混沌海杂波背景下的微弱信号检测混合算法

基于经验模态分解理论, 提出了一种基于粒子群算法的支持向量机预测方法. 采用总体平均经验模式分解法将混沌信号分解为若干固有模态函数和趋势分量, 将复杂的非线性信号转化为具有不同尺度特征的平稳分量. 利用粒子群算法对支持向量机的惩罚系数和核函数进行优化, 结合支持向量机建立混沌序列的单步预测模型. 从预测误差中检测淹没在混沌背景中的微弱信号(包括瞬态信号和周期信号). 对Lorenz系统和实测IPIX雷达数据进行仿真实验, 结果表明, 该方法能够有效地从混沌背景噪声中检测出微弱目标信号, Lorenz系统得到的均方根误差0.000000339 (-102.8225 dB时)比传统支持向量机方法的均方根误差0.049 (-54.60 dB时)降低了5个数量级, 从海杂波中检测出具有谐波特性的微弱信号, 表明预测模型具有更低的门限和误差.

Hybrid algorithm for weak signal detection in chaotic sea clutter

According to the empirical mode decomposition (EMD) theory, a prediction method of support vector machine (SVM) is proposed based on particle swarm optimization. The ensemble EMD method is used to decompose the signal into some intrinsic mode function components which are taken as the input of the SVM to predict the data. All the predicted values are combined, and the weak signals submerged in chaos background, including the transient signal and periodic signal, are detected from the prediction error. Lorenz attractor and the data from the McMaster IPIX radar sea clutter database are used in the simulation. The results show that the proposed method can effectively detect the weak target from chaotic signal. When the signal-to-noise ratio is 102.8225 dB in the chaotic noise background, by using the new method the root mean square error can be reduced by five orders of magnitude, reaching 0.00000033092, while the conventional SVM can reach only 0.049 under the condition of -54.60 dB and the weak target detected in sea clutter has the harmonic characteristics, which shows the prediction model has a lower threshold and error.