飞机极曲线模型和参数鲁棒辨识方法  

Robust identification method for both model structures and parameters of aircraft lift-drag curves

作　　者：史忠科[1] 

机构地区：[1]西北工业大学自动控制系,陕西西安710072

出　　处：《控制与决策》2004年第4期437-440,共4页Control and Decision

基　　金：国家自然科学基金资助项目(69925306);航空科技基金资助项目(01D53010).

摘　　要：为了有效地确定飞机极曲线,提出一种鲁棒选择模型的新方法.通过分析数据矩阵模型判定方法,采用U-D分解以避免行列式的复杂计算,从而成倍提高了计算效率.通过估计D阵元素的取值区间,得到了观测量不确定部分带来的模型辨识判据的误差上下界,依此将候选按照重要程度逐个选取.在加权最小二乘算法中,采用下界不等式逼近,得到了鲁棒辨识的新算法和收敛条件.对飞机极曲线的模型和参数进行辨识,结果表明新方法可以得到工程上满意的效果.To identify the model structure of aircraft lift-drag curves efficiently, a robust criterion for model structure selection is developed. By the analysis of model determination method of sample data matrix, a numerical excellent U-D factorization is presented to avoid the computation of determinant values of two complex matrices. By estimating the values of matrix D, both the upper bound and the lower bound of the influence to model criterion caused by system uncertainty are described. The lower bound of uncertain parts generated by uncertain observation matrix is obtained. The model structure and parameter identification algorithms are proposed by means of the lower bound inequality approximation in the least square method. Applications to flight data processing for high performance aircraft show that the new method is efficient.

关 键 词：模型辨识 参数估计 鲁棒估计 飞行试验 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]