PILCO框架对飞行姿态模拟器系统的参数设计与优化  

Parameter design and optimization of a flight attitude simulator system based on PILCO framework

作　　者：杨烨峰 邓凯 左英琦 班晓军[1] 黄显林[1] YANG Ye-feng;DENG Kai;ZUO Ying-qi;BAN Xiao-jun;HUANG Xian-lin(Center for Control Theory and Guidance Technology,Harbin Institute of Technology,Harbin 150001,China;Sichuan Academy of Aerospace Technology,Chengdu 610100,China)

机构地区：[1]哈尔滨工业大学控制理论与制导技术研究中心,黑龙江哈尔滨150001 [2]四川航天系统工程研究所,四川成都610100

出　　处：《光学精密工程》2019年第11期2365-2373,共9页Optics and Precision Engineering

基　　金：国家自然科学基金资助项目(No.61304006,No.61273095)

摘　　要：PID控制是飞行器控制中应用最广泛的控制方法,但是PID参数的调节往往十分繁琐。为了实现飞行模拟器控制系统自主优化PID控制器的参数,从而完成系统的稳定控制,本文使用强化学习中的概率推理学习控制算法(Probabilistic Inference for Learning Control,PILCO)自主优化PID控制器的参数。首先,利用输入输出数据拟合出系统的概率动力学模型,并使用策略评估的方法对当前PID控制器进行评价;最后,使用策略提升的方式对当前PID控制器进行优化。在系统采样频率为100 Hz,每次采集8 s数据的实验中,经过10个回合的离线训练之后,系统控制效果已经可以满足要求,PID控制器参数已经收敛。经过PILCO优化的飞行姿态模拟器在定点实验中表现出良好的鲁棒性,表明PILCO算法可以优化PID控制器的参数,并且在解决非线性控制和参数优化方面具有很大潜能。Proportional-integral-derivative(PID)controllers are widely used in flight control systems.However,it is often very cumbersome to adjust the parameters of a PID controller.In this study,we use Probabilistic Inference for Learning Control(PILCO)to optimize the parameters of a PID controller.As the first step,we develop a probabilistic dynamics model of the flight control system using input and output data.Next,the existing PID controller is evaluated using the policy evaluation method.Finally,the evaluated PID controller is optimized by policy update.The sampling frequency of the system is 100 Hz and the data acquisition time per round is 8 s.The optimized PID controller can achieve stable control post 10 rounds of offline training.Through PILCO optimization,the flight attitude simulator performed robustly in a fixed-point experiment,indicating that PILCO has tremendous potential in solving nonlinear control and parameter optimization problems.

关 键 词：飞行器控制 概率推理学习控制 强化学习 参数优化 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置] TP249[自动化与计算机技术—控制科学与工程]