CN118034371B - Aircraft motion control method and system based on adaptive optimization algorithm - Google Patents
Aircraft motion control method and system based on adaptive optimization algorithm Download PDFInfo
- Publication number
- CN118034371B CN118034371B CN202410246998.7A CN202410246998A CN118034371B CN 118034371 B CN118034371 B CN 118034371B CN 202410246998 A CN202410246998 A CN 202410246998A CN 118034371 B CN118034371 B CN 118034371B
- Authority
- CN
- China
- Prior art keywords
- aircraft
- error
- dynamic model
- establishing
- optimization algorithm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000005457 optimization Methods 0.000 title claims abstract description 74
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 66
- 238000000034 method Methods 0.000 title claims abstract description 55
- 230000003044 adaptive effect Effects 0.000 title claims description 26
- 239000002245 particle Substances 0.000 claims description 41
- 238000005312 nonlinear dynamic Methods 0.000 claims description 26
- 238000004088 simulation Methods 0.000 claims description 24
- 239000011159 matrix material Substances 0.000 claims description 20
- 238000012706 support-vector machine Methods 0.000 claims description 17
- 230000004044 response Effects 0.000 claims description 15
- 238000004458 analytical method Methods 0.000 claims description 14
- 238000000354 decomposition reaction Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000010354 integration Effects 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 230000000452 restraining effect Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 description 8
- 230000007613 environmental effect Effects 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000006872 improvement Effects 0.000 description 4
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000011217 control strategy Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000007620 mathematical function Methods 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Landscapes
- Feedback Control In General (AREA)
Abstract
The invention provides an aircraft motion control method and system based on a self-adaptive optimization algorithm, and relates to the field of aircraft intelligent control, wherein the aircraft motion control method based on the self-adaptive optimization algorithm comprises the following steps: establishing a closed loop dynamic model of the aircraft and analyzing the error amplitude characteristics of the aircraft in various flight states; establishing a dynamic compensator for adjusting the aircraft control signal based on the obtained error amplitude characteristic; performing parameter optimization on the dynamic compensator by using a self-adaptive optimization algorithm to obtain optimal parameters; and transmitting the obtained optimal parameters to a dynamic compensator, and adjusting the control signals of the aircraft in real time to realize the motion control of the aircraft. According to the invention, after the optimal parameters are obtained through the self-adaptive optimization algorithm, the optimal parameters are applied to the dynamic compensator, so that the optimal adjustment of the aircraft control signals is realized, the system performance is improved, and the complex flight situation is more effectively dealt with.
Description
Technical Field
The invention relates to the field of intelligent control of aircrafts, in particular to an aircraft motion control method and system based on a self-adaptive optimization algorithm.
Background
With the deep development of social informatization technology, high-performance automation systems are increasingly required in various fields of industry, agriculture, scientific research and the like. In the field of aerospace, the continuous improvement of the autonomous capability of aircrafts and spacecraft has become a core task for designing novel advanced aircrafts. The key to improving the autonomous performance of a flight system is to realize the autonomous control of an aircraft, and an aerospace Unmanned Aircraft (UASV) is taken as a new generation of unmanned advanced aerospace aircraft and plays an important role in the trend of the development of the aerospace technology in the world today. From the current development trend of aerospace technology, and in order to meet the requirements of an aerospace unmanned aircraft for performing space reconnaissance, monitoring, detection, relay, early warning and other tasks, it is important to achieve complete autonomous control and management of the aircraft.
Thus, improvements in autonomous performance of a flight system are not only reflected in a technical aspect, but also include autonomous planning of flight tasks, environmental awareness, decision making, emergency response, and improvements in self-healing capabilities. Furthermore, with the development of artificial intelligence and machine learning techniques, the application of these techniques in autonomous control systems of aircraft will become critical to improving the autonomous performance of the aircraft.
At present, the conventional aircraft control method does not consider the complex dynamic characteristics of the aircraft in different flight states, and when the aircraft encounters these changes in the actual flight process, the conventional control method may not accurately predict and adjust the behavior of the aircraft, so that the actual performance has a significant deviation from the theoretical expectation, and thus the flight safety and efficiency are affected.
For the problems in the related art, no effective solution has been proposed at present.
Disclosure of Invention
In view of the above, the present invention provides an aircraft motion control method and system based on an adaptive optimization algorithm, so as to solve the above-mentioned problem that the conventional control method may not accurately predict and adjust the behavior of the aircraft.
In order to solve the problems, the invention adopts the following specific technical scheme:
according to an aspect of the present invention, there is provided an aircraft motion control method based on an adaptive optimization algorithm, the aircraft motion control method based on the adaptive optimization algorithm comprising the steps of:
s1, establishing a closed loop dynamic model of the aircraft and analyzing the error amplitude characteristics of the aircraft in various flight states;
s2, establishing a dynamic compensator for adjusting an aircraft control signal based on the obtained error amplitude characteristic;
s3, performing parameter optimization on the dynamic compensator by using a self-adaptive optimization algorithm to obtain optimal parameters;
And S4, transmitting the obtained optimal parameters to a dynamic compensator, and adjusting the control signals of the aircraft in real time to realize the motion control of the aircraft.
Preferably, establishing a closed loop dynamic model of the aircraft and analyzing the error magnitude characteristics of the aircraft under various flight conditions comprises the steps of:
S11, acquiring historical operation data of an aircraft and preprocessing to obtain standard data, wherein the preprocessing comprises coarse error detection, noise filtering, mean value removal and standardization;
s12, establishing a closed-loop dynamic model of the aircraft based on the obtained standard data;
s13, simulating the aircraft under various flight states by using the established closed-loop dynamic model of the aircraft;
S14, comparing the simulation result with actual data, and calculating the error amplitude characteristics of the aircraft in various flight states.
Preferably, establishing the closed loop dynamic model of the aircraft based on the obtained standard data comprises the following steps:
s121, calculating correlation coefficients among variables through pearson correlation coefficients for each variable in standard data;
S122, calculating variance expansion factors of each variable and other variables based on the correlation coefficient of each variable, and deleting variable data with variance expansion factors larger than a preset threshold value to obtain effective data;
Wherein, based on the correlation coefficient of each variable, the calculation formula for calculating the variance expansion factor of each variable and other variables is:
G＝1/(1-R2)；
Wherein G represents the variance expansion factor of the variable in the standard data and other variables;
r represents a correlation coefficient between a variable in standard data and other variables;
s123, determining a model structure of the closed-loop dynamic model of the aircraft, and determining a model order of the closed-loop dynamic model of the aircraft through a singular value decomposition method;
s124, building a closed-loop dynamic model of the aircraft based on the model structure and the model order.
Preferably, determining the model structure of the closed-loop dynamic model of the aircraft and determining the order of the closed-loop dynamic model of the aircraft by a singular value decomposition method comprises the following steps:
S1231, determining a model structure of a closed-loop dynamic model of the aircraft based on physical characteristics, control logic and dynamic response of the aircraft;
S1232, constructing a Hankel matrix based on the obtained effective data and performing singular value decomposition to obtain a left singular vector matrix, a singular value matrix and a right singular vector matrix;
S1233, calculating the ratio of the singular values of the adjacent matrixes, and finding out the singular value with the largest ratio;
S1234, according to the singular value with the largest ratio, determining the index corresponding to the singular value, and taking the index as the order of the closed loop dynamic model of the aircraft.
Preferably, using the established closed loop dynamic model of the aircraft, simulating the aircraft under various flight conditions comprises the steps of:
s131, setting simulation conditions of the aircraft, including an initial state, flight time, time step and flight track;
S132, determining control input of the aircraft, including setting a control surface and engine thrust;
S133, solving a differential equation of the dynamic model of the aircraft by a numerical integration method, and updating the state of the aircraft;
S134, recording the state information of the aircraft, including the position, the speed, the gesture and the angular speed, of each time step in the aircraft simulation process.
Preferably, the calculation of the error amplitude characteristics of the aircraft in various flight conditions based on the comparison of the simulation results with the actual data comprises the following steps:
s141, acquiring actual data under various flight states through a sensor of the aircraft;
s142, simulating the behavior of the aircraft in different flight states by using the established closed-loop dynamic model of the aircraft, and recording data of simulation output;
S143, comparing the actual data with the data output by simulation one, analyzing the difference between the actual data and the data output by simulation, and calculating an error value;
S144, calculating the amplitude characteristic of the error according to the obtained error value, wherein the amplitude characteristic comprises the average value, the maximum value, the minimum value and the standard deviation of the error.
Preferably, the establishment of a dynamic compensator for adjusting an aircraft control signal based on the obtained error magnitude characteristic comprises the steps of:
S21, analyzing the error amplitude characteristics of the aircraft in various flight states;
s22, determining a target error to be compensated based on an analysis result of the error amplitude characteristic, wherein the target error comprises a position error, a speed error and an attitude error;
S23, establishing an error compensation strategy according to the determined compensation target;
s24, establishing a dynamic compensator of the aircraft based on the error compensation strategy and the error amplitude characteristic.
Preferably, the parameter optimization is performed on the dynamic compensator by using an adaptive optimization algorithm, and the obtaining of the optimal parameter comprises the following steps:
s31, analyzing the state and the behavior of the dynamic compensator, and establishing a nonlinear dynamic model of the dynamic compensator;
s32, performing preliminary parameter setting according to the working characteristics and requirements of the dynamic compensator;
And S33, optimizing parameters of the nonlinear dynamic model based on a particle swarm optimization algorithm and a support vector machine algorithm.
Preferably, optimizing parameters of the nonlinear dynamic model based on the particle swarm optimization algorithm and the support vector machine algorithm comprises the following steps:
s331, randomly generating a group of particles in a parameter space of a nonlinear dynamic model, wherein each particle represents a parameter of the nonlinear dynamic model;
s332, establishing an adaptability function, and performing performance evaluation on the current parameter combination;
s333, updating the speed and the position of each particle in the particle swarm according to the rule of the particle swarm optimization algorithm;
s334, restraining parameters of the nonlinear dynamic model by using a support vector machine algorithm;
s334, calculating the fitness of each particle in the updated particle swarm, and updating the historical optimal position and the global optimal position of each particle;
s335, judging whether a preset fitness threshold is reached, if not, returning to the step S333, otherwise, taking the parameter corresponding to the global optimal position as the optimal parameter.
According to another aspect of the present invention, there is provided an aircraft motion control system based on an adaptive optimization algorithm, the aircraft motion control system based on the adaptive optimization algorithm comprising: the system comprises an error amplitude analysis module, a compensator building module, a parameter optimization module and a motion control module;
The error amplitude analysis module is used for establishing an aircraft closed-loop dynamic model and analyzing the error amplitude characteristics of the aircraft in various flight states;
The compensator establishing module is used for establishing a dynamic compensator for adjusting the aircraft control signal based on the obtained error amplitude characteristics;
the parameter optimization module is used for carrying out parameter optimization on the dynamic compensator by utilizing a self-adaptive optimization algorithm to obtain optimal parameters;
And the motion control module is used for transmitting the obtained optimal parameters to the dynamic compensator, and adjusting the aircraft control signals in real time to realize motion control of the aircraft.
The beneficial effects of the invention are as follows:
1. according to the invention, the dynamic behavior of the aircraft under different situations can be more accurately understood by establishing the closed-loop dynamic model of the aircraft and analyzing the error amplitude characteristics under various flight conditions, the accurate control model is facilitated to be established, the dynamic compensator is introduced based on the obtained error amplitude characteristics, the compensator can adjust the control signal of the aircraft in real time, the adaptive optimization algorithm is introduced to perform parameter optimization on the dynamic compensator, the automatic adjustment of the control parameters can be realized to adapt to different environment and task requirements, the adaptability and the robustness of the system are improved, the optimal parameters are obtained through the adaptive optimization algorithm and then are applied to the dynamic compensator, the optimal adjustment of the control signal of the aircraft is realized, the system performance is improved, and the system can more effectively cope with the complex flight situations.
2. According to the invention, the historical operation data of the aircraft can be obtained and preprocessed, so that the historical data can be utilized more comprehensively, the standard data can be obtained, a more accurate closed-loop dynamic model is built, the correlation coefficient among the variables is calculated by adopting the Pearson correlation coefficient, the effective data is obtained through the calculation of the correlation coefficient and the variance expansion factor, redundant information is eliminated, the accuracy and the robustness of the model are improved, the model structure and the order of the closed-loop dynamic model of the aircraft are determined through the singular value decomposition method, the dynamic characteristics of the aircraft can be reflected more accurately, the modeling reliability is improved, the error amplitude characteristics of the aircraft under various flight states are calculated through the comprehensive comparison and analysis of the simulation result and the actual data, and a powerful basis can be provided for further optimizing the control strategy.
3. According to the method, the global optimal solution can be found in the parameter space by utilizing the global searching capability of the particle swarm optimization algorithm, the parameter space can be searched more comprehensively, the potential optimal solution can be found, the global convergence of the algorithm is improved, the robustness of the system can be effectively improved by introducing the support vector machine algorithm to constrain the parameters of the nonlinear dynamic model, the optimized parameters are more universal, the speed and the position of each particle in the particle swarm are iteratively updated, the historical optimal position and the global optimal position are updated according to the fitness function, the parameters can be gradually optimized in the optimization process, the optimal solution is gradually approached, and the parameter optimization process of the dynamic compensator is more effective and reliable.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:
FIG. 1 is a flow chart of an aircraft motion control method based on an adaptive optimization algorithm in accordance with an embodiment of the invention;
FIG. 2 is a functional block diagram of an aircraft motion control system based on an adaptive optimization algorithm in accordance with an embodiment of the present invention.
In the figure:
1. The error amplitude analysis module; 2. a compensator building module; 3. a parameter optimization module; 4. and a motion control module.
Detailed Description
In order to make the technical solution of the present application better understood by those skilled in the art, the technical solution of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, but not all embodiments of the present application. All other embodiments, based on the embodiments of the application, which would be apparent to one of ordinary skill in the art without undue burden are intended to be within the scope of the application.
According to the embodiment of the invention, an aircraft motion control method and system based on an adaptive optimization algorithm are provided.
The invention will now be further described with reference to the accompanying drawings and detailed description, as shown in fig. 1, according to one embodiment of the invention, there is provided an aircraft motion control method based on an adaptive optimization algorithm, the aircraft motion control method based on the adaptive optimization algorithm comprising the steps of:
s1, establishing a closed loop dynamic model of the aircraft and analyzing the error amplitude characteristics of the aircraft in various flight states;
As a preferred embodiment, establishing a closed loop dynamic model of an aircraft and analyzing the error magnitude characteristics of the aircraft under various flight conditions comprises the steps of:
S11, acquiring historical operation data of an aircraft and preprocessing to obtain standard data, wherein the preprocessing comprises coarse error detection, noise filtering, mean value removal and standardization;
Specifically, coarse error checking refers to identifying and excluding outliers or significant errors in the data. In aircraft operational data, abnormal data points may be generated for various reasons (e.g., sensor failure, data transmission errors, etc.), and by identifying and excluding these abnormal values, the quality of the data for subsequent analysis and modeling may be ensured.
Noise filtering, which is the removal or attenuation of random fluctuations in the data by mathematical methods (e.g., low pass filters, moving averages, etc.) to improve the clarity and usability of the data, refers to aircraft data that is typically affected by various environmental and system noise.
The de-averaging is to subtract the overall average value from each data point, which helps to eliminate the fixed deviation in the data, and to concentrate the data at zero point, thereby simplifying the subsequent analysis and modeling process.
Normalization (also called normalization) refers to scaling data to a specific range (e.g., -1 to 1), or to a standard deviation of 1, to help eliminate the effects of different dimensions and magnitudes on analysis results, making the data more comparable.
S12, establishing a closed-loop dynamic model of the aircraft based on the obtained standard data;
as a preferred embodiment, building a closed loop dynamic model of an aircraft based on the obtained standard data comprises the steps of:
s121, calculating correlation coefficients among variables through pearson correlation coefficients for each variable in standard data;
It should be noted that, the pearson correlation coefficient is a statistic that measures the degree of linear correlation between two variables, and its value is between-1 and 1, where 1 represents a complete positive correlation, -1 represents a complete negative correlation, and 0 represents no linear relationship.
Specifically, for each variable, the average value of all the observed values is calculated, then the covariance and standard deviation between each variable are calculated, and finally the pearson correlation coefficient is calculated through the covariance and the respective variances.
S122, calculating variance expansion factors of each variable and other variables based on the correlation coefficient of each variable, and deleting variable data with variance expansion factors larger than a preset threshold value to obtain effective data;
it should be noted that, deleting variable data with variance expansion factor greater than the preset threshold may help to identify and eliminate multiple collinearity problems in the data set that may affect the accuracy of the model, and by removing those variables that are highly related to other variables, the stability and predictive power of the model may be improved.
Wherein, based on the correlation coefficient of each variable, the calculation formula for calculating the variance expansion factor of each variable and other variables is:
G＝1/(1-R2)；
Wherein G represents the variance expansion factor of the variable in the standard data and other variables;
r represents a correlation coefficient between a variable in standard data and other variables;
s123, determining a model structure of the closed-loop dynamic model of the aircraft, and determining a model order of the closed-loop dynamic model of the aircraft through a singular value decomposition method;
As a preferred embodiment, determining the model structure of the closed-loop dynamic model of the aircraft and determining the order of the closed-loop dynamic model of the aircraft by means of a singular value decomposition method comprises the following steps:
s1231, determining a model structure of a closed-loop dynamic model of the aircraft based on physical characteristics, control logic, dynamic response and the like of the aircraft;
It should be noted that, analyzing the physical characteristics of the aircraft includes the dimensions, mass, thrust characteristics, aerodynamic characteristics, etc. of the aircraft, the control logic includes the design of the flight control system, such as stability enhancement, flight mode switching, autopilot logic, etc., the dynamic response of the aircraft involves the speed and manner of response of the aircraft to control inputs and environmental changes, the dynamic response characteristics include, for example, response time, transient and steady state characteristics, and, in combination with the above information, the design of a model containing the necessary dynamics, control and response characteristics.
S1232, constructing a Hankel matrix based on the obtained effective data and performing singular value decomposition to obtain a left singular vector matrix, a singular value matrix and a right singular vector matrix;
Specifically, the Hankel matrix is a special square matrix in which elements of each row are shifted right by one column to form the next row, and for time-series data, the Hankel matrix may be constructed by stacking delayed versions of the time-series into a matrix.
S1233, calculating the ratio of the singular values of the adjacent matrixes, and finding out the singular value with the largest ratio;
It should be noted that, first, a singular value matrix is obtained from the previous singular value decomposition process, the matrix is diagonal, the elements on the diagonal are singular values, for each singular value in the singular value matrix, the ratio of the singular value matrix to the next singular value is calculated, all the calculated ratios are checked to find the largest one of the singular values, and the previous singular value corresponding to the largest ratio is generally considered as the most critical singular value.
S1234, according to the singular value with the largest ratio, determining the index corresponding to the singular value, and taking the index as the order of the closed loop dynamic model of the aircraft.
It should be noted that in singular value decomposition, each singular value corresponds to a particular feature or pattern in the data set, a larger singular value corresponds to a primary feature in the data, and a smaller singular value corresponds to a secondary feature or noise, with a larger ratio of singular values generally representing the most significant dynamic change in the data. The index corresponding to the maximum singular value ratio reflects an important change in the data characteristics at this point and thus, as an order of the closed loop dynamic model of the aircraft, represents the number of dominant dynamic characteristics that the model should capture.
S124, building a closed-loop dynamic model of the aircraft based on the model structure and the model order.
Specifically, according to the physical characteristics and control logic of the aircraft, the input variables, state variables and control variables required by the model are determined, and based on the determined model order and the respective variables, the state equation of the aircraft is established. The state equation should be able to describe the dynamic behavior of the aircraft at a given control input, including the variation of state variables such as position, speed, attitude, etc., defining a control law based on the aircraft's control logic and control objectives. The control law should be able to generate appropriate control inputs based on the current state and the target state to achieve the desired dynamic response of the aircraft, and integrate the determined state equations and control laws together to form a complete closed loop dynamic model of the aircraft.
S13, simulating the aircraft under various flight states by using the established closed-loop dynamic model of the aircraft;
as a preferred embodiment, using the established closed loop dynamic model of the aircraft, simulating the aircraft under various flight conditions comprises the steps of:
s131, setting simulation conditions of the aircraft, including an initial state, flight time, time step and flight track;
S132, determining control input of the aircraft, including setting a control surface and engine thrust;
It should be noted that, the control inputs are used to adjust the state and dynamic behavior of the aircraft to achieve the desired flight trajectory and performance, the control plane refers to a component on the aircraft for controlling the flight attitude, such as an elevator, a rudder, an aileron, etc., and the engine thrust is another important control input that directly affects the speed and the position of the aircraft, and by adjusting the thrust of the engine, precise control of parameters such as the flight speed, the climb/descend rate, etc. can be achieved.
S133, solving a differential equation of the dynamic model of the aircraft by a numerical integration method, and updating the state of the aircraft;
It should be noted that, solving the differential equation of the dynamic model of the aircraft by the numerical integration method, and updating the state of the aircraft includes the following steps:
Discretizing a differential equation of the aircraft dynamic model into a form which can be solved by a numerical method;
Initializing the state of the aircraft, including position, speed, attitude, etc.;
a selected numerical integration method is applied during each time step to update the state of the aircraft. For example, four different slopes are calculated in each time step and the state is updated with these slopes;
And updating the state variables such as the position, the speed, the attitude and the like of the aircraft according to the result of the numerical integration.
S134, recording the state information of the aircraft, including the position, the speed, the gesture and the angular speed, of each time step in the aircraft simulation process.
S14, comparing the simulation result with actual data, and calculating the error amplitude characteristics of the aircraft in various flight states.
As a preferred embodiment, calculating the error magnitude characteristics of the aircraft in various flight conditions based on comparing the simulation results with the actual data comprises the steps of:
s141, acquiring actual data under various flight states through a sensor of the aircraft;
s142, simulating the behavior of the aircraft in different flight states by using the established closed-loop dynamic model of the aircraft, and recording data of simulation output;
S143, comparing the actual data with the data output by simulation one, analyzing the difference between the actual data and the data output by simulation, and calculating an error value;
Specifically, actual flight data and analog output data are collected and these data are ensured to cover the same flight conditions and time periods, and for each point in time or time window, the difference between the actual data and the analog data is calculated. The differences may be determined by direct subtraction or by calculating relative errors, etc., common difference calculations include absolute errors, relative errors, mean square errors, etc.
S144, calculating the amplitude characteristic of the error according to the obtained error value, wherein the amplitude characteristic comprises the average value, the maximum value, the minimum value and the standard deviation of the error.
S2, establishing a dynamic compensator for adjusting an aircraft control signal based on the obtained error amplitude characteristic;
as a preferred embodiment, the creation of a dynamic compensator for adjusting an aircraft control signal based on the obtained error magnitude characteristic comprises the steps of:
S21, analyzing the error amplitude characteristics of the aircraft in various flight states;
it should be noted that, the error characteristics under different flight conditions, including the magnitude, the trend, the frequency distribution, etc. of the error are analyzed, for example, the error may increase during take-off and landing, and may be smaller during steady flight.
S22, determining a target error to be compensated based on an analysis result of the error amplitude characteristic, wherein the target error comprises a position error, a speed error and an attitude error;
It should be noted that, the position error is caused by the fact that the aircraft cannot accurately reach the predetermined position, the speed error is caused by the fact that the aircraft cannot maintain a stable flight state, and the attitude error is caused by the fact that the aircraft cannot accurately perform the predetermined action or the response to external interference is inaccurate.
S23, establishing an error compensation strategy according to the determined compensation target;
Specifically, the error compensation strategy includes feed-forward compensation, which is a method of predetermining the compensation input, and feedback compensation, based on accurate knowledge of the system dynamics. By predicting errors, feedforward compensation can be performed before errors occur, so that the response speed and the accuracy of the system are improved; feedback compensation relies on actual output feedback, and by comparing the desired output with the actual output, an error can be calculated and the control input adjusted accordingly.
S24, establishing a dynamic compensator of the aircraft based on the error compensation strategy and the error amplitude characteristic.
Specifically, based on the error compensation strategy, a dynamic compensator of the aircraft is implemented. The dynamic compensator can monitor the state and error of the aircraft in real time and dynamically adjust the control signal according to the current error condition.
S3, performing parameter optimization on the dynamic compensator by using a self-adaptive optimization algorithm to obtain optimal parameters;
As a preferred embodiment, the parameter optimization of the dynamic compensator by using the adaptive optimization algorithm, and obtaining the optimal parameter comprises the following steps:
s31, analyzing the state and the behavior of the dynamic compensator, and establishing a nonlinear dynamic model of the dynamic compensator;
It should be noted that the collection of data of the dynamic compensator under different operating conditions, including input, output and any relevant environmental parameters; analyzing the response mode of the dynamic compensator, such as response speed, stability and any nonlinear behavior; the main factors influencing the behavior of the dynamic compensator, such as the characteristics of input signals, environment variables, internal settings and the like, are determined, and a nonlinear dynamic model of the dynamic compensator is built according to the physical principles and behavior characteristics of the dynamic compensator.
S32, performing preliminary parameter setting according to the working characteristics and requirements of the dynamic compensator;
Specifically, it is clear what performance index, such as response speed, stability, accuracy, etc., the dynamic compensator needs to reach, under what environment the analytical compensator will work, environmental factors such as temperature, humidity, vibration, etc. may affect its performance, identify adjustable parameters and make preliminary settings.
And S33, optimizing parameters of the nonlinear dynamic model based on a particle swarm optimization algorithm and a support vector machine algorithm.
As a preferred embodiment, optimizing parameters of the nonlinear dynamic model based on the particle swarm optimization algorithm and the support vector machine algorithm comprises the following steps:
s331, randomly generating a group of particles in a parameter space of a nonlinear dynamic model, wherein each particle represents a parameter of the nonlinear dynamic model;
s332, establishing an adaptability function, and performing performance evaluation on the current parameter combination;
specifically, it is first necessary to determine which performance indicators are most important for the nonlinear dynamic model, and a mathematical function is constructed to evaluate the performance of a given parameter combination according to the selected performance indicators, where the fitness function may be a function of a single indicator or a comprehensive evaluation of multiple indicators.
S333, updating the speed and the position of each particle in the particle swarm according to the rule of the particle swarm optimization algorithm;
it should be noted that, according to the rule of the particle swarm optimization algorithm, the speed and position of the particle are updated based on the historical optimal position and the global optimal position of the particle, and the particle gradually approaches to the historical optimal position and the global optimal position, so as to search the optimal solution in the parameter space.
S334, restraining parameters of the nonlinear dynamic model by using a support vector machine algorithm;
It should be noted that, the constraint on the parameters of the nonlinear dynamic model by using the support vector machine algorithm includes the following steps:
collecting and preparing data for training and verification, including actual output data and corresponding input data of the nonlinear dynamic model;
selecting features related to parameters of the nonlinear dynamic model, including inputs, outputs or other related variables of the model;
Training a support vector machine model using the training dataset, selecting a complex relationship between kernel function (e.g., linear kernel, polynomial kernel, or radial basis function kernel) description features;
Parameters of the support vector machine model are adjusted through cross validation or other optimization technologies so as to obtain optimal prediction performance;
and taking the parameters of the nonlinear dynamic model as the input of the support vector machine model, predicting by using the trained model, and determining the constraint range or constraint condition of each parameter according to the output of the support vector machine model.
S334, calculating the fitness of each particle in the updated particle swarm, and updating the historical optimal position and the global optimal position of each particle;
s335, judging whether a preset fitness threshold is reached, if not, returning to the step S333, otherwise, taking the parameter corresponding to the global optimal position as the optimal parameter.
And S4, transmitting the obtained optimal parameters to a dynamic compensator, and adjusting the control signals of the aircraft in real time to realize the motion control of the aircraft.
Specifically, the obtained optimal parameters are transmitted to a dynamic compensator, and aircraft control signals are adjusted in real time, so that the motion control of the aircraft is realized, and the method comprises the following steps:
The optimal parameters obtained through the particle swarm optimization algorithm and the support vector machine algorithm are applied to the dynamic compensator, and the parameters are subjected to optimization and constraint processing, so that the performance of the dynamic compensator can be improved;
Dynamically adjusting control signals of the aircraft according to the real-time state and the target track of the aircraft, which can be realized through a feedback loop of a flight control system, so that the aircraft can track a desired track and keep a stable motion state;
The updated dynamic compensator and the control signal adjusting module are integrated into the aircraft;
In the flight process, the state and the track of the aircraft are monitored in real time, control signals are adjusted according to requirements, and the aircraft can stably run in a dynamic environment through an automatic control system of a flight control system;
according to the actual performance and performance data of the aircraft, the parameters of the dynamic compensator and the adjustment strategy of the control signals are continuously optimized, and the control accuracy and stability of the aircraft are continuously improved and iterated.
According to another embodiment of the present invention, there is provided an aircraft motion control system based on an adaptive optimization algorithm, the aircraft motion control system based on the adaptive optimization algorithm including: the system comprises an error amplitude analysis module 1, a compensator establishing module 2, a parameter optimizing module 3 and a motion control module 4;
The error amplitude analysis module 1 is used for establishing an aircraft closed-loop dynamic model and analyzing the error amplitude characteristics of the aircraft in various flight states;
A compensator establishing module 2 for establishing a dynamic compensator for adjusting the aircraft control signal based on the obtained error amplitude characteristics;
the parameter optimization module 3 is used for carrying out parameter optimization on the dynamic compensator by utilizing a self-adaptive optimization algorithm to obtain optimal parameters;
and the motion control module 4 is used for transmitting the obtained optimal parameters to the dynamic compensator, and adjusting the aircraft control signals in real time to realize motion control of the aircraft.
In summary, by means of the technical scheme, the method can more accurately understand the dynamic behavior of the aircraft under different situations by establishing the closed-loop dynamic model of the aircraft and analyzing the error amplitude characteristics under various flight conditions, is beneficial to establishing an accurate control model, introduces a dynamic compensator based on the obtained error amplitude characteristics, can adjust the control signal of the aircraft in real time, introduces an adaptive optimization algorithm to optimize parameters of the dynamic compensator, can automatically adjust the control parameters to adapt to different environment and task requirements, improves the adaptability and robustness of the system, and after obtaining the optimal parameters through the adaptive optimization algorithm, applies the optimal parameters to the dynamic compensator to realize optimal adjustment of the control signal of the aircraft, is beneficial to improving the performance of the system and enables the system to more effectively cope with complex flight situations; according to the invention, the historical operation data of the aircraft is obtained and preprocessed, so that the historical data can be more comprehensively utilized to obtain the standard data, a more accurate closed-loop dynamic model is built, the correlation coefficient among the variables is calculated by adopting the Pearson correlation coefficient, the effective data is obtained by calculating the correlation coefficient and the variance expansion factor, redundant information is eliminated, the accuracy and the robustness of the model are improved, the model structure and the order of the closed-loop dynamic model of the aircraft are determined by a singular value decomposition method, the dynamic characteristic of the aircraft can be more accurately reflected, the modeling reliability is improved, the error amplitude characteristic of the aircraft under various flight states is calculated by comprehensively comparing and analyzing the simulation result with the actual data, and a powerful basis is provided for further optimizing the control strategy; according to the method, the global optimal solution can be found in the parameter space by utilizing the global searching capability of the particle swarm optimization algorithm, the parameter space can be searched more comprehensively, the potential optimal solution can be found, the global convergence of the algorithm is improved, the robustness of the system can be effectively improved by introducing the support vector machine algorithm to constrain the parameters of the nonlinear dynamic model, the optimized parameters are more universal, the speed and the position of each particle in the particle swarm are iteratively updated, the historical optimal position and the global optimal position are updated according to the fitness function, the parameters can be gradually optimized in the optimization process, the optimal solution is gradually approached, and the parameter optimization process of the dynamic compensator is more effective and reliable.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (5)
1. The aircraft motion control method based on the adaptive optimization algorithm is characterized by comprising the following steps of:
s1, establishing a closed loop dynamic model of the aircraft and analyzing the error amplitude characteristics of the aircraft in various flight states;
s2, establishing a dynamic compensator for adjusting an aircraft control signal based on the obtained error amplitude characteristic;
s3, performing parameter optimization on the dynamic compensator by using a self-adaptive optimization algorithm to obtain optimal parameters;
S4, transmitting the obtained optimal parameters to a dynamic compensator, and adjusting aircraft control signals in real time to realize motion control of the aircraft;
The method for establishing the closed-loop dynamic model of the aircraft and analyzing the error amplitude characteristics of the aircraft in various flight states comprises the following steps:
s11, acquiring historical operation data of an aircraft and preprocessing to obtain standard data, wherein the preprocessing comprises coarse error detection, noise filtering, mean value removal and standardization;
s12, establishing a closed-loop dynamic model of the aircraft based on the obtained standard data;
s13, simulating the aircraft under various flight states by using the established closed-loop dynamic model of the aircraft;
s14, comparing the simulation result with actual data, and calculating the error amplitude characteristics of the aircraft in various flight states;
The establishment of the closed loop dynamic model of the aircraft based on the obtained standard data comprises the following steps:
s121, calculating correlation coefficients among variables through pearson correlation coefficients for each variable in standard data;
S122, calculating variance expansion factors of each variable and other variables based on the correlation coefficient of each variable, and deleting variable data with variance expansion factors larger than a preset threshold value to obtain effective data;
The calculation formula for calculating the variance expansion factor of each variable and other variables based on the correlation coefficient of each variable is as follows:
G=1/(1-R2)；
Wherein G represents the variance expansion factor of the variable in the standard data and other variables;
r represents a correlation coefficient between a variable in standard data and other variables;
s123, determining a model structure of the closed-loop dynamic model of the aircraft, and determining a model order of the closed-loop dynamic model of the aircraft through a singular value decomposition method;
s124, establishing a closed-loop dynamic model of the aircraft based on the model structure and the model order;
The establishing a dynamic compensator for adjusting an aircraft control signal based on the obtained error magnitude characteristic comprises the following steps:
S21, analyzing the error amplitude characteristics of the aircraft in various flight states;
s22, determining a target error to be compensated based on an analysis result of the error amplitude characteristic, wherein the target error comprises a position error, a speed error and an attitude error;
S23, establishing an error compensation strategy according to the determined compensation target;
s24, establishing a dynamic compensator of the aircraft based on an error compensation strategy and error amplitude characteristics;
the method for optimizing parameters of the dynamic compensator by utilizing the self-adaptive optimization algorithm comprises the following steps:
s31, analyzing the state and the behavior of the dynamic compensator, and establishing a nonlinear dynamic model of the dynamic compensator;
s32, performing preliminary parameter setting according to the working characteristics and requirements of the dynamic compensator;
S33, optimizing parameters of the nonlinear dynamic model based on a particle swarm optimization algorithm and a support vector machine algorithm;
the particle swarm optimization algorithm and the support vector machine algorithm-based optimization of the parameters of the nonlinear dynamic model comprise the following steps:
s331, randomly generating a group of particles in a parameter space of a nonlinear dynamic model, wherein each particle represents a parameter of the nonlinear dynamic model;
s332, establishing an adaptability function, and performing performance evaluation on the current parameter combination;
s333, updating the speed and the position of each particle in the particle swarm according to the rule of the particle swarm optimization algorithm;
s334, restraining parameters of the nonlinear dynamic model by using a support vector machine algorithm;
s334, calculating the fitness of each particle in the updated particle swarm, and updating the historical optimal position and the global optimal position of each particle;
s335, judging whether a preset fitness threshold is reached, if not, returning to the step S333, otherwise, taking the parameter corresponding to the global optimal position as the optimal parameter.
2. The method for controlling the motion of an aircraft based on the adaptive optimization algorithm according to claim 1, wherein the determining the model structure of the closed-loop dynamic model of the aircraft and determining the order of the closed-loop dynamic model of the aircraft by the singular value decomposition method comprises the following steps:
S1231, determining a model structure of a closed-loop dynamic model of the aircraft based on physical characteristics, control logic and dynamic response of the aircraft;
S1232, constructing a Hankel matrix based on the obtained effective data and performing singular value decomposition to obtain a left singular vector matrix, a singular value matrix and a right singular vector matrix;
S1233, calculating the ratio of the singular values of the adjacent matrixes, and finding out the singular value with the largest ratio;
S1234, according to the singular value with the largest ratio, determining the index corresponding to the singular value, and taking the index as the order of the closed loop dynamic model of the aircraft.
3. An aircraft motion control method based on an adaptive optimization algorithm according to claim 2, wherein the simulation of an aircraft under various flight conditions using an established closed-loop dynamic model of the aircraft comprises the steps of:
s131, setting simulation conditions of the aircraft, including an initial state, flight time, time step and flight track;
S132, determining control input of the aircraft, including setting a control surface and engine thrust;
S133, solving a differential equation of the dynamic model of the aircraft by a numerical integration method, and updating the state of the aircraft;
S134, recording the state information of the aircraft, including the position, the speed, the gesture and the angular speed, of each time step in the aircraft simulation process.
4. A method of controlling the movement of an aircraft based on an adaptive optimization algorithm according to claim 3, wherein the calculation of the error magnitude characteristics of the aircraft in various flight conditions based on the comparison of the simulation results with the actual data comprises the steps of:
s141, acquiring actual data under various flight states through a sensor of the aircraft;
s142, simulating the behavior of the aircraft in different flight states by using the established closed-loop dynamic model of the aircraft, and recording data of simulation output;
S143, comparing the actual data with the data output by simulation one, analyzing the difference between the actual data and the data output by simulation, and calculating an error value;
S144, calculating the amplitude characteristic of the error according to the obtained error value, wherein the amplitude characteristic comprises the average value, the maximum value, the minimum value and the standard deviation of the error.
5. An adaptive optimization algorithm-based aircraft motion control system for implementing the adaptive optimization algorithm-based aircraft motion control method of any one of claims 1-4, comprising: the system comprises an error amplitude analysis module, a compensator building module, a parameter optimization module and a motion control module;
the error amplitude analysis module is used for establishing an aircraft closed-loop dynamic model and analyzing the error amplitude characteristics of the aircraft in various flight states;
The compensator establishing module is used for establishing a dynamic compensator for adjusting the aircraft control signal based on the obtained error amplitude characteristics;
the parameter optimization module is used for carrying out parameter optimization on the dynamic compensator by utilizing a self-adaptive optimization algorithm to obtain optimal parameters;
The motion control module is used for transmitting the obtained optimal parameters to the dynamic compensator, and adjusting the aircraft control signals in real time to realize motion control of the aircraft.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410246998.7A CN118034371B (en) | 2024-03-05 | 2024-03-05 | Aircraft motion control method and system based on adaptive optimization algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410246998.7A CN118034371B (en) | 2024-03-05 | 2024-03-05 | Aircraft motion control method and system based on adaptive optimization algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118034371A CN118034371A (en) | 2024-05-14 |
| CN118034371B true CN118034371B (en) | 2024-08-13 |
Family
ID=91002172
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410246998.7A Active CN118034371B (en) | 2024-03-05 | 2024-03-05 | Aircraft motion control method and system based on adaptive optimization algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118034371B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118276539B (en) * | 2024-06-03 | 2024-08-06 | 景鸿超精密工业(青岛)有限公司 | Intelligent optimization method for dry ice cooling process |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111582510A (en) * | 2020-05-13 | 2020-08-25 | 中国民用航空飞行学院 | Intelligent identification method and system based on support vector machine and civil aircraft engine |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107077140B (en) * | 2016-03-28 | 2018-11-30 | 深圳市大疆创新科技有限公司 | Hovering control method, control system and the unmanned vehicle of unmanned vehicle |
| EP3586212B1 (en) * | 2017-02-24 | 2021-09-29 | FLIR Detection, Inc. | Control systems for unmanned aerial vehicles |
| CN212873583U (en) * | 2020-08-11 | 2021-04-02 | 山西联安矿用设备有限公司 | Colliery unmanned aerial vehicle inspection device based on 5G technique |
| CN114003052B (en) * | 2021-10-31 | 2023-09-15 | 河海大学 | Fixed wing unmanned aerial vehicle longitudinal movement robust self-adaptive control method based on dynamic compensation system |
| US11613380B1 (en) * | 2021-11-11 | 2023-03-28 | Beta Air, Llc | System and method for aircraft recommendation for an electric aircraft |
| US11803197B2 (en) * | 2021-11-15 | 2023-10-31 | Beta Air, Llc | Systems and methods for controlling a flight boundary of an aircraft |
-
2024
- 2024-03-05 CN CN202410246998.7A patent/CN118034371B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111582510A (en) * | 2020-05-13 | 2020-08-25 | 中国民用航空飞行学院 | Intelligent identification method and system based on support vector machine and civil aircraft engine |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118034371A (en) | 2024-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Khalastchi et al. | Online data-driven anomaly detection in autonomous robots | |
| Zheng et al. | Long short-term memory network for remaining useful life estimation | |
| Cuevas et al. | Nonlinear system identification based on ANFIS-Hammerstein model using Gravitational search algorithm | |
| Aboutalebi et al. | A novel sensor fault detection in an unmanned quadrotor based on adaptive neural observer | |
| Wang et al. | Markov nonlinear system estimation for engine performance tracking | |
| CN118034371B (en) | Aircraft motion control method and system based on adaptive optimization algorithm | |
| Anavatti et al. | Progress in adaptive control systems: past, present, and future | |
| Wu et al. | A gear machining error prediction method based on adaptive Gaussian mixture regression considering stochastic disturbance | |
| Moumouh et al. | A Novel Tuning approach for MPC parameters based on Artificial Neural Network | |
| US11740598B2 (en) | Apparatus and methods to build a reliable deep learning controller by imposing model constraints | |
| Zhang et al. | Iterative learning control for a class of parabolic system fault diagnosis | |
| Guo et al. | Prognostics for an actuator based on an ensemble of support vector regression and particle filter | |
| CN113219821B (en) | Fuzzy sliding mode position control method for numerical control machine tool with proportional integral sliding mode surface | |
| Prasad et al. | A Comprehensive overview on performance of cascaded three tank level system using neural network predictive controller | |
| Lavigne et al. | A model-based technique for early and robust detection of oscillatory failure case in A380 actuators | |
| Grema et al. | Data-driven self-optimizing control: constrained optimization problem | |
| Sun et al. | Robust adaptive fault estimation for a commercial aircraft oscillatory fault scenario | |
| CN110045716B (en) | Method and system for detecting and diagnosing early fault of closed-loop control system | |
| Najafqolian et al. | Formation control of multiple aerial robots using LSTM-based model predictive control | |
| CN114037012A (en) | Flight data anomaly detection method based on correlation analysis and deep learning | |
| CN112379601A (en) | MFA control system design method based on industrial process | |
| Jiang et al. | Neural Network Based Model Predictive Control for a Quadrotor UAV. Aerospace 2022, 9, 460 | |
| Wang et al. | On-line modeling and monitoring for multi-operation batch processes with infinite data types | |
| Masliev et al. | Implementation of the observer on the basis of the digital kalman filter for the lateral deflection control system of the automatic warehouse platform | |
| CN118508823B (en) | Position calibration optimization method and system of limited-angle motor for servo valve |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |