Author(s):
1. Pavel Kovač, Faculty of Technical Sciences, Department for Production Engineering, Serbia
2. Borislav Savković, Faculty of Technical Sciences, Department for Production Engineering, Serbia
3. Dragan Rodić, Faculty of Technical Sciences, Department for Production Engineering, Serbia
4. Dušan Ješić, International technology Management Academy, Novi Sad,

Abstract:
This paper proposes a method for cutting parameters identification using the multi-inputs-multi-outputs fuzzy inference system (MIMO-FIS). The fuzzy inference system (FIS) was used to identify the initial values for cutting parameters (cutting speed, feed rate and depth of cut) and flank wear using cutting temperature and tool life as outputs. The objective was to determine the influence of cutting parameters on cutting temperature and tool life. The model for determining the cutting temperature and tool life of steel AISI 1060 was trained (design rules) and tested by using the experimental data. The average deviation of the testing data for tool life was 11/6 %, while that of the cutting temperature was 3/28 %. The parameters used in these testing data were different from the data collected for the design rules. The test results showed that the proposed MIMO-FIS model can be used successfully for machinability data selection. The effect of parameters and their interactions in machining is analyzed in detail and presented in this study In the paper was carried out modeling of cutting parameters in face milling process of Semi Solid Metal alloys as well. As input parameters in the process of modeling were taken: cutting speed v, the feed per tooth and cutting depth, while for the output characteristics of the process were arithmetic mean surface roughness Ra and maximum roughness Rmax. Modeling was done in two ways. The first model was made with the help of mathematical and statistical methods factorial experiment DoE, where it was used without mutual influence of model parameters. The second model was made by artificial intelligence and as a tool is chosen neural networks

Thematic field:
SYMPOSIUM A - Science of matter, condensed matter and physics of solid states

Date of abstract submission:
03.09.2021.

Conference:
Contemporary Materials 2021 - Savremeni materijali