基于不完整约束自然梯度算法的多道盲解卷  

Multichannel Blind Deconvolution Based on Natural Gradient Algorithms with Nonholonomic Constraints

作　　者：陈海洋[1] 马建仓[1] 牛奕龙[1] 

机构地区：[1]西北工业大学电子信息学院,陕西西安710072

出　　处：《微电子学与计算机》2005年第6期16-18,共3页Microelectronics & Computer

摘　　要：针对多输入多输出(MIMO)系统的Bussgang算法可能收敛到错误的解,而且收敛速度慢的缺点。章提出了不完整约束的自然梯度算法,该算法是由不完整约束条件与自然梯度算法的结合而推导出来的。通过计算机仿真对这两种多道盲解卷算法进行了比较,仿真试验表明:提出的算法收敛速度快,并且比Bussgang算法稳定。The main weak-point of Bussgang algorithm is that it possibly converges to wrong solutions and causes very slowly in MIMO dynamical system. In order to solve problem, this paper proposes the natural gradient algorithms with nonholomic constraints. We derive it by incorporating a nonholonomic constraint into the natural gradient learning algorithm. A large number of computer simulations have been performed to compare the performance of this two algorithms for the multichannel blind deconvolution. The result shows that the proposed algorithm coverges very quickly and is more stable than Bussgang algorithm.

关 键 词：Bussgang算法 自然梯度下降法 不完整约束 盲解卷 

分 类 号：TN911.7[电子电信—通信与信息系统]