Advertisement

A neural-network-based methodology for the prediction of surface roughness in a turning process

  • A. Kohli
  • U.S. DixitEmail author
Original Article

Abstract

A neural-network-based methodology is proposed for predicting the surface roughness in a turning process by taking the acceleration of the radial vibration of the tool holder as feedback. Upper, most likely and lower estimates of the surface roughness are predicted by this method using very few experimental data for training and testing the network. The network model is trained using the back-propagation algorithm. The learning rate, the number of neurons in the hidden layer, the error goal, as well as the training and the testing dataset size, are found automatically in an adaptive manner. Since the training and testing data are collected from experiments, a data filtration scheme is employed to remove faulty data. The validation of the methodology is carried out for dry and wet turning of steel using high speed steel and carbide tools. It is observed that the present methodology is able to make accurate prediction of surface roughness by utilising small sized training and testing datasets.

Keywords

Artificial neural networks  Dry and wet turning Surface roughness Vibration 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Risbood KA, Dixit US, Sahasrabudhe AD (2003) Prediction of surface roughness and dimensional deviation by measuring cutting forces and vibrations in turning process. J Mater Process Technol 132:203–214Google Scholar
  2. 2.
    Wang XF, Feng CX (2002) Development of empirical models for surface roughness prediction in finish turning. Int J Adv Manuf Technol 20(5):348–356CrossRefGoogle Scholar
  3. 3.
    Sundaram RM, Lambert BK (1981) Mathematical model to predict surface finish in fine turning of steel. Int J Prod Res 19:547–564Google Scholar
  4. 4.
    Mittal A, Mehta M (1988) Surface finish prediction models for fine turning. Int J Prod Res 26:1861–1876 1988.Google Scholar
  5. 5.
    Yan D, Popplewell N, Balkrishnan S, Kaye JE (1996) On-line prediction of surface roughness in finish turning. Eng Des Autom 2:115–126Google Scholar
  6. 6.
    Fang XD, Jawahir IS (1994) Predicting total machining performance in finish turning using integrated fuzzy-set models of the machinability parameters. Int J Prod Res 32:833–849Google Scholar
  7. 7.
    Azouzi R, Guillot M (1998) On-line optimisation of turning process using an inverse process Neuro controller. ASME J Manuf Sci Eng 120:101–108Google Scholar
  8. 8.
    Lin WS, Lee BY, Wu CL (2001) Modeling the surface roughness and cutting force for turning. J Mater Process Technol 108:286–293Google Scholar
  9. 9.
    Feng C-X, Wang X-F (2003) Surface roughness prediction modelling: neural networks versus regression. IIE Trans 35(1):11–27Google Scholar
  10. 10.
    Chryssolouris G, Guillot M (1990) A comparison of statistical and AI approaches to the selection of process parameters in intelligent machining. ASME J Eng Ind 112:112–131Google Scholar
  11. 11.
    Dixit US, Chandra S (2003) A neural network based methodology for the prediction of roll force and roll torque in fuzzy form for cold rolling process. Int J Adv Manuf Technol 22(11–12):883–889Google Scholar
  12. 12.
    Tsoukalas LH, Uhrig RE (1997) Fuzzy and neural approaches in engineering. Wiley, New YorkGoogle Scholar
  13. 13.
    Dieter GE (1991) Engineering design: a materialistic and processing approach, 2nd edn. McGraw-Hill, New YorkGoogle Scholar
  14. 14.
    Ishibuchi H, Tanaka H (1991) Regression analysis with interval model by neural networks. Proc of the IEEE Int Joint Conf on Neural Networks, Singapore, pp 1594–1599Google Scholar

Copyright information

© Springer-Verlag 2004

Authors and Affiliations

  1. 1.Department of Mechanical EngineeringIndian Institute of TechnologyGuwahatiIndia

Personalised recommendations