| 紧致型小波网络在模拟电路故障诊断中的应用 |
| |
| 引用本文： | 韩宝如,孟玲玲. 紧致型小波网络在模拟电路故障诊断中的应用[J]. 现代电子技术, 2006, 29(16): 145-146,149 |
| |
| 作者姓名： | 韩宝如 孟玲玲 |
| |
| 作者单位： | 燕山大学,信息科学与工程学院,河北,秦皇岛,066004 |
| |
| 摘 要： | 提出了一种新的基于紧致型小波神经网络的模拟电路故障诊断方法。该法首先利用小波包变换对故障信号进行预处理,减少了紧致型小波神经网络的输入数目,简化了紧致型小波神经网络结构,然后对紧致型小波神经网络进行训练和测试。仿真试验表明,该方法比普通BP神经网络方法训练速度更快,诊断准确率更高,容错能力强,非常适用于模拟电路故障诊断。
|
| 关 键 词： | 模拟电路 小波包变换 小波神经网络 故障诊断 |
| 文章编号： | 1004-373X（2006）16-145-02 |
| 收稿时间： | 2006-04-13 |
| 修稿时间： | 2006-04-13 |
Application of Inlay Model Wavelet Neural Network in Analog Circuit Fault Diagnosis |
| |
| HAN Baoru,MENG Lingling. Application of Inlay Model Wavelet Neural Network in Analog Circuit Fault Diagnosis[J]. Modern Electronic Technique, 2006, 29(16): 145-146,149 |
| |
| Authors: | HAN Baoru MENG Lingling |
| |
| Affiliation: | College of Information Science and Engineering, Yanshan University, Qinhuangdao, 066004, China |
| |
| Abstract: | A new analog ciruit fault diagnosis method based on inlay model wavelet neural network is introduced in this paper.The method uses wavelet packet transform to preprocess fault signal,to reduce the number of inputs fed to the inlay model wavelet neural network and simplify its architecture.Afterward training and testing wavelet neural network.Experimentation indicates that the method has faster training speed;higher diagnosis nicety rate and stronger tolerating fault ability than general neural network method.So the method is very applies to analog ciruit fault diagnosis. |
| |
| Keywords: | analog ciruit wavelet packet transform wavelet neural network fault diagnosis |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
