Naslov
INVESTIGATION OF DRILLING PROCESS USING REGRESSION ANALYSIS AND NEURAL NETWORK

Autori
Bajić, Dražen ; Jozić, Sonja ; Celent, Luka

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
CIM 2009 COMPUTER INTEGRATED MANUFACTURING AND HIGH SPEED MACHINING / Abele, Eberhard ; Udiljak, Toma ; Ciglar, Damir - Zagreb : Hrvatska udruga proizvodnog strojarstva (HUPS), 2009, 7-12

ISBN
978-953-7689-00-1

Skup
12th INTERNATIONAL SCIENTIFIC CONFERENCE ON PRODUCTION ENGINEERING

Mjesto i datum
Biograd na Moru, Hrvatska, 17.06.2009. - 20.06.2009

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
drilling; thrust force and torque; regression analysis; neural network.

Sažetak
The focus of this paper is to develop a reliable model to predict the depth of drilling, by standard drilling, where the conditions of machinability still stay satisfactory. In this sense, this paper is concerned with the influence of spindle speed and feedrate on increasing thrust force and torque in drilling process. Two modeling methodologies, namely regression analysis and artificial neural network, have been applied to experimentally determined data by means of the design of experiments. The results obtained by the models have been compared. The best prediction of depth of drilling shows neural network model with average relative prediction error of 6, 16%.

Izvorni jezik
Engleski

Znanstvena područja
Strojarstvo

POVEZANOST RADA