基于特征参数的旋转机械智能故障诊断方法

Intelligent Fault Diagnosis of Rotating Machinery Using Characteristic Parameters

为了对轴心轨迹进行特征提取和自动识别,使用了分形维数中的盒维数、信息维数、关联维数3个参量来描述轴心轨迹的分形特征;还引入紧密度和丰度两个量,从几何方面对轴心轨迹进行分析;最后,采用神经网络技术对3种状态下的轴心轨迹进行分类识别。试验结果表明,通过对轴心轨迹的分形特征和几何特征联合对转子的运行状态进行评定,有良好的区分度。

The shaft orbit is an important feature of rotating machinery. In order to research the shaft orbit for feature extraction and automatic identification,three fractal dimensions,the box dimension,the information dimension and the correlation dimension,were used to describe the fractal characteristics of the shaft orbit. In addition,two geometrical characteristics as tightness and voluptuous parameter were introduced into the analysis of the shaft orbit. The neural network technology was used to classify the orbit shapes under different conditions. The results show that by using the fractal and geometry characteristics of the shaft orbit,the application of neural networks to discriminating different operational states can get a high accuracy.