The carbon fibre reinforced plastic (CFPR) has been widely used in aircraft structural applications due to the superior modulus, specific tensile strength, and fatigue strength. The inhomogeneous and anisotropic nature of these composites poses great challenges on the machining process. Particularly, the delamination is one of major defects associated with drilling, which has a significant impact on CFRP’s structure integrity and application. Machine learning approaches can help facilitate the optimization of machining processes. In this study, we develop the Gaussian process regression (GPR) model to predict delaminations in carbon fibre reinforced plastic composites during drilling from machining parameters. The model is simple and highly accurate and stable that contributes to fast delamination estimations. By combining the optimization results from the Taguchi method and GPR approach, it is expected that more quantitative data can be extracted from fewer experimental trials at the same time.
RahimEA andSasaharaH. High performance machining of carbon fiber-reinforced plastics. In: Mohammad J and Mohamed T (eds) Sustainable composites for aerospace applications. Cambridge: Woodhead Publishing, 2018, pp. 211–226.
2.
SchwartzJKochCCZhangY, et al. Formation of bismuth strontium calcium copper oxide superconductors. U.S. Patent US9773962B2, USA, September 26, 2017.
3.
ZhangYJohnsonSNaderiG, et al.High critical current density Bi2Sr2CaCu2O x/Ag wire containing oxide precursor synthesized from nano-oxides. Superconduct Sci Technol2016;
29: 095012.
ZhangYKochCC andSchwartzJ.Synthesis of Bi2Sr2CaCu2Ox superconductors via direct oxidation of metallic precursors. Superconduct Sci Technol2014;
27: 055016.
6.
InagakiM.New carbons-control of structure and functions. Amsterdam: Elsevier, 2000.
7.
WangYChanWK andSchwartzJ.Self-protection mechanisms in no-insulation (RE) Ba2Cu3Ox high temperature superconductor pancake coils. Superconduct Sci Technol2016;
29: 045007.
8.
WangYWengFLiJ, et al.No-insulation high temperature superconductor winding technique for electrical aircraft propulsion. IEEE Trans Transp Electrificat2020; 6: 1613–1624.
9.
KarpatYCamuşcuNil içAK, et al., Drilling carbon fiber reinforced plastics with diamond coated carbide cutting tools. In: Srichand H and Lin L (eds) Proceedings of the 36th international MATADOR conference. London: Springer, 2010, pp. 205–208.
10.
TsaoCC andHochengH.Parametric study on thrust force of core drill. J Mater Process Technol2007;
192: 37–40.
11.
ShyhaISAspinwallDKSooSL, et al.Drill geometry and operating effects when cutting small diameter holes in CFRP. Int J Mach Tools Manuf2009;
49: 1008–1014.
12.
RahimEOgawaTMiuraA, et al. 3417 A novel approach to evaluate the delamination factor of CFRP hole. In: Proceedings of international conference on leading edge manufacturing in 21st century: LEM21 2011.6. Tokyo: The Japan Society of Mechanical Engineers, November 2011, pp. 3417–3421.
13.
DandekarCR andShinYC.Modeling of machining of composite materials: a review. Int J Mach Tools Manuf2012;
57: 102–121.
14.
SiddiqueeANKhanZAGoelP, et al.Optimization of deep drilling process parameters of AISI 321 steel using Taguchi method. Proc Mater Sci2014;
6: 1217–1225.
15.
MaliHSUnuneDR andTiwariS. Modelling and prediction of material removal rate in electrical discharge diamond surface grinding process of Inconel-718. In: Shrikrishna J and Uday D (eds) Proceedings of 5th AIMTDR, 2014, pp. 822. New Delhi: Springer.
16.
KrishnamoorthyABoopathySR andPalanikumarK.Delamination prediction in drilling of CFRP composites using artificial neural network. J Eng Sci Technol2011;
6: 191–203.
ZhangY andXuX.Solubility predictions through LSBoost for supercritical carbon dioxide in ionic liquids. New J Chem2020; 44: 20544–20567.
19.
ZhangY andXuX.Yttrium barium copper oxide superconducting transition temperature modeling through Gaussian process regression. Comput Mater Sci2020;
179: 109583.
20.
ZhangY andXuX.Predicting doped MgB2 superconductor critical temperature from lattice parameters using Gaussian process regression. Phys C Superconduct Appl2020;
573: 1353633.
21.
ZhangY andXuX.Curie temperature modeling of magnetocaloric lanthanum manganites using Gaussian process regression. J Magnet Magnet Mater2020;
512: 166998.
22.
ZhangY andXuX.Machine learning the magnetocaloric effect in manganites from lattice parameters. Appl Phys A2020;
126: 341.
23.
ZhangY andXuX.Machine learning the magnetocaloric effect in manganites from compositions and structural parameters. AIP Adv2020;
10: 035220.
24.
ZhangY andXuX.Predicting the thermal conductivity enhancement of nanofluids using computational intelligence. Phys Lett A2020;
384: 126500.
25.
ZhangY andXuX.Machine learning modeling of lattice constants for half-Heusler alloys. AIP Adv2020;
10: 045121.
26.
ZhangY andXuX.Machine learning optical band gaps of doped-ZnO films. Optik2020;
217: 164808.
27.
ZhangY andXuX.Relative cooling power modeling of lanthanum manganites using Gaussian process regression.RSC Adv2020;
10: 20646–20653.
28.
ZhangY andXuX.Machine learning band gaps of doped-TiO2 photocatalysts from structural and morphological parameters. ACS Omega2020;
5: 15344–15352.
ZhangY andXuX. Lattice misfit predictions via the Gaussian process regression for Ni-based single crystal superalloys. Metals Mater Int 2021; 27: 235–253.
32.
ZhangY andXuX.Machine learning lattice constants from ionic radii and electronegativities for cubic perovskite compounds.Phys Chem Miner2020;
47: 39.
33.
ZhangY andXuX. Transformation temperature predictions through computational intelligence for NiTi-based shape memory alloys. Shape Memory Superelast. Epub ahead of print 15 October 2020. DOI: 10.1007/s40830-020-00303-0.
34.
ZhangY andXuX.Machine learning lattice parameters of monoclinic double perovskites. Int J Quant Chem 2021; 121: e26480.
35.
ZhangY andXuX.Fe-based superconducting transition temperature modeling through Gaussian process regression. J Low Temp Phys 2021; 202: 205–218.
36.
ZhangY andXuX.Machine learning decomposition onset temperature of lubricant additives. J Mater Eng Perform2020;
29: 6605–6616.
37.
ZhangY andXuX.Predicting doped Fe-based superconductor critical temperature from structural and topological parameters using machine learning. Int J Mater Res 2021; 112: 2–9.
38.
ZhangY andXuX. Machine learning glass transition temperature of polymers.Heliyon2020;
6: e05055.
ZhangY andXuX.Machine learning the central magnetic flux density of superconducting solenoids.MaterTechnol. Epub ahead of print 15 October 2020. DOI: 10.1080/10667857.2020.1830567.
ZhangY andXuX.Machine learning glass transition temperature of styrenic random copolymers. J Mol Graph Model2021; 103: 107796.
43.
ZhangY andXuX. Predictions of adsorption energies of methane-related species on Cu-based alloys through machine learning. Mach Learn Appl2021; 3: 100010.
44.
JongWRHuangYMLinYZ, et al.Integrating Taguchi method and artificial neural network to explore machine learning of computer aided engineering. J Chin Inst Eng2020;
43: 346–356.
45.
VoßS. Meta-heuristics: The state of the art. In: Alexander N (ed) Workshop on local search for planning and scheduling. Berlin: Springer, 2000, pp. 1–23.
46.
LelaBBajićD andJozićS,
Regression analysis, support vector machines, and Bayesian neural network approaches to modeling surface roughness in face milling. Int J AdvManuf Technol2009;
42: 1082–1088.
47.
ZuperlU andCusF.Tool cutting force modeling in ball-end milling using multilevel perceptron. J Mater Process Technol2004;
153: 268–275.
48.
AykutŞGölcüMSemizS, et al.Modeling of cutting forces as function of cutting parameters for face milling of satellite 6 using an artificial neural network. J Mater Process Technol2007;
190: 199–203.
49.
LiYYangWDongR, et al.MLatticeABC: generic lattice constant prediction of crystal materials using machine learning. arXiv preprint arXiv:2010.16099. Epub ahead of print 30 October 2020.
50.
BullAD.Convergence rates of efficient global optimization algorithms. J Mach Learn Res2011;
12: 2879–2904.
51.
SnoekJLarochelleH andAdamsRP.Practical Bayesian optimization of machine learning algorithms.Adv Neural Inf Process Syst 2012; 25: 2951–29519.
52.
GelbartMASnoekJ, andAdamsRP. Bayesian optimization with unknown constraints. arXiv preprint arXiv:1403.5607. Epub ahead of print 22 March 2014.
53.
WilliamsCK andRasmussenCE.Gaussian processes for machine learning.
Cambridge, MA:
MIT Press, 2006, p. 4.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
