shape aircraft flight linear change parameter model, obtaining the state control feedback matrix corresponding to each wingspan change rate; generating flight simulation data based on the data to be simulated, the data to be simulated includes the initial value of the aircraft state variable, the wingspan change rate and the state control feedback matrix, and each group of flight simulation data includes flight state parameters at multiple moments; generating sample data based on the flight simulation data, the sample data includes the flight simulation data and the fault label corresponding to the flight simulation data, when the wingspan change rate corresponding to the state control feedback matrix included in the flight simulation data is inconsistent with the wingspan change rate included in the flight simulation data, the fault label is fault, when the wingspan change rate corresponding to the state control feedback matrix included in the flight simulation data is consistent with the wingspan change rate included in the flight simulation data, the fault label is no fault; training is performed based on multiple groups of sample data to obtain a variable shape aircraft fault detection model. The variable shape aircraft fault detection method includes: obtaining flight state parameters of the aircraft to be detected, and inputting the flight state parameters into a variable shape aircraft fault detection model; obtaining the fault detection result output by the variable shape aircraft fault detection model, wherein the variable shape aircraft fault detection model is generated based on the aforementioned variable shape aircraft fault detection model generation method.

[0058] In addition, the logic instructions in the above-mentioned memory 1130 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0059] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the deformable shape aircraft fault detection model generation method and / or deformable shape aircraft fault detection method provided by the above-mentioned methods. The deformable shape aircraft fault detection model generation method includes: based on each wingspan change rate, the initial value of the aircraft state variable and a preset linear change parameter model of the flight of the deformable shape aircraft, obtaining a state control feedback matrix corresponding to each wingspan change rate; generating flight simulation data based on the data to be simulated, and the data packet to be simulated The invention discloses a method for detecting a variable shape aircraft fault by training a plurality of groups of sample data. The method comprises the following steps: obtaining the flight state parameters of the aircraft to be detected, inputting the flight state parameters into the variable shape aircraft fault detection model, and obtaining the fault detection result output by the variable shape aircraft fault detection model, wherein the variable shape aircraft fault detection model is generated based on the flight simulation data, wherein the variable shape aircraft fault detection model is generated based on the aforementioned variable shape aircraft fault detection model generation method. The method comprises the following steps: obtaining the flight state parameters of the aircraft to be detected, inputting the flight state parameters into the variable shape aircraft fault detection model, and obtaining the fault detection result output by the variable shape aircraft fault detection model, wherein the variable shape aircraft fault detection model is generated based on the aforementioned variable shape aircraft fault detection model generation method.

[0060] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, it is implemented to execute the deformable shape aircraft fault detection model generation method and / or deformable shape aircraft fault detection method provided by the above-mentioned methods, and the deformable shape aircraft fault detection model generation method includes: based on each wingspan change rate, the initial value of the aircraft state variable and a preset linear change parameter model of the flight of the deformable shape aircraft, a state control feedback matrix corresponding to each wingspan change rate is obtained; based on the data to be simulated, flight simulation data is generated, and the data to be simulated includes the initial value of the aircraft state variable, the wingspan, and the flight linear change parameter model of the preset deformable shape aircraft. The invention relates to a method for generating sample data based on the flight simulation data, wherein the sample data includes the flight simulation data and the fault label corresponding to the flight simulation data. When the wingspan change rate corresponding to the state control feedback matrix included in the flight simulation data is inconsistent with the wingspan change rate included in the flight simulation data, the fault label is fault. When the wingspan change rate corresponding to the state control feedback matrix included in the flight simulation data is consistent with the wingspan change rate included in the flight simulation data, the fault label is no fault. The variable shape aircraft fault detection model is obtained by training based on multiple groups of sample data. The variable shape aircraft fault detection method comprises: obtaining the flight state parameters of the aircraft to be detected, inputting the flight state parameters into the variable shape aircraft fault detection model; obtaining the fault detection result output by the variable shape aircraft fault detection model, wherein the variable shape aircraft fault detection model is generated based on the aforementioned variable shape aircraft fault detection model generation method.

[0061] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0062] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0063] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention 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 invention.

Claims

1. A method for generating a fault detection model for a deformable aircraft, characterized in that: include: Based on each wingspan change rate, the initial value of the aircraft state variable and a preset flight linear change parameter model of the deformable aircraft, a state control feedback matrix corresponding to each wingspan change rate is obtained; Generate flight simulation data based on the data to be simulated, wherein the data to be simulated includes the initial value of the aircraft state variable, the wingspan change rate and the state control feedback matrix, and each group of the flight simulation data includes flight state parameters at multiple moments; Generate sample data based on the flight simulation data, wherein the sample data includes the flight simulation data and a fault label corresponding to the flight simulation data, when the wingspan change rate corresponding to the state control feedback matrix included in the flight simulation data is inconsistent with the wingspan change rate included in the flight simulation data, the fault label is a fault, and when the wingspan change rate corresponding to the state control feedback matrix included in the flight simulation data is consistent with the wingspan change rate included in the flight simulation data, the fault label is a no-fault; A deformable aircraft fault detection model is obtained by training based on multiple groups of sample data.

2. The method for generating a fault detection model for a deformable aircraft according to claim 1, characterized in that: The flight state parameters include flight speed, angle of attack, pitch angle, pitch angular velocity and flight altitude, and the aircraft state variables include flight speed change, angle of attack change, pitch angle change, pitch angular velocity change and flight altitude change.

3. The method for generating a fault detection model for a deformable aircraft according to claim 1, characterized in that: The flight linear variation parameter model is: ； in, , is the wingspan change rate, is the flight speed, is the state control feedback matrix, is the aircraft state variable, Indicates the interference during the flight of the aircraft. , , , is the preset fitting matrix.

4. The method for generating a fault detection model for a deformable aircraft according to claim 3, characterized in that: The fitting matrix in the flight linear variation parameter model is obtained by linearizing the nonlinear dynamic equations of each working point of the deformable aircraft in the flight envelope, and then fitting and simplifying them.

5. The method for generating a fault detection model for a deformable aircraft according to claim 1, characterized in that: The deformable aircraft fault detection model is constructed based on a decision tree algorithm.

6. A method for detecting faults in a deformable aircraft, characterized in that: include: Acquiring flight state parameters of the aircraft to be detected, and inputting the flight state parameters into a deformable aircraft fault detection model; Obtaining a fault detection result output by the deformable shape aircraft fault detection model; The deformable shape aircraft fault detection model is generated based on the deformable shape aircraft fault detection model generation method as described in any one of claims 1 to 5.

7. A device for generating a fault detection model for a deformable aircraft, characterized in that: include: A controller determination module, for obtaining a state control feedback matrix corresponding to each of the wingspan change rates based on each wingspan change rate, an initial value of an aircraft state variable, and a preset flight linear change parameter model of a shape-shifting aircraft; A simulation module, used to generate flight simulation data based on data to be simulated, wherein the data to be simulated includes initial values ​​of the aircraft state variables, the wingspan change rate, and the state control feedback matrix, and each set of the flight simulation data includes flight state parameters at multiple moments; A data set generating module, used for generating sample data based on the flight simulation data, wherein the sample data includes the flight simulation data and a fault label corresponding to the flight simulation data, when the wingspan change rate corresponding to the state control feedback matrix included in the flight simulation data is inconsistent with the wingspan change rate included in the flight simulation data, the fault label is a fault, and when the wingspan change rate corresponding to the state control feedback matrix included in the flight simulation data is consistent with the wingspan change rate included in the flight simulation data, the fault label is a no-fault; The training module is used to obtain a deformable aircraft fault detection model through training based on multiple groups of sample data.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for generating a fault detection model for a deformable aircraft as described in any one of claims 1 to 5 and / or the method for detecting a fault for a deformable aircraft as described in claim 6 are implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for generating a fault detection model for a deformable aircraft as claimed in any one of claims 1 to 5 and / or the method for detecting a fault for a deformable aircraft as claimed in claim 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for generating a fault detection model for a deformable aircraft as claimed in any one of claims 1 to 5 and / or the method for detecting a fault for a deformable aircraft as claimed in claim 6 are implemented.

Images