About Us

KEY WORDS

Friction, friction coefficient, genetic algorithm, artificial neural networks.

ABSTRACT

In this work was presented the method of determination of the friction coefficient by using multilayer artificial neural networks on the basis of experimental database
obtained from the strip drawing test. Using genetic algorithm the optimization of number of input variables of artificial neural networks has been done. As an input parameters for training artificial neural networks following parameters has been used: surface parameters of the sheet and dies, sheet material parameters and clamping force. Some results have pointed out that genetic algorithm has been successfully appled to optimization of training set.

CITATION INFORMATION

Acta Mechanica Slovaca. Volume 16, Issue 2, Pages 54 – 60, ISSN 1335-2393

DOWNLOAD

  Application of Genetic Algorithm for Optimization of Neural Networks for Selected Tribological Test

REFERENCES

[1] Darendeiler H., Akkok M., Yucesoy C.A., Effect of variable coefficient on sheet metal drawing, Tribol. Int., vol. 35, no. 2, 2002, p. 97-104.

[2] Fratini L., Lo Casto S., Lo Valvo E., A technical note on an experimental device to measure friction coefficient in sheet metal forming, J. Mat. Proc. Technol., vol. 172, no. 1, 2006, p.16-21.

[3] Lee B.H., Keum Y.T., Wagoner R.H., Modeling of the friction caused by lubrication and surface roughness in sheet metal forming, J. Mat. Proc. Technol., vol. 130-131, 2002,

p. 60-63.
[4] Guo B., Gong F., Wang C., Shan D., Size effect on friction in scaled down strip drawing, J. Mater. Sci., vol. 45, no. 15, 2010, p. 4067–4072.
[5] Pacana A., Korzyński M.: Roller burnishing parameters analyse with Taguchi method. Międzynarodowa Konferencja Naukowa „MECHANIKA 2002”, Rzeszów, July 2002,

s. 273 – 279, ISSN 0209-2689
[6] Pacana A., Noga S.: Application neural networks to find the relation between the roller burnishing parameters and the surface roughness. Computer science for design
and technology 2000 (Конгресса; Конструкторско –технологическая информатика 2000), Moccow, СТАНКИН, 3-6.10.2000 s.292-294 ISBN 5-7028-0117-2
[7] Hertz J., Krogh A., Palmer R. G., Wstęp do teorii obliczeń neuronowych, WNT, Warszawa, 1993.
[8] Tadeusiewicz R., Sieci neuronowe, WNT, Warszawa 1998.
[9] Michalewicz Z., Algorytmy genetyczne + struktury danych = programy ewolucyjne, WNT, Warszawa, 1999.
[10] Lula P., Tadeusiewicz R., STATISTICA Neural Networks PL, Przewodnik problemowy, Statsoft, Kraków, 2001.
[11] StatSoft, Inc. Manual of STATISTICA Neural Networks Software. StatSoft Inc., Tulsa, 1998.
[12] Stachowicz F., Trzepieciński T., ANN application for determination of frictional characteristics of brass sheet metal, Journal of Artificial Intelligence, Vol. 1, No 2, 2004, pp 81-90.

Latest Issue

ams 2 2016

Download

Guests Online

We have 13 guests and no members online