基于ARMA时序模型的结构参数识别集员算法

研究在时域内利用含噪声观测数据识别结构参数问题.建立了与结构振动微分方程等价的自回归滑动平均(ARMA, Autoregressive Moving-Average)时序模型,将结构参数识别问题转换为ARMA模型参数辨识问题.在不确定但有界(UBB, Unknown-But-Bounded)噪声假设下,基于线性时不变系统参数集员辨识的区间算法,寻求与观测数据和噪声相容的参数的最小超长方体(或区间向量),进而得到结构参数的估计值.通过数值算例,将本文算法与最小二乘算法进行了比较,显示了其可行性和有效性.

Set-membership algorithm for identification of structural parameters based on ARMA time-series model

Identification of structural parameters by using observation data with noise in time domain was studied.Autoregressive moving-average(ARMA) model of a vibrating structure was established,and the identification problem of structural parameters was transformed into the identification problem of parameters of ARMA model.Based on the assumption of the unknown-but-bounded(UBB) noise,an interval algorithm for set-membership identification of parameters of linear time-invariant system was used to seek the minimal hyper-rectangle(or interval vector) of parameters,which is compatible with the measurements and the bounded noise,so that the structural parameters can be obtained.The numerical example illustrates its feasibility and effectiveness in comparison with the least squares algorithm.