Carrier rocket load shedding control method and system based on LSTM-FCNN attack angle estimation

The angle of attack of the rocket is estimated through the LSTM-FCNN deep neural network and introduced a control system, solving the problem of excessive aerodynamic load in high altitude flight, and improving the adaptability and structural safety of the launch vehicle.

CN118936245AActive Publication Date: 2024-11-12DALIAN UNIV OF TECH

Patent Information

Application Number
CN202411071704.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-06
Publication Date
2024-11-12
Estimated Expiration
2044-08-06

AI Technical Summary

Technical Problem

The prior art is difficult to accurately measure and utilize angle of attack information during high-altitude flight of launch vehicles, resulting in excessive aerodynamic load, affecting the safety of rocket structure and launch cost.

Method used

A deep neural network based on LSTM-FCNN is adopted to establish the relationship between attitude response and wind speed mapping through the flight status and wind speed data of the rocket in high-altitude wind area, estimate the angle of attack and introduce the control system to reduce the aerodynamic load.

Benefits of technology

The accuracy of angle of attack estimation is improved, the aerodynamic load of the launch vehicle is reduced, the flight adaptability in high-altitude wind areas is enhanced, and the influence of structural interference and measurement noise is avoided.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118936245A_ABST
    Figure CN118936245A_ABST
Patent Text Reader

Abstract

The invention discloses a carrier rocket load shedding control method and system based on LSTM-FCNN attack angle estimation, and relates to the technical field of carrier rocket control, and the method comprises the following steps: generating a data set according to flight state data of a rocket in a high-altitude wind region and measured wind speed data, and processing the data set through linear normalization; training an LSTM-FCNN deep neural network by using the normalized data, and establishing a mapping relation between the rocket attitude response and the wind speed; and the trained LSTM-FCNN deep neural network is migrated to the actual flight of the rocket, the attack angle is obtained based on the estimated high-altitude wind speed, and then a load shedding control method based on attack angle feedback is adopted to reduce the aerodynamic load of the carrier rocket. The method improves the estimation precision of the attack angle under the condition that the wind field is uncertain, reduces the aerodynamic load of the carrier rocket, and improves the adaptability of the carrier rocket flying in a high-altitude wind area.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of launch vehicle control technology, and in particular to a launch vehicle load reduction control method and system based on LSTM-FCNN angle of attack estimation. Background Art

[0002] When a launch vehicle flies in a dense atmosphere, it is subjected to high-altitude winds and generates large aerodynamic loads. If the load level exceeds the carrying capacity of the rocket body's structural strength, the rocket body will be damaged, causing devastating effects on the flight mission. Reducing the impact of high-altitude winds on launch vehicles, reducing the aerodynamic loads of launch vehicles, and ensuring their safe and reliable flight in windy areas are difficult problems faced by the launch field. If the load reduction control technology can be better utilized to reduce the aerodynamic loads of launch vehicles, the requirements for the rocket's structural strength can be appropriately reduced during the design, the structural mass of the launch vehicle can be reduced, the carrying capacity can be improved, and the launch cost can be reduced.

[0003] At present, there are two types of control schemes for reducing aerodynamic loads: passive load reduction, also known as "ballistic wind correction", and active load reduction. Passive load reduction uses data information from the wind field to design the optimal trajectory, thereby minimizing the expected aerodynamic load on the launch vehicle before launch. The compensation effect of passive load reduction mainly depends on the accuracy of the model and the accuracy of the judgment of the wind field law before launch. Active load reduction introduces angle of attack information into the control, so that the launch vehicle has a tendency to fly against the airflow, thereby reducing the rocket's angle of attack and sideslip angle during flight, and reducing the aerodynamic load on the rocket. The key to active load reduction lies in the measurement of angle of attack information, which is generally divided into two methods: direct measurement and indirect measurement. Direct measurement obtains the flight angle of attack through an angle of attack sensor, but considering the measurement accuracy and installation and use issues, it has not yet been involved in real-time control on the launch vehicle. Indirect measurement uses information from accelerometers and extended state observers to perform load shedding control. However, directly introducing accelerometer signals into the control loop will change the structure of the control system, which in turn affects the stability of the control loop. The extended state observer cannot distinguish between structural interference and wind interference, and the estimated angle of attack information is more accurate only when wind interference is the main factor. Therefore, the key to active load shedding control is to comprehensively utilize measurement information and related overall parameters and develop a high-precision angle of attack estimation method.

[0004] Chinese patent document CN117146660A discloses a rocket load reduction control method based on multi-source sensors, which relates to the field of aerospace, including: considering multiple rocket parameters, designing a rocket attitude controller, and establishing a rocket load reduction control task model; using a load reduction accelerometer to obtain the rocket normal acceleration; the rocket normal acceleration includes the normal acceleration caused by aerodynamic force and the normal acceleration caused by engine thrust; during the rocket flight, using the engine chamber pressure sensor to measure the chamber pressure in real time to determine the real-time engine thrust of the rocket; determining the normal acceleration caused by the aerodynamic force according to the rocket normal acceleration and the engine thrust; adding the normal acceleration feedback corresponding to the normal acceleration caused by the aerodynamic force to the rocket attitude controller, and determining the total airflow attack angle after the reduction based on the rocket load reduction control task model, thereby realizing the precise load reduction control of the rocket in the ascending stage. Although it can determine the normal acceleration caused by the aerodynamic force according to the rocket normal acceleration and the engine thrust, this method relies on the measurement accuracy of the chamber pressure sensor and cannot eliminate the influence of structural interference in the normal acceleration.

[0005] Chinese patent document CN115729096A discloses a method and system for reducing the load of a sounding rocket, which uses an angle of attack sensor to measure the wind angle of attack, introduces the real-time angle of attack into the control system loop of the sounding rocket, and compensates for wind interference by controlling the engine swing, so that the load on the sounding rocket in the windy area is minimized, the aerodynamic torque caused by the wind is reduced, and the launch adaptability of the sounding rocket is improved. Although it can measure the angle of attack according to the angle of attack sensor and then control the rocket to reduce the load, due to the installation restrictions of the angle of attack sensor, most rockets cannot directly install the angle of attack sensor to measure the angle of attack. Summary of the invention

[0006] The purpose of the present invention is to propose a launch vehicle load reduction control method and system based on LSTM-FCNN angle of attack estimation, to improve the estimation accuracy of the angle of attack under uncertain wind field conditions, to reduce the aerodynamic load of the launch vehicle, and to improve the adaptability of the launch vehicle to fly in high-altitude wind areas.

[0007] According to a first aspect of an embodiment of the present disclosure, a launch vehicle load reduction control method based on LSTM-FCNN angle of attack estimation is provided, comprising the following steps:

[0008] A data set is generated based on the flight status data of the rocket in the high-altitude wind area and the measured wind speed data, and the data set is processed using linear normalization;

[0009] The normalized data is used to train the LSTM-FCNN deep neural network to establish the mapping relationship between the rocket attitude response and the wind speed;

[0010] The trained LSTM-FCNN deep neural network is transferred to the actual flight of the rocket. The angle of attack is obtained based on the estimated high-altitude wind speed, and then a load reduction control method based on angle of attack feedback is adopted to reduce the aerodynamic load of the launch vehicle.

[0011] According to a second aspect of an embodiment of the present disclosure, a launch vehicle load reduction control system based on LSTM-FCNN angle of attack estimation is provided, including:

[0012] The data acquisition module generates a data set based on the flight status data of the rocket in the high-altitude wind area and the measured wind speed data, and processes the data set using linear normalization;

[0013] The mapping relationship establishment module uses the normalized data to train the LSTM-FCNN deep neural network to establish the mapping relationship between the rocket attitude response and the wind speed;

[0014] The load reduction control module transfers the trained LSTM-FCNN deep neural network to the actual flight of the rocket, obtains the angle of attack based on the estimated high-altitude wind speed, and then adopts a load reduction control method based on angle of attack feedback to reduce the aerodynamic load of the launch vehicle.

[0015] According to a third aspect of an embodiment of the present disclosure, there is provided an electronic device, comprising a memory, a processor, and a computer program stored and running on the memory, wherein when the processor executes the program, the method for controlling a launch vehicle load reduction based on LSTM-FCNN angle of attack estimation is implemented.

[0016] According to the fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the launch vehicle load reduction control method based on LSTM-FCNN angle of attack estimation is implemented.

[0017] Compared with the prior art, the above technical scheme adopted by the present invention has the following advantages: (1) In view of the limited accuracy of the angle of attack estimation of the launch vehicle, the present invention uses the LSTM-FCNN deep neural network to establish a mapping relationship between the rocket attitude response and the wind speed, and estimates the angle of attack by estimating the wind speed, thereby effectively improving the accuracy of the angle of attack estimation with wind field uncertainty.

[0018] (2) In view of the situation where the aerodynamic load of a launch vehicle is too large during flight, the present invention obtains the angle of attack information and introduces it into the control system, which can effectively reduce the aerodynamic load of the launch vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings in the specification, which constitute a part of the present application, are used to provide further understanding of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute improper limitations on the present application.

[0020] Figure 1 This is the principle block diagram of the launch vehicle load reduction control method based on LSTM-FCNN angle of attack estimation. Specific implementation methods

[0022] The present disclosure is further described below in conjunction with the accompanying drawings and embodiments.

[0023] It should be noted that the following detailed descriptions are illustrative and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.

[0024] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0025] It should be noted that the flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the methods and systems according to various embodiments of the present disclosure. It should be noted that each box in the flowchart or block diagram can represent a module, a program segment, or a part of a code, and the module, program segment, or a part of a code may include one or more executable instructions for implementing the logical functions specified in each embodiment. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, or they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the flowchart and / or block diagram, and the combination of boxes in the flowchart and / or block diagram can be implemented using a dedicated hardware-based system that performs a specified function or operation, or can be implemented using a combination of dedicated hardware and computer instructions.

[0026] Embodiment 1:

[0027] like Figure 1 As shown, this embodiment provides a launch vehicle load reduction control method based on LSTM-FCNN attack angle estimation, comprising the following steps:

[0028] Step 1: Generate a data set based on the rocket's flight status data in the high-altitude wind area and the measured wind speed data, and process the data set using linear normalization;

[0029] Specifically, in order to avoid large network prediction errors caused by large differences in order of magnitude, and to speed up the network training speed and improve the prediction accuracy, the data normalization method used in the present invention is linear normalization, and the formula is:

[0030]

[0031] Where x′ is the normalized data, the normalized data range is [0,1], max(x) and min(x) are the maximum and minimum values ​​of the data respectively.

[0032] Step 2: Use the normalized data to train the LSTM-FCNN deep neural network to establish the mapping relationship between the rocket attitude response and wind speed; specifically,

[0033] By analyzing the motion of the launch vehicle's center of mass and around its center of mass, the input of the LSTM-FCNN deep neural network is established as:

[0034]

[0035] The output is

[0036]

[0037] Where t0 is the starting time of each state quantity in the sequence, t f For the end of time, is the pitch angle deviation, Δψ is the yaw angle deviation, is the apparent acceleration deviation in the y direction, is the apparent acceleration deviation in the z direction, V fx is the wind speed in the x direction, V fz is the wind speed in the z direction, H(t0) is the rocket flight altitude at time t0, H(t f ) is t f The rocket's flight altitude at that moment.

[0038] The long-short cycle neural network LSTM is used to process the flight status data and wind speed data sequences, and the multi-layer fully connected neural network FCNN is used to extract features from the output of the long-short cycle neural network LSTM to obtain a more accurate mapping relationship that is closer to the actual situation. The activation function between each layer of the neural network is Relu.

[0039] The normalized data is used to train the LSTM-FCNN deep neural network. The training algorithm uses the Adam algorithm, and the network weights are continuously adjusted according to the loss function and evaluation index until the network converges and the training is completed. The loss function during training is the mean square error function MSE, and the evaluation index is the root mean square error function RMSE, which is defined as:

[0040]

[0041] in is the predicted value of the neural network, y i is the true value, and n is the number of training samples.

[0042] Step 3: Migrate the trained LSTM-FCNN deep neural network to the actual flight of the rocket, obtain the angle of attack based on the estimated high-altitude wind speed, and then adopt a load reduction control method based on angle of attack feedback to reduce the aerodynamic load of the launch vehicle.

[0043] The trained LSTM-FCNN deep neural network is used to estimate the wind speed online, and the angle of attack is obtained based on the wind speed, specifically:

[0044] Convert rocket velocity from launch system to arrow system:

[0045]

[0046] in is the coordinate transformation matrix from the rocket launch system to the arrow system, V x 、V y 、V z is the velocity of the rocket relative to the ground in three directions in the launch coordinate system, V qxB 、V qyB 、V qzB is the rocket's air speed in three directions in the rocket body coordinate system;

[0047] In the arrow system, the rocket attack angle and sideslip angle are obtained based on the air speed as follows:

[0048]

[0049] In the above formula, V qB is the air speed of the rocket in the rocket body coordinate system, α1 and β1 are the total angle of attack and total sideslip angle respectively. The specific expressions are as follows:

[0050]

[0051] Where α is the response angle of attack, α w is the airflow attack angle, β is the response sideslip angle, β w is the airflow sideslip angle.

[0052] After estimating the angle of attack, the angle of attack information is introduced into the control system, and the rocket pitch channel control equation is as follows:

[0053]

[0054] in is the attitude angle feedback gain coefficient, is the attitude angular velocity feedback gain coefficient, is the angle of attack feedback load reduction gain coefficient, Δα is the response angle of attack deviation, It is the engine swing angle command.

[0055] When considering the influence of shear wind, the rocket pitch attitude motion equation can be expressed as:

[0056]

[0057] where α wq is the airflow attack angle caused by shear wind, and the coefficient The expression is as follows:

[0058]

[0059] in is the moment of inertia of the pitch channel, is the derivative of the normal aerodynamic coefficient with respect to α, q is the dynamic pressure, S M is the reference cross-sectional area of ​​the rocket, X d is the distance from the theoretical tip of the rocket to the aerodynamic pressure center, X z is the distance from the theoretical tip of the rocket to the center of mass, P is the rocket thrust, X R is the distance from the engine swing point to the theoretical tip of the rocket body, m R is the mass of the swinging part of a single engine, is the apparent longitudinal acceleration of the rocket body, l R is the distance from the engine mass center to the swing axis.

[0060] Further combining equation (8) and equation (9), we can get the total angle of attack deviation caused by shear wind:

[0061]

[0062] Formula (12) shows that after introducing the angle of attack information estimated by the neural network, by selecting the appropriate The selected value can reduce the total angle of attack, thereby reducing the aerodynamic load on the rocket body and improving the adaptability of the launch vehicle to fly in high-altitude wind areas.

[0063] This method can resist the influence of structural interference force and measurement noise under the condition of uncertain wind field and improve the accuracy of angle of attack estimation. It does not require additional measurement equipment and is easy to implement. It can effectively reduce the aerodynamic load of the rocket and improve the adaptability of the launch vehicle to fly in high-altitude wind areas.

[0064] Embodiment 2:

[0065] This embodiment provides a launch vehicle load reduction control system based on LSTM-FCNN angle of attack estimation, including:

[0066] The data acquisition module generates a data set based on the flight status data of the rocket in the high-altitude wind area and the measured wind speed data, and processes the data set using linear normalization;

[0067] The mapping relationship establishment module uses the normalized data to train the LSTM-FCNN deep neural network to establish the mapping relationship between the rocket attitude response and the wind speed;

[0068] The load reduction control module transfers the trained LSTM-FCNN deep neural network to the actual flight of the rocket, obtains the angle of attack based on the estimated high-altitude wind speed, and then adopts a load reduction control method based on angle of attack feedback to reduce the aerodynamic load of the launch vehicle.

[0069] Embodiment three:

[0070] An electronic device includes a memory, a processor, and a computer program stored and running on the memory, wherein the processor implements the above-mentioned launch vehicle load reduction control method based on LSTM-FCNN attack angle estimation when executing the program, including:

[0071] A data set is generated based on the flight status data of the rocket in the high-altitude wind area and the measured wind speed data, and the data set is processed using linear normalization;

[0072] The normalized data is used to train the LSTM-FCNN deep neural network to establish the mapping relationship between the rocket attitude response and the wind speed;

[0073] The trained LSTM-FCNN deep neural network is transferred to the actual flight of the rocket. The angle of attack is obtained based on the estimated high-altitude wind speed, and then a load reduction control method based on angle of attack feedback is adopted to reduce the aerodynamic load of the launch vehicle.

[0074] Embodiment 4:

[0075] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned launch vehicle load reduction control method based on LSTM-FCNN angle of attack estimation, including:

[0076] A data set is generated based on the flight status data of the rocket in the high-altitude wind area and the measured wind speed data, and the data set is processed using linear normalization;

[0077] The normalized data is used to train the LSTM-FCNN deep neural network to establish the mapping relationship between the rocket attitude response and the wind speed;

[0078] The trained LSTM-FCNN deep neural network is transferred to the actual flight of the rocket. The angle of attack is obtained based on the estimated high-altitude wind speed, and then a load reduction control method based on angle of attack feedback is adopted to reduce the aerodynamic load of the launch vehicle.

[0079] Those skilled in the art should understand that the modules or steps of the present disclosure can be implemented by a general-purpose computer device, or alternatively, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. The present disclosure is not limited to any specific combination of hardware and software.

[0080] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0081] Although the above describes the specific implementation methods of the present disclosure in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present disclosure. Technical personnel in the relevant field should understand that on the basis of the technical solution of the present disclosure, various modifications or variations that can be made by those skilled in the art without creative work are still within the scope of protection of the present disclosure.

Claims

1. A launch vehicle load reduction control method based on LSTM-FCNN angle of attack estimation, characterized in that: The following steps are involved: A data set is generated based on the flight status data of the rocket in the high-altitude wind area and the measured wind speed data, and the data set is processed using linear normalization; The normalized data is used to train the LSTM-FCNN deep neural network to establish the mapping relationship between the rocket attitude response and the wind speed; The trained LSTM-FCNN deep neural network is transferred to the actual flight of the rocket. The angle of attack is obtained based on the estimated high-altitude wind speed, and then a load reduction control method based on angle of attack feedback is adopted to reduce the aerodynamic load of the launch vehicle.

2. According to claim 1, a launch vehicle load reduction control method based on LSTM-FCNN angle of attack estimation is characterized in that: By analyzing the motion of the launch vehicle's center of mass and around its center of mass, the input of the LSTM-FCNN deep neural network is established as: The output is: Where t0 is the starting time of each state quantity in the sequence, t f For the end of time, is the pitch angle deviation, Δψ is the yaw angle deviation, is the apparent acceleration deviation in the y direction, is the apparent acceleration deviation in the z direction, V fx is the wind speed in the x direction, V fz is the wind speed in the z direction, H(t0) is the rocket flight altitude at time t0, H(t f ) is t f The rocket's flight altitude at that moment.

3. According to claim 1, a launch vehicle load reduction control method based on LSTM-FCNN angle of attack estimation is characterized in that: In the LSTM-FCNN deep neural network, the long-short cycle neural network LSTM is first used to process the flight status data and wind speed data sequences, and the multi-layer fully connected neural network FCNN is combined to extract features from the output of the long-short cycle neural network LSTM to obtain a mapping relationship close to the actual situation.

4. According to claim 1, a launch vehicle load reduction control method based on LSTM-FCNN angle of attack estimation is characterized in that: The trained LSTM-FCNN deep neural network is used to estimate the wind speed online, and the angle of attack is obtained based on the wind speed, specifically: Convert rocket velocity from launch system to arrow system: in is the coordinate transformation matrix from the rocket launch system to the arrow system, V x 、V y 、V z is the velocity of the rocket relative to the ground in three directions in the launch coordinate system, V qxB 、V qyB 、V qzB is the rocket's air speed in three directions in the rocket body coordinate system; In the arrow system, the rocket attack angle and sideslip angle are obtained based on the air speed as follows: In the above formula, V qB is the air speed of the rocket in the rocket body coordinate system, α1 and β1 are the total angle of attack and total sideslip angle respectively. The specific expressions are as follows: Where α is the response angle of attack, α w is the airflow attack angle, β is the response sideslip angle, β w is the airflow sideslip angle.

5. According to claim 4, a launch vehicle load reduction control method based on LSTM-FCNN angle of attack estimation is characterized in that: Introducing the angle of attack information into the control system, the rocket pitch channel control equation is as follows: in is the attitude angle feedback gain coefficient, is the attitude angular velocity feedback gain coefficient, is the angle of attack feedback load reduction gain coefficient, Δα is the response angle of attack deviation, It is the engine swing angle command.

6. According to claim 4, a launch vehicle load reduction control method based on LSTM-FCNN angle of attack estimation is characterized in that: When considering the effect of shear wind, the rocket pitch attitude motion equation is expressed as: where α wq is the airflow attack angle caused by shear wind, and the coefficient The expression is as follows: in is the moment of inertia of the pitch channel, is the derivative of the normal aerodynamic coefficient with respect to α, q is the dynamic pressure, S M is the reference cross-sectional area of ​​the rocket, X d is the distance from the theoretical tip of the rocket to the aerodynamic pressure center, X z is the distance from the theoretical tip of the rocket to the center of mass, P is the rocket thrust, X R is the distance from the engine swing point to the theoretical tip of the rocket body, m R is the mass of the swinging part of a single engine, is the apparent longitudinal acceleration of the rocket body, l R is the distance from the engine center of mass to the swing axis.

7. A launch vehicle load reduction control method based on LSTM-FCNN angle of attack estimation according to claim 5 or 6, characterized in that: The total angle of attack deviation caused by shear wind is: The above formula shows that after introducing the angle of attack information estimated by the neural network, by selecting The value reduces the total angle of attack, thereby reducing the aerodynamic load on the rocket body and improving the launch vehicle's adaptability to flying in high-altitude wind areas.

8. A launch vehicle load reduction control system based on LSTM-FCNN angle of attack estimation, characterized in that: include: The data acquisition module generates a data set based on the flight status data of the rocket in the high-altitude wind area and the measured wind speed data, and processes the data set using linear normalization; The mapping relationship establishment module uses the normalized data to train the LSTM-FCNN deep neural network to establish the mapping relationship between the rocket attitude response and the wind speed; The load reduction control module transfers the trained LSTM-FCNN deep neural network to the actual flight of the rocket, obtains the angle of attack based on the estimated high-altitude wind speed, and then adopts a load reduction control method based on angle of attack feedback to reduce the aerodynamic load of the launch vehicle.

9. An electronic device comprising a memory, a processor and a computer program stored and running on the memory, characterized in that: When the processor executes the program, the launch vehicle load reduction control method based on LSTM-FCNN angle of attack estimation is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by the processor, a launch vehicle load reduction control method based on LSTM-FCNN angle of attack estimation is implemented.

Citation Information

Patent Citations

  • Sounding rocket load shedding method and system

    CN115729096A

  • Rocket load shedding control method based on multi-source sensor

    CN117146660A

  • Rocket recovery control method and device, electronic equipment and storage medium

    CN112696988A

  • Carrier rocket load shedding control method based on inverse reinforcement learning

    CN113504723A

  • Carrier rocket sublevel landing area control method and system, medium and computer equipment

    CN115562314A

Cited By

  • Missile guidance method based on hierarchical reinforcement learning

    CN120426830A

  • Rocket load shedding control method and device and electronic equipment

    CN120667984A

  • A rocket load reduction control method, device and electronic equipment

    CN120667984B