基于Nonnegative Garrote的ARX和ARMA模型定阶方法  

Order Determination of ARX and ARMA Models Based on Nonnegative Garrote

作　　者：谭力宁[1] 韩海涛 马红光[1] 

机构地区：[1]第二炮兵工程大学701教研室,西安710025

出　　处：《科学技术与工程》2013年第9期2509-2512,共4页Science Technology and Engineering

基　　金：国家自然科学基金(61174207;61074072)资助

摘　　要：针对传统ARX和ARMA模型定阶方法计算量大和稳定性不强的缺点,提出采用非负绞杀法对ARX和ARMA模型进行定阶。通过分析ARX和ARMA模型的特点,对常规非负绞杀方法进行了改进,使其更适用于动态系统辨识问题,进而给出了相应的求解算法。仿真实验的结果表明了该方法的有效性,且在稳定性上优于传统的信息量准则法。Classical order determination methods of ARX and ARMA models suffer from the drawbacks of com- putationally infeasible and poor stability. To solve these problems, order determination using nonnegative garrote （NNG） method is proposed. By analyzing the properties of AR and ARMA models, a modification of original NNG method is made to fit the dynamical system identification problem. Furthermore, the solution algorithm of proposed method is presented. Simulations show the validation of proposed method, which has better stability than classical information based criteria methods.

关 键 词：带外部输入的自回归模型 自回归滑动平均模型 非负绞杀 定阶 

分 类 号：TN911.7[电子电信—通信与信息系统]