金刚石滚轮修整时的径向圆跳动状态在线判别  

On-line discrimination of radial runout state during diamond roller trimming

作　　者：付庭斌 朱振伟[1] 张瑞[1] 赵华东[1] FU Tingbin;ZHU Zhenwei;ZHANG Rui;ZHAO Huadong(College of Mechanical and Power Engineering,Zhengzhou University,Zhengzhou 450001,China)

机构地区：[1]郑州大学机械与动力工程学院,郑州450001

出　　处：《金刚石与磨料磨具工程》2022年第2期233-239,共7页Diamond & Abrasives Engineering

基　　金：郑州市协同创新项目(18XTZX12006)。

摘　　要：金刚石滚轮修整砂轮时的性能受其径向圆跳动的影响,而其径向圆跳动状态判别的智能化程度较低。为此,对金刚石滚轮修整状态下的径向圆跳动磨削声发射信号,提出一种基于小波分解和SVM的在线检测方法。将磨削声发射信号通过小波变换并分解,提取小波分解系数的有效值、方差及能谱系数3种特征参数。结果表明:将3种特征参数彼此组合输入到SVM中进行状态识别时的准确率都在96.0%以上;3种特征参数同时输入时的准确率最高,达到了98.3%。该检测方法具有实际应用价值。The performance of diamond roller when dressing grinding wheel was affected by its radial runout,but the intelligent degree of judging its radial runout state was low.Therefore,an on-line detection method based on wavelet de-composition and SVM was proposed for the grinding acoustic emission signal of radial runout under the trimming state of diamond roller.The grinding acoustic emission signal was transformed and decomposed by wavelet transform,and the three characteristic parameters of wavelet decomposition coefficients were extracted,which were effective value,variance value and energy spectrum coefficient.The results show that the accuracies of combining the three feature parameters into SVM for state recognition are more than 96.0%.When the three characteristic parameters are input at the same time,the accuracy is the highest,reaching 98.3%.The detection method has practical application value.

关 键 词：金刚石滚轮 声发射 小波变换 修整状态识别 支持向量机 

分 类 号：TQ164[化学工程—高温制品工业]