一种基于经验模式分解与支持向量机的转子故障诊断方法

A Fault Diagnosis Approach for Rotor Systems Based on Empirical Mode Decomposition Method and Support Vector Machines

转子系统故障诊断的关键是故障特征提取和状态识别,在故障特征提取中,采用自回归(AR)模型参数作为特征向量来分析系统的状态变化是十分有效的,但AR模型只适用于平稳信号的分析,而转子系统的振动信号表现出非平稳特征;同时在状态识别中,支持向量机(SVM)有效地改善了传统分类方法的缺陷。针对这些问题,提出一种基于经验模态分解(empiricalmodedecomposition,EMD)和支持向量机的转子系统故障诊断方法。该方法对转子系统的振动信号进行经验模态分解,将其分解为若干个固有模态函数(intrinsicmodefunction,IMF);对每一个IMF分量建立AR模型,取模型的自回归参数和残差的方差作为故障特征向量,并以此作为输入来建立支持向量机分类器,判断转子系统的工作状态和故障类型。实验结果分析表明,文中提出的方法能有效地应用于转子系统的故障诊断。

A fault diagnosis approach for rotor systems based on EMD method and support vector machine is proposed The EMD method is used to decompose the vibration signal of a rotor system into a number of intrinsic mode function components and then the autoregressive mode（AR） model of each IMF component is established. The main auto-regressive parameters and the variances of remnant are regarded as the feature vectors. Then, the support vector machines used as fault classifiers are established to identify the condition and fault pattern of the rotor system. Practical examples show that the proposed approach can be applied to the rotor system fault diagnosis effectively.