基于高斯过程回归方法的钛合金铣削刀具磨损预测
|
摘要
通过钛合金材料切削试验,对铣削加工中切削参数对高进给铣刀刀齿后刀面最大磨损量的影响规律进行分析。采用高斯过程回归法建立了刀齿后刀面最大磨损宽度的预测模型,并进行试验验证。预测结果与试验结果吻合程度较高,验证了预测模型的有效性,为钛合金铣削刀具的磨损预测提供了理论方法和试验依据。
Through the titanium alloy material cutting tests,analyzing the influence of cutting parameters on the maximum wear of the flank face of high feed milling cutters during milling. The wear model of milling cutter was obtained by using the method of Gaussian process regression,it is verified by cutting test that the prediction results are consistent with the experimental results,the research results show that the milling cutter wear prediction model is correct and effective. This research provided theoretical method and experimental basis for tool wear prediction in titanium milling.
Through the titanium alloy material cutting tests,analyzing the influence of cutting parameters on the maximum wear of the flank face of high feed milling cutters during milling. The wear model of milling cutter was obtained by using the method of Gaussian process regression,it is verified by cutting test that the prediction results are consistent with the experimental results,the research results show that the milling cutter wear prediction model is correct and effective. This research provided theoretical method and experimental basis for tool wear prediction in titanium milling.
引文
[1]金和喜,魏克湘,李建明,等.航空用钛合金研究进展[J].中国有色金属学报,2015,25(2):280-292.
[2]张绪虎,单群,陈永来,等.钛合金在航天飞行器上的应用和发展[J].中国材料进展,2011,30(6):28-32,63.
[3]Bo-Hua Duan,Hai-Xia Hong,De-Zhi Wang,etal.Porous nickeltitanium alloy prepared by gel-casting[J].Rare Metals,2014,33(4):394-399.
[4]宋一平.钛合金TC4铣削的理论和实验研究[D].湘潭:湖南科技大学,2009.
[5]Feng X U,Zhao Y,Ning W.Application of the titanium alloy in civil aviation[J].Baosteel Technical Research,2011,5(4):25-35.
[6]Fu Chunjuan,Tian Wenming,Yang Kang,et al.Effects of sodium tartrate anodizing on fatigue life of TA15 titanium alloy[J].Chinese Journal of Aeronautics,2015,28(4):1281-1286.
[7]严鲁涛,袁松梅,刘强.绿色切削高强度钢的刀具磨损及切屑形态[J].机械工程学报,2010,46(9):187-192.
[8]Li K M,Liang S Y.Predictive modeling of flank wear in turning under flood cooling[J].Journal of Manufacturing Science and Engineering,2007,129:513.
[9]Molinari A,Nouari M.Modeling of tool wear by diffusion in metal cutting[J].Wear,2002,252:135-149.
[10]Rasmussen C E,Williams C K.I.Gaussian processes for Machine Learning[M].Massachuseits:the MIT Press,2006:7-31.
[11]Seeger M,Williams C K I,Lawrence N D.fast forward selection to speed up sparse gaussian process regression[J].Artificial Intelligence&Statistics,2003,9:1-8.
[12]Park C,Huang J Z,Ding Y.Domain decomposition approach for fast gaussian process regression of large spatial data sets[J].Journal of Machine Learning Research,2011,12(4):1697-1728.
[13]Rostami H,Azin R,Dianat R.Prediction of undersaturated crude oil density using gaussian process regression[J].Petroleum Science&Amp;Technology,2013,31(4):418-427.
[2]张绪虎,单群,陈永来,等.钛合金在航天飞行器上的应用和发展[J].中国材料进展,2011,30(6):28-32,63.
[3]Bo-Hua Duan,Hai-Xia Hong,De-Zhi Wang,etal.Porous nickeltitanium alloy prepared by gel-casting[J].Rare Metals,2014,33(4):394-399.
[4]宋一平.钛合金TC4铣削的理论和实验研究[D].湘潭:湖南科技大学,2009.
[5]Feng X U,Zhao Y,Ning W.Application of the titanium alloy in civil aviation[J].Baosteel Technical Research,2011,5(4):25-35.
[6]Fu Chunjuan,Tian Wenming,Yang Kang,et al.Effects of sodium tartrate anodizing on fatigue life of TA15 titanium alloy[J].Chinese Journal of Aeronautics,2015,28(4):1281-1286.
[7]严鲁涛,袁松梅,刘强.绿色切削高强度钢的刀具磨损及切屑形态[J].机械工程学报,2010,46(9):187-192.
[8]Li K M,Liang S Y.Predictive modeling of flank wear in turning under flood cooling[J].Journal of Manufacturing Science and Engineering,2007,129:513.
[9]Molinari A,Nouari M.Modeling of tool wear by diffusion in metal cutting[J].Wear,2002,252:135-149.
[10]Rasmussen C E,Williams C K.I.Gaussian processes for Machine Learning[M].Massachuseits:the MIT Press,2006:7-31.
[11]Seeger M,Williams C K I,Lawrence N D.fast forward selection to speed up sparse gaussian process regression[J].Artificial Intelligence&Statistics,2003,9:1-8.
[12]Park C,Huang J Z,Ding Y.Domain decomposition approach for fast gaussian process regression of large spatial data sets[J].Journal of Machine Learning Research,2011,12(4):1697-1728.
[13]Rostami H,Azin R,Dianat R.Prediction of undersaturated crude oil density using gaussian process regression[J].Petroleum Science&Amp;Technology,2013,31(4):418-427.