摘要
故障诊断的基本问题是故障的分类问题。神经网络有很强的分类能力，并且有着特有的联想记忆、并行推理和抗干扰的能力，这些使得它成为研究故障诊断的一个新的课题。本文介绍了神经网络几种典型的模型：ＢＰ网、Ｈｏｐｆｉｅｄ、网、ＢＡＭ网和ＡＲＴ网在故障诊断中的应用。
The basic problem of fault dignosis is itsclassification and neural calculation network has strongcapability of sorting and peculiar associative memory,parallel inference and antijamming;all these makes theneural network to be a new project of studying faultdiagnosis.This paper introduces the application of afew typical models of neural networks as BP.HOPFIELD. BAM and ART network to faultdiagnosis.
出处
《自动化与仪器仪表》
1995年第6期1-4,共4页
Automation & Instrumentation
