一种新的混沌扩频序列产生方法

本文提出了一种新的混沌扩频序列产生方法。该方法基于神经网络的强大学习能力和副近非线性函数能力，应用具有全局最优的ＢＰ改进算法通过训练学习建立起具有混沌性态的优化神经网络模型，利用网络权值调整的灵活性来产生混沌扩频序列。计算机仿真结果表明，该模型产生的混沌扩频序列调整更容易，比基于单一混沌映射能产生更多符合扩频通信要求的扩频序列。

A New Chaotic Spread-Spectrum Sequences Generation Method

A new Chaotic Spread-Spectrum Sequence Generation method is proposed in this paper based on the strong learning ability and nonlinear function approximation capacity of Multi-Layer Perceptrons (MLPs). The chaos generation neural network model and synaptic weights database have been built to generate many chaotic spread-spectrum sequences trained by the modified Back-Propagation (BP) algorithm with various discrete chaotic time series. This model can very easily generate many chaotic spread-spectrum sequences by changing weights of this MLPs. Experimental results show that this scheme can generate much more spread-spectrum sequences than single chaotic map to satisfy the demand of spread-spectrum communication.