计算机工程与应用 ›› 2008, Vol. 44 ›› Issue (22): 169-171.DOI: 10.3778/j.issn.1002-8331.2008.22.050

• 数据库、信号与信息处理 • 上一篇    下一篇

基于ADALINE神经网络的自适应滤波方法

乔新勇,刘 玮   

  1. 装甲兵工程学院 机械工程系 机电工程教研室,北京 100072
  • 收稿日期:2007-10-10 修回日期:2008-01-21 出版日期:2008-07-11 发布日期:2008-07-11
  • 通讯作者: 乔新勇

Method for self-adapting filtering based on ADALINE neural network

QIAO Xin-yong,LIU Wei   

  1. Department of Mechanical Engineering,The Academy of Armored Forces Engineering,Beijing 100072,China
  • Received:2007-10-10 Revised:2008-01-21 Online:2008-07-11 Published:2008-07-11
  • Contact: QIAO Xin-yong

摘要: 自适应滤波器能够适应系统和环境的动态变化,具有较高的滤波精度。介绍了一种利用ADALINE神经网络进行自适应滤波的方法,根据自适应噪声抵消原理建立了ADALINE自适应神经滤波器模型,并使用该模型将发动机高压油管振动信号中的机体振动噪声滤除,提高了信噪比,为利用高压油管振动信号进行喷油器故障的精确诊断奠定了基础。

关键词: 自适应滤波, 人工神经网络, 振动信号

Abstract: Adaptive filter can adapt the change of system and environment,so has higher filtering accuracy.This paper introduces a self-adapting filtering method based on ADALINE neural network to cancel noises,sets up an adaptive filter model according to the principle of adaptive noise cancellation,and uses this method to filter the noise which is excited by the body vibration from the vibration signal of high-pressure line of engine.By this method the signal-to-noise ratio is improved effectively.It contributes to the following signal analysis and fault diagnosis of fuel injector.

Key words: self-adapting filtering, neural network, vibration signal