Intelligent control method for hypersonic flight vehicle driven by coupling information

Abstract

The invention belongs to the technical field of hypersonic flight vehicle control, and relates to an intelligent control method for a hypersonic flight vehicle driven by coupling information. Firstly, a longitudinal dynamic model of the elastic hypersonic aircraft is established; then, a coupling database based on sampling analysis is constructed, different flight envelope data are simulated, a coupling degree matrix is calculated through a sampling statistical algorithm, and the coupling database is formed to quantify the mutual influence between variables; furthermore, deep neural network training driven by coupling data is carried out, a long-short term memory network is adopted, and a coupling database is used as a data sample to carry out offline training, so that the autonomous fine control capability of the aircraft in a strong coupling environment is improved. And finally, designing an online controller to realize a coupling information intelligent compensation scheme, dividing aircraft maneuvering control into a speed loop and an attitude loop, and designing a corresponding control instruction and a neural network updating law to realize real-time and intelligent flight control.

Description

Technical Field

[0001] The present invention belongs to the technical field of hypersonic aircraft control, and relates to a coupled information driven hypersonic aircraft intelligent control method. Background Art

[0002] Hypersonic vehicles use combined power as a propulsion system to achieve wide-range high performance, which leads to strong cross-coupling of the airframe, power mode, trajectory, guidance and attitude control, and extremely complex characteristics, which brings great challenges to the design and control of the control system. On the one hand, it is difficult to fully consider the coupling of the aircraft modeling, and it is difficult to obtain an accurate aircraft system coupling model, which requires a comprehensive and in-depth understanding of the coupling mechanism of hypersonic aircraft. On the other hand, the aircraft system exhibits strong coupling and strong nonlinear characteristics, which requires more serious coupling effects to be considered in the control process, and it is necessary to further achieve high-precision control under complex and uncertain and comprehensive performance requirements. Therefore, it is necessary to study the coupling characteristics of hypersonic aircraft under the stacking of various physical fields, and design controllers based on the consideration of coupling to improve flight quality.

[0003] Traditional control designs use decoupling or ignore coupling, resulting in multiple cases of loss of control and failure, which further demonstrates that the above schemes cannot meet the performance requirements of higher speeds and wider envelopes for hypersonic vehicles. Although there have been many research results on the control system design of hypersonic vehicles, the impact of coupling analysis on control performance is often ignored. Coupling analysis aims to reveal the dynamic relationship between the stacking of multiple physical fields and the laws of their mutual influence. Therefore, it is necessary to design a hypersonic vehicle control system that fully utilizes coupling analysis to greatly reduce the control requirements of actuators and effectively improve the control efficiency and dynamic performance of the control system. This method aims to promote the development of hypersonic vehicle technology towards higher reliability and better stability.

[0004] Wang Yuhui, Zhen Wubin, Ying Junqi, etc. proposed a method for hypersonic aircraft attitude coordination control based on coupling analysis in "Hypersonic aircraft attitude coordination control method based on coupling analysis" (CN 107085435 A), which can effectively enhance the controllability and maneuverability of the aircraft. However, compared with the coupling data-driven analysis method, this method assumes that the coupling relationship is a static constant throughout the flight mission, while in fact the coupling characteristic is a dynamic process throughout the flight mission, and does not fully reveal the coupling relationship between variables, which is not conducive to improving flight quality.

[0005] Wang Zhi, Dong Wenqiang, Yang Ming, Gong Yulian, and Li Maomao proposed a hypersonic aircraft attitude coupling control method in "Hypersonic Aircraft Attitude Coupling Control Method" (CN110609564 A), which improved the rapidity of the aircraft's roll maneuver response. However, compared with the coupling data-driven analysis method, this method relies on a simplified model of motion coupling analysis, lacks a systematic analysis of attitude coupling, and does not combine coupling with controller design, which may affect the performance of the control system.

[0006] Feng Xingkai, Wang Yuhui, Qin Xu, etc. proposed a method for coordinated control of hypersonic aircraft based on dynamic coupling analysis in "Attitude coordination control of hypersonic aircraft based on dynamic equations" (see Journal of Jilin University, March 2018, Vol. 36, No. 2, pp. 133-141), which comprehensively and objectively reflects the coupling situation under actual flight conditions. However, the steps of this method are relatively cumbersome in the design process. For complex systems, the dynamic equations may be very complex and difficult to establish and solve. Compared with the use of neural networks for The coupling database obtained by training with flight envelope data and the coupling matrix calculated by the dynamic equations in a single flight mission are insufficient to cope with the changes of hypersonic aircraft, and lack real-time analysis and feedback of data-driven decision-making.

[0007] Shou Yingxin and Han Xudong proposed a channel coupling coordinated robust adaptive control algorithm in "Channel coupling coordinated robust adaptive control algorithm for hypersonic vehicles" (see "Science China", September 2024, Vol. 54, No. 10, pp. 2308-2325). Through composite learning and RISE technology, the dynamic performance and steady-state error of the system have been greatly improved. However, compared with the long short-term memory network (LSTM), this method cannot better capture the long-term dependencies in the data and the patterns and features in the time series data, and the pressure of adjusting the control parameters is too high, and the dependence on the model is high.

[0008] Most of the existing coupling analysis technologies rely on prior assumptions and preset theoretical models, which makes it difficult to comprehensively analyze the nonlinearity and dynamic coupling in the system, resulting in inflexible and poor adaptability of control strategies in practical applications. In addition, coupling characteristic analysis has always been an open-loop analysis method, which is difficult to combine with a closed-loop controller, especially when facing uncertain systems. This may cause the control system to be unstable in actual operation and produce large jitter. In the current technological development trend, data-driven and intelligent learning technologies (such as machine learning and artificial intelligence) play an important role in improving the performance and adaptability of the system. The LSTM deep neural network based on coupling data drive can better capture the long-term dependencies in the data, learn the patterns and features in the data, and organize the potential coupling modes by processing a large number of coupling databases, using the gating mechanism and its own good memory performance. In addition, combining deep neural network coupling analysis with intelligent control can enhance the robustness of the system and ensure the flight performance of the aircraft in various complex environments. Summary of the invention

[0009] Aiming at the control problem of strongly coupled hypersonic aircraft, the present invention proposes a coupling information driven hypersonic aircraft intelligent control method. First, a longitudinal dynamics model of elastic hypersonic aircraft is established, integrating rigid body, aerodynamic, structural elasticity and thrust coupling models to comprehensively describe the dynamic characteristics of the aircraft. Next, a coupling database based on sampling analysis is constructed. By simulating different flight envelope data, the coupling degree matrix is ​​calculated using a sampling statistical algorithm to form a coupling database to quantify the mutual influence between variables. Further, coupled data driven deep neural network training is carried out, and a long short-term memory network is adopted. The coupling database is used as a data sample for offline training to improve the autonomous fine control capability of the aircraft in a strongly coupled environment. Finally, an online controller is designed to implement the coupling information intelligent compensation scheme, and the aircraft maneuvering control is divided into a speed loop and an attitude loop. The corresponding control instructions and neural network update law are designed to realize real-time and intelligent flight control. Through this coupling information driven hypersonic aircraft intelligent control method, not only can the control accuracy and stability of the aircraft be improved, but also its autonomous adaptability and survivability can be enhanced, which provides strong technical support for the research and development and application of hypersonic aircraft.

[0010] The technical solution of the present invention is as follows:

[0011] A coupled information driven hypersonic vehicle intelligent control method is as follows:

[0012] Step (1) Construction of longitudinal dynamics model of elastic hypersonic vehicle

[0013] Based on the rigid body mathematical model, aerodynamic coupling model, structural elastic coupling model and thrust coupling model, the longitudinal dynamics model of elastic hypersonic vehicle is established:

[0014] (1)

[0015] in, is the speed of the hypersonic vehicle, is the flight altitude, is the track angle, is the pitch angle, is the pitch angular rate, is the angle of attack and satisfies . is the mass of the aircraft, is the acceleration due to gravity, For along The moment of inertia of the shaft. represents the elastic mode, represents the damping factor, represents the natural oscillation frequency, represents the generalized force, denotes the first and second order modes considered. They are thrust, lift, and drag, respectively. is the pitching moment, and the specific expression is:

[0016] (2)

[0017] in, is the dynamic pressure, is the distance from the center of mass to the center of reference moment, is the wing reference area, is the body coordinate axis system The force in the axial direction, is the mean aerodynamic chord length, is the elevator surface deflection angle; is the aileron rudder surface deflection angle; is the total lift coefficient, is the total thrust coefficient; is the total drag coefficient, and They represent the basic drag coefficient, the incremental drag coefficient caused by the elevator and the incremental drag coefficient caused by the aileron respectively; and They represent the basic lift coefficient, the lift increment coefficient caused by the elevator and the lift caused by the aileron respectively; is the total pitching moment coefficient, and They represent the basic pitching moment coefficient, the incremental pitching moment coefficient caused by the elevator and the incremental pitching moment coefficient caused by the aileron. is the incremental coefficient of the pitch moment caused by the pitch angular rate.

[0018] Total thrust coefficient The expression is as follows:

[0019] (3)

[0020] in, is the throttle opening, and represent the basic resistance coefficients respectively. hour, , ;when hour, , ; The dynamic process of the engine is a second-order system:

[0021] (4)

[0022] in, It is the control signal of the throttle opening. is the natural oscillation frequency, It is the throttle opening adjustment damping.

[0023] Step (2) Construction of coupled database based on sampling analysis and dynamic equations

[0024] Based on the longitudinal dynamics model of the elastic hypersonic vehicle constructed in the previous step, in this step, the coupled data analysis methods based on sampling analysis and dynamic equations are first given, and then a coupled database with sufficient samples is obtained based on these two methods.

[0025] 2.1) Give the construction method of the sampling analysis method database:

[0026] set up and are two mutually coupled variable groups in the system. Sampling and calculating the variables yields and ,use express right The impact quantification index is right The influence of can be expressed as

[0027] (5)

[0028] in, for right The degree of influence.

[0029] Similarly, right The influence degree can be expressed as

[0030] (6)

[0031] in, for right The degree of influence.

[0032] Furthermore, the variables in the system and The coupling degree can be expressed as

[0033] (7)

[0034] For the elastic hypersonic vehicle longitudinal dynamics model in step (1), define the state variable group and control input variable groups The coupling matrix is , trajectory variable group and posture variable group The coupling matrix is , posture variables and posture variable group The coupling matrix is , the specific expression is:

[0035] (8)

[0036] (9)

[0037] (10)

[0038] The flight position remains unchanged at the beginning and end, and the attack angle and flight speed instructions are changed to simulate the A set of flight envelope data is obtained, and then the coupling matrix is ​​calculated using a sampling statistical algorithm in each flight envelope, so that Flight envelopes Dimensional coupled database , , .

[0039] 2.2) The construction method of the dynamic equation analysis method database is given:

[0040] Consider the following nonlinear system:

[0041] (11)

[0042] in, is the state variable, is the input variable.

[0043] Based on nonlinear theory, the analysis method of dynamic equations can be expressed as follows:

[0044] For the nonlinear system shown in equation (11), the dynamic coupling matrix between the state variables is It can be defined as:

[0045] (12)

[0046] Similarly, variables With variables The dynamic coupling matrix between It can be defined as:

[0047] (13)

[0048] For the elastic hypersonic vehicle longitudinal dynamics model in step (1), define the state variable group and control input variable groups The coupling matrix is , trajectory variable group and posture variable group The coupling matrix is , posture variables and posture variable group The coupling matrix is , the specific expression is:

[0049] (14)

[0050] (15)

[0051] (16)

[0052] in, , is the state variable group Middle variables, , is the control input variable group Middle variables, . , is the trajectory variable group Middle variables, , is the posture variable group Middle variables, , , is the posture variable group Middle variables, .

[0053] The flight position remains unchanged at the beginning and end, and the attack angle and flight speed instructions are changed to simulate the Then, the coupling matrix is ​​calculated using the dynamic equation method in each flight envelope. Flight envelopes Dimensional coupled database , , .

[0054] 2.3) Construction of hybrid database based on sampling analysis and dynamic equation coupling analysis

[0055] The coupled database is obtained by sampling analysis method and dynamic equation method, and then after screening and compensation, the final result is Total coupling database of dimension , , , providing sufficient training data for the next step (3) of deep neural network training.

[0056] Step (3) Deep neural network training based on coupled data drive

[0057] This step will use the offline data of the coupling degree database of different input variables in the offline training to carry out training under the PID control framework as data samples. In the offline neural network training process, it mainly includes data set generation, training, verification and testing steps.

[0058] 3.1) Dataset generation: This step is to generate reliable and representative data that can cover the complex flight conditions and flight missions of hypersonic vehicles, that is, to generate the total coupled database in step (2). , , , thereby training a neural network prior knowledge model with high accuracy and high generalization. First, it is necessary to collect and generate a coupling degree database covering various flight conditions and flight missions, various cross-linked coupling effects, model uncertainties and multi-source disturbance effects. These data need to simulate the performance of actual aircraft in various complex environments and tasks as comprehensively as possible to ensure the adequacy and generalization ability of model training. Then simulate data generation, simulate various possible flight conditions and interference situations, and generate a large amount of training data. Specifically, first, by changing the aerodynamic and torque model parameters, data containing model errors are generated to simulate model uncertainty. Second, by simulating different environmental conditions (such as wind speed, airflow changes, etc.), external interference data is generated to simulate environmental interference. Third, by simulating different flight missions, a generalized coupling database is generated to simulate complex flight missions and conditions. Finally, the data set is divided into training set, validation set and test set in a certain distribution ratio for subsequent design verification.

[0059] 3.2) Training, verification and testing: After the data set is generated, the data is used for training under the PID control framework. The neural network used for training is the long short-term memory network (LSTM). First, the database in step (2) is divided into input data samples and target data samples. The input data samples are historical data used for model input, and the target data samples are future data to be predicted. During the training process, the model parameters, parameters in LSTM and control strategies are continuously adjusted to enable it to effectively cope with various flight missions, model uncertainties and multi-source disturbances. Each LSTM has three gate structures to control the flow of gradients, namely: forget gate, input gate and output gate.

[0060] The forget gate decides whether to keep or forget information by considering the input of the previous time step and the input of the current time step. Its calculation process is as follows:

[0061] (17)

[0062] In the formula, is the value of the forget gate, Indicates a connection operation. is the weight matrix of the forget gate, is the bias term of the forget gate, yes Input values ​​for the time grid: The total coupling matrix , select the first 80% Variable groups As input; Total coupling data of the dimension , select the first 80% Variable groups As input; Total coupling data of the dimension , select the first 80% Variable groups As input; is the output value of LSTM at the previous moment, Function The activation function is as follows:

[0063] (18)

[0064] Input gate through Activation function to calculate new memory unit candidate values , is the value of the input gate, quilt After processing, the value range is located in interval, and By multiplying each element, we can determine the candidate value of the memory cell For update , the calculation process is as follows:

[0065] (19)

[0066] (20)

[0067] Update the value of a memory cell:

[0068] (twenty one)

[0069] In the formula, and is the weight matrix, and is the bias term, is the unit state at the current moment, is the unit state at the previous moment, " means element-wise multiplication, The specific form of the function is as follows:

[0070] (twenty two)

[0071] Output gate usage The activation function determines the output. The activation function converts the value of the memory cell Mapped to a range between -1 and 1. The calculation process is as follows:

[0072] (twenty three)

[0073] (twenty four)

[0074] In the formula, is the value of the output gate, is the output of the LSTM unit, is the weight matrix, is the bias matrix.

[0075] In the LSTM forward propagation, the original data is input into the neural network, and each neuron calculates an output value based on the input data and its own weight, that is, , , , , The values ​​of the five vectors are processed by each layer of neurons and gradually passed to the next layer, and finally the prediction results of the neural network are obtained at the output layer.

[0076] The training algorithm of LSTM is the back propagation algorithm, which calculates the error term of each neuron , the direction of back propagation of the LSTM error term is: the error term propagates to the upper layer as the error input of the LSTM unit in the upper layer, and the gradient after each weight update is calculated according to the error to obtain the updated weight parameter to reduce the value of the loss function. Then, the values ​​of weights and biases are updated according to the gradient of the loss function to weights and biases, so that the loss function gradually decreases. Generally, the gradient descent method is used to update the parameters:

[0077] (25)

[0078] (26)

[0079] In the formula, is the learning rate, is the loss function, , They are Moment and Moment The weights of the layers include , , and . , They are Moment and Moment Layer bias, including , , and .

[0080] In this step, based on the effective data set, after training, verification and testing, the generated LSTM neural network covers the main features of the coupled data. The obtained LSTM neural network has the function of updating weights and biases, and will be used as a coupled neural network in the design of subsequent intelligent controllers.

[0081] Step (4) Design of intelligent controller based on coupled deep neural network

[0082] This step makes full use of the coupled neural network generated by updating weights and biases through LSTM in step (3) to design an intelligent controller. The details are as follows:

[0083] Firstly, the maneuver control model of the hypersonic vehicle is divided into a velocity loop and an attitude loop. The velocity loop is expressed as:

[0084] (27)

[0085] Where: and represents the transformed kinetic model coefficient, represents the coupling effect in the speed loop, represents the external disturbance of the speed loop, Represents the control input of the speed loop, i.e., the throttle opening. The speed reference signal is The corresponding tracking error is .

[0086] The pitch angle reference signal is defined as , the altitude of the hypersonic vehicle By pitch angle Obtained by tracking the proportional-integral-derivative (PID) algorithm In the design, the left elevon rudder surface deflection angle is considered to be equal to the right elevon rudder surface deflection angle, that is, , the attitude loop is given by:

[0087] (28)

[0088] Where: and represents the transformed kinetic model coefficient, represents the coupling effect in the attitude loop, represents the external disturbance of the attitude loop, represents the control input of the attitude loop, i.e., the elevator deflection angle, is the pitch angular velocity. The pitch angular velocity reference signal is , the tracking error of the pitch angular velocity is .

[0089] The design fuel equivalence ratio command and elevator control command are:

[0090] (29)

[0091] Where: , is the positive parameter to be designed, , , and represents the nonlinear function approximated by the neural network, and express and The projection operator is used to avoid the occurrence of singular phenomena in the fuel equivalence ratio command and the elevator control command.

[0092] Among them, the neural network update law is designed as

[0093] (30)

[0094] Where: , , , , , , , , , , , , , , , is the positive parameter to be designed.

[0095] Beneficial effects of the present invention:

[0096] The invention discloses a coupling information driven hypersonic aircraft intelligent control method, which meets the requirements of stable performance and robust performance faced by strongly coupled hypersonic aircraft when flying across airspace in a wide speed range. Compared with the traditional passive suppression coupling idea, it effectively solves the contradiction between complex uncertainty and good performance requirements. On the one hand, the difficulty of modeling coupled aircraft is fully considered, and it is difficult to obtain an accurate aircraft system coupling model. The aircraft motion equation is expressed by constructing an elastic hypersonic aircraft longitudinal dynamics model, and the coupling database is constructed based on the sampling analysis algorithm and the deep neural network training driven by coupling data is used to deeply understand the coupling mechanism of hypersonic aircraft. On the other hand, for the aircraft system showing strong coupling and strong nonlinear characteristics, an intelligent controller based on a coupled deep neural network is designed to further realize high-precision control under complex and uncertain and comprehensive performance requirements. Therefore, the designed hypersonic aircraft control system makes full use of coupling analysis, greatly reduces the actuator control requirements, reduces the dependence of traditional coupling analysis on a fixed number of sampling points, uses neural networks to realize fast iterative coupling information feedback, learns the patterns and features in the coupling database, and predicts the coupling degree matrix of any input state, effectively improving the control efficiency and dynamic performance of the control system. BRIEF DESCRIPTION OF THE DRAWINGS

[0097] Figure 1 It is the overall flow chart of the coupled information driven hypersonic vehicle intelligent control method;

[0098] Figure 2 It is a framework of coupled information-driven intelligent control methods for hypersonic vehicles;

[0099] Figure 3 is the speed tracking curve of the hypersonic vehicle;

[0100] Figure 4 is the position tracking curve of the hypersonic vehicle;

[0101] Figure 5 It is the curve of hypersonic vehicle fuel command changing with time;

[0102] Figure 6 It is the curve of the hypersonic vehicle rudder deflection command changing with time;

[0103] Figure 7 is the curve of neural network weights ω1 and ω2 changing with time;

[0104] Figure 8 It is the curve of neural network weights ω3 and ω4 changing with time. DETAILED DESCRIPTION

[0105] The following further illustrates the implementation of the present invention in conjunction with the accompanying drawings and technical solutions.

[0106] like Figure 1 and Figure 2 As shown, a coupling information driven hypersonic aircraft intelligent control method of the present invention, in this embodiment, the mass of the hypersonic aircraft is kg, and the power system adopts a scramjet engine. The specific control process is as follows:

[0107] Step (1) Construction of longitudinal dynamics model of elastic hypersonic vehicle

[0108] Based on the rigid body mathematical model, aerodynamic coupling model, structural elastic coupling model and thrust coupling model, the longitudinal dynamics model of elastic hypersonic vehicle is established:

[0109] (1)

[0110] in, is the speed of the hypersonic vehicle, is the flight altitude, is the track angle, is the pitch angle, is the pitch angular rate, is the angle of attack and satisfies . is the mass of the aircraft, is the acceleration due to gravity, For along The moment of inertia of the shaft. represents the elastic mode, represents the damping factor, represents the natural oscillation frequency, represents the generalized force, denotes the first and second order modes considered. They are thrust, lift, and drag, respectively. is the pitching moment, and the specific expression is:

[0111] (2)

[0112] in, is the dynamic pressure, is the distance from the center of mass to the center of reference moment, is the wing reference area, is the body coordinate axis system The force in the axial direction, is the mean aerodynamic chord length, is the elevator surface deflection angle; is the aileron rudder surface deflection angle; is the total lift coefficient, is the total thrust coefficient; is the total drag coefficient, and They represent the basic drag coefficient, the incremental drag coefficient caused by the elevator and the incremental drag coefficient caused by the aileron respectively; and They represent the basic lift coefficient, the lift increment coefficient caused by the elevator and the lift caused by the aileron respectively; is the total pitching moment coefficient, and They represent the basic pitching moment coefficient, the incremental pitching moment coefficient caused by the elevator and the incremental pitching moment coefficient caused by the aileron. is the incremental coefficient of the pitch moment caused by the pitch angular rate.

[0113] Total thrust coefficient The expression is as follows:

[0114] (3)

[0115] in, is the throttle opening, and represent the basic resistance coefficients respectively. hour, , ;when hour, , ; The dynamic process of the engine is a second-order system:

[0116] (4)

[0117] in, It is the control signal of the throttle opening. is the natural oscillation frequency, It is the throttle opening to adjust the damping.

[0118] Step (2) Construction of coupling database based on sampling analysis algorithm

[0119] Based on the longitudinal dynamics model of the elastic hypersonic vehicle constructed in the previous step, in this step, the coupled data analysis methods based on sampling analysis and dynamic equations are first given, and then a coupled database with sufficient samples is obtained based on these two methods.

[0120] 2.1) Provide a method for constructing a sampling analysis method database

[0121] set up and are two mutually coupled variable groups in the system. Sampling and calculating the variables yields and ,use express right The impact quantification index is right The influence of can be expressed as

[0122] (5)

[0123] in, for right The degree of influence.

[0124] Similarly, right The influence degree can be expressed as

[0125] (6)

[0126] in, for right The degree of influence.

[0127] Furthermore, the variables in the system and The coupling degree can be expressed as

[0128] (7)

[0129] For the elastic hypersonic vehicle longitudinal dynamics model in step (1), define the state variable group and control input variable groups The coupling matrix is , trajectory variable group and posture variable group The coupling matrix is , posture variables and posture variable group The coupling matrix is , the specific expression is:

[0130] (8)

[0131] (9) (10)

[0132] The flight position remains unchanged at the beginning and end, and the attack angle and flight speed instructions are changed to simulate the Ten thousand sets of flight envelope data are then used to calculate the coupling matrix in each flight envelope using sampling statistics algorithm. Thousands of flight envelopes are obtained Dimensional coupled database , , .

[0133] 2.2) The construction method of the dynamic equation analysis method database is given:

[0134] Consider the following nonlinear system:

[0135] (11)

[0136] in, is the state variable, is the input variable.

[0137] Based on nonlinear theory, the form of dynamic coupling is given as follows:

[0138] For the nonlinear system shown in equation (11), the dynamic coupling matrix between the state variables is It can be defined as:

[0139] (12)

[0140] Similarly, variables With variables The dynamic coupling matrix between can be defined as:

[0141] (13)

[0142] For the elastic hypersonic vehicle longitudinal dynamics model in step (1), define the state variable group and control input variable groups The coupling matrix is , trajectory variable group and posture variable group The coupling matrix is , posture variables and posture variable group The coupling matrix is , the specific expression is:

[0143] (14)

[0144] (15)

[0145] (16)

[0146] in, , is the state variable group Middle variables, , is the control input variable group Middle variables, . , is the trajectory variable group Middle variables, , is the posture variable group Middle variables, , , is the posture variable group Middle variables, .

[0147] The flight position remains unchanged at the beginning and end, and the attack angle and flight speed instructions are changed to simulate the Ten thousand sets of flight envelope data are then used to calculate the coupling matrix in each flight envelope using the dynamic equation method. Thousands of flight envelopes are obtained Dimensional coupled database , , .

[0148] 2.3) Construction of hybrid database based on sampling analysis and dynamic equation coupling analysis

[0149] The coupled database is obtained by sampling analysis method and dynamic equation method, and then after screening and compensation, the final result is Total coupling database of dimension , , , providing sufficient training data for the next step (3) of deep neural network training.

[0150] Step (3) Deep neural network training based on coupled data drive

[0151] This step will use the offline data of the coupling degree database of different input variables in the offline training to carry out training under the PID control framework as data samples. In the offline neural network training process, it mainly includes data set generation, training, verification and testing steps.

[0152] 3.1) Dataset generation: This step is to generate reliable and representative data that can cover the complex flight conditions and flight missions of hypersonic vehicles, that is, to generate the total coupled database in step (2). , , , thereby training a neural network prior knowledge model with high accuracy and high generalization. First, it is necessary to collect and generate a coupling degree database covering various flight conditions and flight missions, various cross-linked coupling effects, model uncertainties and multi-source disturbance effects. These data need to simulate the performance of actual aircraft in various complex environments and tasks as comprehensively as possible to ensure the adequacy and generalization ability of model training. Then simulate data generation, simulate various possible flight conditions and interference situations, and generate a large amount of training data. Specifically, first, by changing the aerodynamic and torque model parameters, data containing model errors are generated to simulate model uncertainty. Second, by simulating different environmental conditions (such as wind speed, airflow changes, etc.), external interference data is generated to simulate environmental interference. Third, by simulating different flight missions, a generalized coupling database is generated to simulate complex flight missions and conditions. Finally, the data set is divided into training set, validation set and test set in a certain distribution ratio for subsequent design verification.

[0153] 3.2) Training, verification and testing: After the data set is generated, the data is used for training under the PID control framework. The neural network used for training is the long short-term memory network (LSTM). First, the database in step (2) is divided into input data samples and target data samples. The input data samples are historical data used for model input, and the target data samples are future data to be predicted. During the training process, the model parameters, parameters in LSTM and control strategies are continuously adjusted to enable it to effectively cope with various flight missions, model uncertainties and multi-source disturbances. Each LSTM has three gate structures to control the flow of gradients, namely: forget gate, input gate and output gate. The number of LSTM layers is selected to be 4, with 300 LSTM units in each layer. The formula for LSTM forward propagation is as follows:

[0154] The forget gate decides whether to keep or forget information by considering the input of the previous time step and the input of the current time step. Its calculation process is as follows:

[0155] (17)

[0156] In the formula, is the value of the forget gate, Indicates a connection operation. is the weight matrix of the forget gate, is the bias term of the forget gate, yes Input values ​​of the moment grid: The total coupling matrix , before selecting Variable groups As input; Total coupling data of the dimension , before selecting Variable groups As input; Total coupling data of the dimension , before selecting Variable groups As input; is the output value of LSTM at the previous moment, Function The activation function is as follows:

[0157] (18)

[0158] Input gate through Activation function to calculate new memory unit candidate values , is the value of the input gate, quilt After processing, the value range is located in interval, and By multiplying each element, we can determine the candidate value of the memory cell For update , the calculation process is as follows:

[0159] (19)

[0160] (20)

[0161] Update the value of a memory cell:

[0162] (twenty one)

[0163] In the formula, and is the weight matrix, and is the bias term, is the unit state at the current moment, is the unit state at the previous moment, " means element-wise multiplication, The specific form of the function is as follows:

[0164] (twenty two)

[0165] Output gate usage The activation function determines the output. The activation function converts the value of the memory cell Mapped to a range between -1 and 1. The calculation process is as follows:

[0166] (twenty three)

[0167] (twenty four)

[0168] In the formula, is the value of the output gate, is the output of the LSTM unit, is the weight matrix, is the bias matrix.

[0169] In the LSTM forward propagation, the original data is input into the neural network, and each neuron calculates an output value based on the input data and its own weight, that is, , , , , The values ​​of the five vectors are processed by each layer of neurons and gradually passed to the next layer, and finally the prediction results of the neural network are obtained at the output layer.

[0170] The training algorithm of LSTM is the back propagation algorithm, which calculates the error term of each neuron , the direction of back propagation of the LSTM error term is: the error term propagates to the upper layer as the error input of the LSTM unit in the upper layer, and the gradient after each weight update is calculated according to the error to obtain the updated weight parameter to reduce the value of the loss function. Then, the values ​​of weights and biases are updated according to the gradient of the loss function to weights and biases, so that the loss function gradually decreases. Generally, the gradient descent method is used to update the parameters:

[0171] (25)

[0172] (26)

[0173] In the formula, is the learning rate, . is the loss function, , They are Moment and Moment The weights of the layers include , , and . , They are Moment and Moment Layer bias, including , , and .

[0174] In this step, based on the effective data set, after training, verification and testing, the generated LSTM neural network covers the main features of the coupled data. The obtained LSTM neural network has the function of updating weights and biases, and will be used as a coupled neural network in the design of subsequent intelligent controllers.

[0175] Step (4) Design of intelligent controller based on coupled deep neural network

[0176] This step makes full use of the coupled neural network generated by updating weights and biases through LSTM in step (3) to design an intelligent controller. The details are as follows:

[0177] Firstly, the maneuver control model of the hypersonic vehicle is divided into a velocity loop and an attitude loop. The velocity loop is expressed as:

[0178] (27)

[0179] Where: and represents the transformed kinetic model coefficient, represents the coupling effect in the speed loop, represents the external disturbance of the speed loop, Represents the control input of the speed loop, i.e., the throttle opening. The speed reference signal is The corresponding tracking error is .

[0180] The pitch angle reference signal is defined as , the altitude of the hypersonic vehicle By pitch angle Obtained by tracking the proportional-integral-derivative (PID) algorithm In the design, the left elevon rudder surface deflection angle is considered to be equal to the right elevon rudder surface deflection angle, that is, , the attitude loop is given by:

[0181] (28)

[0182] Where: and represents the transformed kinetic model coefficient, represents the coupling effect in the attitude loop, represents the external disturbance of the attitude loop, Represents the control input of the attitude loop, namely the elevator deflection angle. is the pitch angular velocity. The pitch angular velocity reference signal is , the tracking error of the pitch angular velocity is .

[0183] The design fuel equivalence ratio and command elevator control commands are:

[0184] (29)

[0185] Where: , , , , and represents the nonlinear function approximated by the neural network, and express and The projection operator is used to avoid the occurrence of singular phenomena in the fuel equivalence ratio command and the elevator control command.

[0186] Among them, the neural network update law is designed as

[0187] (30)

[0188] In this embodiment: Select =0.1, =0.1, =0.2, =0.2, =0.5, =0.5, =0.4, = 0.4, =0.1, =0.1, =0.1, =0.1, =1, =2, =1, =10.

[0189] In order to verify this coupled information driven hypersonic vehicle intelligent control method, the simulation experiment results are as follows Figure 3-8 shown. Figure 3 The speed tracking effect curve is given. The tracking signal rises synchronously with the speed command, indicating that the control system has an excellent tracking effect on the speed reference command. Figure 4 The effect curve of altitude tracking is shown. In the first 60 seconds, there is a gap between the command and the tracking signal, and the position value of the tracking signal is higher than the command. After 60 seconds, the gap between the two gradually narrows until they almost completely overlap in the later stage, indicating that the altitude tracking signal gradually becomes consistent with the command. Figure 5The fuel command changes are given. It can be seen that the value of the fuel command is high, which means that the aircraft needs a large fuel supply at startup to support its high-speed flight. From about 20 seconds, the value of the fuel command gradually stabilizes, and the fuel command finally remains at a level of about 0.2. This shows that after the aircraft reaches a certain flight speed, the fuel demand tends to stabilize in order to maintain its continuous hypersonic flight. Figure 6 The curve of the rudder angle command changing with time is shown. In the first 20 seconds, the rudder angle command has significant fluctuations, reflecting the adjustment process of the aircraft during takeoff. After 60 seconds, the rudder angle command basically remains in a small amplitude range, indicating that the aircraft has entered a relatively stable flight state and no longer needs frequent rudder adjustment. Figure 7 to Figure 8 The weight curve is shown in Figure 2. As can be seen from the figure, when the time is close to 0 seconds, each weight undergoes a sharp decline. Then it slowly recovers and gradually enters a relatively stable stage. After 20 seconds, the weight of the neural network is basically stable, and its change amplitude is very small in the following time. The above simulation experiments prove the effectiveness of this coupled information-driven hypersonic aircraft intelligent control method, which can improve the performance and stability of the control system and ensure that hypersonic aircraft can achieve high-precision and high-reliability autonomous control in practical applications.

Claims

1. A method for intelligent control of a hypersonic vehicle driven by coupled information, characterized in that: The details are as follows: Step (1) Construction of longitudinal dynamics model of elastic hypersonic vehicle Based on the rigid body mathematical model, aerodynamic coupling model, structural elastic coupling model and thrust coupling model, the longitudinal dynamics model of elastic hypersonic vehicle is established: (1) in, is the speed of the hypersonic vehicle, is the flight altitude, is the track angle, is the pitch angle, is the pitch angular rate, is the angle of attack and satisfies ; is the mass of the aircraft, is the acceleration due to gravity, For along The moment of inertia of the shaft; represents the elastic mode, represents the damping factor, represents the natural oscillation frequency, represents the generalized force, represents the first and second order modes considered; They are thrust, lift, and drag, respectively. is the pitching moment, and the specific expression is: (2) in, is the dynamic pressure, is the wing reference area, is the mean aerodynamic chord length, is the distance from the center of mass to the center of reference moment, is the body coordinate axis system The force in the axial direction, is the elevator surface deflection angle; is the aileron rudder surface deflection angle; is the total lift coefficient, is the total thrust coefficient; is the total drag coefficient, and They represent the basic drag coefficient, the incremental drag coefficient caused by the elevator and the incremental drag coefficient caused by the aileron respectively; and They represent the basic lift coefficient, the incremental lift coefficient caused by the elevator, and the lift caused by the aileron; is the total pitching moment coefficient, and They represent the basic pitching moment coefficient, the incremental pitching moment coefficient caused by the elevator and the incremental pitching moment coefficient caused by the aileron. is the incremental coefficient of pitch moment caused by pitch angular rate; Total thrust coefficient The expression is as follows: (3) in, is the throttle opening, and Respectively represent the basic resistance coefficient; when hour, , ;when hour, , ; The dynamic process of the engine is a second-order system: (4) in, It is the control signal of the throttle opening. It is the throttle opening adjustment damping. is the natural oscillation frequency; Step (2) Construction of coupled database based on sampling analysis and dynamic equations 2.1) Give the construction method of the sampling analysis method database: set up and are two mutually coupled variable groups in the system; sampling and calculation of the variables yields and ,use express right The impact quantification index is right The influence is expressed as (5) in, for right The degree of influence; Similarly, right The influence degree can be expressed as (6) in, for right The degree of influence; Furthermore, the variables in the system and The coupling degree can be expressed as (7) For the elastic hypersonic vehicle longitudinal dynamics model in step (1), define the state variable group and control input variable groups The coupling matrix is , trajectory variable group and posture variable group The coupling matrix is , posture variables and posture variable group The coupling matrix is , the specific expression is: (8) (9) (10) The flight position remains unchanged at the beginning and end, and the attack angle and flight speed instructions are changed to simulate the A set of flight envelope data is obtained, and then the coupling matrix is ​​calculated using a sampling statistical algorithm in each flight envelope, so that Flight envelopes Dimensional coupled database , , ; 2.2) The construction method of the dynamic equation analysis method database is given: Consider the following nonlinear system: (11) in, is the state variable, is the input variable; Based on nonlinear theory, the form of dynamic coupling is given as follows: For the nonlinear system shown in equation (11), the dynamic coupling matrix between the state variables is It can be defined as: (12) Similarly, variables With variables The dynamic coupling matrix between Defined as: (13) For the elastic hypersonic vehicle longitudinal dynamics model in step (1), define the state variable group and control input variable groups The coupling matrix is , trajectory variable group and posture variable group The coupling matrix is , posture variables and posture variable group The coupling matrix is , the specific expression is: (14) (15) (16) in, , is the state variable group Middle variables, , is the control input variable group Middle variables, ; , is the trajectory variable group Middle variables, , is the posture variable group Middle variables, , , is the posture variable group Middle variables, ; The flight position remains unchanged at the beginning and end, and the attack angle and flight speed instructions are changed to simulate the Then, the coupling matrix is ​​calculated by the dynamic equation method in each flight envelope. Flight envelopes Dimensional coupled database , , ; 2.3) Construction of hybrid database based on sampling analysis and dynamic equation coupling analysis The coupled database is obtained by sampling analysis method and dynamic equation method, and then after screening and compensation, the final result is Total coupling database of dimension , , , providing sufficient training data for the next step (3) of deep neural network training; Step (3) Deep neural network training based on coupled data drive 3.1) Dataset generation: Generate the total coupling database in step (2) , , ; 3.2) Training, validation and testing: After the data set is generated, the data is used for training under the PID control framework. First, the database in step (2) is divided into input data samples and target data samples. The input data samples are historical data used for model input, and the target data samples are future data to be predicted. During the training process, the model parameters, parameters in LSTM and control strategies are continuously adjusted to enable it to effectively cope with various flight tasks, model uncertainties and multi-source disturbances. Each LSTM has three gate structures to control the flow of gradients, namely: forget gate, input gate and output gate. The forget gate decides whether to keep or forget information by considering the input of the previous time step and the input of the current time step. Its calculation process is as follows: (17) In the formula, is the value of the forget gate, Indicates a connection operation. is the weight matrix of the forget gate, is the bias term of the forget gate, yes Input values ​​of the moment grid: The total coupling matrix , select the first 80% Variable groups As input; Total coupling data of the dimension , select the first 80% Variable groups As input; Total coupling data of the dimension , select the first 80% Variable groups As input; is the output value of LSTM at the previous moment, Function The activation function is as follows: (18) Input gate through Activation function to calculate new memory unit candidate values , is the value of the input gate, quilt The processed value range is located in interval, and By multiplying each element, we can determine the candidate value of the memory unit For update , the calculation process is as follows: (19) (20) Update the value of a memory cell: (21) In the formula, and is the weight matrix, and is the bias term, is the unit state at the current moment, is the unit state at the previous moment, " " means element-wise multiplication, The specific form of the function is as follows: (22) Output gate usage The activation function determines the output. The activation function converts the value of the memory cell is mapped to a range between -1 and 1; the calculation is as follows: (23) (24) In the formula, is the value of the output gate, is the output of the LSTM unit, is the weight matrix, is the bias matrix; In the LSTM forward propagation, the original data is input into the neural network, and each neuron calculates an output value based on the input data and its own weight, that is, , , , , The values ​​of the five vectors are processed by each layer of neurons and gradually passed to the next layer, and finally the prediction results of the neural network are obtained in the output layer; Step (4) Design of intelligent controller based on coupled deep neural network Using the coupled neural network generated by updating weights and biases through LSTM in step (3), the intelligent controller design is carried out as follows: Firstly, the maneuvering control model of the hypersonic vehicle is divided into a velocity loop and an attitude loop. The velocity loop is expressed as: (27) Where: and represents the transformed kinetic model coefficient, represents the coupling effect in the speed loop, represents the external disturbance of the speed loop, represents the control input of the speed loop, i.e., the throttle opening; the speed reference signal is The corresponding tracking error is ; The pitch angle reference signal is defined as , the altitude of the hypersonic vehicle By pitch angle pass The algorithm obtained To control, the design considers that the left elevon rudder surface deflection angle is equal to the right elevon rudder surface deflection angle, that is, , the attitude loop is given by: (28) Where: and represents the transformed kinetic model coefficient, represents the coupling effect in the attitude loop, represents the external disturbance of the attitude loop, represents the control input of the attitude loop, i.e., the elevator deflection angle, is the pitch angular velocity; the pitch angular velocity reference signal is , the tracking error of the pitch angular velocity is ; The design fuel equivalence ratio command and elevator control command are: (29) Where: , is the positive parameter to be designed, , , and represents the nonlinear function approximated by the neural network, and express and The projection operator of Among them, the neural network update law is designed as (30) Where: , , , , , , , , , , , , , , , is the positive parameter to be designed.

2. The method for intelligent control of a hypersonic vehicle driven by coupled information according to claim 1, characterized in that: Step 3.1) includes: first, it is necessary to collect and generate a coupling degree database covering various flight conditions and flight missions, various cross-linked coupling effects, model uncertainties and multi-source disturbance effects; then, simulation data generation is performed to simulate various possible flight conditions and interference situations, and a large amount of training data is generated; specifically, first, by changing the aerodynamic force and torque model parameters, data containing model errors are generated to simulate model uncertainty; second, by simulating different environmental conditions, external interference data is generated to simulate environmental interference; third, by simulating different flight missions, a generalized coupling database is generated to simulate complex flight missions and conditions; finally, the data set is divided into training set, validation set and test set in a certain distribution ratio for subsequent design verification.

3. The method for intelligent control of a hypersonic vehicle driven by coupled information according to claim 1, characterized in that: In step 3.2), the LSTM training algorithm is the back propagation algorithm, which includes two directions: one is the back propagation along time, that is, from the current Starting from the moment, calculate the error term at each moment; One is to propagate the error term to the upper layer; then, based on the corresponding error term, the gradient of each weight is calculated and the weight parameters of the model are updated to reduce the value of the loss function; Then, the values ​​of weights and biases are updated according to the gradient of the loss function to weights and biases, so that the loss function gradually decreases, and the gradient descent method is used to update the parameters: (25) (26) In the formula, is the learning rate, is the loss function, , They are Moment and Moment The weights of the layers include , , and ; , They are Moment and Moment Layer bias, including , , and .

Images