Comparison of Ensemble and Base Learner Algorithms for the Prediction of Machining Induced Residual Stresses in Turning of Aerospace Materials

Abstract

Estimation of residual stresses is important to prevent the catastrophic failures of the components used in the aerospace industry. The objective of this work is to predict the machining induced residual stresses with bagging, boosting, and single-based machine learning models based on the design and cutting parameters used in turning of Inconel 718 and Ti6Al4V alloys. Experimentally measured residual stress data of these two materials was compiled from the literature including the surface material of the cutting tools, cooling conditions, rake angles as well as the cutting speed, feed, and width of cut to show the robustness of the models. These variables were also grouped with different combinations to clearly show the contribution and necessity of each element. Various predictive models in machine learning (AdaBoost, Random Forest, Artificial Neural Network, K-Neighbors Regressor, Linear Regressor) were then applied to estimate the residual stresses on the machined surfaces for the classified groups using the generated data. It was found that the AdaBoost algorithm was able to predict the machining induced residual stresses with the mean absolute errors of 18.1 MPa for IN718 alloy and 31.3 MPa for Ti6Al4V by taking into account all the variables while artificial neural network provides the lowest mean absolute errors for the Ti6Al4V alloy. On the other hand, linear regression model gives poor agreement with the experimental data. All the analyses showed that AdaBoost (boosting) ensemble learning, and artificial neural network models can be used for the prediction of the machining induced residual stresses with the small datasets of the IN718 and Ti6Al4V materials.

Keywords

• Residual stress
• Machining
• Inconel
• Titanium
• AdaBoost
• Neural Network

References

1. D. Ulutan and T. Ozel, “Machining induced surface integrity in titanium and nickel alloys: A review,” International Journal of Machine Tools and Manufacture. 2011, doi: 10.1016/j.ijmachtools.2010.11.003.
2. J. Holmberg, J. M. Rodríguez Prieto, J. Berglund, A. Sveboda, and P. Jonsén, “Experimental and PFEM-simulations of residual stresses from turning tests of a cylindrical Ti-6Al-4V shaft,” 2018, doi: 10.1016/j.procir.2018.05.087.
3. Y. Hua and Z. Liu, “Experimental investigation of principal residual stress and fatigue performance for turned nickel-based superalloy Inconel 718,” Materials (Basel)., 2018, doi: 10.3390/ma11060879.
4. F. Jafarian, H. Amirabadi, and J. Sadri, “Experimental measurement and optimization of tensile residual stress in turning process of Inconel718 superalloy,” Meas. J. Int. Meas. Confed., 2015, doi: 10.1016/j.measurement.2014.11.021.
5. G. Kartheek, K. Srinivas, and C. Devaraj, “Optimization of Residual Stresses in Hard Turning of Super Alloy Inconel 718,” 2018, doi: 10.1016/j.matpr.2017.12.029.
6. K. Satyanarayana, A. V. Gopal, and N. Ravi, “Studies on surface integrity and its optimisation in turning Ti-6Al-4V,” Int. J. Precis. Technol., 2015, doi: 10.1504/ijptech.2015.073837.
7. D. M. Madyira, R. F. Laubscher, N. Janse Van Rensburg, and P. F. J. Henning, “High speed machining induced residual stresses in Grade 5 titanium alloy,” Proc. Inst. Mech. Eng. Part L J. Mater. Des. Appl., 2013, doi: 10.1177/1464420712462319.
8. Y. Ayed, G. Germain, A. P. Melsio, P. Kowalewski, and D. Locufier, “Impact of supply conditions of liquid nitrogen on tool wear and surface integrity when machining the Ti-6Al-4V titanium alloy,” Int. J. Adv. Manuf. Technol., 2017, doi: 10.1007/s00170-017-0604-7.

9. A. Devillez, G. Le Coz, S. Dominiak, and D. Dudzinski, “Dry machining of Inconel 718, workpiece surface integrity,” J. Mater. Process. Technol., 2011, doi: 10.1016/j.jmatprotec.2011.04.011.
10. G. Le Coz, R. Piquard, A. D’Acunto, D. Bouscaud, M. Fischer, and P. Laheurte, “Precision turning analysis of Ti-6Al-4V skin produced by selective laser melting using a design of experiment approach,” Int. J. Adv. Manuf. Technol., 2020, doi: 10.1007/s00170-020-05807-8.
11. T. Özel and D. Ulutan, “Prediction of machining induced residual stresses in turning of titanium and nickel based alloys with experiments and finite element simulations,” CIRP Ann. - Manuf. Technol., 2012, doi: 10.1016/j.cirp.2012.03.100.
12. A. Paranjpe and A, “RESIDUAL STRESSES IN MACHINED TITANIUM (Ti-6Al-4V) ALLOYS,” Statew. Agric. L. Use Baseline 2015, 2015.
13. A. R. C. Sharman, J. I. Hughes, and K. Ridgway, “An analysis of the residual stresses generated in Inconel 718TM when turning,” J. Mater. Process. Technol., 2006, doi: 10.1016/j.jmatprotec.2005.12.007.
14. A. Simeone, T. Segreto, and R. Teti, “Residual stress condition monitoring via sensor fusion in turning of Inconel 718,” 2013, doi: 10.1016/j.procir.2013.09.013.
15. K. Jacobus, R. E. DeVor, and S. G. Kapoor, “Machining-induced residual stress: Experimentation and modeling,” J. Manuf. Sci. Eng. Trans. ASME, 2000, doi: 10.1115/1.538906.
16. S. Agrawal and S. S. Joshi, “Analytical modelling of residual stresses in orthogonal machining of AISI4340 steel,” J. Manuf. Process., 2013, doi: 10.1016/j.jmapro.2012.11.004.
17. J. S. Y. Liang and J. C. Su, “Residual stress modeling in orthogonal machining,” CIRP Ann. - Manuf. Technol., 2007, doi: 10.1016/j.cirp.2007.05.018.
18. D. Ulutan, B. Erdem Alaca, and I. Lazoglu, “Analytical modelling of residual stresses in machining,” J. Mater. Process. Technol., 2007, doi: 10.1016/j.jmatprotec.2006.09.032.
19. J. C. Outeiro, J. C. Pina, R. M’Saoubi, F. Pusavec, and I. S. Jawahir, “Analysis of residual stresses induced by dry turning of difficult-to-machine materials,” CIRP Ann. - Manuf. Technol., 2008, doi: 10.1016/j.cirp.2008.03.076.
20. N. K. Sahu and A. B. Andhare, “Prediction of residual stress using RSM during turning of Ti–6Al–4V with the 3D FEM assist and experiments,” SN Appl. Sci., 2019, doi: 10.1007/s42452-019-0809-5.
21. M. Salio, T. Berruti, and G. De Poli, “Prediction of residual stress distribution after turning in turbine disks,” Int. J. Mech. Sci., 2006, doi: 10.1016/j.ijmecsci.2006.03.009.
22. X. Ji, A. H. Shih, M. Rajora, Y. M. Shao, and S. Y. Liang, “A hybrid neural network for prediction of surface residual stress in MQL face turning,” 2014, doi: 10.4028/www.scientific.net/AMM.633-634.574.
23. M. Cheng et al., “Prediction of surface residual stress in end milling with Gaussian process regression,” Meas. J. Int. Meas. Confed., 2021, doi: 10.1016/j.measurement.2021.109333.
24. J. Mathew, J. Griffin, M. Alamaniotis, S. Kanarachos, and M. E. Fitzpatrick, “Prediction of welding residual stresses using machine learning: Comparison between neural networks and neuro-fuzzy systems,” Appl. Soft Comput. J., 2018, doi: 10.1016/j.asoc.2018.05.017.
25. O. Sagi and L. Rokach, “Ensemble learning: A survey,” Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery. 2018, doi: 10.1002/widm.1249.
26. M. A. Ganaie, M. Hu, A. K. Malik, M. Tanveer, and P. N. Suganthan, “Ensemble deep learning: A review,” Apr. 2021, doi: 10.48550/arxiv.2104.02395.
27. I. Tsamardinos, E. Greasidou, and G. Borboudakis, “Bootstrapping the out-of-sample predictions for efficient and accurate cross-validation,” Mach. Learn., 2018, doi: 10.1007/s10994-018-5714-4.
28. Y. Freund and R. E. Schapire, “Experiments with a New Boosting Algorithm,” 1996, Accessed: Sep. 16, 2021. [Online]. Available: http://www.research.att.com/orgs/ssr/people/fyoav,schapireg/.
29. H. Drucker, “Improving regressors using boosting techniques,” 14th Int. Conf. Mach. Learn., 1997.
30. M. Tranmer, J. Murphy, M. Elliot, and M. Pampaka, “Multiple Linear Regression (2 nd Edition),” 2020, Accessed: Sep. 16, 2021. [Online]. Available: https://hummedia.manchester.ac.uk/institutes/cmist/a.
31. G. E. Hinton, S. Osindero, and Y. W. Teh, “A fast learning algorithm for deep belief nets,” Neural Comput., 2006, doi: 10.1162/neco.2006.18.7.1527.
32. S. Karsoliya, “Approximating Number of Hidden layer neurons in Multiple Hidden Layer BPNN Architecture,” Int. J. Eng. Trends Technol., 2012.
33. S. Ray, “A Quick Review of Machine Learning Algorithms,” 2019, doi: 10.1109/COMITCon.2019.8862451.
34. Y. Liu, Y. Wang, and J. Zhang, “New machine learning algorithm: Random forest,” 2012, doi: 10.1007/978-3-642-34062-8_32.
35. D. Chicco, M. J. Warrens, and G. Jurman, “The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation,” PeerJ Comput. Sci., 2021, doi: 10.7717/PEERJ-CS.623.
36. X. Fu et al., “Accuracy of X-ray diffraction measurement of residual stresses in shot peened titanium alloy samples,” Nondestruct. Test. Eval., 2019, doi: 10.1080/10589759.2019.1573239.
37. M. R. Abonazel and O. M. Saber, “A comparative study of robust estimators for poisson regression model with outliers,” J. Stat. Appl. Probab., 2020, doi: 10.18576/jsap/090208.
38. M. Kontaki, A. Gounaris, A. N. Papadopoulos, K. Tsichlas, and Y. Manolopoulos, “Efficient and flexible algorithms for monitoring distance-based outliers over data streams,” Inf. Syst., 2016, doi: 10.1016/j.is.2015.07.006.
39. I. Oleaga, C. Pardo, J. J. Zulaika, and A. Bustillo, “A machine-learning based solution for chatter prediction in heavy-duty milling machines,” Meas. J. Int. Meas. Confed., 2018, doi: 10.1016/j.measurement.2018.06.028.
40. A. Kortabarria, A. Madariaga, E. Fernandez, J.a. Esnaola, and P. J. Arrazola, “A comparative study of residual stress profiles on inconel 718 induced by dry face turning,” 2011, doi: 10.1016/j.proeng.2011.11.105.
41. A. B. Sadat, M. Y. Reddy, and B. P. Wang, “Plastic deformation analysis in machining of Inconel-718 nickel-base superalloy using both experimental and numerical methods,” Int. J. Mech. Sci., 1991, doi: 10.1016/0020-7403(91)90005-N.
42. V. Veeranaath, R. K. Das, S. K. Rai, S. Singh, and P. Sharma, “Experimental Study and Optimization of Residual Stresses in Machining of Ti6Al4V Using Titanium and Multi-layered Inserts,” 2020, doi: 10.1088/1757-899X/912/3/032028.
43. J. D. P. Velásquez, A. Tidu, B. Bolle, P. Chevrier, and J. J. Fundenberger, “Sub-surface and surface analysis of high speed machined Ti-6Al-4V alloy,” Mater. Sci. Eng. A, 2010, doi: 10.1016/j.msea.2009.12.018.
44. S. Isakson, M. I. Sadik, A. Malakizadi, and P. Krajnik, “Effect of cryogenic cooling and tool wear on surface integrity of turned Ti-6Al-4V,” 2018, doi: 10.1016/j.procir.2018.05.061.
45. Z. Pan, S. Y. Liang, H. Garmestani, D. Shih, and E. Hoar, “Residual stress prediction based on MTS model during machining of Ti-6Al-4V,” Proc. Inst. Mech. Eng. Part C J. Mech. Eng. Sci., 2019, doi: 10.1177/0954406218805122.
46. S. Joshi, A. Tewari, and S. S. Joshi, “Microstructural characterization of chip segmentation under different machining environments in orthogonal machining of Ti6Al4V,” J. Eng. Mater. Technol. Trans. ASME, 2015, doi: 10.1115/1.4028841.