基于小波包变换的船舶轴系轴心轨迹特征提取

Features extracting of ship shaft centerline orbit based on wavelet packet transform

为实现通过轴心轨迹识别船舶轴系的工作状态,在船舶轴系轴心轨迹测试实验台上测试各轴承处水平和垂直的位移信号,应用小波包变换对各轴承处的轴心轨迹进行特征提取及分析.结果表明:实测船舶轴系轴心轨迹混乱,无法用于船舶轴系工作状态的识别;利用小波包变换提取的轴心轨迹呈清晰的香蕉形、椭圆形及外"8"字形,其中香蕉形和外"8"字形轴心轨迹刻画了转子不对中工作状态,椭圆形轴心轨迹刻画了转子不平衡工作状态.因此,小波包变换可用于船舶轴系轴心轨迹的提取,实现船舶轴系工作状态的识别.

In order to identify the working status of ship shaft by the shaft centerline orbit, a testing platform is built up to obtain the shaft centerline orbit by using the both vertical and horizontal signals from the eddy current displacement sensors, and the wavelet packet transform is used to extract the features of ship shaft eentedine orbit. Test results show that it is diffieuh to rec- ognize the features of shaft centerline orbit because of the noise interference, and the features of banana-shaped, ellipse-shaped and ＂8＂ shaped are extracted by using the wavelet packet trans- form. The misalignment of rotor is due to the features of banana- shaped and ＂8＂ shaped, and the imbalance state of rotor is due to the feature of ellipse-shaped. Therefore the wavelet packet transform can be used to extract the features of ship shaft center- line orbit for state recognition of ship shaft.