摘要
为解决当飞行器出现破损以及飞行器受干扰时的轨迹优化问题,新一代的再入式飞行器需要有实时在线轨迹优化的能力。神经网络动态优化算法(neural dynamic optimization,NDO)的主要特点是能使神经网络逼近最优解。神经网络动态优化算法可以避免传统的间接法在求解轨迹优化问题时协态变量初值猜测问题。给出了神经网络动态优化的原理,详细介绍了优化流程。仿真结果表明神经网络动态优化算法可以很好的避免协态变量初值猜测问题,具有较强的鲁棒性,能满足实时性要求。
The next generation of the reentry vehicle is envisioned to have the onboard capability of real-time trajectory planning to overcome in-flight vehicle damage or various disturbances.The main feature of neural dy-namic optimization （NDO）is that it enables neural networks to approximate the optimal feedback solution.The NDO can avoid the problem of guessing the initial state of costate variables.The principle of the method is intro-duced and the detail of the optimization process is presented.Simulation results show that using NDO can avoid the guessing initial state of costate variables of the problem.The properly trained NDO has strong robustness which can meet the real-time requirements.
出处
《系统工程与电子技术》
EI
CSCD
北大核心
2015年第10期2347-2351,共5页
Systems Engineering and Electronics
基金
国家自然科学基金(9106017)
山西省青年科技基金(2015021089)
太原科技大学博士科研启动基金(20132020)
江苏省自然科学基金(BK20130234)
江苏省高校自然科学基金(13KJD510003)
常州市科技支撑计划项目(CE20145056)
