摘要
针对机床刀具磨损故障诊断,开发了基于经验模态分解和香农熵进行信号处理的刀具故障诊断系统。在信号处理阶段,对机床加工过程中刀具的振动信号进行经验模态分解,得到若干固有模态函数(IMF),并基于香农熵从分解得到的IMF分量中提取有效分量,去除虚假分量,最后将有效的IMF分量的能量作为特征向量输入向量机(SVM)分类器来识别刀具的磨损状态。经实验验证,该系统能对刀具磨损状态进行准确快速地判断。
For tool wear fault diagnosis,a CNC tool wearing fault diagnosis syetem was developed based on empirical mode decomposition(EMD) and Shannon for signal processing.In signal processing stage,empirical mode decomposition was done to vibration signal in the machining process,and then a number of intrinsic mode functions(IMFs) were gotten,and then extracting effective IMFs and excluding false functions according to Shannon.At last,the energy of effective IMF functions are taken as inputs of support vector machine(SVM) classifier to identify the state of cutter. Proved by test,this system could judge the tool wear state quickly and accurately.
引文
[1] 孙巍伟,黄民,高延.基于EMD-HMM的机床刀具磨损故障诊断[J].机床与液压,2017(7):178-181.
[2] 高宏力.切削加工过程中刀具磨损的智能监测技术研究[D].成都:西南交通大学,2005.
[3] COHEN L. Time-frequency Distribution-A Review[J]. Proceedings of the IEEE,1989,77(7):941-981.
[4] 程军圣,张亢,杨宇.局部均值分解方法及其在滚动轴承故障诊断中的应用[J].中国机械工程,2009,22(22): 2711-2717.
[5] HUANG J S,SHEN Z,LONG S R. The Empirical Mode Decomposition and Hilbert Spectrum for Nonlinear and Non-stationary Time Series Analysis[J].The Royal Society, 1998,454(12):903-995.
[6] N E Huang, Shen Z S R Long. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J].London,Proc.R.Soc., 1998,454:903-995.
[7] 杨雪特.熵的引入、深化与泛化—从克劳修斯熵到香农熵[J].内江师范学院学报,1991(4):62-65.
[8] 王姣,刘海燕.基于支持向量机和遗传算法的刀具故障诊断[J].组合机床与自动化加工技术,2013(1):74-76.
[9] 常勇,何婷.一种EEMD阈值降噪方法在故障诊断中的应用[J].工业仪表与自动化装置,2018(04):3-7.
[10] 赵文忠,张传军.基于经验模态分解的算法改进[J]. 自动化与仪器仪表,2009(05):25-33.