摘要
针对时滞时变系统,提出了一种参数辨识的新方法。该算法一方面采用互相关函数来辨识滞后时间,并引进了快速傅里叶变换及其反变换,提高了计算效率;另一方面,在变参数增量估计递推最小二乘算法估计时变参数的基础上,引入误差级序列,改善了时变参数的辨识精度。最后通过仿真验证了该方法的良好性能。
A new method is proposed for parameter identification of the time-delay/time-varying system. On the one hand, cross-correlation function is used for time-delay identification; Fast Fourier Transform and its inverse transform are applied to improve the computational efficiency. On the other hand, the time- varying parameter is identified via incremental estimation RLS algorithm with variable parameters, and at the same time the sequence arrayed according to the value of the errors is introduced. The estimation precision was improved greatly. The performance of the algorithm is verified via simulation
出处
《电光与控制》
北大核心
2008年第1期94-96,共3页
Electronics Optics & Control
基金
华北电力大学博士学位教师基金资助项目(93103020)
关键词
时变参数
滞后时间
互相关函数
参数估计
time-varying parameter
time-delay
cross-correlation function
parameter estimation
