Tool wear prediction and machining performance improvement using regression algorithms and the non-dominated sorting genetic algorithm II in the milling of Ti 2 AlNb intermetallic
Restricted accessResearch articleFirst published online 2025
Tool wear prediction and machining performance improvement using regression algorithms and the non-dominated sorting genetic algorithm II in the milling of Ti 2 AlNb intermetallic
Ti2AlNb intermetallic is a crucial material for advanced aero engines. Improper cutting parameters for milling Ti2AlNb intermetallic increase tool wear and reduce tool life. Therefore, predicting tool wear and selecting appropriate cutting parameters in milling is essential. In this paper, three tool wear prediction methods based on the nonlinear least squares regression algorithm, Gaussian process regression algorithm, and support vector regression algorithm are proposed. Among the three methods, the nonlinear least squares regression method achieves the highest prediction accuracy. This paper also presents a cutting parameter selection strategy based on the Non-dominated Sorting Genetic Algorithm II. The optimization goals are to maximize cutter life, maximize material removal rate, and minimize cutting force. The optimization results reveal the relationship between cutter life, material removal rate, and cutting force under certain cutting parameters. Seventeen sets of suitable cutting parameters are identified for the 6 mm diameter end mill, and five sets are identified for the 8 mm diameter end mill, considering conditions of cutter life, material removal rate, and cutting force.
LiuDX.One generation of new material, one generation of new type engine: development trend of aero-engine and its requirements for materials. J Mater Eng2017; 45: 1–5.
KellerMMJonesPEPorterWJIII, et al. Effects of processing variables on the creep behavior of investment cast Ti-48Al-2Nb-2Cr. Warrendale, PA: Minerals, Metals and Materials Society, 1995.
4.
KamatSVGogiaAKBanerjeeD.Effect of alloying elements and heat treatment on the fracture toughness of Ti-Al-Nb alloys. Acta Mater1998; 46: 239−251.
5.
LiuSSCaoJXZhouY, et al. Research and prospect of Ti2AlNb alloy. Chin J Nonferrous Met2021; 31: 3106–3126.
6.
LiuJWangKLLuSQ, et al. Optimization of process parameters of Ti2AlNb-based alloys based on response surface methodology. Rare Met Mat Eng2023; 52: 3581–3589.
7.
MantleALAspinwallDK.Surface integrity of a high speed milled gamma titanium aluminide. J Mater Process Technol2001; 118: 143–150.
8.
KlockeFLungDArftM, et al. On high-speed turning of a third-generation gamma titanium aluminide. Int J Adv Manuf Technol2013; 65: 155–163.
9.
BarryJByrneGLennonD.Observations on chip formation and acoustic emission in machining Ti–6Al–4V alloy. Int J Mach Tools Manuf2001; 41: 1055–1070.
10.
AspinwallDKMantleALChanWK, et al. Cutting temperatures when ball nose end milling γ-TiAl intermetallic alloys. Manuf Technol2013; 62: 75–78.
11.
KuradaSBradleyC.A review of machine vision sensors for tool condition monitoring. Comput Ind1997; 34: 55–72.
12.
TetiRJemielniakKDonnellGO, et al. Advanced monitoring of machining operations. CIRP Ann2010; 59: 717–739.
13.
Abellan-NebotJVSubirónFR.A review of machining monitoring systems based on artificial intelligence process models. Int J Adv Manuf Technol2010; 47: 237–257.
14.
CastejónMAlegreEBarreiroJ, et al. On-line tool wear monitoring using geometric descriptors from digital images. Int J Mach Tools Manuf2007; 47: 1847–1853.
15.
BarreiroJCastejónMAlegreE, et al. Use of descriptors based on moments from digital images for tool wear monitoring. Int J Mach Tools Manuf2008; 48: 1005–1013.
16.
MikołajczykTNowickiKOdowskiAK, et al. Neural network approach for automatic image analysis of cutting edge wear. Mech Syst Signal Process2017; 88: 100–110.
17.
Van Der MaatenLPostmaEOVan Den HerikHJ. Dimensionality reduction: a comparative review. J Mach Learn Res2009; 10: 13.
18.
WeiWCongRLiY, et al. Prediction of tool wear based on GA-BP neural network. Proc IMechE, Part B: J Engineering Manufacture2022; 236(12): 1564–1573.
19.
ChengYNJinYBGaiXY, et al. Prediction of tool wear in milling process based on BP neural network optimized by firefly algorithm. Proc IMechE, Part B: J Engineering Manufacture2024; 238(5): 2387–2403.
20.
ZouZGaoXLeiS, et al. Development of tool wear condition on-line monitoring method for impeller milling based on new data processing approach and DAE-BP-ANN-integrated modeling. Proc IMechE, Part B: J Engineering Manufacture2024; 238(1–2): 124–136.
21.
WuSLiYLiW, et al. Tool remaining useful life prediction considering wear state based on hybrid attention network. Proc IMechE, Part B: J Engineering Manufacture2024; 238(6–7): 837–850.
22.
NiakiFAFengLUlutanD, et al. A wavelet-based data-driven modelling for tool wear assessment of difficult to machine materials. Int J Mechatron Manuf Syst2016; 9: 7–121.
23.
WangGFYangYWZhangYC, et al. Vibration sensor based tool condition monitoring using ν support vector machine and locality preserving projection. Sens Actuators A Phys2014; 209: 24–32.
24.
ErhanDBengioYCourvilleA, et al. Why does unsupervised pre-training help deep learning. J Mach Learn Res2010; 11: 625–660.
25.
KamarthiSVPittnerS.Fourier and wavelet transform for flank wear estimation—a comparison. Mech Syst Signal Process1997; 11: 791–809.
26.
DeiabIAssalehKHammadF.On modeling of tool wear using sensor fusion and polynomial classifiers. Mech Syst Signal Process2009; 23: 1719–1729.
27.
GdulaMKnapčíkováLHuśarJ, et al. Modeling and measurement of tool wear during angular positioning of a round cutting insert of a toroidal milling tool for multi-axis milling. Appl Sci2024; 14(22): 10405.
28.
GdulaMMrówka-NowotnikGNowotnikA.Modeling and comprehensive mechanism analysis of torus milling cutter wear in multi-axis milling of Ni-based superalloy using the active cutting edge segment change technique. Tribol Int2025; 204: 110509.
29.
AlhadeffLMarshallMCurtisD, et al. Applying experimental micro-tool wear measurement techniques to industrial environments. Proc IMechE, Part B: J Engineering Manufacture2021; 235(10): 1588–1601.
30.
ArmaregoEJARusselJK. Maximum profit rate as a criterion for the selection of machining conditions. Int J Mach Tool Des Res1966; 6: 15–22.
31.
BhattacharyyaAFaria-GonzalezRHamI.Regression analysis for predicting surface finish and its application in the determination of optimum machining conditions. J Eng Ind1970; 92: 711–714.
32.
SatyanarayanaBRaoPNTewariNK. Application of nonlinear goal programming technique in metal cutting. In: Proceedings of 12th AMTDR conference, Delhi, India, vol. 484, 1986.
33.
ChuaMSLohHTWongYS, et al. Optimization of cutting conditions for multi-pass turning operations using sequential quadratic programming. J Mater Process Technol1991; 28: 253–262.
34.
BaskarNSaravananRAsokanP, et al. Ants colony algorithm approach for multi-objective optimisation of surface grinding operations. Int J Adv Manuf Technol2004; 23: 311–317.
35.
SreeramSSenthilkumarARahmanM, et al. Optimization of cutting parameters in micro end milling operations under dry cutting conditions using genetic algorithms. Int J Adv Manuf Technol2006; 30: 1030–1039.
36.
SardinasRQSantanaMRBrindisEA.Genetic algorithm- based multi-objective optimization of cutting parameters in turning processes. Eng Appl Artif Intell2006; 19: 127–133.
37.
KuriakoseSShunmugamMS.Multi objective optimization of wire electro discharge machining process by non dominated sorting genetic algorithm. J Mater Process Technol2005; 170: 133–141.
38.
YusoffYNgadimanMSZainAM.Overview of NSGA-II for optimizing machining process parameters. Procedia Eng2011; 15: 3978–3983.
39.
ChenJL. Multi-objective optimization of cutting parameters with improved NSGA-II. In: International conference on management and service science, Beijing, China, 20–22 September 2009; pp.1–4. New York: IEEE.
DingKShenYOuJ.Linear fitting by total least squares method. Liaoning Tech Univ2010; 29: 44–47.
42.
ShiHSunXWangS, et al. Total least squares estimation model based on uncertainty theory. J Ambient Intell Humaniz Comput2023; 14: 10069–10075.
43.
WilliamsCKI. Prediction with Gaussian processes: from linear regression to linear prediction and beyond. In: JordanMI (ed.) Learning in graphical models. Norwell, MA: Kluwer Academic, 1998, pp.599–621.
44.
MacKayDJC. Gaussian processes - a replacement for supervised neural networks? Stochastic modelling & applied probability 1999. DOI:10.1016/S0893-9659(98)0 0024-X.
45.
RasmussenCE.Gaussian processes in machine learning. In: BousquetOLuxburgURätschG (eds) Advanced lectures on machine learning. Berlin, Heidelberg: Springer, 2004, vol. 3176, pp.63–71.
46.
SuykensJAKVandewalleJ. Least squares support vector machine classifiers. Neural Process Lett1999; 9: 293–300.
47.
SchölkopfBSmolaAJWilliamsonRC, et al. New support vector algorithms. Neural Comput2000; 12: 1207–1245.
48.
DuttaSPalSKSenR.On-machine tool prediction of flank wear from machined surface images using texture analyses and support vector regression. Precis Eng2016; 43: 34–42.
49.
DebKPratapAAgarwalS, et al. A fast and elitist multi-objective genetic algorithm: NSGA- II. IEEE Trans Evol Comput2002; 6: 182–197.
50.
QuSZhaoJWangT.Experimental study and machining parameter optimization in milling thin-walled plates based on NSGA-II. Int J Adv Manuf Technol2017; 89: 2399–2409.
51.
ChenXShenDOuC, et al. Optimization of machining efficiency and side quality in irregular sheet metal parts milling based on improved multi-objective seagull optimization algorithm. Int J Adv Manuf Technol2024; 135: 2755–2776.
52.
ZhuZRPengFYYanR, et al. High efficiency simulation of five-axis cutting force based on the symbolically solvable cutting contact boundary model. Int J Adv Manuf Technol2018; 94(5–8): 2435–2455.
