摘要
建立了一种基于轨迹相似性和支持向量回归机的集成预测模型,可以预测刀具的寿命。对试验采集到的信号进行了时域和小波分析,研究了信号特征量与刀具磨损之间的关系。计算了45个特征量与刀具磨损之间的相关系数,最终选择5个特征向量作为预测模型的输入向量。样本刀具1、2和3在稳定加工阶段的寿命预测精度分别为88.5%,87.5%和90.5%。并同其他模型进行了对比,结果表明,所提出的集成模型在刀具剩余使用寿命预测方面预测精度更优。
As the tool wear increases,the surface quality of the work-piece will decrease,and even the work-piece will be scrapped.Therefore,in order to obtain a better machined work-piece quality,monitoring the tool wear is necessary.By monitoring the machining condition,the remaining useful life(RUL)can be obtained in time.This paper established an integrated prediction model based on trajectory similarity and support vector regression,which can predict the tool life.The time domain and wavelet analysis were carried out.The relationship between the signal characteristic quantity and the tool wear was studied.Five eigenvectors were selected as the input vectors of the prediction model by studying the correlation between 45 characteristic quantities and the tool wear.The prediction accuracy of the stable stage of sample tool 1,2,3 is 88.5%,87.5%,90.5%respectively,by using this integrated prediction model,which is better than other four single algorithms.
作者
黄志平
黄新宇
李亮
郭月龙
HUANG Zhiping;HUANG Xinyu;LI Liang;GUO Yuelong(Institute of Mechanical Manufacturing Technology,China Academy of Engineering Physics,Mianyang 621900,CHN;College of Mechanical and Electrical Engineering,Nanjing University of Aeronautics and Astronautics,Nanjing 210016,CHN)
出处
《制造技术与机床》
北大核心
2020年第1期153-161,共9页
Manufacturing Technology & Machine Tool
关键词
刀具磨损
剩余寿命
集成预测模型
轨迹相似性
支持向量回归机
tool wear
remaining useful life
integrated prediction model
trajectory similarity
support vector regression
