摘要
当前对高速通信的需求导致对信道资源的利用已经超出了可以采用线性模型建模的范围,必须采用适当的非线性模型进行描述。为了实现对高速通信中非线性信道的辨识,提出采用自适应神经模糊推理系统进行信道辨识的方法。利用减法聚类法实现对ANFIS网络结构识别,在此基础上采用误差反传和最小二乘相结合的混合学习算法训练网络,从而实现对非线性信道的辨识。仿真结果表明,该方法与BP网络相比具有更高的收敛速度和识别精度,与基于网格划分的ANFIS相比,具有更高的运算效率。
The demand of high-speed communication leads that the application for resource of channel exceeds the range of linear model. As a result, nonlinear model should be taken into account. According to the property of the channel in high-speed communication, an adaptive neuron-fuzzy inference system(ANFIS)to identify the nonlinear channel is presented. The subtract cluster is applied to identify the construction of ANFIS and the hybrid learning algorithm based on the least square and back-propagation is used to train network. The simulation results show that the convergence rate and identification accuracy of ANFIS are better than BP network and the efficiency of ANFIS based on subtract cluster partition is higher than that of ANFIS based on grid partition.
出处
《辽宁科技大学学报》
CAS
2008年第1期11-14,共4页
Journal of University of Science and Technology Liaoning