摘要
研究了基于声发射方法的Logistic回归模型的铣削过程中刀具可靠性评估.从试验数据分析得出铣削过程的声发射信号和切削力信号,与刀具磨损量具有较强线性相关性,是刀具性能退化监测的有效方法.运用小波包分解提取声发射信号的能量,选取与刀具磨损相关的频带能量作为特征指标.将应用切削力和声发射两种监测方法建立的可靠性模型与仅用声发射监测的可靠性模型进行对比发现,两个模型都较为准确地评估出了刀具在铣削过程中的可靠度指标,而基于声发射可靠性评估模型更为方便,在实际切削力不易获得的情况下,运用此方法能够进行刀具的可靠性评估与寿命预测.
Logistic regression model for reliability evaluation based on acoustic emission monitoring for milling cutter is investigated.According to experimental data analyses,acoustic emission and cutting force signals have linear relationship with milling cutter wear.It is an effective method for milling cutter degradation estimation.Frequency band energy related with milling cutter wear is determined to be as characteristic vector for acoustic emission signal using wavelet packet decomposition.Two reliability estimation models are constructed based on cutting force and acoustic emission signals,one uses two kinds of signals,the other just uses acoustic emission signal.The reliability can be estimated using the two models.The model just using acoustic emission signal is more convenient to estimate reliability and predict life as it is difficult to monitor cutting force in the practical working conditions.
出处
《大连理工大学学报》
EI
CAS
CSCD
北大核心
2014年第4期418-423,共6页
Journal of Dalian University of Technology
基金
国家自然科学基金资助项目(51175057)
国家高档数控机床与基础制造装备科技重大专项资助项目(2013ZX04012071)
