双输入多率系统辅助模型增广随机梯度算法  

Extended Gradient Identification for Two-input Multirate Systems Based on the Auxiliary Model

作　　者：张彩霞[1] 陆静[1] 

机构地区：[1]江南大学通信与控制工程学院,江苏无锡214122

出　　处：《控制工程》2009年第S2期103-105,109,共4页Control Engineering of China

基　　金：国家自然科学基金资助项目(60574051);江苏省自然科学基金资助项目(BK2007017);江南大学创新团队发展计划基金资助项目(005723)

摘　　要：针对有色噪声干扰的双输入多率系统,为解决辨识模型信息向量中存在未知变量和不可测噪声项的问题,结合辅助模型思想和递推增广随机梯度算法的优点,用辅助模型的输出代替系统的未知变量,用估计残差代替信息向量中的不可测噪声项,进而提出了双输入多率系统的辅助模型增广随机梯度算法。为了提高辨识算法的收敛速度和改善参数估计精度,在算法中引入遗忘因子,得到相应的辅助模型带遗忘因子增广随机梯度算法。仿真实例说明,引入遗忘因子,能加快算法的收敛性,提高参数估计精度。An auxiliary model is presented based on extended stochastic gradient(AM-ESG) algorithm in terms of the auxiliary model identification principle and extended stochastic gradient(ESG) identification principle,that is,replacing the unknown true outputs in the information vector with the outputs of the auxiliary model and the unmeasurable noise terms in the information vector with the estimated residuals.In order to improve parameter estimation accuracy and increase convergence speed,the auxiliary model based forgetting factor stochastic gradient algorithm is presented by introducing a forgetting factor.The simulation results show that the proposed algorithm has high estimation accuracy and fast convergence rates.

关 键 词：多率系统 辅助模型 增广随机梯度 状态空间模型 传递函数模型 

分 类 号：TP11[自动化与计算机技术—控制理论与控制工程]