基于EEMD-SVM的铣刀磨损状态监测系统设计
|
摘要
为实现铣刀磨损状态准确、快速的识别,设计了一套基于集合经验模态分解(EEMD)和支持向量机(SVM)的刀具状态在线监控系统。首先,应用EEMD将采集的铣刀声发射(AE)信号分解成多个固有模态函数(IMF),并基于相关系数法从分解得到的IMF分量中提取有效分量,剔除虚假成分。最后,将有效IMF分量的能量作为特征向量输入支持向量机分类器来完成铣刀磨损状态的识别。使用TwinCAT和Matlab实现了整套系统的功能。经实验验证,监控系统运行稳定并能够对刀具状态进行准确、快速的识别。
In order to recognize milling-tool wear state accurately and quickly,a system based on ensemble empirical mode decomposition(EEMD) and support vector machine(SVM) is designed.Firstly,acoustic emission(AE) signal is decomposed into several intrinsic mode function(IMF) by EEMD method.Then extracting effective intrinsic mode functions(IMFs) and excluding false functions according to correlation coefficient method.At last,the energy of effective IMF functions are taken as inputs of support vector machine(SVM) classifier to identify the state of cutter.using TwinCAT and Matlab to implement the system's functions.Proved by test,the system work well and judge the cutter wear state quickly and accurately.
In order to recognize milling-tool wear state accurately and quickly,a system based on ensemble empirical mode decomposition(EEMD) and support vector machine(SVM) is designed.Firstly,acoustic emission(AE) signal is decomposed into several intrinsic mode function(IMF) by EEMD method.Then extracting effective intrinsic mode functions(IMFs) and excluding false functions according to correlation coefficient method.At last,the energy of effective IMF functions are taken as inputs of support vector machine(SVM) classifier to identify the state of cutter.using TwinCAT and Matlab to implement the system's functions.Proved by test,the system work well and judge the cutter wear state quickly and accurately.
引文
[1] 丛明,房波,周孜亮.车-车拉数控机床拖板有限元分析及优化设计[J].中国机械工程,2008,19(2):208-213.
[2] COHEN L.Time-frequency Distribution-A Review[J].Proceedings of the IEEE,1989,77(7):941-981.
[3] I.Marinescu,D.A.Axinte,A critical analysis of effectiveness of acoustic emission signals to detect tool and workpiece malfunctions in milling operations,International Journal of Machine Tools & Manufacture,48(2008)1148 -1160.
[4] 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.
[5] WU Z H,HUANG N E.Ensemble empirical mode decomposition:A noise-assisted data analysis method[J].Advances in Adaptive Data Analysis,2009,(1):1 -41.
[6] 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术,2013,(1):74 -76.
[7] 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.
[8] 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.
[9] 钱桃林,高宏力,李辅翼,等.基于EMD和ADS的刀具磨损在线监控系统开发[J].组合机床与自动化加工术,2017,(5):108-129.
[10] 李威霖.车铣刀具磨损状态监测及预测关键技术研究[D].成都:西南交通大学,2013.
[11] 周胜凯,刘强,李传军,等.开放式数控系统平台的设计与开发[J].机械设计与制造,2015,(1):169 -171,176.
[12] 彭美武,陈洪涛,钟成明.基于支持向量机的刀具磨损决策融合技术[J].组合机床与自动化加工技术,2014,(4):89 -93.
[13] 周少梅 .数控机床控制及故障诊断系统的设计与实现[J].自动化与仪器仪表,2018,(10):105-108.
[14] 陈仁祥,黄鑫,杨黎霞等.基于卷积神经网络和离散小波变换的滚动轴承故障诊断[J].振动工程学报,2018,(5):883-891.
[15] 刘广,刘济科,吕中荣.基于时域响应灵敏度分析的非线性系统参数识别[J].振动与冲击,2018,(11):213-219.
[2] COHEN L.Time-frequency Distribution-A Review[J].Proceedings of the IEEE,1989,77(7):941-981.
[3] I.Marinescu,D.A.Axinte,A critical analysis of effectiveness of acoustic emission signals to detect tool and workpiece malfunctions in milling operations,International Journal of Machine Tools & Manufacture,48(2008)1148 -1160.
[4] 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.
[5] WU Z H,HUANG N E.Ensemble empirical mode decomposition:A noise-assisted data analysis method[J].Advances in Adaptive Data Analysis,2009,(1):1 -41.
[6] 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术,2013,(1):74 -76.
[7] 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.
[8] 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.
[9] 钱桃林,高宏力,李辅翼,等.基于EMD和ADS的刀具磨损在线监控系统开发[J].组合机床与自动化加工术,2017,(5):108-129.
[10] 李威霖.车铣刀具磨损状态监测及预测关键技术研究[D].成都:西南交通大学,2013.
[11] 周胜凯,刘强,李传军,等.开放式数控系统平台的设计与开发[J].机械设计与制造,2015,(1):169 -171,176.
[12] 彭美武,陈洪涛,钟成明.基于支持向量机的刀具磨损决策融合技术[J].组合机床与自动化加工技术,2014,(4):89 -93.
[13] 周少梅 .数控机床控制及故障诊断系统的设计与实现[J].自动化与仪器仪表,2018,(10):105-108.
[14] 陈仁祥,黄鑫,杨黎霞等.基于卷积神经网络和离散小波变换的滚动轴承故障诊断[J].振动工程学报,2018,(5):883-891.
[15] 刘广,刘济科,吕中荣.基于时域响应灵敏度分析的非线性系统参数识别[J].振动与冲击,2018,(11):213-219.