基于EMD和SVM的刀具故障诊断

为有效监测刀具在机床中可能出现的故障,提出基于经验模态分解(EMD)和支持向量机(SVM)的一种故障诊断方法。首先用EMD方法将振动信号分解为有限个固有模态函数(IMF),并选取能量较大的IMF进行标量量化得到特征向量,最后将其输入SVM进行测试进而判断故障类型。分析结果表明,基于EMD-SVM的刀具故障方法能够更有效地识别刀具故障状态。

Tool Fault Diagnosis Based on Empirical Mode Decomposition and Support Vector Machine

In order to effectively monitor the possible faults of cutting tools,fault diagnosis method based on empirical mode decomposition (EMD) and support vector machine (SVM) is presented.With EMD,the vibration signals are decomposed into a finite number of intrinsic mode functions (IMF).Those IMFs with larger energy are selected for IMF scalar quantization to get feature vectors and for the SVM to test and judge the fault type.Results show that the EMD-SVM-based tool failure diagnosis method can identify tool fault state more effectively.