一种新型粗糙集神经网络的故障诊断方法  

Research into Fault Diagnosis Method based on New Rough Set-Neural Networks

作　　者：冯惊雷[1] 张喜斌[1] 张恒喜[1] 

机构地区：[1]空军工程大学,陕西西安710038

出　　处：《火力与指挥控制》2007年第1期84-87,共4页Fire Control & Command Control

基　　金：国防预研基金资助项目(98J19.3.2.JB3201)

摘　　要：结合粗糙集理论,建立了基于SOFM网络的新型粗糙集神经网络故障诊断模型,给出了该模型的流程图,描述了系统各组成部分的工作原理。应用该模型对某型雷达进行故障诊断,实例证明新模型能够减少输入端数量,简化神经网络的结构,提高系统的速度,诊断时间短,准确性高,结果易于实现可视化,最后得到了故障可视拓扑映射图。A new rough set-neural network hybrid model based on self organized feature map （SOFM） network is presented in this paper. Firstly,we design a system flow chart and describe work principles of each part. Secondly, the validity of these models was tested by a type of radar system fault data. The results show that the new model can decrease the number of the network input nerve ceils, ameliorate network inner structural, decrease the computation time, and visualize the result. Finally, visualized topology-ordering map was founded.

关 键 词：雷达 粗糙集 神经网络 故障诊断 SOFM网络 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP306.3[自动化与计算机技术—控制科学与工程]