Consistency of Stochastic Gradient Parameter and Missing Output Estimation by Using a Polynomial Transformation

摘要：

This paper uses a polynomial transformation technique to derive a mathematical model for dualrate sampled-data systems and present a gradient-based recursive algorithm to estimate the model parameters and missing outputs; the algorithm is based on the dualrate input-output data directly. Furthermore, we study performance of the parameter and missing estimation in the stochastic framework, and show that the parameter estimation error converges to zero and the missing output estimation error is bounded. Moreover, we test the proposed algorithms with example systems, including an experimental water-level system.

关键词： Recursive identification output estimation dual-rate systems multirate systems convergence properties stochastic gradient parameter estimation.

作者: Feng Ding Huibo Chen Yongsong Xiao

作者单位: Control Science and Engineering Research Center Southern Yangtze University, Wuxi, Jiangsu, P.R. China 214122

会议类型: 国际会议

会议名称: 第三届国际脉冲动力系统及应用学术会议

会议地点: 青岛

会议语种:英文

在线出版日期: 2006-07-21（万方平台首次上网日期，不代表论文的发表时间）