作　　者： ; (向增俊）;

机构地区： 东南大学信息科学与工程学院无线电工程系

出　　处： 《通信学报》 1992年第5期49-53,共5页

摘　　要： 本文提出了一种可用于MQAM数字移动通信自适应接收系统的分数抽头判决反馈式多层感知器结构(FSDFMLP),该系统可以同时对MQAM数字移动通信系统中因多径衰落所引起的性能损失和共信道干扰(CCI)等非高斯干扰进行有效的补偿和抑制。频率选择性衰落信道采用了两径模型。文中提出了一种基于混合梯度法、变步长、选择性修正权值的快速学习算法。实验结果表明:FSDFMLP的性能优于传统的基于LMS算法的判决反馈式滤波器(LMSDFF)。 This paper describes a fractionally spaced decision feedback multi-layer perceptron(FSDFMLP) for adaptive MQAM digital mobile radio reception, which can overcome the performance degradations due to the multipath fading of channels and reject non-Gaussian interferences, such as CCI, simultaneously. A two-ray model is used for the frequency selective fading channel. The fast adaptive learning algorithm called mixed gradient based fast learning algorithm with variable learning gain and selective updates is adopted to train the FSDFMLP. Preliminary experimental results obtained are satisfactory, which shows that the FSDFMLP can perform more efficiently than the conventional LMS based decision feedback filter (LMSDFF) in the presence of multipath fading of channels with non-Gaussian interferences Digital mobile communication, Multipath fading, Multilayer perceptron, Fast learning algorithm.

关 键 词： 移动通信 接收机

领　　域： [电子电信] [电子电信]