自动机振动信号去基线漂移

Removing Baseline Wander of Automatic Machine Signal

针对高速自动机振动信号中工作信号频率高,因低频背景噪音、传感器线头松动等原因引起的基线漂移信号频率相对较低的固有特点,采用小波多分辨率分析方法对实测自动机信号进行分解重构,去除基线漂移,对去除基线漂移前后的信号进行小波包特征提取并将特征进行对比,结果表明该方法不仅有效地去除了自动机振动信号中的漂移信号,而且较好地保持了自动机信号的原有形态,为特征提取、故障诊断工作提供了便利。

In view of the high frequency of the working signal in the vibration signal of the high speed automatic machine and the relatively low frequency of the baseline wander signal caused by the low frequency background noise,the loose wire of the sensor and other reasons,wavelet multiresolution analysis method is used to decompose and reconstruct the measured automata signal and remove baseline wander,wavelet packet feature extraction is performed on the signals before and after removal of the baseline wander and the features are compared. The results show that this method not only can effectively remove the drift signals in the automatic machine vibration signal,but also preserve the original form of the automatic machine signal,and facilitate the feature extraction and fault diagnosis.