CN-122018524-A - Aircraft track optimization method and device, electronic equipment and storage medium

CN122018524ACN 122018524 ACN122018524 ACN 122018524ACN-122018524-A

Abstract

The invention provides an aircraft track optimization method, an apparatus, electronic equipment and a storage medium, belonging to the technical field of track optimization, comprising the steps of constructing a three-dimensional relative motion model of an aircraft and a maneuvering target; the method comprises the steps of determining a first control law based on a three-dimensional relative motion model and a self-adaptive dynamic programming network, determining an integral sliding mode variable based on the three-dimensional relative motion model and the first control law, determining a second control law based on a semi-positive barrier function, wherein the semi-positive barrier function takes the integral sliding mode variable as an independent variable, determining a flight control instruction based on the first control law and the second control law, and performing trajectory optimization on an aircraft based on the flight control instruction to obtain an optimized trajectory. According to the invention, the optimal control of the nominal system is realized by utilizing the self-adaptive dynamic programming network, and the unknown disturbance is self-adaptively restrained by combining the integral sliding mode control based on the semi-positive barrier function, so that the accuracy and the robustness of the aircraft track can be improved, and the requirements of the aircraft in the interception maneuvering target scene can be met.

Inventors

WEI QINGLAI
DU YANBIN
NI DONGDONG
WANG YUDONG
CHENG XIANG
LI HONGYANG
JIAO SHANSHAN

Assignees

中国科学院自动化研究所

Dates

Publication Date: 20260512
Application Date: 20260127

Claims (10)

1. A method of aircraft trajectory optimization, comprising: constructing a three-dimensional relative motion model of the aircraft and the maneuvering target; Determining a first control law based on the three-dimensional relative motion model and an adaptive dynamic programming network; Determining an integral sliding mode variable based on the three-dimensional relative motion model and the first control law; determining a second control law based on a semi-positive barrier function, wherein the semi-positive barrier function takes the integral sliding mode variable as an independent variable; and determining a flight control instruction based on the first control law and the second control law, and performing track optimization on the aircraft based on the flight control instruction to obtain an optimized track.
2. The method of aircraft trajectory optimization of claim 1, wherein the determining a first control law based on the three-dimensional relative motion model and an adaptive dynamic programming network comprises: Determining an optimal control performance function based on a state variable penalty and a control quantity penalty of the three-dimensional relative motion model; determining a hamiltonian function based on gradient information of the optimal control performance function on the state variables and dynamic terms and control input terms of the three-dimensional relative motion model; determining an objective function based on the hamiltonian function; updating the weight of the self-adaptive dynamic programming network based on the objective function and the auxiliary function to obtain a self-adaptive dynamic programming updating network; And determining the first control law based on the output value of the adaptive dynamic programming updating network, the control quantity penalty term and the control input term of the three-dimensional relative motion model.
3. The method of optimizing an aircraft trajectory according to claim 2, wherein updating weights of the adaptive dynamic programming network based on the objective function and the auxiliary function to obtain an adaptive dynamic programming update network comprises: carrying out normalized gradient descent treatment on the objective function to obtain a first weight updating item; Determining a second weight update term based on the auxiliary function; and updating the weight of the self-adaptive dynamic programming network in real time based on the first weight updating item and the second weight updating item until the self-adaptive dynamic programming network converges, so as to obtain the self-adaptive dynamic programming updating network.
4. The method of claim 1, wherein the determining a second control law based on a semi-positive barrier function comprises: Substituting the real-time value of the integral sliding mode variable into the semi-positive fixed obstacle function to obtain an obstacle function output value; Determining a sliding mode control gain based on the barrier function output value and a control input matrix of the three-dimensional relative motion model; The second control law is determined based on the sliding mode control gain and a sign function of the integrated sliding mode variable.
5. The method of claim 1, wherein the determining an integral sliding mode variable based on the three-dimensional relative motion model and the first control law comprises: acquiring real-time values and initial values of state variables in the three-dimensional relative motion model; performing time integration on the sum of the dynamic term in the three-dimensional relative motion model and the control term of the first control law to obtain a dynamic integral term; The integral sliding mode variable is determined based on the real-time value of the state variable, the initial value, and the dynamic integral term.
6. The method of claim 1, wherein said constructing a three-dimensional relative motion model of an aircraft and a maneuver target comprises: Constructing a three-dimensional relative motion model based on state variables and flight time, wherein the state variables are the sight inclination angle rate and the sight deflection angle rate of the aircraft relative to the maneuvering target; The three-dimensional relative motion model includes a dynamic term associated with the state variable, a control input describing the aircraft normal acceleration, and a disturbance input describing the maneuver target normal acceleration.
7. A method according to claim 3, wherein the auxiliary function is a Lyapunov function, and the determining a second weight update term based on the auxiliary function comprises: And generating the second weight updating item according to gradient information of the Lyapunov function on the state variable.
8. An aircraft trajectory optimization device, comprising: The relative motion modeling module is used for constructing a three-dimensional relative motion model of the aircraft and the maneuvering target; The first control law determining module is used for determining a first control law based on the three-dimensional relative motion model and the self-adaptive dynamic planning network; the integral sliding mode construction module is used for determining an integral sliding mode variable based on the three-dimensional relative motion model and the first control law; The second control law determining module is used for determining a second control law based on a semi-positive barrier function, and the semi-positive barrier function takes the integral sliding mode variable as an independent variable; and the track optimization module is used for determining a flight control instruction based on the first control law and the second control law, and carrying out track optimization on the aircraft based on the flight control instruction to obtain an optimized track.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and running on the processor, characterized in that the processor implements the aircraft trajectory optimization method according to any one of claims 1 to 7 when executing the computer program.
10. A non-transitory computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when executed by a processor, implements the aircraft trajectory optimization method according to any one of claims 1 to 7.

Description

Aircraft track optimization method and device, electronic equipment and storage medium Technical Field The present invention relates to the field of trajectory optimization technologies, and in particular, to an aircraft trajectory optimization method, an apparatus, an electronic device, and a storage medium. Background The aircraft trajectory optimization is a key technology for realizing the accurate completion of tasks of the aircraft in a complex environment, and particularly has higher requirements on the accuracy and the robustness of the aircraft trajectory optimization in a scene of maneuvering target interception. At present, the trajectory optimization of the aircraft is usually realized by a control law based on a linear model, however, the method is difficult to ensure the accuracy and the robustness of the trajectory of the aircraft, and the requirements of the aircraft under the condition of intercepting maneuvering target scenes are difficult to meet. Disclosure of Invention The invention provides an aircraft track optimization method, an apparatus, electronic equipment and a storage medium, which are used for solving the defects that in the prior art, the accuracy and the robustness of an aircraft track are difficult to ensure by a control law based on a linear model, and the requirements of an aircraft under a maneuvering target interception scene are difficult to meet. The invention provides an aircraft track optimization method, which comprises the following steps: constructing a three-dimensional relative motion model of the aircraft and the maneuvering target; Determining a first control law based on the three-dimensional relative motion model and an adaptive dynamic programming network; Determining an integral sliding mode variable based on the three-dimensional relative motion model and the first control law; determining a second control law based on a semi-positive barrier function, wherein the semi-positive barrier function takes the integral sliding mode variable as an independent variable; and determining a flight control instruction based on the first control law and the second control law, and performing track optimization on the aircraft based on the flight control instruction to obtain an optimized track. According to the aircraft trajectory optimization method provided by the invention, the first control law is determined based on the three-dimensional relative motion model and the self-adaptive dynamic planning network, and the method comprises the following steps: Determining an optimal control performance function based on a state variable penalty and a control quantity penalty of the three-dimensional relative motion model; determining a hamiltonian function based on gradient information of the optimal control performance function on the state variables and dynamic terms and control input terms of the three-dimensional relative motion model; determining an objective function based on the hamiltonian function; updating the weight of the self-adaptive dynamic programming network based on the objective function and the auxiliary function to obtain a self-adaptive dynamic programming updating network; And determining the first control law based on the output value of the adaptive dynamic programming updating network, the control quantity penalty term and the control input term of the three-dimensional relative motion model. According to the aircraft trajectory optimization method provided by the invention, the weight of the self-adaptive dynamic programming network is updated based on the objective function and the auxiliary function to obtain the self-adaptive dynamic programming updating network, and the method comprises the following steps: carrying out normalized gradient descent treatment on the objective function to obtain a first weight updating item; Determining a second weight update term based on the auxiliary function; and updating the weight of the self-adaptive dynamic programming network in real time based on the first weight updating item and the second weight updating item until the self-adaptive dynamic programming network converges, so as to obtain the self-adaptive dynamic programming updating network. According to the aircraft trajectory optimization method provided by the invention, the second control law is determined based on the semi-positive barrier function, and the method comprises the following steps: Substituting the real-time value of the integral sliding mode variable into the semi-positive fixed obstacle function to obtain an obstacle function output value; Determining a sliding mode control gain based on the barrier function output value and a control input matrix of the three-dimensional relative motion model; The second control law is determined based on the sliding mode control gain and a sign function of the integrated sliding mode variable. According to the aircraft trajectory optimization method provided by the invention, the integral sl