Elsevier

Computer-Aided Design

Volume 30, Issue 13, November 1998, Pages 1003-1007
Computer-Aided Design

Technical Note 4
Hint-based reasoning for feature recognition: status report

https://doi.org/10.1016/S0010-4485(98)00061-XGet rights and content

Abstract

This technical note reports the feature recognition test results using three systems: IF2, F-Rex and FBMach. Hint-based reasoning extends the portions of an object's boundary that are associated with a machining feature so as to create a material removal volume. Portions of the feature that are missing because of spatial intersections with others are reconstructed. Recognized features also provide useful information about accessibility and other machinability constraints.

Section snippets

Algorithms

The most important issue in machining feature recognition is the capability of recognizing intersecting features. When features intersect, their topological patterns are often altered, and therefore naive pattern matching is likely to fail. In our approach, we observed that a feature and its associated machining operation should leave a trace in the part boundary even when features intersect[1]. This provides a hint for the potential existence of a feature. Geometric completion procedures start

Test results with benchmark parts

All of the nine benchmark parts are successfully decomposed by IF2, F-Rex and FBMach. However, we will report on seven to avoid an overly lengthy technical note. For the test results of the remaining two parts, readers are referred to Ref. [5].

Conclusion

In this note, we showed that the geometric completion procedures of hint-based reasoning can deal with complex feature intersections. This is not surprising because a hint is not an exact pattern of geometric entities and was introduced precisely to resolve the problem of recognizing intersecting features. The output of the systems is a set of volumetric features that decompose the material to be machined into cutter-swept volumes, which can be associated with machining operations.

Acknowledgements

This work done by the first author was supported in part by SEOK CHUN Research Fund, Sung Kyun Kwan University, 1997.

Dr JungHyun Han is a faculty member in the School of Electrical and Computer Engineering, Sung Kyun Kwan University in Korea, and directs the Computer Graphics Laboratory. Prior to joining the University, he worked at the US National Institute of Standards and Technology. He received a BS degree in computer engineering at Seoul National University, an MS degree in computer science at the University of Cincinnati, and a PhD degree in computer science at the University of Southern California. His

References (6)

  • J.H Vandenbrande et al.

    Spatial reasoning for automatic recognition of machinable feature in solid models

    IEEE Trans. Pattern Analysis and Machine Intelligence

    (1993)
  • Regli, W. C. Geometric algorithms for recognition of features from solid models. PhD thesis, Computer Science...
  • Han, J. and Requicha, A. A. G., Feature recognition from CAD models. IEEE Computer Graphics and Applications. 1998,...
There are more references available in the full text version of this article.

Cited by (0)

  1. Download : Download full-size image
Dr JungHyun Han is a faculty member in the School of Electrical and Computer Engineering, Sung Kyun Kwan University in Korea, and directs the Computer Graphics Laboratory. Prior to joining the University, he worked at the US National Institute of Standards and Technology. He received a BS degree in computer engineering at Seoul National University, an MS degree in computer science at the University of Cincinnati, and a PhD degree in computer science at the University of Southern California. His research interests include geometric and solid modeling, CAD/CAM, computer graphics and vision.

  1. Download : Download full-size image
William Regli is an Assistant Professor in the Department of Mathematics and Computer Science at Drexel University. He has previously been visiting research faculty at Carnegie Mellon University (1997) and a National Research Council Postdoctoral Research Associate at the National Institute of Standards and Technology (1996–97). During his tenure at NIST, Dr Regli was involved in numerous programs bridging academia, industry, and government; he was the chair of industry-university workshops, including those on process planning and network-enabled design and manufacturing. Dr Regli's research interests include solid modeling, artificial intelligence, integration of distributed manufacturing systems, Internet technology, and computer-integrated design and manufacturing. He is the recipient of a 1998 National Science Foundation CAREER Award, the University of Maryland Institute for Systems Research Outstanding Graduate Student Award (1994–95), NIST Special Service Award (1995), General Electric Corporation Teaching Incentive Grant (1994–95), among other awards. He is a member of ACM, ASME, IEEE, AAAI, and Sigma Xi and on the editorial board of the journal IEEE Internet Computing. Dr Regli has authored or co-authored more than 40 technical publications.

  1. Download : Download full-size image
Steve Brooks is a Staff Engineer at Allied Signal Aerospace Co. and received his PhD in Mechanical Engineering from the University of Kansas. His areas of specialization include software engineering, solid modeling applications, process planning and graphics programming.

View full text