Global sliding mode guidance law construction method and device with intersection angle constraint, equipment, medium and product

Abstract

The invention discloses a global sliding mode guidance law construction method and device with intersection angle constraint, equipment, a medium and a product, and relates to the field of guidance laws, and the method comprises the steps: obtaining an expected line-of-sight angle expression according to a missile-target relative kinematics equation and a missile-target intersection angle definition; constructing a nonlinear term of a sliding mode in the global sliding mode control method; based on a global sliding mode control method, a sliding mode expression and an angle constraint guidance law based on global sliding mode control are obtained according to a missile-target relative kinematics equation and a nonlinear term of a sliding mode; by taking the minimum angle error of the missile and the minimum acceleration of the missile in the reward function as targets, optimizing a sliding mode control function in a global sliding mode control method by adopting reinforcement learning to obtain an optimized sliding mode control function; and determining that the function and the expression are global sliding mode guidance laws with intersection angle constraints. According to the method, the acceleration requirement on the guided missile can be reduced while the expected intersection angle hits the target, and the angle error is small.

Description

Technical Field

[0001] The present application relates to the field of guidance law, and in particular to a method, device, equipment, medium and product for constructing a global sliding mode guidance law with intersection angle constraint. Background Art

[0002] With the development of aerospace technology, the speed and maneuverability of aircraft have been greatly improved. In order to improve the damage efficiency, missiles need to hit the target under specific angle constraints, such as head-on hits, vertical hits, etc. Therefore, the guidance law under angle constraints is of great significance.

[0003] Angle constraint guidance includes line of sight angle constraint, heading angle constraint, intersection angle constraint, etc.

[0004] Both the sight angle constraint and the heading angle constraint are angle constraints under a fixed coordinate system. When the target is maneuvering, the damage effect when hitting the target at the expected sight angle or the expected heading angle will be reduced.

[0005] The rendezvous angle constraint is an angle constraint in the target heading coordinate system. When the target is hit at the expected rendezvous angle, the damage effect is not affected by the target maneuver. However, the rendezvous angle constraint has high requirements on the missile's acceleration and large angle error. This is a problem that needs to be solved in the construction of the rendezvous angle constraint guidance law. Summary of the invention

[0006] The purpose of this application is to provide a method, device, equipment, medium and product for constructing a global sliding mode guidance law with an intersection angle constraint, which can reduce the acceleration requirements for the missile while hitting the target at the expected intersection angle and with a small angle error.

[0007] To achieve the above objectives, this application provides the following solutions:

[0008] In a first aspect, the present application provides a method for constructing a global sliding mode guidance law with an intersection angle constraint, comprising:

[0009] Construct the relative kinematic equation of projectile and target;

[0010] The expression of the expected sight angle is obtained according to the relative kinematic equation of the missile and the target and the definition of the missile-target intersection angle;

[0011] Construct the nonlinear term of sliding mode in the global sliding mode control method;

[0012] Based on the global sliding mode control method, the sliding mode expression and the angle constraint guidance law based on global sliding mode control are obtained according to the relative kinematic equation of the missile and the target and the nonlinear term of the sliding mode.

[0013] Taking the minimum angle error of the missile and the acceleration of the missile in the reward function as the goal, reinforcement learning is used to optimize the sliding mode control function in the global sliding mode control method to obtain an optimized sliding mode control function; the angle error is the difference between the sight angle of the missile and the expected sight angle of the missile;

[0014] The expected sight angle expression, the optimized sliding mode control function, the nonlinear term of the sliding mode, the sliding mode expression and the angle constraint guidance law based on the global sliding mode control are determined as the global sliding mode guidance law with the intersection angle constraint.

[0015] In a second aspect, the present application provides a global sliding mode guidance law construction device with intersection angle constraint, comprising:

[0016] The module for constructing the relative kinematics equation of projectile and target is used to construct the relative kinematics equation of projectile and target;

[0017] The module for determining the expression of the expected sight angle is used to obtain the expression of the expected sight angle according to the relative kinematic equation of the missile and the target and the definition of the missile-target intersection angle;

[0018] Nonlinear term building module, used to build nonlinear terms of sliding mode in global sliding mode control method;

[0019] The global sliding mode module is used to obtain the sliding mode expression and the angle constraint guidance law based on the global sliding mode control method according to the relative kinematic equation of the missile and the target and the nonlinear term of the sliding mode;

[0020] A reinforcement learning module is used to optimize the sliding mode control function in the global sliding mode control method by using reinforcement learning with the goal of minimizing the angle error of the missile and the acceleration of the missile in the reward function, so as to obtain an optimized sliding mode control function; the angle error is the difference between the sight angle of the missile and the expected sight angle of the missile;

[0021] The module for determining the global sliding mode guidance law with intersection angle constraint is used to determine the expected sight angle expression, the optimized sliding mode control function, the nonlinear term of the sliding mode, the sliding mode expression and the angle constraint guidance law based on the global sliding mode control as the global sliding mode guidance law with intersection angle constraint.

[0022] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the above-described methods for constructing a global sliding mode guidance law with an intersection angle constraint.

[0023] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-mentioned methods for constructing a global sliding mode guidance law with an intersection angle constraint.

[0024] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned methods for constructing a global sliding mode guidance law with an intersection angle constraint.

[0025] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0026] The present application provides a method, device, equipment, medium and product for constructing a global sliding mode guidance law with a rendezvous angle constraint. The present application optimizes the sliding mode control function in the global sliding mode control method by using reinforcement learning with the goal of minimizing the angle error of the missile and the acceleration of the missile in the reward function, and obtains the optimized sliding mode control function steps, so that the optimized sliding mode control function can achieve the minimum angle error and acceleration, so that the global sliding mode guidance law with the rendezvous angle constraint can reduce the acceleration requirement for the missile and reduce the angle error while hitting the target at the expected rendezvous angle. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0028] Figure 1 This is a flow chart of a method for constructing a global sliding mode guidance law with an intersection angle constraint in one embodiment of the present application;

[0029] Figure 2 This is a schematic diagram of the relative relationship between the projectile and the target;

[0030] Figure 3 A schematic diagram of a global sliding mode guidance law with intersection angle constraint in one embodiment of the present application;

[0031] Figure 4 This is the ballistic simulation result diagram;

[0032] Figure 5 This is the acceleration diagram of the missile during the simulation;

[0033] Figure 6 It is the sliding mode control function diagram of the global sliding mode guidance law in the simulation process;

[0034] Figure 7A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0036] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0037] The method for constructing a global sliding mode guidance law with intersection angle constraint provided in the embodiment of the present application is as follows: Figure 1 and Figure 3 As shown, the steps include steps 201 to 206. Among them:

[0038] Step 201: Construct the relative kinematic equation between the projectile and the target.

[0039] Step 202: Obtain an expression for a desired sight angle according to the relative kinematic equation between the projectile and the target and the definition of the projectile-target intersection angle.

[0040] Step 203: construct the nonlinear term of the sliding mode in the global sliding mode control method.

[0041] Step 204: Based on the global sliding mode control method, the sliding mode expression and the angle constraint guidance law based on the global sliding mode control are obtained according to the relative kinematic equation of the missile and the target and the nonlinear term of the sliding mode.

[0042] Step 205: With the goal of minimizing the angle error of the missile and the acceleration of the missile in the reward function, reinforcement learning is used to optimize the sliding mode control function in the global sliding mode control method to obtain an optimized sliding mode control function; the angle error is the difference between the sight angle of the missile and the expected sight angle of the missile.

[0043] Step 206: Determine the expected sight angle expression, the optimized sliding mode control function, the nonlinear term of the sliding mode, the sliding mode expression and the angle constraint guidance law based on the global sliding mode control as a global sliding mode guidance law with an intersection angle constraint.

[0044] In another exemplary embodiment of the present application, the above step 201 is specifically as follows:

[0045] The motion of a missile in three-dimensional space can be decomposed into two planes, horizontal and vertical, so the problem is studied in the horizontal plane.

[0046] The relative relationship between projectile and target in two-dimensional space is as follows Figure 2 shown. Figure 2 In the figure, Oxy is the absolute coordinate system in the horizontal plane, M represents the missile, T represents the target, the straight line through the missile and the target is called the line of sight (LOS), r represents the distance from the missile M to the target T, q represents the line of sight angle of the missile, that is, the angle between the LOS and the Ox axis, and v M represents the speed of the missile, a M is the missile's acceleration, v T represents the speed of the target, a T Represents the acceleration of the target. The angle between the velocity direction and the Ox axis is called the ballistic deviation angle, σ M represents the ballistic deviation angle of the missile, σ T The angle between the velocity direction and LOS is called the lead angle, η M represents the lead angle of the missile, η T represents the lead angle of the target, Indicates the projectile-target intersection angle.

[0047] The relative kinematic equation of projectile and target is established as follows:

[0048]

[0049] in, represents the first-order derivative of r with respect to time t, represents the first-order derivative of q with respect to time t, Represents σ M The first derivative with respect to time t is Represents σ T The first derivative with respect to time t.

[0050] In another exemplary embodiment of the present application, the above step 202 is replaced by the following steps:

[0051] According to the definition of the projectile-target intersection angle (projectile-target intersection angle Defined as the angle between the target and the missile's velocity direction) to construct the expression for the missile-target intersection angle

[0052] The missile sight angle expression is determined based on the missile-target relative kinematics equation and the missile-target intersection angle expression.

[0053] The expected sight angle expression is obtained based on the missile sight angle expression.

[0054] In practical applications, the missile sight angle expression is determined based on the missile-target relative kinematics equation and the missile-target intersection angle expression, specifically:

[0055] According to the relative kinematic equation of missile and target, and the definition of missile-target intersection angle, the missile sight angle q and target intersection angle can be obtained: The relationship is:

[0056]

[0057] Then the calculation formula of the missile sight angle q can be obtained:

[0058]

[0059] The binary function atan2(·,·) is defined as follows:

[0060]

[0061] The function sgn(·) is defined as follows:

[0062]

[0063] In practical applications, the expected sight angle expression is obtained based on the missile sight angle expression, specifically:

[0064] The expected intersection angle is expressed as The missile meets the target angle The sight angle when the target is hit with zero miss is defined as q d , that is, the expected sight angle of the missile, that is, the expected sight angle must meet two conditions: 1. Expected intersection angle condition 2. Zero miss hit conditions Right now According to the calculation formula of q, the expected sight angle q of the missile can be obtained d The calculation formula of the expected sight angle is:

[0065]

[0066] In another exemplary embodiment of the present application, according to the concept of global sliding mode control, the nonlinear term f(t) of the sliding mode in the global sliding mode control method constructed in the above step 203 needs to satisfy the following three conditions.

[0067]

[0068] Wherein, c is the coefficient of the sliding mode, x1 represents the first component of the state variable, x2 represents the second component of the state variable, x1(0) represents the value of x1 when time t=0, and x2(0) represents the value of x2 when time t=0.

[0069] In order to satisfy these three conditions, f(t) is designed as

[0070]

[0071] Among them, q0 and is when t = 0 q and The initial value of It means that when t = 0 The initial value of u(t)∈[u min ,u max ], where u min The lower bound of u(t) is an arbitrarily small positive number, u max represents the upper bound of u(t).

[0072] In another exemplary embodiment of the present application, the desired sight angle q d To hit the target, the above step 204 is replaced by the following steps:

[0073] Constructing the equation of state Among them, x1 represents the first component of the state variable, x2 represents the second component of the state variable, Indicates q d The first derivative with respect to time t.

[0074] The relative motion state equation of the projectile and the target is obtained according to the state equation and the relative kinematic equation of the projectile and the target in, represents the first-order derivative of x1 with respect to time t, represents the first-order derivative of x2 with respect to time t, Represents σ T The second derivative with respect to time t is the angular acceleration of the target's ballistic deviation angle.

[0075] Construct the sliding mode s=cs1+x2-f(t).

[0076] The sliding mode of the projectile-target motion is obtained according to the projectile-target relative motion state equation and the sliding mode. Specifically, the projectile-target relative motion state equation is substituted into the sliding mode to obtain the expression of the sliding mode s, i.e., the projectile-target motion sliding mode:

[0077]

[0078] The nonlinear term of the sliding mode is differentiated to obtain the derivative nonlinear term of the sliding mode f'(t)=-u(t)f(t).

[0079] Constructing the sliding mode reaching law Here, ε is a small positive number.

[0080] According to the sliding mode reaching law The missile acceleration expression is obtained by the sliding mode of the missile-target motion and the nonlinear term of the sliding mode after differentiation.

[0081] According to the missile acceleration expression and the target's ballistic deflection acceleration The estimated value expression of is used to obtain the angle constrained guidance law based on global sliding mode control.

[0082] In practical applications, according to the sliding mode reaching law The missile acceleration expression is obtained by the sliding mode of the missile-target motion and the nonlinear term of the sliding mode after derivative:

[0083] According to the designed sliding mode reaching law As well as the expression of the sliding mode s and the derivative of f(t), we get

[0084] The inverse solution is used to obtain the missile acceleration expression:

[0085] In practical applications, according to the missile acceleration expression and the angular acceleration of the target's trajectory deflection angle, The estimated value expression of is used to obtain the angle constraint guidance law based on global sliding mode control, which is:

[0086] Target The measurement error is large and cannot be used as a known quantity. is bounded, Indicates a T The first derivative with respect to time t is express The upper bound of , according to the Lyapunov stability condition, Estimated value of Can be designed as:

[0087]

[0088] Will Substituting the missile acceleration expression, the angle constraint guidance law based on global sliding mode control is obtained as follows:

[0089]

[0090] In another exemplary embodiment of the present application, the sliding mode control function u(t) can be optimized by reinforcement learning. The optimization object of reinforcement learning is the agent θ, the input variable of the agent, i.e., the state, is S, and the output variable, i.e., the action, is A, i.e., A=θ(S).

[0091] The classic DDPG algorithm is used as the reinforcement learning method. The environment consists of the missile motion state and the target motion state. The DDPG algorithm only needs to determine the input variable S, output variable A, and reward function R to perform training.

[0092] The input variables include: the distance from the missile to the target, the sight angle of the missile, the expected sight angle of the missile, the speed of the missile, the ballistic deviation angle of the missile, the speed of the target, the ballistic deviation angle of the target and the acceleration of the target. d ,v M ,σ M ,v T ,σ T ,a T}. The output variable is the sliding mode control function to be optimized u(t), that is, A = u(t). Therefore, the sliding mode control function to be optimized can be expressed as:

[0093] u(t)=θ(r,q,q d ,v M ,σ M ,v T ,σ T ,a T )

[0094] The agent’s reward function is designed as:

[0095] R=-c q (qq d )-c a a M

[0096] Among them, R represents the reward function, c q Indicates QQ d The cost coefficient of (angle error). c a represents the missile acceleration a M The reward function is designed to minimize the angle error and missile acceleration.

[0097] Use the DDPG algorithm for training. The training process is the process of maximizing the reward function. After the training, the optimal agent can be obtained. That is, the goal is to minimize the angular error of the missile and the acceleration of the missile in the reward function, the distance from the missile to the target, the sight angle of the missile, the expected sight angle of the missile, the speed of the missile, the ballistic angle of the missile, the speed of the target, the ballistic angle of the target and the acceleration of the target are taken as the states, and the sliding mode control function in the global sliding mode control method is taken as the action. The DDPG algorithm is used to optimize the intelligent agent to obtain

[0098] The optimized sliding mode control function u can be expressed as:

[0099]

[0100] In another exemplary embodiment of the present application, the global sliding mode guidance law with intersection angle constraint is:

[0101]

[0102] This application first calculates the expected sight angle through the expected intersection angle, and then adjusts the angle constraint guidance law through a sliding mode control function based on the global sliding mode control method. Finally, the sliding mode control function is optimized through reinforcement learning. The specific process is as follows Figure 3 The advantage of global sliding mode control is that it has strong anti-interference performance. The design of the reinforcement learning reward function enables the optimized global sliding mode function to achieve the minimum angle error and acceleration. Therefore, this application has both strong anti-interference performance and small acceleration and angle error, thereby achieving the ultimate goal: hitting the maneuvering target under the intersection angle constraint.

[0103] The present application also provides an embodiment of ballistic simulation using the above method, and compares it with two other guidance laws. The three guidance laws involved in the simulation are: a trained global sliding mode guidance law (a global sliding mode guidance law with intersection angle constraint provided in the embodiment of the present application), an untrained global sliding mode guidance law (the sliding mode control function u(t) takes a certain constant, and u(t)=0.5 is set in the simulation), and a traditional sliding mode guidance law (the sliding mode does not contain nonlinear terms, that is, f(t)=0). At the initial moment of the simulation, the missile position is (0m, 0m), the target position is (10000m, 2000m), the missile speed is 1000m / s, and the target speed is 400m / s. The results are as follows: Figures 4 to 6 As shown, Figure 4 The x-axis represents the position in the x direction in the horizontal plane, and the y-axis represents the position in the y direction in the horizontal plane, both in meters. Figure 5 The x-axis represents the simulation time in seconds, and the y-axis represents the missile acceleration in m / s. 2 , Figure 6 The x-axis represents the simulation time in seconds, and the y-axis represents the sliding mode control function, which is dimensionless. Figure 4 and Figure 6 It can be seen that the trained global sliding mode guidance law has a straighter trajectory and a smaller missile acceleration than the other two guidance laws. It can reduce the acceleration requirement for the missile while hitting the target at the expected intersection angle and has a small angle error.

[0104] The present application also provides an application scenario, which applies the above-mentioned global sliding mode guidance law construction method with intersection angle constraint. Specifically: the global sliding mode guidance law construction method with intersection angle constraint provided in this embodiment can be applied in the guidance scenario. The internal distribution scenario includes guidance law construction and guidance according to the guidance law. The global sliding mode guidance law construction method with intersection angle constraint provided in this embodiment belongs to the guidance law construction link.

[0105] Based on the same inventive concept, the embodiment of the present application also provides a device for constructing a global sliding mode guidance law with intersection angle constraint for implementing the method for constructing a global sliding mode guidance law with intersection angle constraint mentioned above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of one or more devices for constructing a global sliding mode guidance law with intersection angle constraint provided below can refer to the limitations of the method for constructing a global sliding mode guidance law with intersection angle constraint mentioned above, and will not be repeated here.

[0106] In an exemplary embodiment, a global sliding mode guidance law construction device with intersection angle constraint is provided, comprising:

[0107] The module for constructing the relative kinematics equation between projectile and target is used to construct the relative kinematics equation between projectile and target.

[0108] The module for determining the expression of the expected sight angle is used to obtain the expression of the expected sight angle according to the relative kinematic equation between the missile and the target and the definition of the missile-target intersection angle.

[0109] The nonlinear term building module is used to build the nonlinear terms of the sliding mode in the global sliding mode control method.

[0110] The global sliding mode module is used to obtain the sliding mode expression and the angle constraint guidance law based on the global sliding mode control method according to the relative kinematic equation of the projectile and the target and the nonlinear terms of the sliding mode.

[0111] The reinforcement learning module is used to optimize the sliding mode control function in the global sliding mode control method by using reinforcement learning with the goal of minimizing the angle error of the missile and the acceleration of the missile in the reward function, so as to obtain the optimized sliding mode control function; the angle error is the difference between the sight angle of the missile and the expected sight angle of the missile.

[0112] The module for determining the global sliding mode guidance law with intersection angle constraint is used to determine the expected sight angle expression, the optimized sliding mode control function, the nonlinear term of the sliding mode, the sliding mode expression and the angle constraint guidance law based on the global sliding mode control as the global sliding mode guidance law with intersection angle constraint.

[0113] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 7 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store global sliding mode guidance law construction data with intersection angle constraints. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for constructing a global sliding mode guidance law with an intersection angle constraint is implemented.

[0114] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the above-mentioned method embodiments when executing the computer program.

[0115] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the above-mentioned method embodiments are implemented.

[0116] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the above-mentioned method embodiments are implemented.

[0117] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0118] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0119] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0120] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0121] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for constructing a global sliding mode guidance law with intersection angle constraint, characterized in that: The method for constructing a global sliding mode guidance law with an intersection angle constraint includes: Construct the relative kinematic equation of projectile and target; The expression of the expected sight angle is obtained according to the relative kinematic equation of the missile and the target and the definition of the missile-target intersection angle; Construct the nonlinear term of sliding mode in the global sliding mode control method; Based on the global sliding mode control method, the sliding mode expression and the angle constraint guidance law based on global sliding mode control are obtained according to the relative kinematic equation of the missile and the target and the nonlinear term of the sliding mode. Taking the minimum angle error of the missile and the acceleration of the missile in the reward function as the goal, reinforcement learning is used to optimize the sliding mode control function in the global sliding mode control method to obtain an optimized sliding mode control function; the angle error is the difference between the sight angle of the missile and the expected sight angle of the missile; The expected sight angle expression, the optimized sliding mode control function, the nonlinear term of the sliding mode, the sliding mode expression and the angle constraint guidance law based on the global sliding mode control are determined as the global sliding mode guidance law with the intersection angle constraint.

2. The method for constructing a global sliding mode guidance law with intersection angle constraint according to claim 1, characterized in that: The expression of the expected sight angle is obtained according to the relative kinematic equation of the projectile and the target and the definition of the projectile-target intersection angle, specifically including: Construct the projectile-target intersection angle expression according to the definition of projectile-target intersection angle; Determine the missile sight angle expression based on the missile-target relative kinematics equation and the missile-target intersection angle expression; The expected sight angle expression is obtained based on the missile sight angle expression.

3. The method for constructing a global sliding mode guidance law with intersection angle constraint according to claim 1, characterized in that: Based on the global sliding mode control method, the sliding mode expression and the angle constraint guidance law based on global sliding mode control are obtained according to the relative kinematic equation of the missile and the target and the nonlinear term of the sliding mode, which specifically include: Construct the equation of state; Obtaining a relative motion state equation of the projectile and the target according to the state equation and the relative kinematic equation of the projectile and the target; Construct sliding modes; Obtaining a projectile-target motion sliding mode according to the projectile-target relative motion state equation and the sliding mode; The nonlinear term of the sliding mode is derived to obtain the nonlinear term of the sliding mode after derivative; Construct the sliding mode reaching law; The missile acceleration expression is obtained according to the sliding mode approaching law, the sliding mode of missile-target motion and the nonlinear term of the sliding mode after derivative. According to the missile acceleration expression and the estimated value expression of the angular acceleration of the target's trajectory deviation angle, the angle constraint guidance law based on global sliding mode control is obtained.

4. The method for constructing a global sliding mode guidance law with intersection angle constraint according to claim 1, characterized in that: Taking the minimization of the missile's angle error and the missile's acceleration in the reward function as the goal, reinforcement learning is used to optimize the sliding mode control function in the global sliding mode control method to obtain the optimized sliding mode control function. The angle error is the difference between the sight angle of the missile and the expected sight angle of the missile, specifically including: The goal is to minimize the angular error of the missile and the acceleration of the missile in the reward function, and the distance from the missile to the target, the sight angle of the missile, the expected sight angle of the missile, the speed of the missile, the ballistic angle of the missile, the speed of the target, the ballistic angle of the target and the acceleration of the target are taken as the states. The sliding mode control function in the global sliding mode control method is taken as the action, and the DDPG algorithm is used to optimize the intelligent agent. The optimized sliding mode control function is obtained according to the optimized intelligent agent.

5. The method for constructing a global sliding mode guidance law with intersection angle constraint according to claim 4, characterized in that: The reward function is: R=-c q (qq d )-c a a M , where R represents the reward function, q represents the sight angle of the missile, and q d represents the expected sight angle of the missile, c q Indicates q and q d The cost coefficient of the difference, a M is the acceleration of the missile, c a Indicates a M The cost coefficient.

6. A device for constructing a global sliding mode guidance law with intersection angle constraints, characterized in that: The global sliding mode guidance law construction device with intersection angle constraint comprises: The module for constructing the relative kinematics equation of projectile and target is used to construct the relative kinematics equation of projectile and target; The module for determining the expression of the expected sight angle is used to obtain the expression of the expected sight angle according to the relative kinematic equation of the missile and the target and the definition of the missile-target intersection angle; Nonlinear term building module, used to build nonlinear terms of sliding mode in global sliding mode control method; The global sliding mode module is used to obtain the sliding mode expression and the angle constraint guidance law based on the global sliding mode control method according to the relative kinematic equation of the missile and the target and the nonlinear term of the sliding mode; A reinforcement learning module is used to optimize the sliding mode control function in the global sliding mode control method by using reinforcement learning with the goal of minimizing the angle error of the missile and the acceleration of the missile in the reward function, so as to obtain an optimized sliding mode control function; the angle error is the difference between the sight angle of the missile and the expected sight angle of the missile; The module for determining the global sliding mode guidance law with intersection angle constraint is used to determine the expected sight angle expression, the optimized sliding mode control function, the nonlinear term of the sliding mode, the sliding mode expression and the angle constraint guidance law based on the global sliding mode control as the global sliding mode guidance law with intersection angle constraint.

7. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for constructing a global sliding mode guidance law with an intersection angle constraint as described in any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for constructing a global sliding mode guidance law with intersection angle constraint as described in any one of claims 1 to 5 is implemented.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for constructing a global sliding mode guidance law with intersection angle constraint as described in any one of claims 1 to 5 is implemented.

Images