基于径向基函数神经网络的混沌背景谐波提取

为提高强混沌背景下谐波信号的提取能力,给出混沌系统的单步预测模型,提出了一种新的径向基函数神经网络模型.由混沌吸引子的维数来确定网络的输入,并给出了基于卡尔曼滤波器的动态学习算法,利用学习算法可以在网络训练时同时确定径向基神经网络隐层中心和输出层权值,提高了网络的收敛速度和预测性能.通过对Bossler混沌背景下低信噪比谐波信号的提取进行计算机认真实验,并且实验表明信噪比最低达一27dB时,仍能有效提取出谐波信号,验证了算法的有效性和可行性.

Signal Extraction in Strong Chaotic Interference Based on Radial Basis Function Neural Network

In order to extract harmonic signal in strong chaotic interference,a single step prediction model and a new method based on radial basis function(RBF) neural network is presented in this paper.The input of the RBF neural network is determined by dimension number of chaotic attractor,and a dynamic learning algorithm based on Karlman filter is proposed to improve the performance and raise the convergence speed of the RBF networks.The validity of RBF neural network with new learning algorithm is tested by sign...