%0 Journal Article %T Hierarchical Optimization Identification of LTI State-space Systems by Projected Gradient Search
基于正交梯度搜索的动态系统递阶优化辨识 %A ZHONG Lu-Sheng %A SONG Zhi-Huan %A
衷路生 %A 宋执环 %J 自动化学报 %D 2008 %I %X A hierarchical optimization method for the identifi- cation of LTI state-space systems is proposed based on projected gradient search.The system parameters are determined by op- timizing an output-error cost function.To deal with the non- uniqueness of the fully parameterized state-space system,a pro- jected gradient search algorithm is presented by restricting the update of the parameters to the tangent space to the manifold of observationally equivalent state-space systems.The sufficient condition to employ L-M algorithm for optimizing parameters is also introduced.The proposed hierarchical optimization identi- fication method includes two steps:First,the parameter search direction is determined by the proposed adaptive L-M projected gradient approach;Second,the optimum step size is computed according to a line search method.Numerical simulation studies show that the proposed algorithm offers improved performance, such as faster convergence speed and better numerical stability, over existing EM and DDLC methods. %K System identification %K parameter estimation %K Levenberg-Marquardt(L-M)algorithm %K hierarchical optimization(HO) %K state-space models %K maximum likelihood estimation
系统辨识 %K 参数估计 %K Levenberg-Marquardt(L-M)算法 %K 递阶优化 %K 状态空间模型 %K 极大似然估计 %K 正交 %K 梯度搜索 %K 动态系统 %K 优化辨识 %K Search %K Gradient %K Systems %K Identification %K Optimization %K 数值稳定性 %K 抗噪能力 %K 收敛速度 %K 梯度方法 %K 仿真实验 %K 蒙特卡罗 %K 步长 %K 最佳 %K 计算 %K 一维 %K 优化方向 %U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=E76622685B64B2AA896A7F777B64EB3A&aid=1DB3B4F0D2188C483A94AA0E037F203C&yid=67289AFF6305E306&vid=339D79302DF62549&iid=B31275AF3241DB2D&sid=FD6137FFCE59D193&eid=EB8E83807F36F05B&journal_id=0254-4156&journal_name=自动化学报&referenced_num=0&reference_num=19