Journal of Intelligent Manufacturing

, Volume 15, Issue 1, pp 5–15 | Cite as

Neural networks for estimating the tool path length in concurrent engineering applications

Article
  • 69 Downloads

Abstract

This paper deals with the development of a neural computing system that can predict the cutting tool path length for milling an arbitrary pocket defined within the domain of a product design, in a computer numerically controlled (CNC) setting. Existing computer aided design and manufacturing systems (CAD/CAM) consume significant amounts of time in terms of data entry pertaining to the geometries and subsequent modifications to them. In the concurrent engineering environment, where even the designer needs information from the CAD/CAM systems, such time-consuming processes can be expensive. To alleviate this problem, a neural network system can be used to estimate machining time by predicting cost-dependent variables such as tool path length for the pocket milling operation. Pockets are characterized and classified into various groups. A randomized design is described so that the training samples that have been chosen represent the domain evenly. An appropriate network was built and trained with the sample pocket geometries. The analysis of the performance of the system in terms of tool path length prediction for new pocket geometries is presented.

Neural networks computer numerically controlled machining concurrent engineering pocket milling tool path length 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Blum, A. (1992) Neural Networks in C ++, John Wiley & Sons Inc., New York.Google Scholar
  2. Bobrow, J. E. (1985) NC machine tool path generation from CSG part representations. Computer-Aided Design, 17(2), 69–76.Google Scholar
  3. CLEARCUT (1993) The Total CAD/CAM Solution, Anilan Electronics Corporation.Google Scholar
  4. Ferstenberg, R., Wang, K. K. and Muckstadt, J. (1986) Automatic generation of optimized 3-axis NC programs using boundary files. Cornell Manufacturing Engineering Productive Program, Cornell University, IEEE.Google Scholar
  5. Gosling, I. G. (1990) A tool-path algorithm exhibiting improved collisional behavior. Computer-Aided Engineering Journal, 7(5), 135–140.Google Scholar
  6. Neural Ware (1991) Neural Computing, Neural Ware Inc.Google Scholar
  7. Pathak, M. A. (1990) Feature Based Design and Milling Process Planning in Concurrent Engineering, West Virginia University, Thesis Col.Google Scholar
  8. Pressman, R. S. and Williams, J. E. (1977) Numerical Control and Computer-Aided Manufacturing, John Wiley & Sons, New York.Google Scholar
  9. Reddy, V. K. (1990) Estimation of Tool Path Length for NC Pocket Milling using a Neural Network, West Virginia University, Thesis Collection.Google Scholar
  10. Satyanarayana, B., Rao, P. N. and Tewari, N. K. (1990) An interactive programming system for milling contours and pockets. International Journal of Advance Manufacturing Technology, 5(3), 188–213.Google Scholar
  11. Wang, H., Chang, H., Wysk, R. A. and Chandawarkar, A. (1987) On the efficiency of NC tool path planning for face milling operations. Journal of Engineering for Industry, 109, 370–376.Google Scholar
  12. Weiss, S. M. and Kulikowski, C. A. (1991) Computer Systems That Learn, Morgan Kaufmann Publishers Inc.Google Scholar
  13. Wesserman, P. D. (1989) Neural Computing—Theory and Practice, Van Nostrand Reinhold.Google Scholar
  14. Winner, R. L., Pennel, J. P., Bertrand, H. E. and Slusarczuk, M. M. G. (1988) The role of concurrent engineering in weapons systems acquisition, IDA Report R-338, Institute for Defense Analysis, Alexandria, Virginia.Google Scholar

Copyright information

© Kluwer Academic Publishers 2004

Authors and Affiliations

  1. 1.Industrial Assessment Center, Department of Industrial and Management Systems EngineeringWest Virginia UniversityMorgantownUSA

Personalised recommendations