Using artificial neural networks for the prediction of dimensional error on inclined surfaces manufactured by ball-end milling

  • Álvar Arnaiz-González
  • Asier Fernández-Valdivielso
  • Andres Bustillo
  • Luis Norberto López de Lacalle


Industrial demand for models and simulation tools that can predict dimensional errors in manufacturing processes is vigorous. One example of these processes is ball-end finishing of inclined surfaces, which is a very complex task, due to the high number of variables that may influence dimensional errors during a cutting process and their different nature. This work firstly analyses the potential of semiempirical models to address the ball-end milling finishing, to conclude that these models are unable to process and to replicate the full range of milling strategies and slope combinations. Secondly, it goes on to analyse the possibilities of artificial neural networks as a means of overcoming this limitation. Two types of neural networks, multilayer perceptron (MLP) and radial basis functions (RBF), are tested. The results show that RBFs predict better than MLPs in all cases, achieving a precision of 1.83 μm in root mean squared error (RMSE) and a correlation coefficient of 0.897 with a 10 × 10 cross-validation scheme. Their training and tuning times are also 2.5 times shorter in all cases. Finally, the use of 3D figures, generated from the best RBF model, yields interesting industrial results in the field of process engineering.


Artificial neural networks Radial basis functions Tool deformation Ball-end milling 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Benardos PG, Vosniakos GC (2003) Predicting surface roughness in machining: a review. Int J Mach Tools Manuf 43(8):833–844CrossRefGoogle Scholar
  2. 2.
    Chandrasekaran M, Muralidhar M, Krishna C, Dixit U (2010) Application of soft computing techniques in machining performance prediction and optimization: a literature review. Int J Adv Manuf Technol 46(5):445–464CrossRefGoogle Scholar
  3. 3.
    Correa M, Bielza C, Ramirez MDJ, Alique JR (2008) A Bayesian network model for surface roughness prediction in the machining process. Int J Syst Sci 39(12):1181–1192CrossRefzbMATHGoogle Scholar
  4. 4.
    Martellotti ME (1941) An analysis of the milling process. Trans ASME 63:667Google Scholar
  5. 5.
    Quintana G, Ribatallada J, Ciurana Q (2010) Surface roughness generation and material removal rate in ball-end milling operations. Mater Manuf Process 25(6):386–398CrossRefGoogle Scholar
  6. 6.
    Arizmendi M, Fernández J, Gil A, Veiga F (2009) Effect of tool setting error on the topography of surfaces machined by peripheral milling. Int J Mach Tools Manuf 49(1):36–52CrossRefGoogle Scholar
  7. 7.
    López de Lacalle LN, Lamikiz A, Sánchez JA, Arana JL (2002) Improving the surface finish in high speed milling of stamping dies. J Mater Process Technol 123(2):292–302Google Scholar
  8. 8.
    Quintana G, Bustillo A, Ciurana J (2012) Prediction, monitoring and control of surface roughness in high-torque milling machine operations. Int J Comput Integr Manuf 25(12):1129–1138CrossRefGoogle Scholar
  9. 9.
    Beggan C, Woulfe M, Young P, Byrne G (1999) Using acoustic emission to predict surface quality. Int J Adv Manuf Technol 15(10):737–742CrossRefGoogle Scholar
  10. 10.
    Vivancos J, Luis CJ, Ortiz JA, González HA (2005) Analysis of factors affecting the high-speed side milling of hardened die steels. J Mater Process Technol 162-163(SPEC. ISS):696–701CrossRefGoogle Scholar
  11. 11.
    Díez-Pastor JF, Bustillo A, Quintana G, García-Osorio C (2012) Boosting projections to improve surface roughness prediction in high-torque milling operations. Soft Comput 16(8):1427–1437CrossRefGoogle Scholar
  12. 12.
    Choudhury SK, Bartarya G (2003) Role of temperature and surface finish in predicting tool wear using neural network and design of experiments. Int J Mach Tools Manuf 43(7):747–753CrossRefGoogle Scholar
  13. 13.
    Thangavel P, Selladurai V (2008) An experimental investigation on the effect of turning parameters on surface roughness. Int J Manuf Res 3(3):285–300CrossRefGoogle Scholar
  14. 14.
    Ho W, Tsai J, Lin B, Chou J (2009) Adaptive network-based fuzzy inference system for prediction of surface roughness in end milling process using hybrid Taguchi-genetic learning algorithm. Expert Syst Appl 36(2 PART 2):3216–3222CrossRefGoogle Scholar
  15. 15.
    Benardos PG, Vosniakos GC (2002) Prediction of surface roughness in CNC face milling using neural networks and Taguchi’s design of experiments. Robot Comput Integr Manuf 18(5-6):343–354CrossRefGoogle Scholar
  16. 16.
    Brezocnik M, Kovacic M (2003) Integrated genetic programming and genetic algorithm approach to predict surface roughness. Mater Manuf Process 18(3):475–491CrossRefGoogle Scholar
  17. 17.
    Ozel T, Karpat Y (2005) Predictive modeling of surface roughness and tool wear in hard turning using regression and neural networks. Int J Mach Tools Manuf 45(4-5):467–479CrossRefGoogle Scholar
  18. 18.
    Bustillo A, Correa M (2012) Using artificial intelligence to predict surface roughness in deep drilling of steel components. J Intell Manuf 23(5):1893–1902CrossRefGoogle Scholar
  19. 19.
    Dhokia VG, Kumar S, Vichare P, Newman ST (2008) An intelligent approach for the prediction of surface roughness in ball-end machining of polypropylene. Robot Comput Integr Manuf 24(6):835–842CrossRefGoogle Scholar
  20. 20.
    Vapnik V (2000) The nature of statistical learning theory. Springer Science & Business MediaGoogle Scholar
  21. 21.
    Drucker H, Burges CJ, Kaufman L, Smola A, Vapnik V (1997) Support vector regression machines. Adv Neural Inf Process Syst 9:155–161Google Scholar
  22. 22.
    Suykens JA, Vandewalle J (1999) Least squares support vector machine classifiers. Neural Process Lett 9(3):293–300CrossRefMathSciNetGoogle Scholar
  23. 23.
    Lela B, Bajić D, Jozić S (2009) Regression analysis, support vector machines, and Bayesian neural network approaches to modeling surface roughness in face milling. Int J Adv Manuf Technol 42(11-12):1082–1088CrossRefGoogle Scholar
  24. 24.
    Gan B, Huang YJ, Zheng GX (2010) Prediction of surface roughness profiles for milling process with fractal parameters based on LS-SVM. Adv Mater Res 97:1186–1193CrossRefGoogle Scholar
  25. 25.
    Quintana G, Garcia-Romeu ML, Ciurana J (2011) Surface roughness monitoring application based on artificial neural networks for ball-end milling operations. J Intell Manuf 22(4):607–617Google Scholar
  26. 26.
    Grzenda M, Bustillo A (2013) The evolutionary development of roughness prediction models. Appl Soft Comput 13(5):2913–2922CrossRefGoogle Scholar
  27. 27.
    Yıldız AR (2013) A new hybrid artificial bee colony algorithm for robust optimal design and manufacturing. Appl Soft Comput 13(5):2906–2912CrossRefGoogle Scholar
  28. 28.
    Yıldız AR (2009) A novel particle swarm optimization approach for product design and manufacturing. Int J Adv Manuf Technol 40(5-6):617–628CrossRefGoogle Scholar
  29. 29.
    El-Mounayri H, Dugla Z, Deng H (2003) Prediction of surface roughness in end milling using swarm intelligence. In Swarm Intelligence Symposium, SIS'03. Proceedings of the 2003 I.E. pp 220–227Google Scholar
  30. 30.
    Yıldız AR, Solanki KN (2012) Multi-objective optimization of vehicle crashworthiness using a new particle swarm based approach. Int J Adv Manuf Technol 59(1-4):367–376CrossRefGoogle Scholar
  31. 31.
    Yang XS, Deb S (2009) Cuckoo search via Lévy flights. In nature & biologically inspired computing. NaBIC 2009. World Congress on, IEEE, pp 210–214Google Scholar
  32. 32.
    Yıldız AR (2013) Cuckoo search algorithm for the selection of optimal machining parameters in milling operations. Int J Adv Manuf Technol 64(1-4):55–61CrossRefGoogle Scholar
  33. 33.
    Chiou JP, Wang FS (1999) Hybrid method of evolutionary algorithms for static and dynamic optimization problems with application to a fed-batch fermentation process. Comput Chem Eng 23(9):1277–1291CrossRefGoogle Scholar
  34. 34.
    Yıldız AR, Ozturk F (2006) Hybrid enhanced genetic algorithm to select optimal machining parameters in turning operation. Proc Inst Mech Eng B J Eng Manuf 220(12):2041–2053CrossRefGoogle Scholar
  35. 35.
    Öztürk N, Yıldız AR, Kaya N, Öztürk F (2006) Neuro-genetic design optimization framework to support the integrated robust design optimization process in CE. Concurr Eng 14(1):5–16CrossRefGoogle Scholar
  36. 36.
    Yıldız AR (2012) A comparative study of population-based optimization algorithms for turning operations. Inf Sci 210:81–88CrossRefGoogle Scholar
  37. 37.
    Bustillo A, Díez-Pastor JF, Quintana G, García-Osorio C (2011) Avoiding neural network fine tuning by using ensemble learning: application to ball-end milling operations. Int J Adv Manuf Technol 57(5-8):521–532CrossRefGoogle Scholar
  38. 38.
    López de Lacalle LN, Lamikiz A, Sánchez JA, Salgado MA (2004) Effects of tool deflection in the high-speed milling of inclined surfaces. Int J Adv Manuf Technol 24:9–10Google Scholar
  39. 39.
    López de Lacalle LN, Lamikiz A, Sánchez JA, Salgado MA (2007) Toolpath selection based on the minimum deflection cutting forces in the programming of complex surfaces milling. Int J Mach Tools Manuf 47:388–400Google Scholar
  40. 40.
    Salgado M, López de Lacalle LN, Lamikiz A, Muñoa M, Sánchez JA (2005) Evaluation of the stiffness chain on the deflection of end-mills under cutting forces. Int J Mach Tools Manuf 45:727–739Google Scholar
  41. 41.
    Quiza R, Figueira L, Davim JP (2008) Comparing statistical models and artificial neural networks on predicting the tool wear in hard machining D2 AISI steel. Int J Adv Manuf Technol 37(7-8):641–648CrossRefGoogle Scholar
  42. 42.
    Ezugwu EO, Arthur SJ, Hines EL (1995) Tool-wear prediction using artificial neural networks. J Mater Process Technol 49(3):255–264CrossRefGoogle Scholar
  43. 43.
    Li X, Nee AYC (1996) Monitoring cutting conditions for tool scheduling in CNC machining. Manuf Syst 25(4):377–383Google Scholar
  44. 44.
    Srinivasa P, Nagabhushana TN, Rao PR (2002) Flank wear estimation in face milling based on radial basis function neural networks. Int J Adv Manuf Technol 20(4):241–247CrossRefGoogle Scholar
  45. 45.
    Ezugwu EO, Fadare DA, Bonney J, Da Silva RB, Sales WF (2005) Modelling the correlation between cutting and process parameters in high-speed machining of Inconel 718 alloy using an artificial neural network. Int J Mach Tools Manuf 45(12):1375–1385CrossRefGoogle Scholar
  46. 46.
    Rosenblatt F (1958) The perceptron: a probabilistic model for information storage and organization in the brain. Psychol Rev 65(6):386CrossRefMathSciNetGoogle Scholar
  47. 47.
    Liu X, Bowyer KW, Hall LO (2004) Decision trees work better than feed-forward back-prop neural nets for a specific class of problems. In Systems, Man and Cybernetics, IEEE International Conference on 6:5969–5974Google Scholar
  48. 48.
    Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2(5):359–366CrossRefGoogle Scholar
  49. 49.
    Yegnanarayana B (2009) Artificial neural networks. PHI Learning Pvt. Ltd.Google Scholar
  50. 50.
    Bloch G, Denoeux T (2003) Neural networks for process control and optimization: two industrial applications. ISA Trans 42(1):39–51CrossRefGoogle Scholar
  51. 51.
    Cybenko G (1989) Approximation by superpositions of a sigmoidal function. Math Control Signals Syst 2(4):303–314CrossRefMathSciNetzbMATHGoogle Scholar
  52. 52.
    Broomhead DS, Lowe D (1988) Multivariable functional interpolation and adaptative networks. Complex Syst 2:321–355MathSciNetzbMATHGoogle Scholar
  53. 53.
    Leonard JA, Kramer MA (1991) Radial basis function networks for classifying process faults. Control Syst IEEE 11(3):31–38CrossRefGoogle Scholar
  54. 54.
    Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten IH (2009) The WEKA data mining software: an update. ACM SIGKDD Explor Newsl 11(1):10–18CrossRefGoogle Scholar
  55. 55.
    Cho S, Binsaeid S, Asfour S (2010) Design of multisensor fusion-based tool condition monitoring system in end milling. Int J Adv Manuf Technol 46(5-8):681–694CrossRefGoogle Scholar
  56. 56.
    Bustillo A, Ukar E, Rodriguez JJ, Lamikiz A (2011) Modelling of process parameters in laser polishing of steel components using ensembles of regression trees. Int J Comput Integr Manuf 24(8):735–747CrossRefGoogle Scholar
  57. 57.
    Arthur D, Vassilvitskii, S (2007) k-means++: The advantages of careful seeding. In proceedings of the eighteenth annual ACM-SIAM symposium on discrete algorithms, Society for Industrial and Applied Mathematics, pp 1027–1035Google Scholar
  58. 58.
    Cameron AC, Windmeijer FA (1997) An R-squared measure of goodness of fit for some common nonlinear regression models. J Econ 77(2):329–342CrossRefMathSciNetzbMATHGoogle Scholar
  59. 59.
    Kanungo DP, Sharma S, Pain A (2014) Artificial neural network (ANN) and regression tree (CART) applications for the indirect estimation of unsaturated soil shear strength parameters. Front Earth Sci 8(3):439–456CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London 2015

Authors and Affiliations

  • Álvar Arnaiz-González
    • 1
  • Asier Fernández-Valdivielso
    • 2
  • Andres Bustillo
    • 1
  • Luis Norberto López de Lacalle
    • 2
  1. 1.Department of Civil EngineeringUniversity of BurgosBurgosSpain
  2. 2.Department of Mechanical Engineering, ETSI of BilbaoUniversity of the Basque Country (UPV/EHU)LeioaSpain

Personalised recommendations