102 results about "Aircraft dynamics" patented technology

The invention discloses a low-altitude traffic flow collaborative awareness and conflict prediction method and system based on a multi-modal large model. The method comprises the following steps: collecting multi-source heterogeneous data of an aircraft, fusing and mapping the multi-source heterogeneous data to a space-time grid with dynamically adjustable granularity based on a real-time traffic situation, and realizing adaptive characterization; the method comprises the following steps of: constructing a robust special prediction model by introducing aircraft dynamics constraint and airspace rule knowledge as priori and performing fine adjustment by adopting a loss function containing an adversarial regularization item based on a pre-trained large model of the body-equipped agent; inputting spatial-temporal characteristics into the model, outputting behavior intentions and probability trajectories in an end-to-end manner, constructing an incomplete information game deduction model based on predicted trajectories, and calculating a comprehensive collision risk index fusing trajectory uncertainty, a motion state and a game deduction result; and generating a hierarchical early warning and collaborative avoidance strategy, and performing network distribution. According to the method, the accuracy, the robustness and the decision intelligence of conflict prediction under the low-altitude dense traffic flow are remarkably improved.

The invention relates to the technical field of aircraft path planning, and particularly provides an aircraft path planning method for a space non-cooperative target. The method comprises the following steps: constructing an aircraft dynamics model and constraint conditions, and obtaining a non-convex optimal control problem; performing discretization processing on a non-convex optimal control problem through a non-equal-interval pseudo-spectrum discrete optimization model, and converting the non-convex optimal control problem into a fixed-time nonlinear programming problem about discrete nodes; according to the method, a fixed time nonlinear programming problem is convexed to form a convex sub problem, a local optimal solution of a non-convex optimal control problem is obtained through sequence iteration, under the multi-state constraint, path planning of an aircraft approaching a space non-cooperative target is achieved, the problem of no feasible solution caused by non-accurate linearization is solved, and the method is suitable for being applied to a non-cooperative target. And the convergence rate of the algorithm is accelerated.

The invention belongs to the field of wind tunnel experiments in a hypersonic flow field environment, and discloses a multi-degree-of-freedom high-frequency motion simulation device for an aircraft dynamic stability test and a calculation method for realizing an actuation angle. According to the technical method, calculation is carried out on the basis of an electromechanical coupling equation, determined by electrical parameters and mechanical parameters, of a piezoelectric material. Modeling can be carried out according to a piezoelectric equation to obtain a calculation method between the voltage applied by the piezoelectric actuator and the pitching and yawing actuation angles of the device, so that the excitation effect of the device in the ground test process can be accurately controlled and predicted. The method is not only suitable for pitching and yawing two-degree-of-freedom actuation calculation, but also can be used for calculating the actuation angle of a three-axis degree-of-freedom experimental device added with rolling drive through coordinate transformation under the condition of adding parameters such as rolling angular velocity and the like in the face of the three-axis degree-of-freedom experimental device added with rolling drive. At present, according to a calculation method based on the device, calculation is carried out only by considering the degree of freedom of the pitching axis and the yawing axis.

The invention relates to the technical field of intelligent flight control, in particular to a multi-source sensing data fused low-altitude flight track offset intelligent repair method, which comprises the following steps of: performing jitter correction on a visual image stream through a motion compensation module, performing resampling on an ADS-B positioning signal by adopting a Lagrange interpolation method, and performing multi-source sensing data fusion on the ADS-B positioning signal; the radar point cloud is mapped to an image coordinate system, and a fusion track representation vector with time-space synchronization is generated; extracting a curvature abrupt change point set, an environment shielding factor and an airspace visibility gradient based on the vector, and constructing a multi-dimensional offset feature tensor in combination with aircraft dynamics constraints; inputting the tensor into a pre-trained space-time diagram neural network, and outputting a risk grading restoration decision comprising a restoration angle, a climbing rate and a speed compensation amount; injecting the repair decision into a flight control simulator for verification, and outputting a final repair instruction when the trajectory deviation value is smaller than a safety threshold value; the method has high precision and closed-loop execution flight path repairing capability, and is suitable for a flight control system in a complex low-altitude environment.

The invention discloses an aircraft dynamic recovery sorting scheduling method based on a re-flight strategy and a related device, and relates to the technical field of air traffic control, and the method comprises the steps: solving an aircraft group dynamic recovery decision model based on a state parameter of a previous decision stage, and obtaining a decision variable of each aircraft in a current decision stage; according to the decision variables of the aircrafts in the current decision stage, the recovery states of the aircrafts in the current decision stage are obtained; removing successfully recycled aircrafts from the to-be-recycled aircraft set in the previous decision-making stage to obtain the to-be-recycled aircraft set in the current decision-making stage, selecting a re-flying strategy for the recycled aircrafts failed in recycling, updating the decision variables according to the re-flying strategy, and obtaining the updated decision variables of the aircrafts in the current decision-making stage; if the aircraft set to be recycled in the current decision-making stage is empty, recycling is completed; according to the method, the recovery efficiency can be improved, and the flight safety can be guaranteed.

The invention discloses a shipborne fixed-wing aircraft landing guidance law design method and system, and belongs to the field of aircraft guidance law design. The problems that the multi-coordinate system coupling effect of ship motion and aircraft dynamics is not fully decoupled and an existing method is weak in adaptability to non-stable sea conditions are solved. The method comprises the following steps: defining related coordinate systems including a world coordinate system, a landing coordinate system and a ship body coordinate system; calculating an ideal landing point height change value caused by ship deck movement in real time according to the position of the ideal position in the ship body coordinate system; utilizing a KOA-LSTM hybrid forecasting model to predict a motion heave value of a ship deck at a future critical moment; designing a compensation value for the longitudinal position deviation based on the predicted motion heave value, and carrying out dynamic compensation correction on the longitudinal guide instruction; and according to the compensated guide instruction and the real-time position of the aircraft, calculating the transverse and longitudinal deviation of the aircraft relative to the expected landing trajectory to form closed-loop control. The device is mainly used for offshore operation.

The invention discloses a dynamic safety interval control method for a low-altitude aircraft, relates to the technical field of low-altitude flight control, and solves the technical problem that the aircraft cannot be effectively controlled in the prior art. The method comprises the following steps: 1, selecting a certain aircraft as a target aircraft, calculating a potential field force FAB generated by a front aircraft on the target aircraft, and defining a state-space equation of the target aircraft in combination with an acceleration requirement of the target aircraft; if the target aircraft is an unmanned aerial vehicle, skipping to the step 2, and if the rear aircraft is a manned aircraft, skipping to the step 3; 2, eliminating a state estimation error caused by the operation time delay of the target aircraft by using an operation time delay compensation method, and obtaining a state-space equation of the target aircraft under the time delay tau; 3, solving the state-space equation by a genetic optimization algorithm to obtain an optimal interval control parameter; the dynamic interval control model provided by the invention greatly improves the operation efficiency of the complex low-altitude fusion airspace on the premise of conforming to the aircraft interval standard.

The invention provides a civil aircraft safety perception method and system based on virtual flight, and relates to the technical field of aircraft safety perception. A dynamic and hierarchical three-dimensional wind shear field model is constructed through space-time alignment and fusion of multi-source meteorological data; deep coupling of wind disturbance and aircraft dynamic response is realized based on a small disturbance theory and a flight dynamics model; continuous and dynamic quantification of risks is realized by combining and analyzing flight parameters and a safety threshold value dynamically adjusted based on wind disturbance intensity and utilizing multi-parameter risk level weighted integration; according to the method, the risk coefficient is coupled with the three-dimensional terrain and the virtual flight trajectory, hierarchical color mapping is adopted to carry out visual space visualization, and a complete closed loop from environment modeling to risk early warning is formed, so that the identification accuracy and timeliness of the flight risk in the wind shear environment are greatly improved, and the scientificity and practicability of security situation awareness are enhanced.

The invention discloses a self-adaptive unmanned aerial vehicle control method for an improved neural network. The method comprises the following steps: constructing a PID controller SSA-BP-PID of a BP neural network; optimizing a PID controller SSA-BP-PID based on a sparrow search algorithm SSA, updating a population position and assigning a value to a weight value and a threshold value of the SSA-BP-PID, so that the SSA-BP-PID outputs an updated PID parameter and a control law; calculating output attitude data of the aircraft according to the control law in combination with an aircraft kinetic model; and S3, setting the number of iterations, constructing a fitness function as a minimization target in combination with the overshoot, the adjustment time and the steady-state error, and iteratively calculating the steps S2-S3 to obtain output attitude data for controlling the flight of the unmanned aerial vehicle. The method is used for optimizing PID controller parameters, compared with a traditional PID control method, the method has remarkable advantages in the aspects of dynamic response speed, steady-state precision, anti-interference capacity and the like, and the control performance of the four-rotor unmanned aerial vehicle is improved.

The invention provides a high-speed aircraft online trajectory planning method based on improved polynomial guidance, which solves the problems of calculation delay and poor trajectory smoothness in the existing autonomous path planning, and comprises the following steps: establishing a plane-coordinate system and a motion equation set of a high-speed aircraft, and determining constraint conditions in the flight process of the high-speed aircraft; constructing an optimization model containing an adaptive penalty function based on an improved sequential quadratic programming algorithm, and generating an obstacle avoidance path point set; performing trajectory optimization by adopting an improved polynomial, generating a trajectory meeting aircraft dynamics constraints among the path points generated in the step 2, and selecting a key path point set; based on the obstacle avoidance path point set and the key path point set, adopting a centripetal parameterized Catmull-Rom spline curve to process the generated path to obtain a smooth trajectory; a guidance instruction is obtained based on smooth trajectory analysis and calculation, and the high-speed aircraft is guided to sail according to the planned trajectory. And the real-time calculation efficiency is improved on the basis of realizing the smooth trajectory.

The invention provides an airport flying area crossing traffic command system based on an A-SMGCS system, and belongs to the technical field of intelligent traffic, and the system comprises a sensor layer which is used for collecting aircraft dynamic data, to-be-passed authorized object data, environment meteorological data, and dynamic obstacle data; the data processing and decision-making layer is used for carrying out standardization processing and space-time mapping processing on the collected data, judging existing potential conflicts in combination with a dynamic threshold adjustment mechanism, and generating an issuing instruction based on a multi-target optimization decision; and the execution layer is used for controlling crossing traffic management and control equipment according to the issued instruction and feeding back an execution result to the data processing and decision-making layer in real time to form closed-loop control. The traffic conflict risk of the airport flight area crossing is effectively reduced, the crossing passing efficiency is improved, the vehicle waiting time and the aircraft taxiing delay are reduced, the fine scheduling requirement for scene movement is met, and reliable support is provided for safe and efficient traffic operation of the airport flight area.

This invention discloses an airborne display and control method for enhancing situational awareness and flight operations, comprising: providing onboard operational information and basic traffic, weather, and terrain displays based on flight phases and crew operational requirements, configuring display content and layout, and establishing basic situational awareness; providing a list of traffic aircraft dynamic information, setting aircraft of interest, and acquiring operational information of aircraft of interest to establish enhanced traffic situational awareness; receiving conflict detection, conflict prediction, and conflict resolution information at short, medium, and long ranges, and outputting alarm information in visual, auditory, or tactile forms according to alarm priority to establish enhanced conflict alarm situational awareness; applying for and receiving control clearance for enhanced flight operations through CPDLC, calling the flight operation setup program, and inputting the information required for enhanced flight operations; and generating target flight paths and target flight states in real time based on enhanced flight operation requirements, and implementing enhanced flight operations by the crew or flight management system.

The invention relates to the technical field of aircraft dynamic model testing, and discloses a method for testing lift force and resistance of an aircraft with a power system through a dynamic model test, which comprises the following steps: step 1, mounting an acceleration sensor and a corresponding data acquisition module on a rail car in a fastening manner, and recording acceleration data of the rail car; secondly, a support is fastened and installed on the rail car, and an aircraft with a power system is installed on the support; step 3, installing a two-dimensional force transducer; 4, debugging and starting a power system; and step 5, data processing: through the obtained acceleration data and the lift force data and resistance data of each fulcrum, the speed, lift force and resistance corresponding to each moment are obtained through data processing. According to the invention, the lift force and resistance of the aircraft can be simply, efficiently and accurately tested.

The application provides a kind of aircraft servo elastic dynamics model correction method considering operating surface gap, first aircraft structure is divided into substructure, and the aircraft dynamics model containing aileron gap nonlinearity is established according to substructure branch modal;And additional inertia force caused by aircraft operating aileron deflection is introduced in dynamics model, and the aircraft open-loop servo elastic motion equation containing aileron gap nonlinearity under independent generalized coordinate is obtained;According to sensor output equation, rudder transfer function and flight control system equation, the aircraft nonlinear servo elastic closed-loop system model containing aileron gap nonlinearity is established, and the model is corrected based on ground vibration test, rudder frequency response test and gap measurement test result, and the stability of the model is judged based on simulation analysis result and open-loop frequency response test result and is further corrected, which improves the accuracy of gap nonlinearity aircraft aerodynamic servo elastic characteristic evaluation, and is helpful to guide aircraft servo elastic ground test engineering practice.

The invention provides an aircraft dynamic derivative test device in a strong interference environment, which relates to the technical field of aircraft aerodynamic characteristic tests and comprises an interference flow field establishing device, a dynamic derivative measuring device and a synchronous control module. The disturbing flow field establishing device is composed of a shock wave generator, a supporting connecting piece and a wind tunnel attack angle mechanism, the shock wave generator is connected with the wind tunnel attack angle mechanism through the supporting connecting piece, + / -15-degree pitching and + / -10-degree yawing motion is achieved based on the wind tunnel attack angle mechanism, and multiple types of strong disturbing flow fields can be established by replacing the shock wave generator; the dynamic derivative measuring device is installed in a plug-in mechanism of a wind tunnel, based on a forced vibration test method, a model is driven by a high-precision servo motor to vibrate slightly, precise acquisition is realized by matching with a high-frequency dynamic balance and a data filtering unit, and the displacement of the model relative to a shock wave generator can be adjusted through the plug-in mechanism. According to the scheme, a real strong interference environment can be accurately reproduced, and the dynamic derivative measurement accuracy is improved.

The invention relates to the technical field of high-speed aircraft health management, and particularly discloses an interpretable aircraft state sensing and predicting system and method. The method comprises the following steps: constructing and training a lightweight anomaly diagnosis network with an expansion perception layer; aircraft dynamics, kinematics and fault mechanism formulas are used as soft constraints to be embedded into the future state estimation network; an SHAP interpretation framework is used for sorting the importance of the input features, and a network structure is optimized accordingly; and finally, accurate diagnosis of abnormal types and positions and rapid prediction of aircraft states at a plurality of moments in the future are realized. According to the method, by introducing three innovation points of an expansion perception layer, physical information embedding and feature importance sorting, the diagnosis accuracy and the model interpretability are remarkably improved, and the high-performance calculation requirement in a scene with limited calculation power is met.

The application provides a kind of aircraft dynamics modeling method containing multi-degree-of-freedom actuator, the modeling method returns general mechanics and advanced theory and thought of mechanics basic disciplines, aircraft is regarded as multi-rigid body system, based on virtual power principle and multi-body system topological configuration recursive modeling method, the deformation multi-body system dynamics model suitable for aircraft containing multi-actuator is established, and the motion characteristics of multi-degree-of-freedom, strong coupling between the motion characteristics of aircraft external body attitude motion and internal component relative motion are accurately described.

The application discloses a kind of reinforcement learning self-tuning method and system of flight controller PID parameter, and it is related to aircraft control technical field.The application includes: establishing aircraft dynamics simulation model;Deep reinforcement learning agent including strategy network and value network is constructed, and strategy network model parameter is trained offline in simulation environment;The model parameter obtained after offline training is loaded into the real-time flight controller of aircraft, and state is collected online and input strategy network, and PID parameter increment is generated by forward operation, and the PID parameter is obtained by adding preset reference value;PID control module calculates control output according to the PID parameter generated and flight state feedback error.The application combines offline training and online inference, and both real-time and adaptive ability are considered, and the calculation load is low, and robustness is strong.

The invention relates to the technical field of aircraft power control, and discloses an artificial intelligence optimized vertical fixed wing power control method and system, and the method comprises the steps: obtaining the original airspeed data of an airspeed sensor, the ground speed data of a global positioning system and the acceleration data of an inertial measurement unit, and generating the ground speed of an aircraft based on the data fusion. Under the low-wind-speed condition, the ground speed of the aircraft is used as the reference airspeed, the difference between the original airspeed data of the airspeed sensor and the reference airspeed is continuously compared, and the sliding average value of the difference is calculated. When the sliding average value continuously exceeds the preset tolerance range, the method can identify that the airspeed sensor has continuous calibration drift. And then, according to the identified continuous calibration drift, performing real-time compensation on original airspeed data of an airspeed sensor to obtain calibrated airspeed data, and inputting the calibrated airspeed data into flight mode switching judgment logic to trigger an action instruction of a tilting mechanism.

The application provides an aircraft parameter identification method combining a gated recurrent unit neural network model and a Gauss-Newton optimization algorithm, which combines the GRU neural network model and the Gauss-Newton optimization algorithm and is used for solving a complex aircraft parameter identification problem. The GRU neural network model is designed to model aircraft dynamics by directly establishing a nonlinear function mapping relationship between measurement input and output of the aircraft system without any dynamic prior assumption. The Gauss-Newton optimization algorithm is combined with the trained GRU network model, and the optimal parameter identification result is obtained by minimizing the cost function related to unknown aerodynamic parameters in an iterative manner.

The invention belongs to the field of design of systems for preventing out-of-control accidents of aircrafts, and particularly relates to an integrated platform and method for preventing out-of-control accidents of aircrafts. The comprehensive platform comprises an airborne modeling and simulation unit used for describing changes of aircraft dynamics and control characteristics caused by aircraft damage and external threats; the aircraft health management unit is used for monitoring and predicting the state of the aircraft and continuously evaluating and managing the health condition and the remaining life of the aircraft; the elastic guidance and control unit is used for aircraft out-of-control prevention and recovery and external threat suppression; and the man-machine interface unit is used for realizing man-machine information exchange and coordination under the condition that the airplane is out of control. The aircraft dynamics and control characteristics can be effectively represented under the condition that the aircraft is abnormal, aircraft health and flight safety are evaluated in real time, and effective context awareness and decision support are provided for flight crew, so that the aircraft out-of-control accident risk is reduced, and related accidents are prevented.

The embodiment of the invention provides an attitude control method and system of an aircraft, the aircraft, a medium and a program product, and relates to the technical field of flight control. The method comprises the following steps: acquiring an actual state observed quantity of an aircraft; estimating a disturbance estimation value of the aircraft dynamics model; wherein the estimation error converges within a preset observation time; generating an expected angular velocity instruction by using a preset time attitude controller; wherein the attitude tracking error converges within a preset first time; generating an expected torque instruction by using a preset time angular velocity controller; wherein the angular velocity tracking error converges within a preset second time; and solving the distribution problem of the expected torque instruction to obtain control instructions of a plurality of execution mechanisms so as to perform attitude control on the aircraft. According to the embodiment of the invention, by setting the related convergence time, the control model can realize convergence of the related state error within the preset time, so that the accuracy and the stability of aircraft attitude control are effectively improved.

The invention provides an active control aeroelastic modeling method and device for a flap of a half-unfolded tilt-rotor aircraft, and the method comprises the steps: integrating a flap model into a cantilever wing model through a trailing edge flap interface and flap structure parameters reserved at a rotor structure assembly through the dynamic comprehensive analysis software of the rotor aircraft, establishing a cantilever wing model with flap active control; establishing a tilt rotor model; the cantilever wing model with the flap active control function and the tilt rotor model are combined together, and a flap active control model of the half-unfolded tilt rotor aircraft is obtained; carrying out aeroelastic stability initialization calculation on the flap active control model of the half-spread tilt-rotor aircraft, and extracting geometric shape data of a flap active control rotor blade of the half-spread tilt-rotor aircraft, so that the flap active control model can be integrated on a wing of a tilt rotor; the semi-expanded tilt rotor active control scaling model is created, and theoretical support is provided for follow-up tilt rotor flap active control aeroelastic design.

The invention provides a flight parameter identification method for a multi-aircraft system, which relates to the field of aircraft dynamics, and comprises the following steps: modeling a dynamic model: in a multi-aircraft cooperative communication network, for each node in the network, modeling based on an ARMAX model with external input and a colored noise structure, each node constructs a local dynamic model according to local observation information; preliminary parameter estimation: performing preliminary parameter estimation on the local dynamic model of each node by adopting a distributed extended least square algorithm; and correcting the initial parameter estimation value based on an adaptive Lasso regularization mechanism to obtain a final parameter estimation result under sparsity constraint. The parameter identification method provided by the invention has excellent modeling precision and engineering adaptability, and is suitable for typical scenes of online modeling, cooperative control, health state monitoring and the like in a multi-aircraft system.

The invention discloses a dynamic model of a fixed-wing aircraft, and relates to the technical field of flight training. Comprising an aircraft mass center kinetic equation of the fixed wing aircraft, a mass center rotation kinetic equation, an aircraft aerodynamic characteristic calculation model, an aircraft kinetic equation resolving model, an abnormal flight state trajectory and attitude inverse solution calculation model and a ski-jump take-off and carrier landing model. Wherein the aircraft aerodynamic characteristic calculation model is used for calculating aerodynamic force and aerodynamic moment of the fixed-wing aircraft; the aircraft kinetic equation resolving model is used for resolving the aircraft mass center kinetic equation and the mass center rotation kinetic equation; the abnormal flight state trajectory and attitude inverse solution calculation model is used for inverse solution calculation of stress and torque of the fixed wing aircraft in an abnormal flight state; and the ski-jump takeoff and carrier landing model is used for solving the carrier landing arresting longitudinal load problem of the fixed-wing aircraft. The technical problems that in the prior art, the flight training process is abstract in theory and large in difficulty are solved.

This invention discloses a method, apparatus, device, and readable storage medium for determining controller parameters, applied in the field of flight controller technology. The method includes: acquiring an ideal model based on flight quality design, a nonlinear aircraft control model, and an aircraft dynamics model; determining the initial controller parameters of the nonlinear aircraft control model; and using a global optimization algorithm to determine the optimal values ​​of the controller parameters for the nonlinear aircraft control model. Furthermore, it enables real-time flight quality evaluation after optimization, ensuring that the optimal controller parameter values ​​meet Level 1 flight quality requirements. Compared to current manual adjustment of controller parameters, this invention utilizes a frequency-domain-dependent ideal model based on flight quality, and optimization objectives based on the time and complex frequency domains, allowing simultaneous optimization of controller parameters in both the time and frequency domains. Moreover, it intelligently determines the optimal controller parameter values ​​based on a global optimization algorithm, improving the comprehensiveness and intelligence of the optimization process.

The invention belongs to a flight control system test technology, and provides a semi-physical simulation and test method and system for a redundancy flight control system, and the method comprises the steps: constructing a semi-physical simulation test environment, constructing a redundancy sensor simulation model integrated with a high-fidelity error model, an execution mechanism model and an aircraft dynamics model in a simulation computer; the simulation computer generates an instruction and drives the model to operate, performs instruction-response-feedback closed-loop data interaction with flight control hardware, and sequentially executes model correction, integration test, scene test, robustness test and stepped fault injection test; quantitative indicators are calculated based on the test data to assess control performance and redundancy management capability of the flight control system. According to the method, the problems of unreal modeling, incomplete test coverage and weak fault verification capability of a traditional simulation method for a redundancy system are solved, and efficient and high-fidelity ground verification of the redundancy flight control system from functions to reliability is realized.

The application discloses a kind of based on the evaluation method of comprehensive energy system of fly / launch collaborative control strategy, it is related to advanced aeronautical power comprehensive energy system. With the comprehensive energy system with multi-source energy extraction mode as the research object, the performance evaluation of comprehensive energy system is realized through the comprehensive evaluation of fly / launch level of typical TBCC engine. Including steps: 1) parameter initialization: 2) establish aircraft dynamics model;3) establish combination engine model;4) establish comprehensive energy system model;5) solve optimal trajectory. The performance influence of different energy extraction modes on combination power is quantitatively analyzed, and the comprehensive evaluation of comprehensive energy system with multi-source energy extraction mode is realized. Under certain energy demand, the fly / launch coordination control for realizing optimal trajectory and lowest fuel consumption is combined, and the evaluation method taking the performance influence of comprehensive energy system on combination power device as evaluation index provides reference value for future comprehensive energy management system design method.

The present invention belongs to the field of path prediction and discloses a flight path stability optimization method, system, storage medium, and device. The method comprises constructing a dynamic fusion dataset by aligning timestamps in response to aircraft dynamics parameters, pilot physiological state parameters, and three-dimensional spatial environmental parameters acquired synchronously from multiple sources. A pre-built dual-channel feature extraction architecture is used to extract dual-channel features from the dynamic fusion dataset. The first channel uses a sparse attention mechanism to analyze dynamic coupling relationships in the time dimension, while the second channel uses a graph neural network to model the spatial correlation topology of environmental parameters. The dual-channel features are then integrated to construct a deep reinforcement learning decision engine, establishing a mapping strategy from environmental state to control action to path stability, and driving control strategy optimization through a reward mechanism. Finally, a real-time decision engine is used to generate multi-parameter collaborative optimization instructions for flight control surfaces. The present invention can improve the efficiency and accuracy of path prediction, thereby optimizing the path.

The invention discloses an aircraft trajectory optimization method based on a fixed thrust engine, and belongs to the field of guidance control, and the method comprises the steps: S1, building an aircraft dynamics model, and determining the working parameters of the engine; s2, determining a drop point range and drop point parameters; s3, determining a power-on point area and a power-off point area which can meet the drop point range and the drop point parameters through Monte Carlo simulation, and obtaining a flight control domain; and S4, making a guidance strategy of an engine working section based on the flight control domain. For the engine which can only be ignited for one time, the trajectory is only adjusted in the working period of the engine, the situation that attitude control consumption is too much due to frequent attitude adjustment is avoided, the attitude control total impulse and the attitude control service life requirement are optimized, and the drop point precision is guaranteed.