作者:秦怡源，刘献礼，岳彩旭，郭斌，丁明娜

Authors:QIN Yiyuan,LIU Xianli,YUE Caixu,GUO Bin,DING Mingna摘要:针对铣削过程中刀具磨损量监测问题，提出一种基于极端随机树和高斯分布与 Ｋ 近邻相结合的刀具磨损监测方法。该方法选用截断法和hampel滤波法剔除力、振动和声发射信号中的异常值和奇异点。其次通过极端随机树和高斯分布的偏离情况对特征集进行优选，降低数据矩阵的复杂性。 分别对比分析了两次优选前后三种Ｋ近邻模型的拟合度和评估度量。利用优选后的特征对逻辑回归、极端随机树、支持向量回归和 Ｋ近邻算法模型进行训练，并利用十折交叉验证法和测试集进行验证。最终得出，基于极端随机树和高斯分布与 K近邻的刀具磨损监测模型的拟合度达到 99.17%，均方误差和平均绝对误差分别为 13.0688、1.8241。结果表明该方法能够实现对铣刀磨损的有效监测，从而提高工件加工质量。
\n\n\t
\n
\n\n\t
\n
\n\n\t
\n
\n

Abstract:\n\t
\n
\n\n\tAiming at the problem of tool wear monitoring in milling process ,a tool wear monitoring method based on extremerandom tree and Gaussian distribution and K-nearest neighbor is proposed. In this method ,truncation method and Hampel filteringmethod are used to eliminate outliers and singular points in force,vibration and acousticemission signals. Secondly,the feature set isoptimized by the deviation of extreme random tree and Gaussian distribution to reduce the complexity of data matrix. The fitting degreeand evaluation measure of the three K-nearest neighbor models before and after the two optimization are compared and analyzed. Theoptimized features are used to train logical regression extreme random tree support vector regression and K-nearest neighbor algorithmmodels and verified by ten fold cross validation method and test set. Finally the fitting degree between the tool wear monitoring modelbased on extreme random tree and Gaussian distribution and K-nearest neighbor is 99. 17%,and the mean square error and meanabsolute error are 13. 0688 and 1. 8241 respectively. The results show that this method can effectively monitor the wear of millingcutter,so as to improve the machining quality of workpiece.\n
\n


PDF全文下载地址:

可免费Download/下载PDF全文