含噪多频信号频率估计算法

Frequency estimation algorithm for multi-tone sinusoidal signals with noises

为抑制多频信号中非待估计频率分量频谱泄漏对频率估计的影响,提出一种新的频率估计算法。利用快速傅里叶变换(FFT)算法对采样信号进行预处理,得到每个频率分量的频谱索引,从而得到各频率分量粗略的幅值和初相位估计值;采用频率搬移策略滤除多频信号中的非待估计频率分量,得到降频信号;对降频信号进行频谱分析,并经迭代计算得到各频率分量信号精确的频率、幅值和初相位估计值。在无噪声、不同信噪比等条件下进行了仿真实验,结果表明,所提算法具有良好的频率估计性能,有效抑制了多频信号中频谱泄漏的影响,提高了频率估计精度,优于现有优秀算法。

To suppress the spectrum leakage influence of non-estimated frequency components of a multi-tone signal,a new frequency estimation algorithm was proposed.Firstly,the sampled signal was preprocessed by fast Fourier transform(FFT)algorithm to get the spectrum index of each frequency component,and the coarse estimation values of the amplitude and initial phase of each frequency component were obtained sequentially.Then,the non-estimated frequency components of the multi-tone single were filtered by afrequency shift strategy to obtain a down frequency signal.Finally,the down frequency signal was processed by spectrum analysis,and the more accurate estimation values of frequency,amplitude and initial phase estimates of each frequency component were achieved with an iterative procedure.Moreover,simulation experiments were carried out in different conditions,such as no noise,different signal to noise ratio,etc.The simulation results indicate that the proposed algorithm has a good frequency estimation performanceand improves the frequency estimation accuracy,which effectively suppresses the spectrum leakage influence of the multi-tone signal and is superior to the existing excellent algorithms.