LabVIEW中BP神经网络的实现及应用  

BP Neural Network′s Realization and Application in LabVIEW

作　　者：廖慎勤[1] 彭良玉[1] 江勇 

机构地区：[1]湖南师范大学物理与信息科学学院,湖南长沙410081 [2]凌阳科技(深圳)有限公司,广东深圳518000

出　　处：《现代电子技术》2009年第4期72-75,共4页Modern Electronics Technique

基　　金：湖南省自然科学基金资助项目(06JJ50117)

摘　　要：BP(Back Propagation)神经网络是一种具有广泛应用性的前馈神经网络,LabVIEW是一种图形化编程语言,其为虚拟仪器设计者提供了一个便捷、轻松的设计环境,被工业界及研究实验室广泛接受。介绍了两种在LabVIEW实现BP神经网络计算的方法,即Matlab Script节点和图形编程,Matlab Script节点采用在LabVIEW中直接导入Matlab程序运行,而图形编程采用图形编程的方式实现算法,并分别以神经网络在函数逼近和某设备分类中的应用说明了各自的实现流程,实验结果精确且形象直观,充分体现了LabVIEW作为图形化编程语言的特点。BP neural network is a widely used feedforward neural network, LabVIEW is a graphical programming language, which provids a convenient and easy design environment, so it＇s normally accepted by industrial sector and research liboratory. Two calculation methods of realizing BP neural network in LabVIEW are introduced,those are Matlab Script node and graphical programming, Matlab Script node imports the Matlab program and running it,graphical programming realizes the algorithm with the method of graphical programming,and takes the apply of BP neural network in function approach and distinguishing between categories as examples to explain the realization process of the two methods,and the results are precise and intuitive, fully reflect the feathures of LabVIEW as a graphical programming language.

关 键 词：BP神经网络 LABVIEW 图形化 MATLAB 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]