基于估值修正的分布式传感器网络最小均方算法  

Improved LMS Algorithm by Estimate Correction in Distributed Sensor Network

作　　者：胡品端 熊庆国[2] HU Pin-duan;XIONG Qing-guo(School of Electrical Engineering and New Energy,China Three Gorges University,Yichang 443002,China;School of Information Science and Technology,Wuhan University of Science and Technology,Wuhan 430081,China)

机构地区：[1]三峡大学电气与新能源学院,湖北宜昌443002 [2]武汉科技大学信息科学与工程学院,武汉430081

出　　处：《火力与指挥控制》2019年第10期27-31,共5页Fire Control & Command Control

基　　金：国家自然科学基金资助项目(61501337)

摘　　要：为使分布式传感器网络自适应滤波算法在具有快速收敛和低稳态误差的同时,具有对脉冲干扰的鲁棒性,在扩散LMS自适应滤波算法基础上,提出一种基于参数估值p阶范数修正的变步长最小均方自适应滤波算法,算法通过使用参数估值的p阶范数增抗其对脉冲噪声的抗干扰能力,通过合理设置变步长控制因子使得算法在收敛初期的收敛速度及收敛后期的稳态误差在一个较小的范围取得一个较好的平衡。对比实验表明,相比已有算法,所提算法性能更优且具有较好的鲁棒性。In order to achieve fast convergence, low steady-state error and robustness to impulse interference of the adaptive filtering algorithm in distributed sensor network, based on the diffusion LMS adaptive filtering algorithm,a variable step size LMS adaptive filtering algorithm based on p-order norm correction of parameter estimation is proposed. in this algorithm, the p -order norm of the parameter estimation is used to enhances the impulse noise interference ability of the proposed method, and the variable step size control function is used to accelerate the convergence speed with a large iteration step size at the beginning and adopt a slower step change rate when tending to be stable to keep less state error. The experimental results show that the proposed algorithm performs better than the existing algorithms.

关 键 词：分布式传感器网络 扩散最小均方自适应滤波 参数估计值约束 变步长 

分 类 号：TN915.5[电子电信—通信与信息系统] TP911.22[电子电信—信息与通信工程]