Dimensional analysis and ANN simulation of chip-tool interface temperature during turning SS304

OBRABOTKAMETALLOV Vol. 23 No. 3 2021 MATERIAL SCIENCE EQUIPMENT. INSTRUMENTS 4 and corresponding EMF was recorded. The calibration graph for the combination of uncoated and PVD single-layer TiAlN and multi-layer TiN / TiAlN coated carbide tools for SS304 work material is shown in Fig. 3. Results and Discussion Signi fi cant research around the world is aimed at improving the workability of SS304 . Table 2 shows the experimental results of cutting temperatures measured during dry turning of SS304 steel with uncoated and PVD single-layer TiAlN and multi-layer TiN / TiAlN coated carbide tools at different cutting conditions. Fig. 4 illustrates the in fl uence of the cutting speed and feed on the cutting temperature when using uncoated and PVD single-layer TiAlN and multi-layer TiN / TiAlN coated carbide tools. In recent years, researchers have been paying considerable attention to the development of predictive models to measure performance during machining. In the present work, statistical-based, dimensional analysis, and arti fi cial neural network models are developed to predict the chip-tool interface temperature. Fig. 3. Calibration curves for uncoated and PVD single-layer TiAlN and multi-layer TiN / TiAlN coated carbide tools Ta b l e 2 Cutting temperature for different tools varying with cutting conditions Expt. no. Cutting speed (m/min) Feed (mm/rev) Chip-tool interface temperature Uncoated TiAlN coated TiN / TiAlN coated 1 140 0.08 825 930 996 2 140 0.14 900 1,039 1,047 3 140 0.2 939 1,041 1,081 4 200 0.08 933 1,109 1,104 5 200 0.14 1,029 1,169 1,161 6 200 0.2 1,039 1,200 1,199 7 260 0.08 1,078 1,186 1,191 8 260 0.14 1,120 1,204 1,252 9 260 0.2 1,175 1,257 1,293