Comparisons of neural network models on surface roughness in electrical discharge machining

Abstract

In this work, two different artificial neural network (ANN) models — back-propagation neural network (BPN) and radial basis function neural network (RBFN) — are presented for the prediction of surface roughness in die sinking electrical discharge machining (EDM). The pulse current (Ip), the pulse duration (Ton), and duty cycle (τ) are chosen as input variables with a constant voltage of 50 volt, and surface roughness is the output parameters of the model. A widespread series of EDM experiments was conducted on AISI D2 steel to acquire the data for training and testing and it was found that the neural models could predict the process performance with reasonable accuracy, under varying machining conditions. However, RBFN is faster than the BPNs and the BPN is reasonably more accurate. Moreover, they can be considered as valuable tools for EDM, by giving reliable predictions and provide a possible way to avoid time-and money-consuming experiments.

Keywords

back-propagation neural network electrical discharge machining radial basis function neural network surface roughness

References

Snoeys

Staelens

Dekeyser

, ‘Current trends in non-conventional material removal processes’ Ann. CIRP 35 (2) (1986): 467–480.

Mamalis

A. G.

Vosniakos

Vaxevanidis

N. M.

Prohászka

, ‘Macroscopic and microscopic phenomena of electro-discharge machined steel surfaces: An experimental investigation’ J. Mech. Work. Technol. 15 (1987): 335–356.

Tsai

K. M.

Wang

P. J.

, ‘Semi-empirical models of surface finish on electrical discharge machining’ Int. J. Machine Tools Mf. 41 (10) (2001): 1455–1477.

Petropoulos

Vaxevanidis

N. M.

Pandazaras

, ‘Modeling of surface finish in electro-discharge machining based upon statistical multi-parameter analysis’ J. Mater. Process. Technol. 155–156 (2004): 1247–1251.

Tsai

K.-M.

Wang

P. J.

, ‘Comparisons of neural network models on material removal rate in electrical discharge machining’ J. Mater. Process. Technol. 117 (2001): 111–124.

Kao

J. Y.

Tarng

Y. S.

, ‘A neural network approach for the on-line monitoring of the electrical discharge machining process’ J. Mater. Process. Technol. 69 (1997): 112–119.

Panda

D. K.

Bhoi

R. K.

, ‘Artificial neural network prediction of material removal rate in electro discharge machining’ Mater. Mfg Processes 20 (4) (2005): 645–672.

Markopoulos

A. P.

Manolakos

D. E.

Vaxevanidis

N. M.

, ‘Artificial neural network models for the prediction of surface roughness in electrical discharge machining’ J. Intell. Mf. 19 (3) (2008): 283–292 DOI: 10.1007/s10845-008-0081-9.

Anonymous, Surtronic 3⁺ operating instructions. September, RTH-HB-103, 1992 (Rank Taylor Hobson).

10.

Wang

Gelgele

H. L.

Wang

Yuan

Fang

, ‘A hybrid intelligent method for modelling the EDM process’ Int. J. Machine Tools Mf. 43 (2003): 995–999.