摘要
由于小波模极大值去噪方法在强背景噪声的情况下提取碰摩信号的能力变弱甚至失效,在本文中提出应用独立分量分析(ICA)方法对碰摩信号进行特征提取。通过对转子模拟实验台模拟的强背景噪声下的碰摩信号进行ICA去噪方法和小波去噪方法仿真实验,结果表明,本方法明显优于小波去噪方法,为强背景噪声下的弱振动信号的检测提供了新的途径。
As Wavelet modules maximum de-noising methods weaken or fail in the intensive noises environment, a method based on independent component analysis feature extraction was applied for rub-impact signals in this paper. The ICA denosing methods experiments of rub-impact signal with intensive noise were compared with the wavelet modules maximum denoising method, the results show that ICA method is more efficient and provides a new approach for the detecting of weak vibration signals from the intensive noises environment.
出处
《汽轮机技术》
北大核心
2006年第2期121-123,155,共4页
Turbine Technology
关键词
碰摩
独立分量分析
小波模极大值
去噪
rub-impact
independent component anaIysis
wavelet modules maximum
de-noising