Journal of the Korean Society for Precision Engineering (한국정밀공학회지)

Korean Society for Precision Engineering (한국정밀공학회)
권호 표지

Geometric Feature Recognition Directly from Scanned Points using Artificial Neural Networks

신경회로망을 이용한 측정 점으로부터 특징형상 인식

  • 전용태 (한국과학기술연구원 CAD/CAM 연구센터) ;
  • 박세형 (한국과학기술연구원 CAD/CAM 연구센터)
  • Published : 2000.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

Reverse engineering (RE) is a process to create computer aided design (CAD) models from the scanned data of an existing part acquired using 3D position scanners. This paper proposes a novel methodology of extracting geometric features directly from a set of 3D scanned points, which utilizes the concepts of feature-based technology and artificial neural networks (ANNs). The use of ANN has enabled the development of a flexible feature-based RE application that can be trained to deal with various features. The following four main tasks were mainly investigated and implemented: (1) Data reduction; (2) edge detection; (3) ANN-based feature recognition; (4) feature extraction. This approach was validated with a variety of real industrial components. The test results show that the developed feature-based RE application proved to be suitable for reconstructing prismatic features such as block, pocket, step, slot, hole, and boss, which are very common and crucial in mechanical engineering products.

Keywords

References

  1. W. B Thompson, J. C. Owen and H. James, 'Feature-Based Reverse Engineering of Mechanical Parts,' University of Utah, Department of Computer Science, Technical Report UUCS-95-010, November 6, 1995
  2. Yongtae Jun, 'A feature-based reverse engineering system using artificial neural networks,' PhD Thesis, School of Engineering, University of Warwick, Coventry, UK, 1999
  3. Jami J. Shah and Matti Mantyla, Parametric and Feature-based CAD/CAM (Concepts, Techniques, and Applications), John Wiley & Sons, Inc., 1995
  4. P. K. Jain and Sharvan Kumar, 'Automatic feature extraction in PRIZCAPP,' International Journal of Computer Integrated Manufacturing, Vol. 11, No. 6, pp. 500-512, 1998 https://doi.org/10.1080/095119298130534
  5. Pramod N Chivate and Andrei G Jablokow, 'Solid-model generation from measured point data,' Computer-Aided Design, Vol. 25, No. 9, pp. 587-599, 1993 https://doi.org/10.1016/0010-4485(93)90074-X
  6. B.Sarkar and C-H Menq, 'Smooth-surface appoximation and Reverse Engineering,' Computer-Aided Design, Vol. 23, No. 9, pp. 623-628, 1991 https://doi.org/10.1016/0010-4485(91)90038-X
  7. J-Y Lai and C-Y Lu, 'Reverse Engineering of composite sculptured surfaces,' International Journal of Advanced Manufacturing Technology, Vol. 12, pp. 180-189, 1996 https://doi.org/10.1007/BF01351197
  8. Saeid Motavalli and Rafie Shamsaasef, 'Object-oriented modelling of a feature-based reverse engineering system,' International Journal of Computer Integrated Manufacturing, Vol. 9, No. 5, pp. 354-368, 1996 https://doi.org/10.1080/095119296131463
  9. Pattern Recognition v.13 Generalising the Hough transform to detect arbitrary shapes Ballard,D.H.
  10. Ballard, D. H., 'Generalising the Hough transform to detect arbitrary shapes,' Pattern Recognition, Vol. 13, pp. 111-119, 1996 https://doi.org/10.1016/0031-3203(81)90009-1
  11. Saeid Motavalli and Jorge Valenzuela, 'A system for reverse engineering of prismatic parts using orthographic images,' International Journal of Computer Integrated Manufacturing, Vol. 11, No. 2. pp. 103-110, 1998 https://doi.org/10.1080/095119298130840
  12. S. Prebhakar and M. R. Henderson, 'Automatic form-feature recognition using neural-network-based techniques on boundary representations of solid models,' Computer-Aided Design, Vol. 24, No. 7, pp. 381-393, 1992 https://doi.org/10.1016/0010-4485(92)90064-H
  13. P. Gu and X. Yan, 'Neural network approach to the reconstruction of freeform surface for reverse engineering,' Computer-Aided Design, Vol. 27, No. 1, pp. 59-64, 1995 https://doi.org/10.1016/0010-4485(95)90753-3
  14. K. Nezis and G. Vosniakos, 'Recognising 2.5D shape features using a neural network and heuristics,' Computer-Aided Design, Vol. 29, No. 7, pp. 523-539, 1997 https://doi.org/10.1016/S0010-4485(97)00003-1
  15. Chandra R. Devireddy and Kalyan Ghosh, 'Feature-based modelling and neural networks-based CAPP for integrated manufacturing,' International Journal of Computer Integrated Manufacturing, Vol. 12, No. 1, pp. 61-74, 1999 https://doi.org/10.1080/095119299130470
  16. H. K. Tonshoff, J. C. Aurich and N. D'Agostino, 'A unified approach to free-form and regular feature modelling,' Annals of the CIRP, Vol. 14, No. 1, pp. 125-128, 1996
  17. R. M. Bolle and D. B. Cooper, 'On optimally pieces of information, with application to estimating 3D complex-object position from range data,' IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 8, No. 5, pp. 619-638, 1986
  18. U.M. Landau, 'Estimation of a circular arc center and its radius,' Computer Vision, Graphics, and Image Processing, Vol. 38, pp. 317-326, 1987 https://doi.org/10.1016/0734-189X(87)90116-2
  19. Renishaw, Brochure on Scanning System, 1998