基于强化学习与直接升力的舰载机自动着舰控制  

Automatic landing control of carrier-based aircraft based on reinforcement learning and direct lift

在线阅读下载全文

作  者:王子博 朱齐丹 孔令鑫 王立鹏[1] WANG Zibo;ZHU Qidan;KONG Lingxin;WANG Lipeng(College of Intelligent Systems Science and Engineering,Harbin Engineering University,Harbin 150001,China)

机构地区:[1]哈尔滨工程大学智能科学与工程学院,黑龙江哈尔滨150001

出  处:《智能系统学报》2025年第2期416-424,共9页CAAI Transactions on Intelligent Systems

基  金:国家自然科学基金项目(52171299,62173103);黑龙江省自然科学基金项目(LH2024F037);中央高校基本科研业务费专项资金项目(3072024XX0403).

摘  要:舰载机着舰过程是舰载机作业事故率最高的阶段,为实现舰载机高精度全自动着舰,提出了一种新的舰载机自动着舰控制方法,设计了基于直接升力的控制器与基于强化学习的纵向制导律。直接升力控制实现舰载机飞行状态之间的解耦,增强舰载机姿态角与气流角的稳定性。制导律通过深度强化学习算法训练的神经网络非线性拟合得到,提高了扰动情况下舰载机对理想下滑道的跟踪精度,同时避免了传统方法繁杂的参数整定工作以及对模型的依赖。通过对比仿真结果,在舰尾流扰动下,相比于滑模控制方法、预设性能控制方法、PID控制方法与基于径向基神经网络的自适应控制方法,本文方法具有更好的鲁棒性,增强了对舰尾流扰动的抑制能力,提高了着舰精度。The landing of carrier-based aircraft is the stage with the highest accident rate.A novel control method for the automatic landing of carrier-based aircraft is proposed to realize high-precision automatic landing of carrier-based aircraft.This method includes a direct lift controller and a longitudinal guidance law based on reinforcement learning.The direct lift control decouples the flight states of the carrier-based aircraft,while the guidance law is derived through nonlinear fitting using a neural network trained by deep reinforcement learning algorithms.This approach improves the precision of the aircraft to the ideal glide path in the presence of disturbances and eliminates the need for complicated parameter tuning and model dependence typically associated with traditional control methods.Simulation results show that,in the presence of carrier air wake disturbance,the proposed method outperforms the sliding mode control method,PID control,and adaptive control based on a radial basis neural networks.This method demonstrates greater robustness,superior capability to restrict the effects of carrier air wake disturbance,and improved landing precision.

关 键 词:舰载机着舰 飞行控制 强化学习 直接升力控制 制导律 舰尾流 神经网络 路径跟踪 

分 类 号:TP273[自动化与计算机技术—检测技术与自动化装置]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象