基于EEMD-SVM的刀具磨損狀態(tài)研究
中國(guó)測(cè)試江 雁， 傅 攀， 李曉暉
摘 要：針對(duì)刀具磨損監(jiān)測(cè)中信號(hào)的非平穩(wěn)特性和小樣本建模中神經(jīng)網(wǎng)絡(luò)容易陷入局部值的問(wèn)題，提出基于多傳感器信號(hào)，運(yùn)用集合經(jīng)驗(yàn)?zāi)B(tài)分解（ensemble empirical mode decomposition，EEMD）和支持向量機(jī)（support vector machine，SVM）相結(jié)合的算法，實(shí)現(xiàn)對(duì)刀具磨損多狀態(tài)的識(shí)別。首先對(duì)振動(dòng)信號(hào)進(jìn)行集合經(jīng)驗(yàn)?zāi)B(tài)分解，將其分解為若干個(gè)本征模態(tài)函數(shù)（intrinsic mode function，IMF）之和，然后計(jì)算得到三向切削力信號(hào)的均值和各本征模態(tài)函數(shù)分量的能量百分比值作為磨損狀態(tài)分類(lèi)特征，最后運(yùn)用支持向量機(jī)和Elman神經(jīng)網(wǎng)絡(luò)對(duì)刀具在不同磨損狀態(tài)下的特征數(shù)據(jù)樣本進(jìn)行訓(xùn)練和識(shí)別。實(shí)驗(yàn)結(jié)果證明該方法能很好地實(shí)現(xiàn)對(duì)刀具磨損狀態(tài)的識(shí)別，與Elman神經(jīng)網(wǎng)絡(luò)相比，支持向量機(jī)具有更高的識(shí)別率，更適合小樣本情況下刀具磨損狀態(tài)的分類(lèi)識(shí)別。
關(guān)鍵詞：刀具磨損狀態(tài)識(shí)別；集合經(jīng)驗(yàn)?zāi)B(tài)分解；支持向量機(jī)；多傳感器
文獻(xiàn)標(biāo)志碼：A 文章編號(hào)：1674-5124（2016）01-0087-05
Study of tool wear based on EEMD-SVM
JIANG Yan， FU Pan， LI Xiaohui
（School of Mechanical Engineering，Southwest Jiaotong University，Chengdu 610031，China）
Abstract: To make the signals steady in cutting-tool wear monitoring and prevent neural networks from easily falling into local minimum values during small sample modeling， we have proposed a new method to identify cutting-tool wear conditions based on multi-sensor signals， ensemble empirical mode decomposition（EEMD） and support vector machine（SVM）. First， collected vibration signals are decomposed into a number of stationary intrinsic mode functions and further into the sum of multiple intrinsic mode functions. Second， these functions are used to calculate the mean value of three-direction cutting force signals and the energy percentage of each intrinsic mode function component and the calculation results were taken as the classification features of wear conditions. Next， the characteristic samples under different wear extents were trained and identified by SVM and Elman Neural Network. The experiment shows that this method can be used to determine the wear conditions of cutting tools and the SVM has a higher identification rate and more suitable for classified identification of cutting-tool wear conditions for small samples.
Keywords: tool wear condition identification； ensemble empirical mode decomposition； support vector machine； multi-sensor
