Sage Journals: Discover world-class research

Abstract

Eliminating the gap between the grinding wheel and workpiece is a major time-wasting step during grinding operations. Reducing the time of this step has attracted many investigations. Several researchers have investigated the variation in some process parameters during the wheel-workpiece contact. These parameters include grinding force, grinding power and acoustic emission. During the approach of the grinding wheel to the workpiece, there are three primary stages which have an effect on these parameters: hydrodynamic stage, grit contact stage and wheel contact stage. A few researchers introduced a method to identify the start of the wheel contact stage, which is the practical contact stage. Most of these methods depend on predefined threshold values for some measured parameters. This paper introduces a new methodology to identify the wheel-workpiece contact event in surface grinding operations. A hybrid neural network with supervised learning is used to extract the contact event from the measured parameters. It consists of two neural nets. The first is a self-organizing map neural network with unsupervised learning and the second is a feedforward neural network with supervised learning. Using this hybrid network produces first self-organized clusters for the input data at the first network and then the second network recognizes these clusters. This results in the detection and classification of the contact events automatically from the measured data. This presents a very important step towards the full control of grinding operations in a computer numerically controlled (CNC) environment.

Keywords

neural network grinding wheel-workpiece interaction contact event

References

Kovach

Improved grinding of ceramic components. In Proceedings of the Department of Defence Machine Tool/Manufacturing Development Conference, AFWAL-TR-4137, 1987, Vol. 7, pp. 72–100.

Dornfeld

Cai

H. G.

An investigation of grinding and wheel loading using acoustic emission. Trans. ASME, J. Engng for Industry, 1984, 106, 28–33.

Maksoud

T. M. A.

Howes

T. D.

Effect of hydrodynamic pressure of high viscosity coolants on the stability of surface grinding processes. In ASME Winter Annual Meeting, Grinding Symposium, San Francisco, California, 10–15 December 1989, pp 183–198.

Webster

Marinescu

Bennett

Acoustic emission for process control and monitoring of surface integrity during grinding. Ann. CIRP, 1994, 43(1), 299–304.

Inasaki

Monitoring of dressing and grinding processes with acoustic emission signals. Ann. CIRP, 1985, 34(1), 277–280.

Dornfeld

Cai

An investigation of grinding and wheel loading using acoustic emission. Trans. ASME, J. Engng for Industry, 1984, 106(1), 28–33.

Wang

Willett

Webster

DeAguiar

R. P.

Improved wheel/workpiece contact detection during grinding via AE. Abrasives Mag., June 1999, 7–13.

Dong

Webster

Willett

An innovative method for improving the dimensional capability of CNC grinding machines. Abrasives Mag., June 2000, 1–4.

Kluft

Monitoring the grinding and dressing operations increases output and quality and reduces costs and waste. In 5th International Grinding Conference, Cincinnati, Ohio, 1995, paper 371, pp. 1–21.

10.

Webster

Dong

W.P.

Lindsay

Raw acoustic emission signal analysis of grinding process. Ann. CIRP, 1996, 45(1), 335–340.

11.

Konig

Meyen

AE in grinding and dressing, accuracy and process reliability. In Proceedings of 4th International Grinding Conference, MR90, 1990, paper MR526-90-1-20.

12.

Mills

Moruzzi

J. L.

Rowe

Grinding wheel selection using a neural network. In Proceedings of Tenth National Manufacturing Research Conference, September 1994, pp. 594–601 (Taylor and Francis Limited, Loughborough).

13.

Park

Rho

Generation of modified cutting condition using neural network for an operation planning system. Ann. CIRP, 1996, 45(1), 475–478.

14.

Sakakura

Inasaki

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

15.

Konig

Klumpen

Monitoring and sensor concepts for higher process reliability. In 5th International Grinding Conference, Cincinnati, Ohio, October 1993, paper MR358-93-1-23.

16.

Takashi

Inasaki

Ogawa

Monitoring of grinding process with a sensor integrated CBN wheel. In 5th International Grinding Conference, Cincinnati, Ohio, 1993, paper MR367-93-1-14.

17.

Roa

Gupta

Wood

H. C.

Neural networks in control systems. IEEE Technical Activities Board, 1996, pp. 429–436.

18.

Leften

Robert

Fuzzy and Neural Approaches in Engineering, 1997 (John Wiley, New York).

19.

Dornfeld

De Vries

Neural network sensor fusion for tool condition monitoring. Ann. CIRP, 1990, 39(1), 101.

20.

Rangwala

Dornfeld

Integration of sensors via neural networks for detection of tool wear states. In Proceedings of ASME Symposium on Integrated and Intelligent Manufacturing Analysis and Synthesis, New York, 1987, Vol. 25, pp. 109–120 (American Society of Mechanical Engineers, New York).

21.

Dong

McAvoy

Sensor data analysis using Auto-associative neural net. In Proceedings of World Congress on Neural Networks, San Diego, California, June 1994, Vol. 1, pp. 161–199.

22.

Jamu

Danai

Malkin

Unsupervised neural network for tool breakage detection in turning. Ann. CIRP, 1993, 42(1), 67.

23.

Reilly

Cooper

A neural model for a category learning. Biol. Cybernetics, 1982, 45, 35–41.

24.

Kohonen

Self-organized formation of topologically correct feature maps. Biol. Cybernetics, 1982, 43, 59–69.

25.

Beale

Jackson

Neural Computing: An Introduction, 1990 (Hilger, Bristol).

Improving wheel—workpiece contact detection using a hybrid neural network

Abstract

Abstract

Keywords

References