基于多重分形的旋转机械振动故障检测方法

Vibration Fault Detection Method for Rotating Machinery Based on Multifractal

为获取更加准确的旋转机械振动故障检测结果,提出基于多重分形的旋转机械振动故障检测方法。通过建立旋转机械振动信号采集模型,获取振动信号,采用小波域维纳滤波算法对振动信号去噪处理。分析不同条件下的振动数据,同时引入多重分形方法提取旋转机械振动信号故障特征,通过核模糊C均值聚类算法区分正常信号和故障信号,最终实现旋转机械振动故障检测。实验结果表明,所提方法进行旋转机械振动故障检测率较高,漏检率较低,检测时间较短,可以快速准确地完成旋转机械振动故障检测。

In order to obtain more accurate vibration fault detection results of rotating machinery,a vibration fault detection method of rotating machinery based on multifractal is proposed.By establishing the vibration signal acquisition model of rotating machinery,the vibration signal is obtained,and the wavelet domain wiener filtering algorithm is used to denoise the vibration signal.The vibration data under different conditions are analyzed,and the multifractal method is introduced to extract the fault characteristics of rotating machinery vibration signal.The normal signal and fault signal are distinguished by kernel fuzzy C-means clustering algorithm,and finally the vibration fault detection of rotating machinery is realized.After a large number of experimental tests,it is proved that the proposed method has high vibration fault detection rate,low missed detection rate and short detection time,and can complete the vibration fault detection of rotating machinery quickly and accurately.