Sage Journals: Discover world-class research

Abstract

This paper presents an intelligent system for optimization of the cylindrical traverse grinding process whose objective is to maximize the material removal rate with constraints on workpiece out-of-roundness and waviness errors, on surface finish, and on grinding temperature. A theoretical analysis of wheel wear development in the traverse grinding process is presented. Next, the results of an experimental test are discussed to establish the most efficient strategy for grinding allowance removal. In the optimization scheme a feedforward neural network is employed to obtain a model which describes relations between the process input parameters and the grinding results. Then this model is used to optimize adaptively the traverse grinding process. The performance of the proposed optimization system is evaluated by simulation research.

Keywords

artificial intelligence cylindrical traverse grinding optimization

Get full access to this article

View all access options for this article.

References

Rowe

W.-B.

Mills

Y.-L.

Allanson

D.-R.

Application of intelligent CNC in grinding. Computers Industry, 1996, 31, 45–60.

Sakakura

Inasaki

A neural network approach to the decision-making process for grinding operations. Ann. CIRP, 1992, 41(1), 353–356.

Liao

T.-W.

Chen

L.-J.

Manufacturing process modelling and optimisation based on multi-layer perceptron network. Trans. ASME, J. Mfg Sci. Engng, 1998, 120, 109–119.

Tönshoff

H.K.

Peters

Inasaki

Paul

Modelling and simulation of grinding process. Ann. CIRP, 1992, 41(2), 677–492.

Kruszy?ski

Lajmert

An intelligent system for supervision and control of traverse grinding operation. In Proceedings of the Sixth International Conference on Monitoring and automatic supervision in manufacturing, Warsaw, Poland, 2004, pp. 21–22 (The Institute of Metal Cutting, Kraków, Poland).

Kruszy?ski

Lajmert

An intelligent supervision system for cylindrical traverse grinding. Ann. CIRP, 2005, 54(1), 305–309.

Verkerk

Plunge grinding data for the control of traverse grinding operations. In Proceedings of the Eighth North American Manufacturing Research Conference, University of Missouri, USA, 1980, pp. 80–87 (Society of Manufacturing Engineers, Dearborn, Michigan).

Lajmert

The use of artificial intelligence methods for the control and optimisation of the traverse grinding process. PhD Thesis, ?ód? Technical University, 2003.

Le?a?ski

Lajmert

An intelligent grinding machine. In Proceedings of Interational Conference on Computer Integrated Manufacturing, Warsaw, Poland, Vol. 1, pp. 293–302. (Panstwowe Wydawnictwo Naukowe, Warsaw).

10.

Rumelhart

D. E.

Hinton

G. E.

Wiliams

R. J.

Learning internal representation by error propagation. Parallel Distributed Processing: Explorations Micro-structs of Cognitions, 1, 318–362.

11.

Charalambous

Conjugate gradient algorithm for efficient training of artificial neural networks. IEE Proc. G, 1992, 139, 301–309.

12.

Findeisen

Szymanowski

Wierzbicki

Theory and computational methods for optimisation, 1980 (Panstwowe Wydawnictwo Naukowe, Warsaw).