遗传算法在过程信号的盲分离中的应用  

Application of Genetic Algorithm in Blind Signal Sepration for Process Signal

作　　者：林蔚天[1] 华容[2] 

机构地区：[1]上海电机技术高等专科学校电气自动化系 [2]上海应用技术学院自动化系

出　　处：《电气自动化》2004年第5期24-25,41,共3页Electrical Automation

摘　　要：盲分离神经网络算法存在着容易陷入局部极小点、收敛速度慢的缺点。提出采用遗传算法优化盲分离神经网络权值的初值,与遗传算法结合形成 GA-HJNN 算法,可迅速得到最佳盲分离神经网络的权值矩阵,实现对过程信号的去噪。通过实验对两种算法进行了比较。One of the main weak-points of the blind sepration algorithm of HJNN is that the optimal procedure is easily stacked into the local minimal value and it causes slow convergence.Based on genetic algorithm(GA),this paper proposed GA-HJNN algorithm to optimize the initial value of the weight of HJNN so as to obtian the optimum weight matrix quickly and realize the denoising of the process signal.The comparison between the two algorithms was given with experiment.

关 键 词：遗传算法 盲分离 神经网络 过程信号 

分 类 号：TN911.6[电子电信—通信与信息系统]