有色噪声自适应滤波的研究

A Research on Adaptive Filtering of Color Noise

本文利用复杂输出相关法解决测量噪声为有色且无任何先念知识的一种自适应滤波方法.该方法对处理有色噪声的滤波不采用扩大状态变量的方法,采用等效观测方程的方法,使得计算没有复杂化,滤波器的维数没有增加,并通过实例模型进行计算,表明该方法可行.

The kalman filter is known to the able to strain the observable noise of asystem,but it is based on the knowledge of the variance of system noise and measurement noise.In general,these variances are not easy to derive,so it is necessary to add an adaptive technique to the kalman filter system.This paper submits a kind of adaptive filtering method to solve the problem of the unknown color observable noise,making use of the complicated correlative method of the system output.This method adopts the equivalent observable equation to avoid expanding the dimension of the state variate while the color noise is leing filteres. This can avoid complicated computation and the expansion of the dimension of the filter.This system gives a good performance through computer simulation of the actual model.