The machining of aviation thin-walled parts has always been a difficult task due to their high machining accuracy requirements. During the machining process of thin-walled parts, machining errors are inevitable, reducing the precision and quality of the components. Therefore, predicting machining errors is beneficial for optimizing process parameters, improving accuracy, and reducing costs. This paper proposes a thin-walled parts machining errors prediction method based on the kriging regression model considering uncertainties. The method establishes a surrogate model considering process parameter uncertainty, part uncertainty, model uncertainty, and unquantified uncertainty. The experimental data were extracted through processing experiments, combined with a Bayesian estimation algorithm to ascertain the model parameter, and combined with a gradient descent method to iteratively solve the uncertainty in the model to determine the optimal parameters of the model. The result of the experiment shows that the prediction model has a higher accuracy in the training parameter range and also in the extrapolation test set, and the root mean square error (RMSE) of the prediction model is 5.4238 μm.
FanH-ZXiGWangW, et al. An efficient five-axis machining method of centrifugal impeller based on regional milling. Int J Adv Manuf Technol2016; 87: 789–799.
2.
FanH-ZWangWXiG. A novel five-axis rough machining method for efficient manufacturing of centrifugal impeller with free-form blades. Int J Adv Manuf Technol2013; 68: 1219–1229.
3.
LiaoLZhangZMengF, et al. Novel rotary chemical mechanical polishing on an integral impeller. J Manuf Process2021; 66: 198–210.
4.
SonthipermpoonKBohezEHasemannH, et al. The vibration behavior of impeller blades in the five-axis CNC flank milling process. Int J Adv Manuf Technol2009; 46: 1171–1177.
5.
HeLSuHXuJ, et al. Inverse identification of constitutive parameters of Ti2AlNb intermetallic alloys based on cooperative particle swarm optimization. Chin J Aeronaut2018; 31: 1774–1785.
6.
LiuHWangBLiuZ, et al. In-situ test of full field deformation and chip formation mechanism during machining of Ti2AlNb intermetallic with digital image correlation method. CIRP J Manuf Sci Technol2024; 49: 40–55.
7.
WangXZhaoBDingW, et al. Wear characteristics and performance in side milling of Ti2AlNb intermetallic alloys with coated and uncoated end mills. Wear2024; 538–539: 205216.
8.
YuanZGaoGWangY, et al. Experimental study on a two-dimensional ultrasonic vibration platform and milling of Ti2AlNb intermetallic alloy. Int J Adv Manuf Technol2022; 121: 4187–4208.
9.
ZhaoJZhengLLiW, et al. Effects of PVD CrAlN/(CrAlB)N/CrAlN coating on pin–disc friction properties of Ti2AlNb alloys compared to WC/Co carbide at evaluated temperatures. Metals2024; 14: 662.
10.
YuMGuoJLeeK-M. A modal expansion method for displacement and strain field reconstruction of a thin-wall component during machining. IEEE/ASME Trans Mechatron2018; 23: 1028–1037.
11.
ZhangSBiQJiY, et al. Real-time thickness compensation in mirror milling based on modified Smith predictor and disturbance observer. Int J Mach Tools Manuf2019; 144(112 B2): 103427.
12.
CaoLZhangX-MHuangT, et al. Online monitoring machining errors of thin-walled workpiece: a knowledge embedded sparse Bayesian regression approach. IEEE/ASME Trans Mechatron2019; 24: 1259–1270.
13.
LiZ-LTuysuzOZhuL-M, et al. Surface form error prediction in five-axis flank milling of thin-walled parts. Int J Mach Tools Manuf2018; 128: 21–32.
14.
SunYJiangS. Predictive modeling of chatter stability considering force-induced deformation effect in milling thin-walled parts. Int J Mach Tools Manuf2018; 135: 38–52.
15.
ChenZYueCLiangSY, et al. Iterative from error prediction for side-milling of thin-walled parts. Int J Adv Manuf Technol2020; 107: 4173–4189.
16.
YiJWangXJiaoL, et al. Research on deformation law and mechanism for milling micro thin wall with mixed boundaries of titanium alloy in mesoscale. Thin-Walled Struct2019; 144: 106329.
17.
HussainALazogluI. Distortion in milling of structural parts. CIRP Ann2019; 68: 105–108.
18.
LinMWangCYueT, et al. Deformation prediction in flank milling of thin-walled parts based on cutter–workpiece engagement. J Manuf Process2024; 115: 375–386.
19.
LiXLiLYangY, et al. Machining deformation of single-sided component based on finishing allowance optimization. Chin J Aeronaut2020; 33: 2434–2444.
20.
ZhangZQiYChengQ, et al. Machining accuracy reliability during the peripheral milling process of thin-walled components. Robot Comput Integr Manuf2019; 59: 222–234.
21.
YuY-YShiD-MDingH, et al. Prediction of thin-walled workpiece machining error: a transfer learning approach. J Intell Manuf2024; 36: 2803–2827.
22.
HüllermeierEWaegemanW. Aleatoric and epistemic uncertainty in machine learning: an introduction to concepts and methods. Mach Learn2021; 110: 457–506.
23.
BuschMSchnoesFElsharkawyA, et al. Methodology for model-based uncertainty quantification of the vibrational properties of machining robots. Robot Comput Integr Manuf2022; 73: 102243.
24.
CatakFOYueTAliS. Uncertainty-aware prediction validator in deep learning models for cyber-physical system data. ACM Trans Softw Eng Methodol2022; 31: 1–31.
25.
ZhangTPengFYanR, et al. Quantification of uncertainty in robot pose errors and calibration of reliable compensation values. Robot Comput Integr Manuf2024; 89: 102765.
26.
ChenGLiYLiuX, et al. Physics-informed Bayesian inference for milling stability analysis. Int J Mach Tools Manuf2021; 167: 103767.
27.
KimGYangSMKimDM, et al. Bayesian-based uncertainty-aware tool-wear prediction model in end-milling process of titanium alloy. Appl Soft Comput2023; 148: 110922.
28.
QinQLiLZhaoG, et al. Robust stability prediction in milling process considering the correlations of input parameters. J Manuf Process2023; 101: 1318–1331.
29.
HuoGLuoYJiangX, et al. Uncertainty quantification and dynamic characteristics identification for predicting milling stability lobe based on surrogate model. Robot Comput Integr Manuf2025; 93: 102922.
30.
ShehzadARuiXDingY, et al. Surface quality predictive model for ultraprecision fly-cutting based on an integrated hybrid CNN–LSTM. Proc Inst Mech Eng B J Eng Manuf2024; 239(2): 09544054241306246.
31.
WuQWangHLiB. Predicting the fatigue life of additively manufactured AlSi10Mg alloy using a physics-informed neural network incorporating continuous damage mechanics. Proc Inst Mech Eng B J Eng Manuf2024; 239(1): 09544054241290283.
32.
KleijnenJPMehdadE. Estimating the variance of the predictor in stochastic kriging. Simul Model Pract Theory2016; 66: 166–173.
33.
WangWHaalandB. Controlling sources of inaccuracy in stochastic kriging. Technometrics2019; 61(3): 309–321.
34.
NeterJKutnerMHNachtsheimCJ, et al. Applied linear statistical model. J Am Stat Assoc1986; 81: 880.
35.
SantnerTJWilliamsBJNotzWI. The design and analysis of computer experiments. Springer, 2003.
36.
AnkenmanBENelsonBLStaumJ. Stochastic kriging for simulation metamodeling. Oper Res2010; 58: 371–382.
37.
LiuJLiuCPengF, et al. Tool wear prediction and machining performance improvement using regression algorithms and the non-dominated sorting genetic algorithm II in the milling of Ti2AlNb intermetallic. Proc Inst Mech Eng B J Eng Manuf2025; 45(1): 09544054251359846.
38.
SunHPengFZhouL, et al. A hybrid driven approach to integrate surrogate model and Bayesian framework for the prediction of machining errors of thin-walled parts. Int J Mech Sci2021; 192: 106111.
