【作者】 苏理云； 马洪； 唐世福；

【Author】 SU Li-yun, MA Hong, TANG Shi-fu (College of Mathematics, Sichuan University, Chengdu 610064, China.

【机构】 四川大学数学学院；

【摘要】 提出一种检测强混沌背景中微弱谐波信号的方法．该方法利用RBF神经网络预测混沌时间序列的能力建立预测模型,用模糊C-均值聚类算法获得RBF神经网络的径向中心,将预测误差送入Duffing混沌振子,并充分利用 Duffing混沌振子对噪声的免疫性检测是否含有微弱信号．该方法充分利用了模糊聚类、神经网络和混沌系统,大大提高了检测微弱信号的性能．仿真实验表明,该方法能够在信噪比-120 dB时检测出微弱谐波信号．更多还原

【Abstract】 A approach of weak sinusoid signal detection from a chaotic noise background is proposed. The RBF neural networks are used to predict the chaotic background, and the radial center is gained by fuzzy c-means algorithm. The noisy error signal extracted from the detected signal, then the error signal is added into the Duffing chaotic oscillator by using the sensitivities to the initial conditions and immune to the noise of the system. Based on the motion transition of a chaotic system, new schemes to detect weak sinusoidal signal berried in a chaotic background are presented forward. Simulation measured data demonstrate the effectiveness of the proposed algorithm.更多还原