Original scientific paper

https://doi.org/10.17559/TV-20200818114207

Modelling and Prediction of Surface Roughness in CNC Turning Process using Neural Networks

Tomislav Šarić* orcid.org/0000-0002-6339-7936 ; Mechanical Engineering Faculty in Slavonski Brod, University of Slavonski Brod, Trg Ivane Brlic Mazuranic 2, HR-35000 Slavonski Brod, Croatia
Đorđe Vukelić orcid.org/0000-0003-2420-6778 ; Faculty of Technical Sciences, University of Novi Sad, Trg Dositeja Obradovica 6, 21000 Novi Sad, Serbia
Katica Šimunović ; Mechanical Engineering Faculty in Slavonski Brod, University of Slavonski Brod, Trg Ivane Brlic Mazuranic 2, HR-35000 Slavonski Brod, Croatia
Ilija Svalina orcid.org/0000-0003-2375-7367 ; Mechanical Engineering Faculty in Slavonski Brod, University of Slavonski Brod, Trg Ivane Brlic Mazuranic 2, HR-35000 Slavonski Brod, Croatia
Branko Tadić ; Faculty of Engineering, University of Kragujevac, Sestre Janjić 6, 34000 Kragujevac, Serbia
Miljana Prica ; Faculty of Technical Sciences, University of Novi Sad, Trg Dositeja Obradovica 6, 21000 Novi Sad, Serbia
Goran Šimunović orcid.org/0000-0002-7159-2627 ; Mechanical Engineering Faculty in Slavonski Brod, University of Slavonski Brod, Trg Ivane Brlic Mazuranic 2, HR-35000 Slavonski Brod, Croatia

Abstract

The paper presents an approach to solving the problem of modelling and prediction of surface roughness in CNC turning process. In order to solve this problem an experiment was designed. Samples for experimental part of investigation were of dimensions 30 × 350 mm, and the sample material was GJS 500 - 7. Six cutting inserts were used for the designed experiment as well as variations of cutting speed, feed and depth of cut on CNC lathe DMG Moriseiki-CTX 310 Ecoline. After the conducted experiment, surface roughness of each sample was measured and a data set of 750 instances was formed. For data analysis, the Back-Propagation Neural Network (BPNN) algorithm was used. In modelling different BPNN architectures with characteristic features the results of RMS (Root Mean Square) error were controlled. Specially analysed were the RMS errors realised by different number of neurons in hidden layers. For the BPNN architecture with one hidden layer the architecture (4 – 8 - 1) was adopted with RMS error of 3,37%. In modelling the BPNN architecture with two hidden layers, a considerable amount of architectures was investigated. The adopted architecture with two hidden layers (4 - 2 - 10 - 1) generated the RMS error of 2,26%. The investigation was also directed at the size of the data set and controlling the level of RMS error.

Keywords

CNC turning; Neural Networks; prediction; surface roughness

Hrčak ID:

248229

URI

https://hrcak.srce.hr/248229

Publication date:

19.12.2020.

Visits: 1.490 *