基于在线模型辨识的飞行器多约束复合制导技术

Multi-constraint compound reentry guidance based on onboard model identification

针对飞行器再入制导问题,该文引入控制变量参数化、积分问题转换和在线模型辨识等技术,提出一种跨周期迭代的可行轨迹预测校正算法,并结合标称轨迹跟踪算法形成一套多约束复合制导方案。利用一种复合高度-速度(height velocity,HV)飞行走廊,将再入轨迹规划问题简化为单调函数寻根问题。为提高射程预测计算效率,引入Gauss-Legendre求积公式,将积分问题转化为函数计算问题。采用递推最小二乘估计方法,收集历史预测信息,实现模型在线辨识功能,并采用跨周期Newton-Raphson方法完成高度权重系数的在线修正。在标称轨迹跟踪器设计的基础上,开展飞行器数值仿真试验,结果表明:基于在线模型辨识的复合制导方法具有显著的速度优势,且具有优异的自主性和自适应能力。

A period-crossing feasible trajectory planning algorithm for reentry guidance was developed based on control variable parameterization,integral transformations,and onboard model identification.A compound height velocity(HV)corridor simplifies the reentry guidance problem into a root-searching problem.A Gauss integral is introduced to improve the time efficiency of the range prediction with the original integral problem converted into a function calculation problem.The recursive least squares estimation method was used to develop functions for on-board information mining and model identification.The reliable,explicit solution model can easily correct the weight coefficients using the period-crossing Newton-Raphson method.Numerical simulations show that the reentry guidance method based on on-board model identification is much faster,more autonomous and more adaptable than the reference trajectory tracking design method.