A hybrid neural network-feature-based manufacturability analysis of mould reinforced plastic parts

Abstract

The purpose of this research is to establish a method to perform manufacturability analysis of reinforced plastic components by using a hybrid system including automatic feature recognition and a feature-based assessment of manufacturability. Feature recognition plays a fundamental role and is usually the first step in downstream activities concerning the product development process, such as design for manufacturing, design for assembly and process planning.

Critical features to successful reinforced plastic moulding are identified, and the relationship between geometric information of the model, expert geometric reasoning and knowledge of related manufacturing processes is clarified and predetermined in a useful and efficient manufacturability analysis system. A prototype system using solid modelling, object-oriented programming and a rule-based system, which is intended to consider the fuzziness of the expert reasoning about reinforced plastic component design, is under construction to test the proposed concepts. The major contribution from this work is a consistent and systematic methodology for analysing the geometry of models, allowing assessment of manufacturability. This methodology considers available manufacturing process capabilities, materials and tooling required. Some virtual parts have been used to test the system, showing promising results.

Keywords

feature recognition neural network design for manufacturing (DFM)reinforced plastics manufacturability analysis

References

Syan

C. S.

Swift

K. G.

Design for manufacturing. In Concurrent Engineering: Concepts, Implementation and Practice (Eds Syan

C.S.

Menon

), 1994, Ch. 6, pp. 101–115 (Chapman and Hall, London).

Prabhakar

Henderson

M. R.

Automatic form-feature recognition using neural-network based techniques on B-rep of solid models. Computer Aided Des., 1992, 24, 381–393.

Ling

Z. K.

Narayau

Heuristic feature recognition from a CAD model. Integrated Computer Aided Engng, 1996, 3(3), 212–224.

Gupta

S. K.

Regli

W. C.

Das

Nau

D. S.

Automated manufacturability analysis: A survey. Res. Engng Des., 1997, 9, 168–190.

Looney

C. G.

Pattern Recognition Using Neural Networks: Theory and Algorithms for Engineers and Scientists, 1997 (Oxford University Press, New York).

Chuang

S. H.

Henderson

M. R.

Three-dimensional shape pattern recognition using vertex classification and vertex-edge graph. Computer Aided Des., 1990, 22(6), 377–387.

Hwang

J. L.

Applying Perceptron to 3D feature recognition. PhD dissertation, Arizona State University, 1991.

Hwang

J. L.

Henderson

M. R.

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

Lankalapalli

Chatterjee

Chang

T. C.

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

10.

Agrawal

Vasudevan

P. T.

PLASSEX: An expert system for plastic selection. Advd Polymer Technol., 1993, 12, 419–428.

11.

Borg

MacCallum

K. J.

A HyperCAD expert system for plastic product design. In Proceedings of 3rd International Conference on Computer Integrated Manufacturing, Singapore, 1995, pp. 295–302.

12.

Ishii

Modelling of concurrent engineering design. In Concurrent Engineering: Automation, Tools and Techniques. ASME Winter Annual Meeting (Ed. Kusiak

), 1993, pp. 19–39 (John Wiley, New York).

13.

Jakiela

Papalambros

Ulsoy

A. G.

Programming optimal suggestions in the design concept phase: Application to the Boothroyd assembly charts. Trans. ASME, J. Mechanism, Transm., and Automn in Des., 1985, 107, 285–289.

14.

Yannoulakis

N. J.

Joshi

S. B.

Wysk

R. A.

A manufacturability evaluation and improvement system. In Proceedings of ASME Design Theory and Methodology Conference (Ed. Stauffer

L.A.

), 1991, pp. 217–226.

15.

Schmitz

J. M.

Desa

The application of the design for producibility methodology to complex stamped products. In Concurrent Product and Process Design, ASME Winter Annual Meeting (Eds Chao

N.L.

S. C. Y.

), 1989, pp. 169–174.

16.

Hayes

C. C.

Desa

Wright

P. K.

Using process planning knowledge to make design suggestions concurrently. In Concurrent Product and Process Design, ASME Winter Annual Meeting (Eds Chao

N.L.

S. C. Y.

), 1989, pp. 87–92.

17.

Marquez

Gill

White

Applications of neural networks in feature recognition of mould reinforced plastic parts. Concurrent Engng: Res. Applic., 1999, 7(2), 115–122.

18.

Murphy

Reinforced Plastics Handbook, 1994 (Elsevier Advanced Technology, Oxford).