基于MATLAB的随机信号方法汇总.ppt

正态分布白噪声序列randn() 韦伯分布白噪声序列weibrnd() 最大熵法与加窗改进周期图法功率谱估计 N=1024 最大熵法 加窗平均 周期图法 0 50 100 150 200 250 300 350 400 450 500 -10 0 10 20 30 Frequency (Hz) Power Spectrum (dB) Maxmum Entropy Method(MEM) Order=74 0 50 100 150 200 250 300 350 400 450 500 -10 0 10 20 30 Frequency Power Spectrum Magnitude (dB) 互相关函数的估计 3 互相关函数估计xcorr c = xcorr(x,y) c = xcorr(x) c = xcorr(x,y,option) c = xcorr(x,option) xcorr(x,y)计算X与Y的互相关，矢量X表示序列x(n)，矢量Y表示序列y(n)。xcorr(x)计算X的自相关。option选项是： biased unbiased coeff none Normalizes the sequence so the autocorrelations at zero lag are identically 1.0 to use the raw, unscaled cross-correlations (default) 3、功率谱估计 Periodogram 周期图法 periodogram Welch Averaged periodograms of overlapped, windowed signal sections pwelch Yule-Walker AR Autoregressive (AR) spectral estimate of a time-series from its estimated autocorrelation function pyulear pburg Autoregressive (AR) spectral estimation of a time-series by minimization of linear prediction errors pburg Covariance Autoregressive (AR) spectral estimation of a time-series by minimization of the forward prediction errors pcov 例2.27 估计两个正弦信号加正态白噪声的功率谱，信号为 ， 其中 =300Hz, =310Hz。 MATLAB程序如下： %功率谱估计 %301个数据点 t = 0:0.001:0.3; %两个频点加随机噪声 x =cos(2*pi*t*300)+cos(2*pi*t*310)+randn(size(t)); %没有加窗的周期图谱估计 subplot(2,2,1); periodogram(x,[],512,1000);%周期图谱估计并画图，512点FFT axis([0 500 -50 0]); %加窗的周期图谱估计 subplot(2,2,2); window = hann(301); periodogram(x,window,512,1000); title(汉宁周期图功率谱估计); axis([0 500 -50 0]); %相关函数法 R = xcorr(x)/15000;%15000为数据点数乘频点宽度，因纵轴为dB/Hz Pw = fft(R); subplot(2,2,3); f = (0:length(Pw)-1)*1000/length(Pw);%不太明白 plot(f,10*log10(abs(Pw))); title(BT功率谱估计); axis([0 500 -50 0]); grid on subplot(2,2,4); pwelch(x,128,64,[],1000); axis([0 500 -50 0]); 4 概率密度估计 概率密度的估计有两个函数：ksdensity()，hist() ksdensity()函数直接估计随机序列概率密度的估计，它的用法是： [f,xi] = ksdensity(x) 它的功能是估计用矢量x表示的随机序列在xi处的概率密度f。也可以指定xi，估计对应点的概率密度值，用法为： f = ksdensity(x,xi) MATLAB程序如下： a=0.8; sigma=2