Thrust and Pressure Control in a Solid Propulsion System via Reinforcement Learning
A reinforcement learning control method for a solid attitude and divert propulsion system is proposed. The system in this study includes four divert thrust nozzles, six attitude thrust nozzles, and a common combustion chamber. To achieve the required thrust, the pressure in the combustion chamber is...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/1/162 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841549441481310208 |
|---|---|
| author | Zuohao Hua Zhuang Fu Lu Niu |
| author_facet | Zuohao Hua Zhuang Fu Lu Niu |
| author_sort | Zuohao Hua |
| collection | DOAJ |
| description | A reinforcement learning control method for a solid attitude and divert propulsion system is proposed. The system in this study includes four divert thrust nozzles, six attitude thrust nozzles, and a common combustion chamber. To achieve the required thrust, the pressure in the combustion chamber is first adjusted by controlling the total opening of the nozzles to generate the gas source. Next, by controlling the opening of nozzles at different positions, the required thrust is produced in the five-axis direction. Finally, the motor speed is regulated to drive the valve core to the specified position, completing the closed-loop control of the nozzle opening. The control algorithm used is the Proximal Policy Optimization (PPO) reinforcement learning algorithm. Through system identification and numerical modeling, the training environment for the intelligent agent is created. To accommodate different training objectives, multiple reward functions are implemented. Ultimately, through training, a multi-layer intelligent agent architecture for pressure, thrust, and nozzle opening is established, achieving effective system pressure and thrust control. |
| format | Article |
| id | doaj-art-5164c64c5a2240b6abcbc41298a01447 |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-5164c64c5a2240b6abcbc41298a014472025-01-10T13:14:39ZengMDPI AGApplied Sciences2076-34172024-12-0115116210.3390/app15010162Thrust and Pressure Control in a Solid Propulsion System via Reinforcement LearningZuohao Hua0Zhuang Fu1Lu Niu2School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, ChinaSchool of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, ChinaShanghai Space Propulsion Technology Research Institute, Shanghai 201109, ChinaA reinforcement learning control method for a solid attitude and divert propulsion system is proposed. The system in this study includes four divert thrust nozzles, six attitude thrust nozzles, and a common combustion chamber. To achieve the required thrust, the pressure in the combustion chamber is first adjusted by controlling the total opening of the nozzles to generate the gas source. Next, by controlling the opening of nozzles at different positions, the required thrust is produced in the five-axis direction. Finally, the motor speed is regulated to drive the valve core to the specified position, completing the closed-loop control of the nozzle opening. The control algorithm used is the Proximal Policy Optimization (PPO) reinforcement learning algorithm. Through system identification and numerical modeling, the training environment for the intelligent agent is created. To accommodate different training objectives, multiple reward functions are implemented. Ultimately, through training, a multi-layer intelligent agent architecture for pressure, thrust, and nozzle opening is established, achieving effective system pressure and thrust control.https://www.mdpi.com/2076-3417/15/1/162solid propulsion systemattitude and divert nozzlesthrust and pressure controlreinforcement learning |
| spellingShingle | Zuohao Hua Zhuang Fu Lu Niu Thrust and Pressure Control in a Solid Propulsion System via Reinforcement Learning Applied Sciences solid propulsion system attitude and divert nozzles thrust and pressure control reinforcement learning |
| title | Thrust and Pressure Control in a Solid Propulsion System via Reinforcement Learning |
| title_full | Thrust and Pressure Control in a Solid Propulsion System via Reinforcement Learning |
| title_fullStr | Thrust and Pressure Control in a Solid Propulsion System via Reinforcement Learning |
| title_full_unstemmed | Thrust and Pressure Control in a Solid Propulsion System via Reinforcement Learning |
| title_short | Thrust and Pressure Control in a Solid Propulsion System via Reinforcement Learning |
| title_sort | thrust and pressure control in a solid propulsion system via reinforcement learning |
| topic | solid propulsion system attitude and divert nozzles thrust and pressure control reinforcement learning |
| url | https://www.mdpi.com/2076-3417/15/1/162 |
| work_keys_str_mv | AT zuohaohua thrustandpressurecontrolinasolidpropulsionsystemviareinforcementlearning AT zhuangfu thrustandpressurecontrolinasolidpropulsionsystemviareinforcementlearning AT luniu thrustandpressurecontrolinasolidpropulsionsystemviareinforcementlearning |