摘要：为监测机床刀具磨损程度，提出了一种基于小波包理论（WPD）、经验模态分解（EMD）以及支持向量机（SVM）等相结合的刀具故障诊断方法。通过小波包理论工具消除刀具的高频噪声信号，并对去噪后的信号进行模态分解、合成，计算出模态函数（IMF）和EMD分解信号的相关参数。将计算出的信号时域上的特征参数作为支持向量机（SVM）的输入特征向量，完成对刀具故障的检测。实验结果分析表明，该方法可以有效地判断刀具磨损程度，验证了方法的可行性。

关键词：小波包理论；经验模态分解；支持向量机；故障诊断

中图分类号：TG806；TH16文献标志码：A

Analysis on Method of Detecting Tool Wear State

Liu Zhijian，Liu Baolin，Hu Yuanbiao

Abstract:In order to monitor the degree of tool wear，a tool fault diagnosis method based on wavelet packet theory (WPD)，empirical mode decomposition (EMD) and support vector machine (SVM) are proposed.The high frequency noise signal of the cutter is eliminated by the wavelet packet theory，and then the modal decomposition and synthesis of the denoised signal are performed，and the modal function and the related parameters of the EMD decomposition signal are calculated.The characteristic parameter of the calculated signal in time domain is used as the input eigenvector of the support vector machine (SVM) to complete the tool fault detection.The experimental results show that the method can effectively judge the wear degree of tool and verify the feasibility of the method.

Keywords:WPD；EMD；SVM；fault diagnosis