Comparisons of stochastic gradient and least squares algorithms for multivariable systems

摘要：

Two identification models are obtained for multivariable ARX systems by different parameterization, and the corresponding two least squares and two stochastic gradient algorithms are given based on the lest squares principle and the stochastic gradient search principle and minimizing different cost functions. The performances of these algorithms are analyzed and compared by the simulation tests.

关键词： Recursive Identification Parameter Estimation Multivariable Systems Least Squares Stochastic Gradient

作者: Yuwu Liao Yanjun Liu Feng Ding

作者单位: Department of Physics and Electronics Information Technology, Xiangfan University, Xiangfan 441053, School of Communication and Control Engineering, Jiangnan University, Wuxi 214122, China

会议类型: 国际会议

会议名称: The 22nd China Control and Decision Conference(2010年中国控制与决策会议)

会议地点: 徐州

会议语种:英文

页码: 3275-3279

在线出版日期: 2010-05-26（万方平台首次上网日期，不代表论文的发表时间）