Using geometric shape variations to create an inverse model for a sheet metal process

Abstract

The output of the sheet metal forming process is subject to much variation. This paper develops a method to measure shape variation in channel forming and relate this back to the corresponding process parameter levels of the manufacturing set-up to create an inverse model. The shape variation in the channels is measured using a modified form of the point distribution model (also known as the active shape model). This means that channels can be represented by a weighting vector of minimal linear dimension that contains all the shape variation information from the average formed channel.

The inverse models were created using classifiers that related the weighting vectors to the process parameter levels for the blank holder force (BHF), die radii (DR) and tool gap (TG) of the parameters. Several classifiers were tested: linear, quadratic Gaussian and artificial neural networks. The quadratic Gaussian classifiers were the most accurate and the most consistent type of classifier over all the parameters.

Keywords

sheet metal forming inverse models classification pattern recognition quality control process control

References

Blümel

Hartmann

LüUbeck

Variation of automobile panel properties due to the manufacturing process. In 14th Biennial Congress of IDDRG, Koeln, Germany, 1986, pp. 179–187.

Blümel

Hartmann

LüUbeck

Variations of the stamping process. In 15th Biennial Congress of IDDRG, Dearborn, Michigan, 1988, pp. 9–16.

Doolan

Kalyanasundaram

Hodgson

Cardew-Hall

Identifying variation in sheet metal stamping. In Proceedings of the 7th International Conference on Sheet Metal (SheMet'99), Erlangen, Germany, 1999, pp. 117–124.

Doolan

Kalyanasundaram

Hodgson

Cardew-Hall

Identifying the cause of variation in sheet metal stamping. In ICME 2000, Australian Technology Park, Sydney, Australia, 2000.

Zeng

Lovenitti

Nagarajah

Accuracy of laser displacement sensors in 3d surface digitising. In ICME 2000, Australian Technology Park, Sydney, Australia, 2000.

Yang

Nezu

Application of an inverse FE approach in the concurrent design of sheet stamping. J. Mater. Processing Technol., 1998, 79, 86–93.

Guo

Batoz

Naceur

Bouabdallah

Mercier

Barlet

Recent developments on the analysis and optimum design of sheet metal forming parts using a simplified inverse approach. Computers and Structs, 2000, 78, 133–148.

Park

Yoon

Yang

Kim

Optimum blank design in sheet metal forming by the deformation path iteration method. Int. J. Mech. Sci., 1999, 41, 1217–1232.

Ghouati

Gelin

J.-C.

A finite element-based identification method for complex metallic material behaviours. Comput. Mater. Sci., 2001, 21, 57–68.

10.

Cootes

Taylor

Cooper

Graham

Active shape models—their training and application. CVGIP: Computer Vision and Image Understanding, 1995, 61(1), 38–59.

11.

Schalkoff

Pattern Recognition: Statistical, Structural and Neural Approaches, 1992 (John Wiley, Toronto).

12.

Fukunaga

Introduction to Statistical Pattern Recognition, 1990 (Academic Press, London).

13.

de Villiers

Barnard

Backpropagation neural nets with one and two hidden layers. IEEE Trans, on Neural Networks, 1992, 4(1), 136–141.

14.

Rolfe

Cardew-Hall

Abdallah

West

Geometric shape errors in forging: Developing a metric and an inverse model. Proc. Instn Mech. Engrs, Part B: J. Engineering Manufacture, 2001, 215(B9), 1229–1240.