Recognition of overlapping machining features based on hybrid artificial intelligent techniques

Abstract

A hybrid feature recognition system using feature hints, graph manipulations and artificial neural networks for the recognition of overlapping machining features is presented. Based on the enhanced attributed adjacency graph (EAAG) representation and the virtual link graph (VLG) of a designed part, the face loops (F-loops) are defined as the generalized feature hints. They are then extracted from the EAAG using vector calculations, and the relationships between the F-loops are established. Next, the F-loops are manipulated according to the six types of the relationship between F-loops to build the F-loop subgraphs (FLGs), which are potential features. Finally, these FLGs are presented to a trained artificial neural network using various overlapping feature cases to be classified into different types of feature. By utilizing the characteristics of three intelligent techniques in the different subtasks of the feature recognition process, the system can recognize complex overlapping machining features with planar faces and quadric surfaces efficiently. The system is open and has the capability to recognize new types of overlapping feature from the learning ability of the artificial neural networks.

Keywords

overlapping feature recognition hint-based recognition neural networks

References

Kyprianou

Shape classification in computer-aided design. PhD thesis, University of Cambridge, 1980.

Choi

B. K.

Barash

M. M.

Anderson

D. C.

Automatic recognition of machined surfaces from a 3D solid model. Computer-Aided Des., 1984, 16(2), 81–86.

Henderson

M. R.

Extraction of feature information from three dimensional CAD data. PhD thesis, Purdue University, West Lafayette, Indiana, 1984.

Chan

A. K. W.

Case

Process planning by recognizing and learning machining features. Int. J. Comput. Integrated Mfg, 1994, 7(2), 125–133.

Joshi

Chang

T. C.

Graph-based heuristics for recognition of machined surfaces from a 3D solid model. Computer-Aided Des., 1988, 20(2), 58–66.

Sakurai

Gossard

D. C.

Recognizing shape feature in solid models. IEEE Computer Graphics Applic., 1990, 10(9), 22–32.

Gao

Shah

J. J.

Automatic recognition of interacting machining features based on minimal condition sub-graph. Computer-Aided Des., 1998, 30(9), 727–739.

Marefat

Kashyap

P. L.

Geometric reasoning for recognition of three-dimensional object features. IEEE Trans. Pattern Analysis Mach. Intell., 1990, 12(10), 949–965.

Marefat

Bayesian approach for extracting and identifying features. Computer-Aided Des., 1995, 27(6), 435–454.

10.

Corney

Clark

D. E. R.

Method for finding holes and pockets that connect multiple faces in 2 1/2D objects. Computer-Aided Des., 1991, 23(10), 658–668.

11.

Vandenbrande

J. H.

Requicha

A. A. G.

Spatial reasoning for the automatic recognition of machinable features in solid models. IEEE Trans. Pattern Analysis Mach. Intell., 1993, 15(12), 1269–1285.

12.

Regli

W. C.

Geometric algorithms for recognition of features from solid models. PhD thesis, University of Maryland, 1995.

13.

Han

3D geometric reasoning algorithm for feature recognition. PhD thesis, University of Southern California, Los Angeles, California, 1996.

14.

Prabhakar

Henderson

M. R.

Automatic form-feature recognition using neural-network-based techniques on boundary representation of solid models. Computer-Aided Des., 1992, 24(7), 381–393.

15.

Hwang

J. L.

Henderson

M. R.

Applying the perceptron to three-dimensional feature recognition. J. Des. Mfg, 1992, 2(4), 187–198.

16.

Lankalapalli

Chatterjee

Chang

T. C.

Feature recognition using ART2: A self-organizing neural network. J. Intelligent Mfg, 1997, 8(3), 203–214.

17.

Zhang

Y. F.

Nee

A. Y. C.

Generic form feature recognition and operation selection using connectionist modelling. J. Intelligent Mfg, 1995, 6(4), 263–273.

18.

Nezis

Vosniakos

Recognizing 2D shape features using a neural network and heuristics. Computer-Aided Des., 1997, 29(7), 523–539.