Cross-domain variable configuration high-speed aircraft adaptive attitude control method and system based on neural network identification, and storage medium

Abstract

The invention discloses a cross-domain variable configuration high-speed aircraft adaptive attitude control method and system based on neural network identification, and a storage medium, relates to the technical field of aircraft control, and aims to solve the problems that in an existing method, unified parametric modeling needs to be carried out on aircraft pneumatics in advance, and parameters need to be identified; the attitude control problem caused by aerodynamic uncertainty cannot be solved under the condition that the aerodynamic parameter model of the cross-domain variable-configuration high-speed aircraft is completely unknown. A three-channel neural network model is constructed and comprises a pitching channel neural network model, a yawing channel neural network model and a rolling channel neural network model; a loss function is constructed based on the influence sensitivity weighting of the rudder deviation error on the attitude change, and a three-channel rudder deviation solver neural network model is obtained through training; and an online transfer learning sample library is constructed for online transfer learning, aerodynamic torque is solved based on a backstepping method controller, and finally a yaw instruction is obtained through solving.

Description

Technical Field

[0001] The present invention relates to the field of aircraft control technology, and in particular to a method, system and storage medium for adaptive attitude control of a cross-domain variable-configuration high-speed aircraft based on neural network identification. Background Art

[0002] In recent years, the demand for repeatable round-trip transportation between the earth and the sky across large airspaces and wide speed ranges has grown rapidly. Cross-domain variable-configuration high-speed aircraft can adjust its configuration according to different mission requirements and flight environments with its shape-changing ability to achieve the optimal aerodynamic shape throughout the entire flight process. In the flight mission of wide-domain variable-configuration aircraft, how to achieve aircraft attitude control in a wide-domain high-speed environment is a key issue. However, while variable-configuration hypersonic aircraft have a larger flight envelope and stronger maneuverability, configuration changes also bring great uncertainty to their aerodynamic models, posing challenges to the design of controllers. Therefore, it is very meaningful to develop an adaptive control method based on aerodynamic identification.

[0003] At present, the commonly used aircraft aerodynamic parameter identification methods are mainly divided into two categories: model-driven and data-driven. Traditional aircraft parameter identification methods, such as least squares method and Kalman filtering, need to establish an aerodynamic model of the aircraft, and compare the predicted value of the aerodynamic data based on the aerodynamic model with the actual value based on the appropriate iterative initial value, so as to iteratively optimize the aerodynamic parameters. The data-driven parameter identification method simulates the input-output relationship of the aircraft aerodynamics through a neural network, and extracts aerodynamic parameters from the neural network through back propagation. These two methods are only different in technical means. In essence, they both require the aerodynamics of the aircraft to be parameterized in advance, so as to identify the parameters using flight data. However, due to the multiple effects of cross-domain, high speed and variable configuration, it is difficult to uniformly parameterize the aerodynamic model of the aircraft. Therefore, there is an urgent need for an adaptive attitude control method for cross-domain variable configuration high-speed aircraft when the aerodynamic parameter model is completely unknown. Summary of the invention

[0004] The technical problems to be solved by the present invention are:

[0005] The existing methods require unified parameterized modeling of the aircraft aerodynamics in advance and identification of the parameters; they are unable to solve the attitude control problem caused by aerodynamic uncertainty when the aerodynamic parameter model of a cross-domain variable-configuration high-speed aircraft is completely unknown.

[0006] The present invention adopts the following technical solutions to solve the above technical problems:

[0007] The present invention provides a cross-domain variable configuration high-speed aircraft adaptive attitude control method based on neural network identification, comprising the following steps:

[0008] Step 1: Collect wind tunnel test and historical flight data of cross-domain variable configuration high-speed aircraft, segment the data, and build an offline training sample library of the three-channel aerodynamic model of the cross-domain variable configuration high-speed aircraft, including: pitch channel sample library, yaw channel sample library and roll channel sample library; preprocess the data, and divide the preprocessed data into a data set, a validation set and a test set;

[0009] Step 2: The three-channel neural network model constructed includes a pitch channel neural network model, a yaw channel neural network model and a roll channel neural network model; the three channel neural network models are trained respectively using the training set, and the loss function is constructed based on the weighted sensitivity of the influence of the rudder error on the attitude change, and the neural network is trained until the loss function converges. During the training process, the validation set is used to verify the model performance, and the three-channel rudder error solver neural network model is obtained;

[0010] Step 3: During the online flight, collect flight data and use the aircraft attitude rotation dynamics equation to build an online transfer learning sample library for the three-channel aerodynamic model of a cross-domain variable configuration high-speed aircraft;

[0011] Step 4: adopting the three-channel rudder deviation solver neural network model, based on the online transfer learning sample library of the cross-domain variable configuration high-speed aircraft three-channel aerodynamic model constructed in step 3, online transfer learning is performed at intervals of T to obtain a three-channel adaptive rudder deviation solver neural network model;

[0012] Step 5: Establish the dynamic equation of aircraft attitude rotation, design a backstepping controller to obtain aerodynamic torque, further reversely solve the torque coefficient, input the torque coefficient into the three-channel adaptive rudder yaw solver neural network model, and solve to obtain the yaw command.

[0013] Furthermore, the wind tunnel test and historical flight data of the cross-domain variable configuration high-speed aircraft in step 1 include: flight state data and aerodynamic moment coefficients, and the flight state data include angle of attack α, sideslip angle β, roll angle σ, pitch rudder deflection angle δ z 、Yaw rudder deflection angle δ y 、Rolling rudder angle δ x and the wing fold angle δ f ; Aerodynamic moment coefficients include: pitch moment coefficient C mz , Yaw moment coefficient C my and rolling moment coefficient C mx ;

[0014] The data is segmented to construct an offline training sample library of a three-channel aerodynamic model of a cross-domain variable-configuration high-speed aircraft, including: a pitch channel sample library [α δ f C mz δ z ], yaw channel sample library [β α δf C my δ y ] and the rolling channel sample library [βα δ f C mx δ x ].

[0015] Furthermore, the data preprocessing in step 1 includes normalizing the data and cleaning abnormal data or erroneous data.

[0016] Furthermore, the three-channel neural network model in step 2 includes:

[0017] The pitch channel neural network model:

[0018] Input layer: The number of input layer nodes is 3;

[0019] Hidden layer: The hidden layer consists of 3 layers, and the neurons use Tanh function;

[0020] Output layer: The number of nodes in the output layer is 1, and a linear activation function is used;

[0021] The yaw channel neural network model and the roll channel neural network model both include:

[0022] Input layer: The number of nodes in the input layer is 4;

[0023] Hidden layer: The hidden layer of the yaw channel and the roll channel consists of 3 layers, and the neurons use the Tanh function;

[0024] Output layer: The number of nodes in the output layer is 1, and a linear activation function is used.

[0025] Furthermore, the construction process of the loss function in step 2 is:

[0026] The intervals are divided according to the different effects of the rudder error on the attitude change, and a higher weight is assigned to the sensitive interval in the loss function.

[0027] The loss function uses the mean square error (MSE):

[0028]

[0029] Among them, y i is the true value, is the predicted value, n is the number of samples;

[0030] The constructed loss function is:

[0031] L=L1+k×L2

[0032] Among them, L1 is the mean square error between the true value and the predicted value of the rudder deviation corresponding to the non-important interval, L2 is the mean square error between the true value and the predicted value of the rudder deviation corresponding to the important interval, and k is the importance weighting factor.

[0033] Furthermore, step 3 includes the following steps:

[0034] First, collect online data including the attitude angular velocity ω of the three channels of the aircraft x ,ω y ,ω z , the aircraft's angle of attack α, sideslip angle β, roll angle σ, dynamic pressure Q, pitch rudder deflection angle δ z 、Yaw rudder deviation value δ y and the rolling rudder bias δ x , folding angle δ f and the characteristic area S, characteristic lengths b and c of the aircraft;

[0035] By adjusting the attitude angular velocity ω of the three channels x ,ω y ,ω z Perform differential calculation to obtain attitude angular acceleration The real torque of the three channels is obtained by reversely solving the dynamic equation of the aircraft attitude rotation:

[0036]

[0037] Among them, M tx 、M ty 、M tz are the real moments of the roll channel, yaw channel and pitch channel respectively, and I1~I9 are the rotational inertia parameters of the aircraft;

[0038] Furthermore, the true moment coefficients of the three channels are solved inversely through the definition of the aircraft aerodynamic moment:

[0039]

[0040] After data segmentation, the online transfer learning sample library for the three-channel aerodynamic model of a cross-domain variable-configuration high-speed aircraft is obtained, including the pitch channel sample library [α δ f C mz δ z ], yaw channel sample library [β α δ f C my δ y ] and the rolling channel sample library [β α δ f C mx δ x ].

[0041] Furthermore, step 5 includes the following steps:

[0042] First, the dynamic equation of the aircraft attitude rotation is established as:

[0043]

[0044] Simplifying it to:

[0045]

[0046] Among them, x1=[α β σ] T , x2=[ω x ω y ω z ] T , the control input is u=[M x M y M z ];

[0047] Furthermore, the outer loop controller is set up, and the specific steps are as follows:

[0048] For the attitude angle equation:

[0049]

[0050] The angular tracking error is defined as:

[0051] e1=x1-x c

[0052] Then the angle tracking error change rate is:

[0053]

[0054] x 2c Treat as a virtual control quantity, select

[0055]

[0056] Where k1 is a diagonal positive definite matrix, and its form is: k1 = diag(k 11 ,k 12 ,k 13 ), x 2c is the expected angular velocity;

[0057] Furthermore, the inner loop controller is set up, and the specific steps are as follows:

[0058] For the attitude angular velocity equation:

[0059]

[0060] The angular velocity tracking error is defined as:

[0061] e2=x2-x2c

[0062] The angular velocity tracking error change rate is:

[0063]

[0064] The final output u of the backstepping controller is:

[0065]

[0066] Where k2 is a diagonal positive definite matrix, and its form is: k2 = diag(k 21 ,k 22 ,k 23 );

[0067] The final output u obtained by the backstepping controller is the required aerodynamic torque [M tx M ty M tz ], the required moment coefficients of the three channels are solved inversely through the definition of the aircraft aerodynamic moment:

[0068]

[0069] After the torque coefficient required at the current moment and the related state quantity are normalized, they are input into the three-channel adaptive rudder deviation solver neural network model completed by online migration in step 4 to obtain the rudder deviation instruction.

[0070] The present invention provides an adaptive attitude control system for a cross-domain variable-configuration high-speed aircraft based on neural network identification. The system has a program module corresponding to the steps of the method described in any one of the above technical solutions, and executes the steps in the above-mentioned adaptive attitude control method for a cross-domain variable-configuration high-speed aircraft based on neural network identification during operation.

[0071] The present invention provides a computer-readable storage medium, which stores a computer program. The computer program is configured to implement the steps in the cross-domain variable-configuration high-speed aircraft adaptive attitude control method based on neural network identification described in any one of the above-mentioned technical solutions when called by a processor.

[0072] Compared with the prior art, the present invention has the following beneficial effects:

[0073] The present invention proposes an adaptive control method based on neural network aerodynamic identification, obtains an adaptive rudder deviation solver through the neural network "offline training + online transfer learning", and introduces it into the backstepping control loop to achieve adaptive attitude control. Compared with the existing methods, it has the following advantages: 1) When the aerodynamic parameter model is completely unknown, the mapping relationship from aerodynamic torque to rudder deviation can be directly learned through the neural network to achieve the identification of the aerodynamic model; 2) By performing rudder deviation sensitivity analysis in advance, the importance weighting strategy is introduced to construct the loss function to achieve high-precision fitting; 3) Through the learning strategy of "offline training + online transfer learning", offline and online data are fully utilized to greatly reduce the online training time. 4) By changing the output of the traditional controller from rudder deviation to torque, a neural network rudder deviation solver is introduced to achieve attitude tracking control in non-nominal environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 It is a flow chart of the cross-domain variable configuration high-speed aircraft adaptive attitude control method based on neural network identification in an embodiment of the present invention;

[0075] Figure 2 Schematic diagram of a neural network for a pitch channel in an embodiment of the present invention;

[0076] Figure 3 This is a flow chart of online transfer learning sample library collection in an embodiment of the present invention;

[0077] Figure 4 is a control loop diagram of a neural network-based adaptive posture controller in an embodiment of the present invention;

[0078] Figure 5 is a neural network training loss curve in an embodiment of the present invention;

[0079] Figure 6 is a neural network steering command fitting curve diagram in an embodiment of the present invention;

[0080] Figure 7 It is a graph of the attitude angle command tracking curve, angular velocity and rudder deflection curve in an embodiment of the present invention. DETAILED DESCRIPTION

[0081] In order to enable those skilled in the art to better understand the scheme of the present invention, exemplary implementations or embodiments of the present invention will be described below in conjunction with the accompanying drawings. Obviously, the described implementations or embodiments are only implementations or embodiments of a part of the present invention, not all of them. Based on the implementations or embodiments of the present invention, all other implementations or embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present invention.

[0082] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0083] Specific implementation plan 1: Figure 1 As shown, the present invention provides a cross-domain variable configuration high-speed aircraft adaptive attitude control method based on neural network identification, comprising the following steps:

[0084] Step 1: Collect wind tunnel test and historical flight data of cross-domain variable configuration high-speed aircraft, segment the data, and build an offline training sample library of the three-channel aerodynamic model of the cross-domain variable configuration high-speed aircraft, including: pitch channel sample library, yaw channel sample library and roll channel sample library; preprocess the data, and divide the preprocessed data into a data set, a validation set and a test set;

[0085] Step 2: The three-channel neural network model constructed includes a pitch channel neural network model, a yaw channel neural network model and a roll channel neural network model; the three channel neural network models are trained respectively using the training set, and the loss function is constructed based on the weighted sensitivity of the influence of the rudder error on the attitude change, and the neural network is trained until the loss function converges. During the training process, the validation set is used to verify the model performance, and the three-channel rudder error solver neural network model is obtained;

[0086] Step 3: During the online flight, collect flight data and use the aircraft attitude rotation dynamics equation to build an online transfer learning sample library for the three-channel aerodynamic model of a cross-domain variable configuration high-speed aircraft;

[0087] Step 4: adopting the three-channel rudder deviation solver neural network model, based on the online transfer learning sample library of the cross-domain variable configuration high-speed aircraft three-channel aerodynamic model constructed in step 3, online transfer learning is performed at intervals of T to obtain a three-channel adaptive rudder deviation solver neural network model;

[0088] Step 5: Establish the dynamic equation of aircraft attitude rotation, design a backstepping controller to obtain aerodynamic torque, further reversely solve the torque coefficient, input the torque coefficient into the three-channel adaptive rudder yaw solver neural network model, and solve to obtain the yaw command.

[0089] Specific implementation plan 2: The wind tunnel test and historical flight data of the cross-domain variable configuration high-speed aircraft described in step 1 include: flight status data and aerodynamic moment coefficients, and the flight status data include angle of attack α, sideslip angle β, roll angle σ, pitch rudder deflection angle δ z 、Yaw rudder deflection angle δ y 、Rolling rudder angle δ x and the wing fold angle δ f ; Aerodynamic moment coefficients include: pitch moment coefficient C mz , Yaw moment coefficient Cmy and rolling moment coefficient C mx ;

[0090] The data is segmented to construct an offline training sample library of a three-channel aerodynamic model of a cross-domain variable-configuration high-speed aircraft, including: a pitch channel sample library [α δ f C mz δ z ], yaw channel sample library [β α δ f C my δ y ] and the rolling channel sample library [βα δ f C mx δ x ]. The rest of this embodiment is the same as the specific embodiment one.

[0091] Specific implementation plan three: The data preprocessing described in step 1 includes normalizing the data, dividing all data by the absolute value of the maximum value, thereby scaling the data range to a fixed interval [-1,1]. This helps to improve the training efficiency of the neural network and prevent the model from converging too slowly or causing gradient explosion / disappearance due to inconsistent data dimensions. The normalization formula is as follows:

[0092]

[0093] Since there may be sensor failures in the wind tunnel data and aircraft historical data collection process, abnormal data or erroneous data are cleaned to ensure data quality. The rest of this implementation plan is the same as the specific implementation plan 2.

[0094] Specific implementation plan 4: Figure 2 As shown, the three-channel neural network model in step 2 includes:

[0095] The pitch channel neural network model:

[0096] Input layer: The number of nodes in the input layer is 3, including the normalized attack angle α and folding angle δ f and the pitching moment coefficient C mz ;

[0097] Hidden layer: The hidden layer consists of 3 layers, with 264, 128 and 64 neurons in each layer respectively. Since the input of the neural network is limited to the interval [-1,1] during the normalization process, the neurons use the Tanh function, and its output range is exactly between -1 and 1, which is consistent with the input and output data range after normalization, which can reduce the numerical offset during model training and promote the propagation and optimization of gradients;

[0098] Output layer: The number of nodes in the output layer is 1, which indicates the aircraft at the angle of attack α and the folding angle δ. f In order to provide the pitch moment coefficient C mz The corresponding pitch rudder deflection value δ z , the output layer uses a linear activation function;

[0099] The yaw channel neural network model and the roll channel neural network model both include:

[0100] Input layer: The number of nodes in the input layer is 4. The input of the yaw channel includes the normalized sideslip angle β, angle of attack α, and folding angle δ. f and the yaw moment coefficient C my ; The input of the roll channel includes the normalized sideslip angle β, attack angle α, and folding angle δ f and rolling moment coefficient C mx ;

[0101] Hidden layer: The hidden layer of the yaw channel and the roll channel consists of 3 layers, and the neurons use the Tanh function;

[0102] Output layer: The number of nodes in the output layer is 1. The output layer of the yaw channel represents the sideslip angle β, attack angle α, and folding angle δ of the aircraft. f In order to provide the yaw moment coefficient C my The corresponding yaw rudder deviation value δ y The output layer of the roll channel represents the sideslip angle β, angle of attack α, and folding angle δ of the aircraft. f In order to provide the rolling moment coefficient C mx The corresponding roll rudder deflection value δ x , the output layer uses a linear activation function. The rest of this implementation is the same as the specific implementation plan three.

[0103] Specific implementation plan 5: Step 2 The process of constructing the loss function is:

[0104] In the process of aircraft attitude tracking, the influence of rudder error on attitude change has obvious interval differences. In different stages of attitude change, the influence of rudder error on attitude change is different, especially in certain specific rudder ranges, its influence on attitude control is more significant. In order to further improve the training accuracy of the neural network, it is necessary to analyze these intervals, and by assigning higher weights to the intervals where the rudder error is more sensitive, the network can fit better in these intervals, thereby improving the overall control performance.

[0105] First, the sensitivity analysis of the rudder error is carried out: During the attitude tracking process of the aircraft, the influence of the rudder error varies depending on the aircraft state and control strategy. In the attitude change stage, the deflection range of the rudder is large (for example, -20 to 20 degrees). At this time, the influence of a 0.1-degree rudder error on the attitude change is small. However, in the attitude holding stage, the deflection range of the rudder is usually small. For example, when the angle of attack of the pitch channel tracks a fixed angle of attack between 0 and 10 degrees, the rudder change range is only about -1 to -3 degrees. At this time, a 0.1-degree rudder error may cause an angle of attack tracking error of about 0.5 degrees, and the impact cannot be ignored. Therefore, the interval is divided according to the different effects of the rudder error on the attitude change, and a higher weight is assigned to the sensitive interval in the loss function.

[0106] Furthermore, based on the above sensitivity analysis, the loss function is constructed based on the importance weighting idea to ensure that the fitting accuracy in the sensitive range of rudder error is improved. The loss function uses the mean square error (MSE). The loss function is defined as the mean of the square of the difference between the predicted value and the true value, and the optimization goal is to minimize this loss function.

[0107]

[0108] Among them, y i is the true value, is the predicted value, n is the number of samples;

[0109] The constructed loss function is:

[0110] L=L1+k×L2

[0111] Among them, L1 is the mean square error between the true value and the predicted value of the rudder deviation corresponding to the non-important interval ([-20°, 20°]), L2 is the mean square error between the true value and the predicted value of the rudder deviation corresponding to the important interval, and k is the importance weighting factor.

[0112] The important interval of the pitch channel neural network loss function is [-4°, 0°], and the important interval of the yaw channel and roll channel neural network loss function is [-2°, 2°]. The importance weighting factor k is 10.

[0113] Furthermore, a gradient descent method (such as the Adam optimizer) is used to minimize the loss function. The Adam optimizer can adaptively adjust the learning rate, usually accelerates convergence, and works better when processing large-scale data. Stop training when the loss function no longer decreases significantly.

[0114] The entire training process is:

[0115] Use the training set data for forward propagation and calculate the steering deviation prediction values ​​of the three channels respectively.

[0116] The error between the predicted rudder deviation and the true rudder deviation is calculated using the importance-weighted loss function.

[0117] The gradient is calculated using the back-propagation algorithm, and the weights of the three-channel neural network are updated separately through the optimization algorithm.

[0118] After each round of iteration, the validation set is used to evaluate the generalization ability of the model to avoid overfitting.

[0119] The early stopping method is selected to avoid overfitting during the training process. When the error of the validation set does not improve significantly within a certain iteration cycle, the training is terminated in advance to obtain a three-channel rudder deviation solver neural network model completed with offline training. The rest of this implementation plan is the same as the specific implementation plan four.

[0120] Specific implementation plan six: Figure 3 As shown, the specific steps of step 3 are as follows:

[0121] During the online flight, data such as vehicle speed, attitude change angular velocity, attitude angle, rudder deflection, deformation, etc. are collected, and the vehicle attitude rotation dynamics are used to construct an online transfer learning sample library for the three-channel aerodynamic model of a cross-domain variable configuration high-speed aircraft.

[0122] First, collect online data including the attitude angular velocity ω of the three channels of the aircraft x ,ω y ,ω z , the aircraft's angle of attack α, sideslip angle β, roll angle σ, dynamic pressure Q, pitch rudder deflection angle δ z 、Yaw rudder deviation value δ y and the rolling rudder bias δ x , folding angle δ f and the characteristic area S, characteristic lengths b and c of the aircraft;

[0123] By adjusting the attitude angular velocity ω of the three channels x ,ω y ,ω z Perform differential calculation to obtain attitude angular acceleration The real torque of the three channels is obtained by reversely solving the dynamic equation of the aircraft attitude rotation:

[0124]

[0125] Among them, M tx 、M ty 、M tz are the real moments of the roll channel, yaw channel and pitch channel respectively, and I1~I9 are the rotational inertia parameters of the aircraft;

[0126] Furthermore, the true moment coefficients of the three channels are solved inversely through the definition of the aircraft aerodynamic moment:

[0127]

[0128] After data segmentation, the online transfer learning sample library for the three-channel aerodynamic model of a cross-domain variable-configuration high-speed aircraft is obtained, including the pitch channel sample library [α δ f C mz δ z ], yaw channel sample library [β α δ f C my δ y ] and the rolling channel sample library [β α δ f C mx δ x ]. The rest of this implementation plan is the same as the specific implementation plan five.

[0129] Specific implementation plan seven: Figure 4 As shown, step 5 includes the following steps:

[0130] First, the dynamic equation of the aircraft attitude rotation is established as:

[0131]

[0132] Simplifying it to:

[0133]

[0134] Among them, x1=[α β σ] T , x2=[ω x ω y ω z ] T , the control input is u=[M x M y M z ];

[0135] Furthermore, the outer loop controller is set up, and the specific steps are as follows:

[0136] For the attitude angle equation:

[0137]

[0138] The angular tracking error is defined as:

[0139] e1=x1-x c

[0140] Then the angle tracking error change rate is:

[0141]

[0142] x 2c Treat as a virtual control quantity, select

[0143]

[0144] Where k1 is a diagonal positive definite matrix, and its form is: k1 = diag(k 11 ,k 12 ,k 13 ), x 2c is the expected angular velocity;

[0145] Furthermore, the inner loop controller is set up, and the specific steps are as follows:

[0146] For the attitude angular velocity equation:

[0147]

[0148] The angular velocity tracking error is defined as:

[0149] e2=x2-x2c

[0150] The angular velocity tracking error change rate is:

[0151]

[0152] The final output u of the backstepping controller is:

[0153]

[0154] Where k2 is a diagonal positive definite matrix, and its form is: k2 = diag(k 21 ,k 22 ,k 23 );

[0155] The final output u obtained by the backstepping controller is the required aerodynamic torque [M tx M ty M tz ], the required moment coefficients of the three channels are solved inversely through the definition of the aircraft aerodynamic moment:

[0156]

[0157] After normalizing the torque coefficient and related state quantity required at the current moment, they are input into the three-channel adaptive rudder deviation solver neural network model completed by online migration in step 4 according to a fixed format, and the rudder deviation instruction is obtained. The rest of this implementation scheme is the same as the specific implementation scheme six.

[0158] The present invention proposes a cross-domain variable-configuration high-speed aircraft adaptive attitude control method (algorithm) based on neural network identification, which is the underlying technical core of the present invention. Various products can be derived based on the algorithm.

[0159] Based on the method proposed in the present invention, a cross-domain variable configuration high-speed aircraft adaptive attitude control system based on neural network identification is developed using a programming language. The system has program modules corresponding to the steps of the above-mentioned technical solution, and executes the steps in the above-mentioned cross-domain variable configuration high-speed aircraft adaptive attitude control method based on neural network identification during operation.

[0160] The computer program of the developed system (software) is stored on a computer-readable storage medium, and the computer program is configured to implement the steps of the above-mentioned cross-domain variable configuration high-speed aircraft adaptive attitude control method based on neural network identification when called by a processor. That is, the present invention is materialized on a carrier to become a computer program product.

[0161] Various implementations of the systems and techniques described herein can be realized in digital electronic circuit systems, integrated circuit systems, dedicated ASICs (application specific integrated circuits), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0162] The computer programs (also referred to as programs, software, software applications, or codes) of the present invention include machine instructions for programmable processors, and these computer programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, device, and / or device (e.g., disk, optical disk, memory, programmable logic device PLD) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as machine-readable signals. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0163] The beneficial effects of the present invention are verified by the following examples.

[0164] Example 1

[0165] This embodiment is based on the method of the above implementation scheme, and uses a digital model of a foldable cross-domain variable-configuration high-speed aircraft for simulation verification.

[0166] In this embodiment, the aircraft is first used to conduct flight experiments under nominal conditions, and the collected data is regarded as wind tunnel data and historical flight data, so as to construct an offline training sample library of the three-channel aerodynamic model of a cross-domain variable configuration high-speed aircraft. The three-channel neural network model is built using the method described in step 2 of the above content, and the loss function is constructed using the importance weighting idea. The neural network is trained until the loss function converges. The convergence diagram of the loss function is shown in the figure below. Figure 5 , we get the three-channel rudder deviation solver after offline training, and the rudder deviation command fitting curve is as follows: Figure 6 . Then, before the start of the online simulation, the aerodynamic parameters of the aircraft are randomly deflected by 25% to simulate the uncertainty brought to the aerodynamic model due to wide range, high speed and configuration changes. Subsequently, the flight altitude of 40km, the flight speed of 3000km / s, the initial angle of attack of 0°, and the tracking angle of attack instruction of 10° are selected for simulation under backstepping control without aerodynamic identification. At the same time, online flight data is collected to perform online transfer learning on the basis of the three-channel rudder deviation solver trained offline to obtain a more accurate rudder deviation solver. At the 3rd second, it is introduced into the backstepping control loop for attitude control. From the simulation results Figure 7 It can be seen that the adaptive attitude control method of the present invention can enable a cross-domain variable-configuration high-speed aircraft to achieve attitude tracking control with aerodynamic uncertainty when the aerodynamic model is completely unknown.

[0167] Although the present invention is disclosed as above, the protection scope of the present invention is not limited thereto. Those skilled in the art may make various changes and modifications without departing from the spirit and scope of the present invention, and these changes and modifications will fall within the protection scope of the present invention.

Claims

1. A cross-domain variable configuration high-speed aircraft adaptive attitude control method based on neural network identification, characterized in that: The following steps are involved: Step 1: Collect wind tunnel test and historical flight data of cross-domain variable configuration high-speed aircraft, segment the data, and build an offline training sample library of the three-channel aerodynamic model of the cross-domain variable configuration high-speed aircraft, including: pitch channel sample library, yaw channel sample library and roll channel sample library; preprocess the data, and divide the preprocessed data into a data set, a validation set and a test set; Step 2: The three-channel neural network model constructed includes a pitch channel neural network model, a yaw channel neural network model and a roll channel neural network model; the three channel neural network models are trained respectively using the training set, and the loss function is constructed based on the weighted sensitivity of the influence of the rudder error on the attitude change, and the neural network is trained until the loss function converges. During the training process, the validation set is used to verify the model performance, and the three-channel rudder error solver neural network model is obtained; Step 3: During the online flight, collect flight data and use the aircraft attitude rotation dynamics equation to build an online transfer learning sample library for the three-channel aerodynamic model of a cross-domain variable configuration high-speed aircraft; Step 4: adopting the three-channel rudder deviation solver neural network model, based on the online transfer learning sample library of the cross-domain variable configuration high-speed aircraft three-channel aerodynamic model constructed in step 3, online transfer learning is performed at intervals of T to obtain a three-channel adaptive rudder deviation solver neural network model; Step 5: Establish the dynamic equation of aircraft attitude rotation, design a backstepping controller to obtain aerodynamic torque, further reversely solve the torque coefficient, input the torque coefficient into the three-channel adaptive rudder yaw solver neural network model, and solve to obtain the yaw command.

2. The cross-domain variable configuration high-speed aircraft adaptive attitude control method based on neural network identification according to claim 1 is characterized in that: The wind tunnel test and historical flight data of the cross-domain variable configuration high-speed aircraft described in step 1 include: flight status data and aerodynamic moment coefficients. The flight status data include angle of attack α, sideslip angle β, roll angle σ, pitch rudder deflection angle δ z 、Yaw rudder deflection angle δ y 、Rolling rudder angle δ x and the wing fold angle δ f ; Aerodynamic moment coefficients include: pitch moment coefficient C mz , Yaw moment coefficient C my and rolling moment coefficient C mx ; The data is segmented to construct an offline training sample library of a three-channel aerodynamic model of a cross-domain variable-configuration high-speed aircraft, including: a pitch channel sample library [α δ f C mz δ z ], yaw channel sample library [β α δ f C my δ y ] and the rolling channel sample library [β α δ f C mx δ x ].

3. The cross-domain variable configuration high-speed aircraft adaptive attitude control method based on neural network identification according to claim 2 is characterized in that: The data preprocessing described in step 1 includes normalizing the data and cleaning the data of abnormal data or erroneous data.

4. The cross-domain variable configuration high-speed aircraft adaptive attitude control method based on neural network identification according to claim 3 is characterized in that: The three-channel neural network model described in step 2 includes: The pitch channel neural network model: Input layer: The number of input layer nodes is 3; Hidden layer: The hidden layer consists of 3 layers, and the neurons use Tanh function; Output layer: The number of nodes in the output layer is 1, and a linear activation function is used; The yaw channel neural network model and the roll channel neural network model both include: Input layer: The number of nodes in the input layer is 4; Hidden layer: The hidden layer of the yaw channel and the roll channel consists of 3 layers, and the neurons use the Tanh function; Output layer: The number of nodes in the output layer is 1, and a linear activation function is used.

5. The cross-domain variable configuration high-speed aircraft adaptive attitude control method based on neural network identification according to claim 4 is characterized in that: The construction process of step 2 loss function is: The intervals are divided according to the different effects of the rudder error on the attitude change, and a higher weight is assigned to the sensitive interval in the loss function. The loss function uses the mean square error (MSE): Among them, y i is the true value, is the predicted value, n is the number of samples; The constructed loss function is: L=L1+k×L2 Among them, L1 is the mean square error between the true value and the predicted value of the rudder deviation corresponding to the non-important interval, L2 is the mean square error between the true value and the predicted value of the rudder deviation corresponding to the important interval, and k is the importance weighting factor.

6. The cross-domain variable configuration high-speed aircraft adaptive attitude control method based on neural network identification according to claim 5 is characterized in that: Step 3 includes the following steps: First, collect online data including the attitude angular velocity ω of the three channels of the aircraft x ,ω y ,ω z , the aircraft's angle of attack α, sideslip angle β, roll angle σ, dynamic pressure Q, pitch rudder deflection angle δ z 、Yaw rudder deviation value δ y and the rolling rudder bias δ x , folding angle δ f and the characteristic area S, characteristic lengths b and c of the aircraft; By adjusting the attitude angular velocity ω of the three channels x ,ω y ,ω z Perform differential calculation to obtain attitude angular acceleration The real torque of the three channels is obtained by reversely solving the dynamic equation of the aircraft attitude rotation: Among them, M tx 、M ty 、M tz are the real moments of the roll channel, yaw channel and pitch channel respectively, and I1~I9 are the rotational inertia parameters of the aircraft; Furthermore, the true moment coefficients of the three channels are solved inversely through the definition of the aircraft aerodynamic moment: After data segmentation, the online transfer learning sample library for the three-channel aerodynamic model of a cross-domain variable-configuration high-speed aircraft is obtained, including the pitch channel sample library [α δ f C mz δ z ], yaw channel sample library [β α δ f C my δ y ] and the rolling channel sample library [β α δ f C mx δ x ].

7. The cross-domain variable configuration high-speed aircraft adaptive attitude control method based on neural network identification according to claim 6 is characterized in that: Step 5 includes the following steps: First, the dynamic equation of the aircraft attitude rotation is established as: Simplifying it to: Among them, x1=[α β σ] T , x2=[ω x ω y ω z ] T , the control input is u=[M x M y M z ]; Furthermore, the outer loop controller is set up, and the specific steps are as follows: For the attitude angle equation: The angular tracking error is defined as: e1=x1-x c Then the angle tracking error change rate is: x 2c Treat as a virtual control quantity, select Where k1 is a diagonal positive definite matrix, and its form is: k1 = diag(k 11 ,k 12 ,k 13 ), x 2c is the expected angular velocity; Furthermore, the inner loop controller is set up, and the specific steps are as follows: For the attitude angular velocity equation: The angular velocity tracking error is defined as: e2=x2-x2c Then the angular velocity tracking error change rate is: The final output u of the backstepping controller is: Where k2 is a diagonal positive definite matrix, and its form is: k2 = diag(k 21 ,k 22 ,k 23 ); The final output u obtained by the backstepping controller is the required aerodynamic torque [M tx M ty M tz ], the required moment coefficients of the three channels are solved inversely through the definition of the aircraft aerodynamic moment: After the torque coefficient required at the current moment and the related state quantity are normalized, they are input into the three-channel adaptive rudder deviation solver neural network model completed by online migration in step 4 to obtain the rudder deviation instruction.

8. A cross-domain variable configuration high-speed aircraft adaptive attitude control system based on neural network identification, characterized in that: The system has a program module corresponding to the steps of the method described in any one of claims 1 to 7, and executes the steps of the cross-domain variable configuration high-speed aircraft adaptive attitude control method based on neural network identification when running.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is configured to implement the steps in the cross-domain variable-configuration high-speed aircraft adaptive attitude control method based on neural network identification according to any one of claims 1 to 7 when called by a processor.

Images