| 改进ART-2A神经网络在故障自诊断中的应用 |
| |
| 引用本文： | 刘智荣,马建辉,任宾.改进ART-2A神经网络在故障自诊断中的应用[J].电光与控制,2008,15(10). |
| |
| 作者姓名： | 刘智荣 马建辉 任宾 |
| |
| 作者单位： | 中国航天时代电子公司第十六研究所,西安,710100 |
| |
| 摘 要： | ART-2A神经网络可以很好地应用于模式识别中的分类问题,但由于算法结构的不足,存在分类漂移现象,导致网络不稳定,严重影响了网络的工程应用.对标准ART-2A网络结构和算法过程进行了深入研究,分析了引起分类漂移的原因,提出了一种ART-2A神经网络改进算法,并通过故障自诊断实验进行网络稳定性和实用性验证.实验证明改进ART-2A神经网络能长期稳定工作,准确进行故障判别,实现系统的故障诊断自动化.
|
| 关 键 词： | 故障诊断 神经网络 |
Application of improved ART-2A neural network in automatic fault detection and diagnosis |
| |
| LIU Zhi-rong,MA Jian-hui,REN Bin.Application of improved ART-2A neural network in automatic fault detection and diagnosis[J].Electronics Optics & Control,2008,15(10). |
| |
| Authors: | LIU Zhi-rong MA Jian-hui REN Bin |
| |
| Affiliation: | No.16 Institute of China Aerospace Times Electronic Company;Xi'an 710100;China |
| |
| Abstract: | ART-2A Neural Network is effective in dealing with classification problem of pattern recognition,but it suffers from classification drift because of the shortage in algorithm structure,which may cause network instability,and in turn severely affect the engineering application of the network.The standard ART-2A network structure and algorithm are studied.And the causes of classification drift are analyzed.An improved ART-2A algorithm is presented and is used in Fault Detection and Diagnosis(FDD) experiments ... |
| |
| Keywords: | ART-2A |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
