| Modelling of a Class of Nonstationary Time Series with Kalman Filter Using Moving Window |
| |
| 作者姓名： | WANG Zheng-ou Institute of Systems Engineering Tianjin University Tianjin PRC
ZHANG Jianping Dept. of Management Beijing Chemical Engineering College Beijing PRC |
| |
| 作者单位： | WANG Zheng-ou Institute of Systems Engineering，Tianjin University，Tianjin，PRC
ZHANG Jianping Dept. of Management，Beijing Chemical Engineering College，Beijing，PRC |
| |
| 摘 要： | In this paper a method for modelling and forecasting of a class of nonstationary time series with Kalmnan filter using moving window is proposed. The procedure of the method is as follows: in terms of parameter estimation during recursive process by using LSM, the state space equation is constructed, then the Kahnan filter using moving window is made to get the data with reduced level of observation noise. Finally, the precise parameter estimation can be obtained by using the LSM again. The algorithm is carried on recursively. Good results for estimating and forecasting are shown by simulation, examples. The algorithm of Kalman filter using moving window proposed by us is introduced in this paper, which can guarantee the precision and convergence of Kalman filter.
|
Modelling of a Class of Nonstationary Time Series with Kalman Filter Using Moving Window |
| |
| WANG Zheng-ou Institute of Systems Engineering,Tianjin University,Tianjin,PRC
ZHANG Jianping Dept. of Management,Beijing Chemical Engineering College,Beijing,PRC.Modelling of a Class of Nonstationary Time Series with Kalman Filter Using Moving Window[J].Journal of Systems Science and Systems Engineering,1992(2). |
| |
| Authors: | WANG Zheng-ou Institute of Systems Engineering Tianjin University Tianjin PRC
ZHANG Jianping Dept of Management Beijing Chemical Engineering College Beijing PRC |
| |
| Abstract: | In this paper a method for modelling and forecasting of a class of nonstationary time series with Kalman filter using moving window is proposed. The procedure of the method is as follows: in terms of parameter estimation during recursive process by using LSM, the state space equation is constructed, then the Kalman filter using moving window is made to get the data with reduced level of observation noise. Finally, the precise parameter estimation can be obtained by using the LSM again. The algorithm is carried on recursively. Good results for estimating and forecasting are shown by simulation, examples. The algorithm of Kalman filter using moving window proposed by us is introduced in this paper, which can guarantee the precision and convergence of Kalman filter. |
| |
| Keywords: | nonstationary time series parameter estimation Kalman filter moving window innovation |
| 本文献已被 CNKI 等数据库收录！ |
