论文部分内容阅读
针对混沌通信系统的非线性信道干扰问题,基于混沌信号重构理论和函数型连接神经网络理论,提出了一种横向滤波器与函数型连接神经网络组合(combination of transversal filter and functional link neural network,CFFLNN)的自适应非线性信道均衡器,并给出基于低复杂度归一化最小均方(NLMS)的自适应算法,并对该均衡器的稳定性以及收敛条件进行了分析.该非线性自适应均衡器充分利用了横向滤波器的快速收敛,以及函数型连接神经网络通过增大输入空间提高非线性逼近能力的特点,进一步提高均衡器的收敛速度和降低稳态误差.仿真研究表明:所提出的非线性自适应均衡器能够有效地消除线性和非线性信道干扰,均衡器输出信号能反映出混沌信号的特性,具有良好的抗干扰性能;且该均衡器的结构简单,收敛稳定性较好,易于工程实现.
Aiming at the problem of nonlinear channel interference in chaotic communication system, based on chaos signal reconstruction theory and functional connection neural network theory, a combination of transversal filter and functional link neural network CFFLNN), and an adaptive algorithm based on low complexity normalized least mean square (NLMS) is given, and the stability and convergence condition of this equalizer are analyzed. The adaptive equalizer makes full use of the fast convergence of the transversal filter and the functional connection neural network can improve the convergence speed of the equalizer and reduce the steady state error by increasing the input space to improve the nonlinear approximation ability.The simulation results show that: The proposed nonlinear adaptive equalizer can effectively eliminate the linear and non-linear channel interference, the equalizer output signal can reflect the chaotic signal characteristics, has good anti-jamming performance; and the equalizer structure is simple, convergence stability Better, easy to implement.