辽宁石油化工大学学报 ›› 2008, Vol. 28 ›› Issue (1): 74-77.

• 计算机与自动化 • 上一篇    下一篇

改进的小波神经网络在管道泄漏故障诊断中的应用

单海欧   

  1. 辽宁石油化工大学信息与控制工程学院,辽宁抚顺 113001
  • 收稿日期:2007-10-10 出版日期:2008-03-20 发布日期:2017-07-22

Improved Wavelet Neural Network’s Application in Pipelines Leakage Fault Diagnosis

SHAN Hai-ou   

  1. School of Information Engineering, Liaoning University of Petroleum & Chemical Technology, Fushun Liaoning 113001, P.R.China
  • Received:2007-10-10 Published:2008-03-20 Online:2017-07-22

摘要: 提出一种增加基于小波神经网络输入与输出节点的部分直接连接网络结构,并且根据输入征兆对输出故障的影响程度的具体情况赋予不同的连接权值,这样就明显突出了输入与输出层即征兆与故障之间的直接关联性,有利于小波神经网络模型的稳定性,同时加快了网络的收敛速度,并能快速而准确地对故障进行分类诊断。将改进的小波神经网络应用于管道泄漏故障的诊断,收到良好的效果。

关键词: 小波神经网络, 故障诊断, 泄漏检测

Abstract: A class of wavelet neural network model with the connections between the input and the output layers in part was proposed. According to the effect extent that input symptom to the output fault, the different weights were given. Therefore the straight correlation between the input and the output layers namely between the symptom and the fault was emphasized, and it is in favor of the stability of the WNN model, at the same time it makes the network has the ability that the rapid convergence and quick and exact fault diagnosis. The application to diagnose the leakage of pipelines is included to demonstrate the effectiveness. 

Key words: Wavelet neural network, Fault diagnosis, Leak detection

引用本文

单海欧. 改进的小波神经网络在管道泄漏故障诊断中的应用[J]. 辽宁石油化工大学学报, 2008, 28(1): 74-77.

SHAN Hai-ou. Improved Wavelet Neural Network’s Application in Pipelines Leakage Fault Diagnosis[J]. Journal of Liaoning Petrochemical University, 2008, 28(1): 74-77.

使用本文

0
    /   /   推荐

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://journal.lnpu.edu.cn/CN/

               https://journal.lnpu.edu.cn/CN/Y2008/V28/I1/74