Skip to main content
SpringerLink
Log in

Surface roughness prediction through internal kernel information and external accelerometers using artificial neural networks

  • Published:
Journal of Mechanical Science and Technology Aims and scope Submit manuscript

Abstract

In this paper, the average surface roughness parameter (Ra) is predicted using artificial neural network (ANN) models and internal kernel information and external piezoelectric accelerometer data. Experiments were conducted to obtain data to develop ANN models to predict surface roughness. A total of 72 samples were used to develop two networks, one based on accelerometer inputs and the other on kernel inputs. The Matlab ANN Toolbox was used for the modeling. The two networks had similar characteristics. Feed-forward backpropagation, ‘newff’, was the network structure selected, with a Levenberg-Marquardt backpropagation training function, ‘trainlm’, and a backpropagation weight and bias learning function, ‘learngdm’. Samples obtained at the experimental stage were randomly divided into three groups to train (70% of the samples), validate (15% of the samples) and test (15% of the samples) the neural networks with a ‘dividerand’ data division function. The input processing functions used were ‘fixunknowns’, ‘removeconstantrows’ and ‘mapminmax’. The transfer function was ‘tansig’ for hidden layers and ‘purelin’ for the output layer. The output processing functions used were ‘removeconstantrows’ and ‘mapminmax’. The inputs consisted of the process parameters of radial depth of cut (Ae), the axial depth of cut (Ap), the spindle speed (N), the feed rate (f), the feed per tooth (fz), the cutting speed (Vc), the tooth passing frequency (ft), the cutting section (Cs), the material removal rate (MRR) and the cutting tool characteristics of the cutter radius (R), the number of teeth (Z) and the tool shape. The main difference between the two neural networks consisted of data origin: one considered data obtained with accelerometers and the other data collected in the NC kernel. Results showing high correlation factors between outputs and targets confirm that data provided by both internal and external sources can be useful for Ra prediction. However, NC kernel data provide several advantages.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. P. G. Benardos and G. C. Vosniakos, Predicting surface roughness in machining: a review, International Journal of Machine Tools and Manufacture, 43(8) (2003) 833–844.

    Article  Google Scholar 

  2. M. Correa, C. Bielza and J. Pamies-Teixeira, Comparison of bayesian networks and artificial neural networks for quality detection in a machining process, Expert Systems with Applications, 36(3) (2009) 7270–7279.

    Article  Google Scholar 

  3. M. E. Martellotti, An analysis of the milling process, Transactions of ASME, 63 (1941) 667.

    Google Scholar 

  4. G. Quintana, J. Ciurana and J. Ribatallada, Surface roughness generation and material removal rate in ball end milling operations, Materials and Manufacturing Processes, 25(6) (2010) 386–398.

    Article  Google Scholar 

  5. H. K. Chang, J. H. Kim, I. H. Kim, D. Y. Jang and D. C. Han, In-process surface roughness prediction using displacement signals from spindle motion, International Journal of Machine Tools and Manufacture, 47(6) (2007) 1021–1026.

    Article  Google Scholar 

  6. W. Grzesik, Influence of tool wear on surface roughness in hard turning using differently shaped ceramic tools, Wear, 265(3–4) (2008) 327–335.

    Article  Google Scholar 

  7. C. Gologlu and N. Sakarya, The effects of cutter path strategies on surface roughness of pocket milling of 1.2738 steel based on Taguchi method, Journal Material Processing Technology, 206(1–3) (2008) 7–15.

    Article  Google Scholar 

  8. W. H. Ho, J. T. Tsai, B. T. Lin and J. H. Chou, Adaptive network-based fuzzy inference system for prediction of surface roughness in end milling process using hybrid Taguchigenetic learning algorithm, Expert Systems with Applications, 36(2) (2009) 3216–3222.

    Article  Google Scholar 

  9. Y. H. Tsai, J. C. Chen and S. J. Lou, An in-process surface recognition system based on neural networks in end milling cutting operations, International Journal of Machine Tools and Manufacture, 39(4) (1999) 583–605.

    Article  Google Scholar 

  10. S. Y. Ho, K. C. Lee, S. S. Chen and S. J. Ho, Accurate modeling and prediction of surface roughness by computer vision in turning operations using an adaptive neuro-fuzzy inference system, International Journal of Machine Tools and Manufacture, 42(13) (2002) 1441–1446.

    Article  Google Scholar 

  11. P. G. Benardos and G. C. Vosniakos, Prediction of surface roughness in CNC face milling using neural networks and Taguchi’s design of experiments, Robotics and Computer-Integrated Manufacturing, 18(5–6) (2002) 343–354.

    Article  Google Scholar 

  12. M. Brezocnik and M. Kovacic, Integrated genetic programming and genetic algorithm approach to predict surface roughness, Materials and Manufacturing Processes, 18(3) (2003) 475–491.

    Article  Google Scholar 

  13. M. Brezocnik, M. Kovacic and M. Ficko, Prediction of surface roughness with genetic programming, Journal of Materials Processing Technology, 157–158 (2004) 28–36.

    Article  Google Scholar 

  14. A. M. Zain, H. Haron and S. Sharif, An overview of GA technique for surface roughness optimization in milling process, Proceedings of the International Symposium on Information Technology, ITSim 3 (2008) art. no 4631925.

  15. A. M. Zain, H. Haron and S. Sharif, Application of GA to optimize cutting conditions for minimizing surface roughness in end milling machining process, Expert Systems and Application, 37(6) (2010) 4650–4659.

    Article  Google Scholar 

  16. A. M. Zain, H. Haron and S. Sharif, Prediction of surface roughness in the end milling machining using Artificial Neural Network. Expert System Application, 37(2) (2010) 1755–1768.

    Article  Google Scholar 

  17. J. R. Shie, Optimization of dry machining parameters for high-purity graphite in end-milling process by artificial neural networks: A case study. Materials and Manufacturing Processes, 21(8) (2006) 838–845.

    Article  Google Scholar 

  18. P. V. S. Suresh, P. Venkateswara and S. G. Deshmukh, A genetic algorithmic approach for optimization of surface roughness prediction model, International Journal of machine Tools & Manufacture, 42 (2007) 675–680.

    Article  Google Scholar 

  19. M. Correa, C. Bielza, M. J. D. Ramirez and J. R. Alique, A bayesian network model for surface roughness prediction in the machining process. International Journal of Systems Science, 39(12) (2008) 1181–1192.

    Article  MATH  Google Scholar 

  20. C. Brecher, G. Quintana, T. Rudolf and J. Ciurana, Use of NC kernel data for surface roughness monitoring in milling operations, International Journal of Advanced Manufacturing Technologies, 53(9–12) (2011) 953–962.

    Article  Google Scholar 

  21. B. Samanta and C. Nataraj, Surface roughness prediction in machining using computational intelligence, International Journal of Manufacturing Research, 3(4) (2008) 379–392.

    Article  Google Scholar 

  22. B. Samanta, Surface roughness prediction in machining using soft computing, International Journal of Computer Integrated Manufacturing, 22(3) (2009) 257–266.

    Article  Google Scholar 

  23. C. Brecher and T. Rudolf, Adaptive logging module for monitoring applications using control internal digital drive signals, Production Engineering, 3(3) (2009) 305–312.

    Article  Google Scholar 

  24. T. Rudolf, C. Brecher and F. Possel-Dölken, Contact-based collision detection — A new approach to avoid hard collisions in machine tools, In: Donmez A, Deshayes L, editors, International Conference on Smart Machining Systems, 2007.

  25. C. Brecher and T. Rudolf, Signalvorverarbeitung zur anwendung steuerungsintegrierter prozessüberwachung, wt Werkstattstechnik online, 99(7/8) (2009) 479–486.

    Google Scholar 

  26. J. Ciurana, G. Quintana and M. L. Garcia-Romeu, Estimating the cost of vertical high-speed machining centres, a comparison between multiple regression analysis and the neural networks approach, International Journal of Production Economics, 115(1) (2008) 171–178.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Cerdanyola del Vallès, ASCAMM Technology Centre, Barcelona, Spain

    Guillem Quintana

  2. Laboratory for Machine Tools and Production Engineering, RWTH Aachen University of Technology, Aachen, Germany

    Thomas Rudolf & Christian Brecher

  3. Department of Mechanical Engineering and Industrial Construction, University of Girona, Girona, Spain

    Joaquim Ciurana

Authors
  1. Guillem Quintana
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Thomas Rudolf
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Joaquim Ciurana
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Christian Brecher
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Joaquim Ciurana.

Additional information

This paper was recommended for publication in revised form by Associate Editor Yong-Tae Kim

Guillem Quintana, Ph.D, is a project manager at Ascamm Technology Centre. He is also, a member of the Research group on Product, Process and Production (GREP) and associate professor in the Department of Mechanical Engineering and Industrial Construction in the University of Girona, UdG. He is Industrial Engineer (UdG) and Business Sciences graduate (UdG). His research is focused on manufacturing technologies, specially machining processes, with principal interest on instabilities and surface roughness evaluation.

Thomas Rudolf studied Mechatronics at the technical University of Darmstadt and received the degree of mechanical engineer in 2005. From 2005 to 2010 he worked as a research assistant at the Laboratory of Machine Tools, RWTH Aachen. His main research focus is the investigation monitoring strategies based on control internal data and drive signals.

Joaquim Ciurana is full Professor at the Department of Mechanical Engineering and Industrial Construction at the University of Girona. He is Head of the Product, Process and Production Engineering Group (GREP) at University of Girona. His research topic is Manufacturing Sciences. His current research focuses on developing models to characterize manufacturing processes. He mainly studies and analyses machining processes and additive manufacturing processes to make better plans for machining operations and better decisions based on process parameters selection and knowledge.

Christian Brecher is full Professor at RWTH Aachen, WZL. He carried out his degree at study of mechanical engineering (production engineering) at Aachen University and holds his Ph.D at the Laboratory for Machine Tools and Production Engineering (WZL) at Aachen University, chair of machine tools, department of machine technology. His current research focuses on developing machine tools and cutting processes. He mainly studies and analyses machine tools and monitoring systems applied to machine tools.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Quintana, G., Rudolf, T., Ciurana, J. et al. Surface roughness prediction through internal kernel information and external accelerometers using artificial neural networks. J Mech Sci Technol 25, 2877–2886 (2011). https://doi.org/10.1007/s12206-011-0806-0

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12206-011-0806-0

Keywords

Search

Navigation