基于前后向线性预测的时变参数估计方法研究  

Time-varying Parameters Estimation Method Based on Forward and Backward Linear Prediction

作　　者：史杰[1] 钟雄虎[1] 宋叔飚[1] 裴承鸣[1] 

机构地区：[1]西北工业大学数据处理中心,陕西西安710072

出　　处：《计算机测量与控制》2006年第11期1515-1517,共3页Computer Measurement &Control

基　　金：航空科学基金资助项目(01I53075;01A53001);西北工业大学研究生创业种子基金资助项目(Z200537)

摘　　要：在基时间函数展开理论基础上,通过同时引入非平稳信号的前向线性预测和后向线性预测来估计模型的时变系数,提出了一种新的时变参数建模方法,有效地克服了现有方法对瞬时频率估计的滞后问题和无法准确估计初始时刻值的困难;仿真试验证明,在相同阶次和基函数维数条件下,该方法对非平稳信号瞬时频率的估计效果要优于现有的方法。Based on the time-varying basis function expansion theory, a new method combining forward and backward linear prediction of non stationary signals is presented to estimate TVAR parameters. Computer simulation shows that the method can solve the one-step delay problem and overcome the computing difficulties at initial time steps in estimating the instantaneous frequency. The results show us that this method is more effective than the present approaches in modeling a non-stationary signal under the same TVAR order and basis function dimension.

关 键 词：时变参数模型 基时间函数展开 线性预测 

分 类 号：TN911.7[电子电信—通信与信息系统]