基于EMD和奇异值分解技术的滚动轴承故障诊断方法

Fault Diagnosis Approach for Roller Bearings Based on EMD Method and Singular Value Decomposition Technique

提出了基于 EMD( Empirical mode decomposition)和奇异值分解技术的滚动轴承故障诊断方法。采用EMD方法将滚动轴承振动信号分解成若干个基本模式分量 ( Intrinsic mode function,IMF)之和 ,并形成初始特征向量矩阵。然后对初始特征向量矩阵进行奇异值分解得到矩阵的奇异值 ,将其作为滚动轴承振动信号的状态特征向量 ,通过建立 Mahalanobis距离判别函数判断滚动轴承的工作状态和故障类型。实验数据的分析结果表明 ,本文方法能有效地应用于滚动轴承故障诊断。

A fault diagnosis approach for roller bearings based on empirical mode decomposition (EMD) method and singular value decomposition technique is proposed. The EMD method is used to decompose the roller bearing vibration signal of a roller bearing into many of intrinsic mode function (IMF) components,from which the initial feature vector matrixes are formed. By applying the singular value decomposition technique to the initial feature vector matrixes,the singular values,regarded as the state feature vectors of the roller bearing vibration signals are obtained. The Mahalanobis distance criterion function is used to identify the condition and fault pattern of a roller bearing. Practical examples show that the approach can be applied to the roller bearings fault diagnosis.