自适应扰动暂态混沌神经网络MPSK盲检测  

Blind Detection for MPSK with Adaptive Perturbation Transiently Chaotic Neural Network

作　　者：于大为[1] 张治民 张昀 于舒娟[2] Yu Dawei;Zhang Zhimin;Zhang Yun;Yu Shujuan(Department of Computer Science and Technology,Suzhou 215200,China;College of Electronic and Optical Engineering&College of Microelectronics,Nanjing University of Posts&Telecommunication,Nanjing 210003,China)

机构地区：[1]苏州信息职业技术学院,江苏苏州215200 [2]南京邮电大学电子与光学工程学院微电子学院,南京210003

出　　处：《计算机测量与控制》2019年第12期213-218,共6页Computer Measurement &Control

基　　金：国家自然科学基金项目（61302155,61871234);2019年苏州高职高专院校第二批优秀教学团队（201905）

摘　　要：基于MPSK系统的神经网络盲检测CHNN_APHM算法具有需求发送数据量短、适用于含公零点信道等优点,相比基于统计量的盲检测算法,更能满足现代通信系统的可靠性要求;但由于神经网络采用梯度下降的优化策略有时会导致系统陷入局部最优,出现收敛不到优化问题的最优解或者近似最优解的情况;为了改善CHNN_APHM性能,提出了带自适应扰动的暂态混沌神经网络盲检测算法,构建了与模型相对应的能量函数并证明该网络的稳定性;算法使用暂态混沌神经网络提高抗噪性能,在运行起始时刻使用一维正弦映射的混沌初始化获得原始信号,选取与发送信号进程相关性高的微小扰动因子使算法跳出局部最优解;实验仿真结果证明,提出的带扰动的幅值相位型离散多电平暂态混沌神经网络MPSK信号盲检测算法需要起点个数少,能在更小的信噪比和更短的数据长度下收敛,有效提高了抗干扰性能。Compared with literature blind detection algorithms of MPSK system based on statistics,the Complex Hopfield Neural Network with Amplitude Phase type Hard Multistate activation function(CHNN_APHM)can be used to blindly detect with shorter received signals and it is appropriate for channels with common zeros,so it can satisfy the requirements that proposed for the reliability of the wireless digital communication system.To improve the performance of CHNN APHM this paper proposes a Disturbed Complex Transiently Chaotic Neural Network with Amplitude-Phase-type Hard Multistate activation function(DCTCNN_APHM),constructs a new energy function and proves the stability mode respectively.The algorithm uses transient chaotic neural network to improve the anti-noise performance,and the chaotic of one dimension sinusoidal mapping initialization to obtain the original signal at the initial moment,and selects the small perturbation factor with high correlation with the transmitted signal to make the algorithm jump out of the local optimal solution.Experimental simulation results show that the MPSK blind detection algorithm with perturbation amplitude phase-phase discrete amplitude multi-level transient chaotic neural network requires fewer starting point,can converge under smaller signal-to-noise ratio and shorter data length.

关 键 词：盲检测 扰动因子 暂态混沌神经网络 最优化 

分 类 号：TN911[电子电信—通信与信息系统]