基于威布尔分布数字特征的电机滚动轴承早期故障诊断

Early Fault Diagnosis of Motor Rolling Bearing Based on Weibull Distribution Numerical Characteristics

电机滚动轴承的振动信号往往能反映轴承的运行状态,因此提取电机滚动轴承振动信号的特征量是非常关键的,也是轴承故障研究的热点问题.首先对电机滚动轴承振动信号进行降噪等预处理,并对预处理的振动信号建立威布尔分布模型,验证模型的恰当性;然后求取威布尔分布模型的尺度参数和形态参数,并估计出其数字特征量均值、方差、二阶原点矩、三阶中心矩、中位数和偏度;最后将估计出的特征信号输入SVM模式识别器进行故障诊断和模式识别,识别结果表明,威布尔分布模型的尺度参数、均值、二阶原点矩、中位数和偏度能很好地反映轴承的运行状态.实验证明所提方法能较好地诊断电机轴承的早期故障.

The vibration signal of the motor rolling bearing can often reflect the running state of the bearing,so it is very important to extract the characteristic value of the vibration signal of the motor rolling bearing.Firstly,the vibration signal of the rolling bearing of the motor is pre-processed,such as noise reduction and so on,and the Weibull distribution model is established to verify the correctness of the model.Then,the scale parameters and shape parameters of the Weibull distribution model are obtained,and the mean,variance,second-order origin moment,third-order central moment,median and skewness of its digital features are estimated.Finally,the estimated characteristic signals are input into SVM pattern recognizer for fault diagnosis and pattern recognition.The recognition results show that the scale parameters,mean,second-order origin moment,median and skewness of the Weibull distribution model can well reflect the running state of the bearing.The experimental results show that the proposed method can effectively diagnose the early faults of motor bearing.