期刊名称：International Journal of Computer Science and Network Security
印刷版ISSN：1738-7906
出版年度：2011
卷号：11
期号：6
页码：288-294
出版社：International Journal of Computer Science and Network Security
摘要：The paper highlights a novel hybrid EKF (Extended Kalman Filter) and Differential evolution (DE) called KDE (Kalman differential evolution) approach for tracking Parameters of a signal corrupted with noise and harmonics. The modeling and measurement of error covariance matrices Q and R are optimized using differential evolution. A new adaptive filtering technique is employed for self adaption of mutation scale factor in DE. To improve the convergence speed of optimization process K-DE, a variant of standard DE is considered for the optimization of Q and R matrices. Simulation results for time varying frequency of the power signal reveal significant improvement in noise rejection and accuracy in obtaining the frequency of the signal.
