Soft Computing

, Volume 16, Issue 8, pp 1427–1437 | Cite as

Boosting Projections to improve surface roughness prediction in high-torque milling operations

  • José-Francisco Díez-Pastor
  • Andres BustilloEmail author
  • Guillem Quintana
  • César García-Osorio
Original Paper


Industrial solutions for surface roughness prediction are in great demand, especially in high-torque milling operations, owing to the exponential expansion of wind power energy generation over the past decade. In this paper, we use Boosting Projections to predict surface roughness in high-torque, high-power face milling operations. A data set is generated from experiments performed under industrial conditions, using a milling machine with a high working volume, to train and validate the new algorithm. The experimental data comprise a very extensive set of parameters that influence surface roughness: cutting tool properties, machining parameters and cutting phenomena. The proposed method is based on non-linear boosting projections (although it uses linear projections to speed up the training process). To the best of our knowledge this is the first time it has been used in an industrial context. It demonstrates a higher prediction accuracy when compared with single multilayer perceptrons, decision trees and classical ensemble methods.


High-torque milling Surface roughness Ensemble methods Linear projections 



This investigation has been partially supported by the Projects CENIT-2008-1028, TIN2011-24046 and IPT-2011-1265-020000 of the Spanish Ministry of Economy and Competitiveness. The authors would especially like to thank Mr. Desiderio Sutil from Nicolas Correa S.A. for his kind-spirited and useful advice.


  1. Agresti A (2010) Analysis of ordinal categorical data. Wiley series in probability and statistics. Wiley, New YorkGoogle Scholar
  2. 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
  3. Bauer E, Kohavi R (1999) An empirical comparison of voting classification algorithms: bagging, boosting, and variants. Mach Learn 36:105–139CrossRefGoogle Scholar
  4. Beggan C, Woulfe M, Young P, Byrne G (1999) Using acoustic emission to predict surface quality. Int J Adv Manuf Technol 15:737–742. 10.1007/s001700050126Google Scholar
  5. Benardos PG, Vosniakos GC (2002) Prediction of surface roughness in CNC face milling using neural networks and Taguchi’s design of experiments. Robot Comput-Integrated Manuf 18(5–6):343–354CrossRefGoogle Scholar
  6. Benardos PG, Vosniakos GC (2003) Predicting surface roughness in machining: a review. Int J Mach Tools Manuf 43(8):833–844CrossRefGoogle Scholar
  7. Binsaeid S, Asfour S, Cho S, Onar A (2009) Machine ensemble approach for simultaneous detection of transient and gradual abnormalities in end milling using multisensor fusion. J Mater Process Technol 209(10):4728–4738CrossRefGoogle Scholar
  8. Breiman L (1996) Bagging predictors. Mach Learn 24(2):123–140MathSciNetzbMATHGoogle Scholar
  9. Brezocnik M, Kovacic M (2003) Integrated genetic programming and genetic algorithm approach to predict surface roughness. Mater Manuf Process 18(3):475–491CrossRefGoogle Scholar
  10. Brezocnik M, Kovacic M, Ficko M (2004) Prediction of surface roughness with genetic programming. J Mater Process Technol 157(158):28–36CrossRefGoogle Scholar
  11. Bustillo A, Ukar E, Rodriguez JJ, Lamikiz A (2011a) 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
  12. Bustillo A, Díez-Pastor JF, Quintana G, García-Osorio C (2011b) Avoiding neural network fine tuning by using ensemble learning: application to ball-end milling operations. Int J Adv Manuf Technol 57:521–532. doi: 10.1007/s00170-011-3300-z Google Scholar
  13. 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
  14. 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):681–694CrossRefGoogle Scholar
  15. 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
  16. Correa M, Bielza C, de J. Ramirez M, Alique JR (2008) A Bayesian network model for surface roughness prediction in the machining process. Int J Syst Sci 39(12):1181–1192zbMATHCrossRefGoogle Scholar
  17. Correa M, Bielza C, Pamies-Teixeira J (2009) Comparison of Bayesian networks and artificial neural networks for quality detection in a machining process. Expert Syst Appl 36(3):7270–7279CrossRefGoogle Scholar
  18. Dietterich TG (1998) Approximate statistical tests for comparing supervised classification learning algorithms. Neural Comput 10(7):1895–1923CrossRefGoogle Scholar
  19. Dietterich TG (2000a) Ensemble methods in machine learning. In: Kittler J, Roli F (eds) Multiple classifier systems. Lecture notes in computer science, vol 1857, pp 1–15Google Scholar
  20. Dietterich TG (2000b) An experimental comparison of three methods for constructing ensembles of decision trees: bagging, boosting, and randomization. Mach Learn 40(2):139–157CrossRefGoogle Scholar
  21. 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-Integrated Manuf 24(6):835–842. In: FAIM 2007, 17th international conference on flexible automation and intelligent manufacturingGoogle Scholar
  22. Dzeroski S, Zenko B (2004) Is combining classifiers with stacking better than selecting the best one? Mach Learn 54(3):255–273zbMATHCrossRefGoogle Scholar
  23. Frank E, Hall M (2001) A simple approach to ordinal classification. In: ECML 2001, pp 145–156Google Scholar
  24. Freund Y, Schapire RE (1996) Experiments with a new boosting algorithm. In: International conference on machine learning, pp 148–156Google Scholar
  25. Freund Y, Schapire RE (1997) A decision-theoretic generalization of on-line learning and an application to boosting. J Comput Syst Sci 55(1):119–139MathSciNetzbMATHCrossRefGoogle Scholar
  26. Fukunaga K, Mantock J (1983) Nonparametric discriminant analysis. IEEE Trans Pattern Anal Mach Intell 6(5):671–678CrossRefGoogle Scholar
  27. García-Pedrajas N, García-Osorio C (2011) Constructing ensembles of classifiers using supervised projection methods based on misclassified instances. Expert Syst Appl 38(1):343–359CrossRefGoogle Scholar
  28. García-Pedrajas N, García-Osorio C, Fyfe C (2007) Nonlinear “boosting” projections for ensemble construction. J Mach Learn Res 8:1–33MathSciNetzbMATHGoogle Scholar
  29. García-Osorio C, García-Pedrajas N (2008) Constructing ensembles of classifiers using linear projections based on misclassified instances. In Verleysen M (ed) 16th European symposium on artificial neural networks (ESANN 2008), pp 283–288, Bruges, Belgium, April 2008. d-side publicationsGoogle Scholar
  30. Groover MP (2006) Fundamentals of modern manufacturing: materials, processes, and systems, 3rd edn. Wiley, New York. ISBN:0471744859; ISBN-13:9780471744856, 978-0471744856Google Scholar
  31. Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten IH (2009) The weka data mining software: an update. SIGKDD Explor Newsl 11:10–18CrossRefGoogle Scholar
  32. Ho TK (1998) The random subspace method for constructing decision forests. IEEE Trans Pattern Anal Mach Intell 20:832–844CrossRefGoogle Scholar
  33. Ho WH, Tsai JT, Lin BT, Chou JH (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):3216–3222CrossRefGoogle Scholar
  34. International Organization for Standardization (1996) ISO-4288. Geometrical product specifications (GPS): rules and procedures for the assessment of surface textureGoogle Scholar
  35. International Organization for Standardization (1997) ISO-4287. Geometrical product specifications (GPS)—surface texture: profile method—terms, definitions and surface texture parametersGoogle Scholar
  36. Iqbal A, He N, Li L, Dar NU (2007) A fuzzy expert system for optimizing parameters and predicting performance measures in hard-milling process. Expert Syst Appl 32(4):1020–1027CrossRefGoogle Scholar
  37. Ismail F, Elbestawi MA, Du R, Urbasik K (1993) Generation of milled surfaces including tool dynamics and wear. J Eng Ind 115(3):245–252Google Scholar
  38. Kuncheva LI (2004) Combining pattern classifiers: methods and algorithms. Wiley-Interscience, New York. ISBN-10: 0471210781; ISBN-13: 978-0471210788Google Scholar
  39. Kuncheva LI (2005) Diversity in multiple classifier systems. Inf Fusion 6(1):3–4MathSciNetCrossRefGoogle Scholar
  40. Kuncheva LI (2001) Combining classifiers: soft computing solutions. In: Pal SK (ed) Pattern recognition: from classical to modern approaches. World Scientific, Singapore, pp 427–452Google Scholar
  41. Lee HS, Park MS, Kim MT, Chu CN (2006) Systematic finishing of dies and moulds. Int J Mach Tools Manuf 46(9):1027–1034CrossRefGoogle Scholar
  42. Lo SP (2003) An adaptive-network based fuzzy inference system for prediction of workpiece surface roughness in end milling. J Mater Process Technol 142(3):665–675CrossRefGoogle Scholar
  43. Maimon O, Rokach L (eds) (2010) Data mining and knowledge discovery handbook, 2nd edn. Springer, BerlinGoogle Scholar
  44. Martellotti ME (1941) An analysis of the milling process. Trans ASME 63:667–700Google Scholar
  45. Montgomery D, Altintas Y (1991) Mechanism of cutting force and surface generation in dynamic milling. J Eng Ind 113(2):160–168CrossRefGoogle Scholar
  46. Oza N, Tumer K (2008) Classifier ensembles: select real-world applications. Inf Fusion 9(1):4–20CrossRefGoogle Scholar
  47. Prakasvudhisarn C, Kunnapapdeelert S, Yenradee P (2009) Optimal cutting condition determination for desired surface roughness in end milling. Int J Adv Manuf Technol 41(5):440–451CrossRefGoogle Scholar
  48. Quintana G, Garcia-Romeu M, Ciurana J (2009) Surface roughness monitoring application based on artificial neural networks for ball-end milling operations. J Intell Manuf. doi: 10.1007/s10845-009-0323-5
  49. Quintana G, de Ciurana J, Ribatallada J (2010) Surface roughness generation and material removal rate in ball end milling operations. Mater Manuf Process 25(6):386–398CrossRefGoogle Scholar
  50. Samanta B, Erevelles W, Omurtag Y (2008) Prediction of workpiece surface roughness using soft computing. Proc Inst Mech Eng B: J Eng Manuf 222(10):1221–1232CrossRefGoogle Scholar
  51. Tian Q, Yu J, Huang TS (2005) Boosting multiple classifiers constructed by hybrid discriminantanalysis. In: Oza NC, Polikar R, Kittler J, Roli F (eds) Multiple classifier systems. Lecture notes in computer science, vol 3541, pp 42–52. Springer, BerlinGoogle Scholar
  52. 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 162–163:696–701Google Scholar
  53. Webb GI (2000) MultiBoosting: a technique for combining boosting and wagging. Mach Learn 40(2):159Google Scholar

Copyright information

© Springer-Verlag 2012

Authors and Affiliations

  • José-Francisco Díez-Pastor
    • 1
  • Andres Bustillo
    • 1
    Email author
  • Guillem Quintana
    • 2
  • César García-Osorio
    • 1
  1. 1.Department of Civil EngineeringUniversity of BurgosBurgosSpain
  2. 2.ASCAMM Technology CentreBarcelonaSpain

Personalised recommendations