Two-Loop Acceleration Autopilot Design and Analysis Based on TD3 Strategy
A two-loop acceleration autopilot is designed using the twin-delayed deep deterministic policy gradient (TD3) strategy to avoid the tedious design process of conventional tactical missile acceleration autopilots and the difficulty of meeting the performance requirements of the full flight envelope....
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Hindawi Limited
2023-01-01
|
| Series: | International Journal of Aerospace Engineering |
| Online Access: | http://dx.doi.org/10.1155/2023/5759135 |
| _version_ | 1797855362451243008 |
|---|---|
| author | Junfang Fan Denghui Dou Yi Ji Ning Liu Shiwei Chen Huajie Yan Junxian Li |
| author_facet | Junfang Fan Denghui Dou Yi Ji Ning Liu Shiwei Chen Huajie Yan Junxian Li |
| author_sort | Junfang Fan |
| collection | DOAJ |
| description | A two-loop acceleration autopilot is designed using the twin-delayed deep deterministic policy gradient (TD3) strategy to avoid the tedious design process of conventional tactical missile acceleration autopilots and the difficulty of meeting the performance requirements of the full flight envelope. First, a deep reinforcement learning model for the two-loop autopilot is developed. The flight state information serves as the state, the to-be-designed autopilot control parameters serve as the action, and a reward mechanism based on the stability margin index is designed. The TD3 strategy is subsequently used to offline learn the control parameters for the entire flight envelope. An autopilot control parameter fitting model that can be directly applied to the guidance loop is obtained. Finally, the obtained fitting model is combined with the impact angle constraint in the guidance system and verified online. The simulation results demonstrate that the autopilot based on the TD3 strategy can self-adjust the control parameters online based on the real-time flight state, ensuring system stability and achieving accurate acceleration command tracking. |
| first_indexed | 2024-04-09T20:22:32Z |
| format | Article |
| id | doaj.art-cef36d0c63174fa1841c05fe889b9c39 |
| institution | Directory Open Access Journal |
| issn | 1687-5974 |
| language | English |
| last_indexed | 2024-04-09T20:22:32Z |
| publishDate | 2023-01-01 |
| publisher | Hindawi Limited |
| record_format | Article |
| series | International Journal of Aerospace Engineering |
| spelling | doaj.art-cef36d0c63174fa1841c05fe889b9c392023-03-31T00:00:08ZengHindawi LimitedInternational Journal of Aerospace Engineering1687-59742023-01-01202310.1155/2023/5759135Two-Loop Acceleration Autopilot Design and Analysis Based on TD3 StrategyJunfang Fan0Denghui Dou1Yi Ji2Ning Liu3Shiwei Chen4Huajie Yan5Junxian Li6School of AutomationSchool of AutomationSchool of AutomationBeijing Key Laboratory of High Dynamic Navigation TechnologySchool of Aerospace EngineerSchool of AutomationSchool of AutomationA two-loop acceleration autopilot is designed using the twin-delayed deep deterministic policy gradient (TD3) strategy to avoid the tedious design process of conventional tactical missile acceleration autopilots and the difficulty of meeting the performance requirements of the full flight envelope. First, a deep reinforcement learning model for the two-loop autopilot is developed. The flight state information serves as the state, the to-be-designed autopilot control parameters serve as the action, and a reward mechanism based on the stability margin index is designed. The TD3 strategy is subsequently used to offline learn the control parameters for the entire flight envelope. An autopilot control parameter fitting model that can be directly applied to the guidance loop is obtained. Finally, the obtained fitting model is combined with the impact angle constraint in the guidance system and verified online. The simulation results demonstrate that the autopilot based on the TD3 strategy can self-adjust the control parameters online based on the real-time flight state, ensuring system stability and achieving accurate acceleration command tracking.http://dx.doi.org/10.1155/2023/5759135 |
| spellingShingle | Junfang Fan Denghui Dou Yi Ji Ning Liu Shiwei Chen Huajie Yan Junxian Li Two-Loop Acceleration Autopilot Design and Analysis Based on TD3 Strategy International Journal of Aerospace Engineering |
| title | Two-Loop Acceleration Autopilot Design and Analysis Based on TD3 Strategy |
| title_full | Two-Loop Acceleration Autopilot Design and Analysis Based on TD3 Strategy |
| title_fullStr | Two-Loop Acceleration Autopilot Design and Analysis Based on TD3 Strategy |
| title_full_unstemmed | Two-Loop Acceleration Autopilot Design and Analysis Based on TD3 Strategy |
| title_short | Two-Loop Acceleration Autopilot Design and Analysis Based on TD3 Strategy |
| title_sort | two loop acceleration autopilot design and analysis based on td3 strategy |
| url | http://dx.doi.org/10.1155/2023/5759135 |
| work_keys_str_mv | AT junfangfan twoloopaccelerationautopilotdesignandanalysisbasedontd3strategy AT denghuidou twoloopaccelerationautopilotdesignandanalysisbasedontd3strategy AT yiji twoloopaccelerationautopilotdesignandanalysisbasedontd3strategy AT ningliu twoloopaccelerationautopilotdesignandanalysisbasedontd3strategy AT shiweichen twoloopaccelerationautopilotdesignandanalysisbasedontd3strategy AT huajieyan twoloopaccelerationautopilotdesignandanalysisbasedontd3strategy AT junxianli twoloopaccelerationautopilotdesignandanalysisbasedontd3strategy |