| 模拟电路故障诊断中故障重分类方法的研究 |
| |
| 引用本文： | 张屹,魏学业,蒋海峰.模拟电路故障诊断中故障重分类方法的研究[J].北京交通大学学报(自然科学版),2006,30(2):53-56,64. |
| |
| 作者姓名： | 张屹 魏学业 蒋海峰 |
| |
| 作者单位： | 北京交通大学,电子信息工程学院,北京,100044;北京交通大学,电子信息工程学院,北京,100044;北京交通大学,电子信息工程学院,北京,100044 |
| |
| 摘 要： | 分析了模拟电路故障诊断中故障类重叠.针对在该情况下神经网络训练困难与故障诊断正确率低的问题,提出了一种适于模拟电路的、基于神经网络故障诊断的故障重分类方法,给出了该方法的数学模型.通过诊断示例表明,该方法在故障类存在重叠时,降低了神经网络的训练难度,故障诊断的正确率达到99%以上.
|
| 关 键 词： | 重分类 故障诊断 模拟电路 神经网络 |
| 文章编号： | 1673-0291（2006）02-0053-04 |
| 收稿时间： | 2005-11-03 |
| 修稿时间： | 2005-11-03 |
Study on the Fault Re-Classification Method in Analog Circuit Fault Diagnosis |
| |
| ZHANG Yi,WEI Xue-ye,JIANG Hai-feng.Study on the Fault Re-Classification Method in Analog Circuit Fault Diagnosis[J].JOURNAL OF BEIJING JIAOTONG UNIVERSITY,2006,30(2):53-56,64. |
| |
| Authors: | ZHANG Yi WEI Xue-ye JIANG Hai-feng |
| |
| Institution: | School of Electronics and Information Engineering, Beijing Jiaotong University, Beijing 100044, China |
| |
| Abstract: | The faults overlap circumstances in analog fault diagnosis are analyzed, In order to solve the problems of high difficulty of neural network training and low accuracy of fault diagnosis under above circumstances, a fault re-classification method based on neural network fault diagnosis in analog circuit is proposed and the mathematics model of the method is given. The fault diagnosis example shows that the difficulty of neural network training is diminished and the fault diagnosis accuracy can reach more then 99 % when faults overlaps exist. |
| |
| Keywords: | re-classification fault diagnosis analog circuit neural network |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
